18068 lines
495 KiB
JSON
18068 lines
495 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.7002528690916164,
|
|
"eval_steps": 3000,
|
|
"global_step": 9000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.742382335662843,
|
|
"epoch": 0.00038902937171756465,
|
|
"grad_norm": 4.78125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.7699,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 9243.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.742357444763183,
|
|
"epoch": 0.0007780587434351293,
|
|
"grad_norm": 5.03125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7654,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 18424.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.74235429763794,
|
|
"epoch": 0.001167088115152694,
|
|
"grad_norm": 5.03125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.729,
|
|
"mean_token_accuracy": 0.00010964912362396718,
|
|
"num_tokens": 27006.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.742323112487792,
|
|
"epoch": 0.0015561174868702586,
|
|
"grad_norm": 4.65625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.68,
|
|
"mean_token_accuracy": 0.00010695187374949455,
|
|
"num_tokens": 35577.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.742191219329834,
|
|
"epoch": 0.0019451468585878235,
|
|
"grad_norm": 4.46875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.5624,
|
|
"mean_token_accuracy": 0.001254092820454389,
|
|
"num_tokens": 43706.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.741874980926514,
|
|
"epoch": 0.002334176230305388,
|
|
"grad_norm": 4.25,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.4785,
|
|
"mean_token_accuracy": 0.01906490430701524,
|
|
"num_tokens": 52571.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.741138744354249,
|
|
"epoch": 0.0027232056020229526,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.3631,
|
|
"mean_token_accuracy": 0.04432072527706623,
|
|
"num_tokens": 61900.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.739378833770752,
|
|
"epoch": 0.0031122349737405172,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.2522,
|
|
"mean_token_accuracy": 0.043363864347338674,
|
|
"num_tokens": 71234.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.736563587188721,
|
|
"epoch": 0.003501264345458082,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.1123,
|
|
"mean_token_accuracy": 0.04502938166260719,
|
|
"num_tokens": 79610.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.733458709716796,
|
|
"epoch": 0.003890293717175647,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.0005,
|
|
"mean_token_accuracy": 0.04512783698737621,
|
|
"num_tokens": 87527.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.731391525268554,
|
|
"epoch": 0.004279323088893211,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.9758,
|
|
"mean_token_accuracy": 0.044215765222907065,
|
|
"num_tokens": 95512.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.728329372406005,
|
|
"epoch": 0.004668352460610776,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.9107,
|
|
"mean_token_accuracy": 0.04661451056599617,
|
|
"num_tokens": 104395.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.723896598815918,
|
|
"epoch": 0.0050573818323283405,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.8199,
|
|
"mean_token_accuracy": 0.049337920546531674,
|
|
"num_tokens": 112562.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.719001293182373,
|
|
"epoch": 0.005446411204045905,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.7691,
|
|
"mean_token_accuracy": 0.04639301113784313,
|
|
"num_tokens": 121962.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.715445232391357,
|
|
"epoch": 0.00583544057576347,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.7611,
|
|
"mean_token_accuracy": 0.04579820521175861,
|
|
"num_tokens": 130714.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.711173343658448,
|
|
"epoch": 0.0062244699474810344,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.665,
|
|
"mean_token_accuracy": 0.0456673588603735,
|
|
"num_tokens": 139674.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.70630578994751,
|
|
"epoch": 0.006613499319198599,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.5765,
|
|
"mean_token_accuracy": 0.04949404634535313,
|
|
"num_tokens": 148654.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.698366928100587,
|
|
"epoch": 0.007002528690916164,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.435,
|
|
"mean_token_accuracy": 0.05969774164259434,
|
|
"num_tokens": 156180.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.684116172790528,
|
|
"epoch": 0.007391558062633729,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.4372,
|
|
"mean_token_accuracy": 0.06196932159364223,
|
|
"num_tokens": 165608.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.664545917510987,
|
|
"epoch": 0.007780587434351294,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.3091,
|
|
"mean_token_accuracy": 0.06599215753376483,
|
|
"num_tokens": 173871.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.63426914215088,
|
|
"epoch": 0.008169616806068859,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.2262,
|
|
"mean_token_accuracy": 0.06208839267492294,
|
|
"num_tokens": 182356.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.588347434997559,
|
|
"epoch": 0.008558646177786422,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.1345,
|
|
"mean_token_accuracy": 0.06493466645479203,
|
|
"num_tokens": 190361.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.534650707244873,
|
|
"epoch": 0.008947675549503988,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.0175,
|
|
"mean_token_accuracy": 0.06511155813932419,
|
|
"num_tokens": 199253.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.498821544647218,
|
|
"epoch": 0.009336704921221552,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.9191,
|
|
"mean_token_accuracy": 0.06383187472820281,
|
|
"num_tokens": 208181.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.446215152740479,
|
|
"epoch": 0.009725734292939117,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.7921,
|
|
"mean_token_accuracy": 0.06596225276589393,
|
|
"num_tokens": 216898.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.361998558044434,
|
|
"epoch": 0.010114763664656681,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.6872,
|
|
"mean_token_accuracy": 0.06298739649355412,
|
|
"num_tokens": 226051.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.26733865737915,
|
|
"epoch": 0.010503793036374246,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.5991,
|
|
"mean_token_accuracy": 0.06326549835503101,
|
|
"num_tokens": 235018.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.166206169128419,
|
|
"epoch": 0.01089282240809181,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.4509,
|
|
"mean_token_accuracy": 0.06088712736964226,
|
|
"num_tokens": 244268.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.03088960647583,
|
|
"epoch": 0.011281851779809376,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.3425,
|
|
"mean_token_accuracy": 0.06427538841962814,
|
|
"num_tokens": 253545.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.861793708801269,
|
|
"epoch": 0.01167088115152694,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.1413,
|
|
"mean_token_accuracy": 0.07204292267560959,
|
|
"num_tokens": 261767.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.695942211151124,
|
|
"epoch": 0.012059910523244505,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.1018,
|
|
"mean_token_accuracy": 0.06669669337570668,
|
|
"num_tokens": 270372.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.514180374145507,
|
|
"epoch": 0.012448939894962069,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.0639,
|
|
"mean_token_accuracy": 0.06147677525877952,
|
|
"num_tokens": 279726.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.323209476470947,
|
|
"epoch": 0.012837969266679634,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.9873,
|
|
"mean_token_accuracy": 0.06152131669223308,
|
|
"num_tokens": 288955.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.155291080474854,
|
|
"epoch": 0.013226998638397198,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.8671,
|
|
"mean_token_accuracy": 0.06018271669745445,
|
|
"num_tokens": 297898.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.913286781311035,
|
|
"epoch": 0.013616028010114764,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.7877,
|
|
"mean_token_accuracy": 0.06726240292191506,
|
|
"num_tokens": 306189.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.70859899520874,
|
|
"epoch": 0.014005057381832327,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.7347,
|
|
"mean_token_accuracy": 0.06567795276641845,
|
|
"num_tokens": 314881.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.591675281524658,
|
|
"epoch": 0.014394086753549893,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.7148,
|
|
"mean_token_accuracy": 0.0621601328253746,
|
|
"num_tokens": 323357.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.47695083618164,
|
|
"epoch": 0.014783116125267459,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.7356,
|
|
"mean_token_accuracy": 0.06571447476744652,
|
|
"num_tokens": 331799.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.370344352722167,
|
|
"epoch": 0.015172145496985022,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.6118,
|
|
"mean_token_accuracy": 0.06905685365200043,
|
|
"num_tokens": 340320.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.324654674530029,
|
|
"epoch": 0.015561174868702588,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.6178,
|
|
"mean_token_accuracy": 0.06449079662561416,
|
|
"num_tokens": 348990.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.174854373931884,
|
|
"epoch": 0.01595020424042015,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.5827,
|
|
"mean_token_accuracy": 0.06486652344465256,
|
|
"num_tokens": 357661.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.168173027038574,
|
|
"epoch": 0.016339233612137717,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.5391,
|
|
"mean_token_accuracy": 0.07107783854007721,
|
|
"num_tokens": 366099.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.15952262878418,
|
|
"epoch": 0.016728262983855283,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.677,
|
|
"mean_token_accuracy": 0.06535900048911572,
|
|
"num_tokens": 374926.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.183490467071532,
|
|
"epoch": 0.017117292355572845,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.5935,
|
|
"mean_token_accuracy": 0.06671289913356304,
|
|
"num_tokens": 383846.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.149136352539063,
|
|
"epoch": 0.01750632172729041,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.5526,
|
|
"mean_token_accuracy": 0.07337053082883357,
|
|
"num_tokens": 393678.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.142791080474854,
|
|
"epoch": 0.017895351099007976,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.5805,
|
|
"mean_token_accuracy": 0.07247933149337768,
|
|
"num_tokens": 401866.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.138428115844727,
|
|
"epoch": 0.01828438047072554,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.5559,
|
|
"mean_token_accuracy": 0.07213828079402447,
|
|
"num_tokens": 411057.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.083276653289795,
|
|
"epoch": 0.018673409842443103,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.5199,
|
|
"mean_token_accuracy": 0.07377653121948242,
|
|
"num_tokens": 419083.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.081015300750732,
|
|
"epoch": 0.01906243921416067,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.423,
|
|
"mean_token_accuracy": 0.07348247244954109,
|
|
"num_tokens": 427503.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.99849009513855,
|
|
"epoch": 0.019451468585878234,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.5381,
|
|
"mean_token_accuracy": 0.07209133058786392,
|
|
"num_tokens": 435820.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.958733320236206,
|
|
"epoch": 0.0198404979575958,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.3981,
|
|
"mean_token_accuracy": 0.07939725071191787,
|
|
"num_tokens": 444692.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.023887872695923,
|
|
"epoch": 0.020229527329313362,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.4495,
|
|
"mean_token_accuracy": 0.07057543247938156,
|
|
"num_tokens": 453536.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.02216215133667,
|
|
"epoch": 0.020618556701030927,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.4635,
|
|
"mean_token_accuracy": 0.07652526497840881,
|
|
"num_tokens": 462264.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.021293640136719,
|
|
"epoch": 0.021007586072748493,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.5942,
|
|
"mean_token_accuracy": 0.07328042685985565,
|
|
"num_tokens": 471819.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.957899475097657,
|
|
"epoch": 0.02139661544446606,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.4982,
|
|
"mean_token_accuracy": 0.0714272040873766,
|
|
"num_tokens": 480878.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.055506563186645,
|
|
"epoch": 0.02178564481618362,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.4444,
|
|
"mean_token_accuracy": 0.08031182736158371,
|
|
"num_tokens": 489454.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.901804733276367,
|
|
"epoch": 0.022174674187901186,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.3353,
|
|
"mean_token_accuracy": 0.07537753507494926,
|
|
"num_tokens": 498378.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.9674581527709964,
|
|
"epoch": 0.02256370355961875,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.558,
|
|
"mean_token_accuracy": 0.07206817306578159,
|
|
"num_tokens": 507638.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.018344259262085,
|
|
"epoch": 0.022952732931336317,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.4655,
|
|
"mean_token_accuracy": 0.08074412941932678,
|
|
"num_tokens": 517047.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.928561210632324,
|
|
"epoch": 0.02334176230305388,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.3931,
|
|
"mean_token_accuracy": 0.07988100573420524,
|
|
"num_tokens": 525287.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.889331293106079,
|
|
"epoch": 0.023730791674771445,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.3272,
|
|
"mean_token_accuracy": 0.07765846103429794,
|
|
"num_tokens": 533266.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.938522481918335,
|
|
"epoch": 0.02411982104648901,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.4553,
|
|
"mean_token_accuracy": 0.07832531034946441,
|
|
"num_tokens": 542448.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.876863288879394,
|
|
"epoch": 0.024508850418206576,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.3373,
|
|
"mean_token_accuracy": 0.07851743251085282,
|
|
"num_tokens": 550872.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.92165994644165,
|
|
"epoch": 0.024897879789924138,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.3913,
|
|
"mean_token_accuracy": 0.08598420470952987,
|
|
"num_tokens": 559616.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.843034791946411,
|
|
"epoch": 0.025286909161641703,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.3644,
|
|
"mean_token_accuracy": 0.0826579324901104,
|
|
"num_tokens": 568379.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.829864072799682,
|
|
"epoch": 0.02567593853335927,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.3671,
|
|
"mean_token_accuracy": 0.08075782656669617,
|
|
"num_tokens": 577288.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.871328210830688,
|
|
"epoch": 0.026064967905076834,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.3243,
|
|
"mean_token_accuracy": 0.08058057203888894,
|
|
"num_tokens": 587054.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.879428195953369,
|
|
"epoch": 0.026453997276794396,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.443,
|
|
"mean_token_accuracy": 0.0813908450305462,
|
|
"num_tokens": 595405.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.87817964553833,
|
|
"epoch": 0.026843026648511962,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.3017,
|
|
"mean_token_accuracy": 0.0837264135479927,
|
|
"num_tokens": 604095.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.7519464015960695,
|
|
"epoch": 0.027232056020229527,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.3331,
|
|
"mean_token_accuracy": 0.08179512321949005,
|
|
"num_tokens": 613518.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.8531310081481935,
|
|
"epoch": 0.027621085391947093,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.1945,
|
|
"mean_token_accuracy": 0.08306437954306603,
|
|
"num_tokens": 621212.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.758134984970093,
|
|
"epoch": 0.028010114763664655,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.2697,
|
|
"mean_token_accuracy": 0.08436251506209373,
|
|
"num_tokens": 629326.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.758914995193481,
|
|
"epoch": 0.02839914413538222,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.2792,
|
|
"mean_token_accuracy": 0.08306139633059502,
|
|
"num_tokens": 637034.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.723426389694214,
|
|
"epoch": 0.028788173507099786,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.1741,
|
|
"mean_token_accuracy": 0.08840271160006523,
|
|
"num_tokens": 645924.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.825829219818115,
|
|
"epoch": 0.02917720287881735,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.3813,
|
|
"mean_token_accuracy": 0.08644352033734322,
|
|
"num_tokens": 655020.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.784128332138062,
|
|
"epoch": 0.029566232250534917,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.2057,
|
|
"mean_token_accuracy": 0.08727380409836769,
|
|
"num_tokens": 663451.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.727108144760132,
|
|
"epoch": 0.02995526162225248,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.2834,
|
|
"mean_token_accuracy": 0.08695143982768058,
|
|
"num_tokens": 671973.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.712132835388184,
|
|
"epoch": 0.030344290993970045,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.1734,
|
|
"mean_token_accuracy": 0.08923292458057404,
|
|
"num_tokens": 680583.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.674439716339111,
|
|
"epoch": 0.03073332036568761,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.1871,
|
|
"mean_token_accuracy": 0.0865532897412777,
|
|
"num_tokens": 689000.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.765862512588501,
|
|
"epoch": 0.031122349737405176,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.1741,
|
|
"mean_token_accuracy": 0.08593220934271813,
|
|
"num_tokens": 698047.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.731269979476929,
|
|
"epoch": 0.03151137910912274,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.2962,
|
|
"mean_token_accuracy": 0.08466848209500313,
|
|
"num_tokens": 707192.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.695866537094116,
|
|
"epoch": 0.0319004084808403,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.1133,
|
|
"mean_token_accuracy": 0.09290924519300461,
|
|
"num_tokens": 715895.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.683174657821655,
|
|
"epoch": 0.03228943785255787,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.1955,
|
|
"mean_token_accuracy": 0.08894984126091003,
|
|
"num_tokens": 724891.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.715670108795166,
|
|
"epoch": 0.032678467224275434,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.2305,
|
|
"mean_token_accuracy": 0.08583205491304398,
|
|
"num_tokens": 733378.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.689523315429687,
|
|
"epoch": 0.033067496595993,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.2038,
|
|
"mean_token_accuracy": 0.08817718252539634,
|
|
"num_tokens": 741098.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.737551879882813,
|
|
"epoch": 0.033456525967710565,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.1523,
|
|
"mean_token_accuracy": 0.08939553946256637,
|
|
"num_tokens": 749902.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.571504878997803,
|
|
"epoch": 0.033845555339428124,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.1379,
|
|
"mean_token_accuracy": 0.09236362501978874,
|
|
"num_tokens": 758638.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.696662092208863,
|
|
"epoch": 0.03423458471114569,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.2068,
|
|
"mean_token_accuracy": 0.0883943185210228,
|
|
"num_tokens": 768170.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.6304443836212155,
|
|
"epoch": 0.034623614082863255,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.0936,
|
|
"mean_token_accuracy": 0.09277842119336129,
|
|
"num_tokens": 776745.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.6743035316467285,
|
|
"epoch": 0.03501264345458082,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.2093,
|
|
"mean_token_accuracy": 0.0887695960700512,
|
|
"num_tokens": 785030.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.6144163608551025,
|
|
"epoch": 0.035401672826298386,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.171,
|
|
"mean_token_accuracy": 0.08834633827209473,
|
|
"num_tokens": 793543.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.52853422164917,
|
|
"epoch": 0.03579070219801595,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.0163,
|
|
"mean_token_accuracy": 0.09290485829114914,
|
|
"num_tokens": 802401.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.607344436645508,
|
|
"epoch": 0.03617973156973352,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.1277,
|
|
"mean_token_accuracy": 0.08786619827151299,
|
|
"num_tokens": 811625.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.560419654846191,
|
|
"epoch": 0.03656876094145108,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.0702,
|
|
"mean_token_accuracy": 0.0898631051182747,
|
|
"num_tokens": 820742.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.608465671539307,
|
|
"epoch": 0.03695779031316864,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.1654,
|
|
"mean_token_accuracy": 0.08933878615498543,
|
|
"num_tokens": 829580.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.560161828994751,
|
|
"epoch": 0.03734681968488621,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.0934,
|
|
"mean_token_accuracy": 0.09360112398862838,
|
|
"num_tokens": 838818.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.639765310287475,
|
|
"epoch": 0.03773584905660377,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.1163,
|
|
"mean_token_accuracy": 0.08306419998407363,
|
|
"num_tokens": 847804.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.4112790584564205,
|
|
"epoch": 0.03812487842832134,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.8803,
|
|
"mean_token_accuracy": 0.10076504200696945,
|
|
"num_tokens": 856395.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.583081674575806,
|
|
"epoch": 0.0385139078000389,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.1207,
|
|
"mean_token_accuracy": 0.09502710178494453,
|
|
"num_tokens": 865219.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.43314561843872,
|
|
"epoch": 0.03890293717175647,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.9119,
|
|
"mean_token_accuracy": 0.09718281924724578,
|
|
"num_tokens": 873868.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.498023557662964,
|
|
"epoch": 0.039291966543474034,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.0232,
|
|
"mean_token_accuracy": 0.09345900416374206,
|
|
"num_tokens": 882698.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.469527721405029,
|
|
"epoch": 0.0396809959151916,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.9475,
|
|
"mean_token_accuracy": 0.0993176445364952,
|
|
"num_tokens": 891280.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.47659912109375,
|
|
"epoch": 0.04007002528690916,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.0011,
|
|
"mean_token_accuracy": 0.09124450460076332,
|
|
"num_tokens": 900044.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.436534833908081,
|
|
"epoch": 0.040459054658626724,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.9727,
|
|
"mean_token_accuracy": 0.0896801546216011,
|
|
"num_tokens": 909297.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.425080251693726,
|
|
"epoch": 0.04084808403034429,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.9447,
|
|
"mean_token_accuracy": 0.0947676196694374,
|
|
"num_tokens": 917514.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.387802982330323,
|
|
"epoch": 0.041237113402061855,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.9388,
|
|
"mean_token_accuracy": 0.09883696585893631,
|
|
"num_tokens": 925842.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.389920854568482,
|
|
"epoch": 0.04162614277377942,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.0398,
|
|
"mean_token_accuracy": 0.09228231534361839,
|
|
"num_tokens": 934676.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.4626116275787355,
|
|
"epoch": 0.042015172145496986,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.9525,
|
|
"mean_token_accuracy": 0.09330017715692521,
|
|
"num_tokens": 943763.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.356891870498657,
|
|
"epoch": 0.04240420151721455,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.9442,
|
|
"mean_token_accuracy": 0.09821118861436844,
|
|
"num_tokens": 952721.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.440818834304809,
|
|
"epoch": 0.04279323088893212,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.9443,
|
|
"mean_token_accuracy": 0.10198782086372375,
|
|
"num_tokens": 960899.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.310132646560669,
|
|
"epoch": 0.04318226026064968,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.9242,
|
|
"mean_token_accuracy": 0.09831049591302872,
|
|
"num_tokens": 969362.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.41514139175415,
|
|
"epoch": 0.04357128963236724,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.9077,
|
|
"mean_token_accuracy": 0.10258749797940254,
|
|
"num_tokens": 978028.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.3455198287963865,
|
|
"epoch": 0.04396031900408481,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.8935,
|
|
"mean_token_accuracy": 0.10291868522763252,
|
|
"num_tokens": 985709.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.418910646438599,
|
|
"epoch": 0.04434934837580237,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.976,
|
|
"mean_token_accuracy": 0.10187083706259728,
|
|
"num_tokens": 994769.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.401043939590454,
|
|
"epoch": 0.04473837774751994,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.962,
|
|
"mean_token_accuracy": 0.10199706852436066,
|
|
"num_tokens": 1003997.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.399074697494507,
|
|
"epoch": 0.0451274071192375,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.9466,
|
|
"mean_token_accuracy": 0.09917582347989082,
|
|
"num_tokens": 1012931.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.332787704467774,
|
|
"epoch": 0.04551643649095507,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.9555,
|
|
"mean_token_accuracy": 0.10086694583296776,
|
|
"num_tokens": 1021149.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.499734544754029,
|
|
"epoch": 0.045905465862672634,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.9548,
|
|
"mean_token_accuracy": 0.10112444758415222,
|
|
"num_tokens": 1029421.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.391014766693115,
|
|
"epoch": 0.0462944952343902,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.0459,
|
|
"mean_token_accuracy": 0.09981294050812721,
|
|
"num_tokens": 1037222.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.352716112136841,
|
|
"epoch": 0.04668352460610776,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.9734,
|
|
"mean_token_accuracy": 0.09807954430580139,
|
|
"num_tokens": 1046903.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.385373210906982,
|
|
"epoch": 0.047072553977825324,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.0123,
|
|
"mean_token_accuracy": 0.09519420191645622,
|
|
"num_tokens": 1055516.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.407522106170655,
|
|
"epoch": 0.04746158334954289,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.9265,
|
|
"mean_token_accuracy": 0.09930946677923203,
|
|
"num_tokens": 1063846.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.281380128860474,
|
|
"epoch": 0.047850612721260455,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.8993,
|
|
"mean_token_accuracy": 0.09943632334470749,
|
|
"num_tokens": 1072500.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.34805383682251,
|
|
"epoch": 0.04823964209297802,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.922,
|
|
"mean_token_accuracy": 0.09708855003118515,
|
|
"num_tokens": 1081399.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.2534126281738285,
|
|
"epoch": 0.048628671464695586,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.8743,
|
|
"mean_token_accuracy": 0.1036634124815464,
|
|
"num_tokens": 1089666.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.336611223220825,
|
|
"epoch": 0.04901770083641315,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.7632,
|
|
"mean_token_accuracy": 0.10756223425269126,
|
|
"num_tokens": 1097496.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.240615320205689,
|
|
"epoch": 0.04940673020813072,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.8822,
|
|
"mean_token_accuracy": 0.10434303507208824,
|
|
"num_tokens": 1105840.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.313789176940918,
|
|
"epoch": 0.049795759579848276,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.9515,
|
|
"mean_token_accuracy": 0.0976039707660675,
|
|
"num_tokens": 1115507.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.261141300201416,
|
|
"epoch": 0.05018478895156584,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.8997,
|
|
"mean_token_accuracy": 0.09827139601111412,
|
|
"num_tokens": 1124820.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.230596017837525,
|
|
"epoch": 0.05057381832328341,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.7406,
|
|
"mean_token_accuracy": 0.10685393288731575,
|
|
"num_tokens": 1133641.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.177046489715576,
|
|
"epoch": 0.05096284769500097,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.792,
|
|
"mean_token_accuracy": 0.10451765954494477,
|
|
"num_tokens": 1142182.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.294152784347534,
|
|
"epoch": 0.05135187706671854,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.8672,
|
|
"mean_token_accuracy": 0.10539027452468872,
|
|
"num_tokens": 1150737.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.172728967666626,
|
|
"epoch": 0.0517409064384361,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.7309,
|
|
"mean_token_accuracy": 0.10050051435828208,
|
|
"num_tokens": 1158899.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.331276702880859,
|
|
"epoch": 0.05212993581015367,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.819,
|
|
"mean_token_accuracy": 0.10705862119793892,
|
|
"num_tokens": 1167397.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.248978996276856,
|
|
"epoch": 0.052518965181871234,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.8332,
|
|
"mean_token_accuracy": 0.10063659623265267,
|
|
"num_tokens": 1177044.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.085381174087525,
|
|
"epoch": 0.05290799455358879,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.693,
|
|
"mean_token_accuracy": 0.10786959677934646,
|
|
"num_tokens": 1185740.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.203679895401001,
|
|
"epoch": 0.05329702392530636,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.8372,
|
|
"mean_token_accuracy": 0.10230442136526108,
|
|
"num_tokens": 1194970.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.245568037033081,
|
|
"epoch": 0.053686053297023924,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.7921,
|
|
"mean_token_accuracy": 0.10874027833342552,
|
|
"num_tokens": 1203565.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.196403169631958,
|
|
"epoch": 0.05407508266874149,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.8265,
|
|
"mean_token_accuracy": 0.10126563459634781,
|
|
"num_tokens": 1213226.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.09236512184143,
|
|
"epoch": 0.054464112040459055,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.7432,
|
|
"mean_token_accuracy": 0.1003255195915699,
|
|
"num_tokens": 1221710.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.216377449035645,
|
|
"epoch": 0.05485314141217662,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.8035,
|
|
"mean_token_accuracy": 0.09862821027636529,
|
|
"num_tokens": 1231125.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.237710189819336,
|
|
"epoch": 0.055242170783894186,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.7667,
|
|
"mean_token_accuracy": 0.10697240307927132,
|
|
"num_tokens": 1239521.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.097472429275513,
|
|
"epoch": 0.05563120015561175,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.6474,
|
|
"mean_token_accuracy": 0.11173419132828713,
|
|
"num_tokens": 1247363.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.1145548820495605,
|
|
"epoch": 0.05602022952732931,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.7447,
|
|
"mean_token_accuracy": 0.10396054536104202,
|
|
"num_tokens": 1255395.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.2065142631530765,
|
|
"epoch": 0.056409258899046875,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.813,
|
|
"mean_token_accuracy": 0.10091793909668922,
|
|
"num_tokens": 1264135.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.164863967895508,
|
|
"epoch": 0.05679828827076444,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.7421,
|
|
"mean_token_accuracy": 0.10169361084699631,
|
|
"num_tokens": 1272375.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.1601451396942135,
|
|
"epoch": 0.057187317642482006,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.7901,
|
|
"mean_token_accuracy": 0.10103225708007812,
|
|
"num_tokens": 1280960.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.184061765670776,
|
|
"epoch": 0.05757634701419957,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.8209,
|
|
"mean_token_accuracy": 0.10675038620829583,
|
|
"num_tokens": 1289273.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.113188409805298,
|
|
"epoch": 0.05796537638591714,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.7247,
|
|
"mean_token_accuracy": 0.10347931683063508,
|
|
"num_tokens": 1297571.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.19926347732544,
|
|
"epoch": 0.0583544057576347,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.7715,
|
|
"mean_token_accuracy": 0.10671985670924186,
|
|
"num_tokens": 1305686.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.111810922622681,
|
|
"epoch": 0.05874343512935227,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.7894,
|
|
"mean_token_accuracy": 0.1026329904794693,
|
|
"num_tokens": 1314483.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.088590431213379,
|
|
"epoch": 0.059132464501069834,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.6599,
|
|
"mean_token_accuracy": 0.10411886721849442,
|
|
"num_tokens": 1323183.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.122695350646973,
|
|
"epoch": 0.05952149387278739,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.7836,
|
|
"mean_token_accuracy": 0.10542866066098214,
|
|
"num_tokens": 1331964.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.062607765197754,
|
|
"epoch": 0.05991052324450496,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.7312,
|
|
"mean_token_accuracy": 0.11025277003645897,
|
|
"num_tokens": 1340185.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.220061302185059,
|
|
"epoch": 0.060299552616222524,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.806,
|
|
"mean_token_accuracy": 0.10550950691103936,
|
|
"num_tokens": 1349522.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.170696592330932,
|
|
"epoch": 0.06068858198794009,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.7858,
|
|
"mean_token_accuracy": 0.10444560423493385,
|
|
"num_tokens": 1357893.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.994049072265625,
|
|
"epoch": 0.061077611359657655,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.6669,
|
|
"mean_token_accuracy": 0.1103596955537796,
|
|
"num_tokens": 1366685.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.130297327041626,
|
|
"epoch": 0.06146664073137522,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.6085,
|
|
"mean_token_accuracy": 0.10908645838499069,
|
|
"num_tokens": 1375245.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.040684175491333,
|
|
"epoch": 0.061855670103092786,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.7932,
|
|
"mean_token_accuracy": 0.10705054327845573,
|
|
"num_tokens": 1383724.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.209282732009887,
|
|
"epoch": 0.06224469947481035,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.7782,
|
|
"mean_token_accuracy": 0.10306280329823495,
|
|
"num_tokens": 1392455.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.1856764793396,
|
|
"epoch": 0.06263372884652792,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.7794,
|
|
"mean_token_accuracy": 0.10756833851337433,
|
|
"num_tokens": 1401262.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.964628410339356,
|
|
"epoch": 0.06302275821824548,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.6675,
|
|
"mean_token_accuracy": 0.1083975151181221,
|
|
"num_tokens": 1409991.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.013374662399292,
|
|
"epoch": 0.06341178758996305,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.6617,
|
|
"mean_token_accuracy": 0.1109016127884388,
|
|
"num_tokens": 1418208.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.072976303100586,
|
|
"epoch": 0.0638008169616806,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.6608,
|
|
"mean_token_accuracy": 0.11023175194859505,
|
|
"num_tokens": 1426665.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.980063629150391,
|
|
"epoch": 0.06418984633339817,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.5932,
|
|
"mean_token_accuracy": 0.11027788445353508,
|
|
"num_tokens": 1435247.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.98336706161499,
|
|
"epoch": 0.06457887570511574,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.6365,
|
|
"mean_token_accuracy": 0.11016326993703843,
|
|
"num_tokens": 1443678.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.947188854217529,
|
|
"epoch": 0.0649679050768333,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.5746,
|
|
"mean_token_accuracy": 0.11637299805879593,
|
|
"num_tokens": 1451567.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.953899240493774,
|
|
"epoch": 0.06535693444855087,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.5881,
|
|
"mean_token_accuracy": 0.10969302877783775,
|
|
"num_tokens": 1460618.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.999412250518799,
|
|
"epoch": 0.06574596382026843,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.667,
|
|
"mean_token_accuracy": 0.11072178110480309,
|
|
"num_tokens": 1469821.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.0580075740814205,
|
|
"epoch": 0.066134993191986,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.7378,
|
|
"mean_token_accuracy": 0.10718388482928276,
|
|
"num_tokens": 1477989.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.051467561721802,
|
|
"epoch": 0.06652402256370356,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.7462,
|
|
"mean_token_accuracy": 0.10824755355715751,
|
|
"num_tokens": 1486822.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.015081548690796,
|
|
"epoch": 0.06691305193542113,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.6159,
|
|
"mean_token_accuracy": 0.1050032138824463,
|
|
"num_tokens": 1496604.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.946830940246582,
|
|
"epoch": 0.06730208130713869,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.6411,
|
|
"mean_token_accuracy": 0.1079692468047142,
|
|
"num_tokens": 1504725.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.015288543701172,
|
|
"epoch": 0.06769111067885625,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.6492,
|
|
"mean_token_accuracy": 0.11273297667503357,
|
|
"num_tokens": 1513222.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.022673845291138,
|
|
"epoch": 0.06808014005057382,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.6131,
|
|
"mean_token_accuracy": 0.10831626504659653,
|
|
"num_tokens": 1522183.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.945608234405517,
|
|
"epoch": 0.06846916942229138,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.6553,
|
|
"mean_token_accuracy": 0.10740983784198761,
|
|
"num_tokens": 1531316.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.046859550476074,
|
|
"epoch": 0.06885819879400895,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.7085,
|
|
"mean_token_accuracy": 0.10943676829338074,
|
|
"num_tokens": 1540053.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.0075178146362305,
|
|
"epoch": 0.06924722816572651,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.5681,
|
|
"mean_token_accuracy": 0.11703129261732101,
|
|
"num_tokens": 1549391.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.040959405899048,
|
|
"epoch": 0.06963625753744408,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.6779,
|
|
"mean_token_accuracy": 0.11206066384911537,
|
|
"num_tokens": 1557364.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.902760457992554,
|
|
"epoch": 0.07002528690916164,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.5277,
|
|
"mean_token_accuracy": 0.10990011170506478,
|
|
"num_tokens": 1567011.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.839785480499268,
|
|
"epoch": 0.0704143162808792,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.6347,
|
|
"mean_token_accuracy": 0.10979588106274604,
|
|
"num_tokens": 1575441.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.96569299697876,
|
|
"epoch": 0.07080334565259677,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.5902,
|
|
"mean_token_accuracy": 0.11274805590510369,
|
|
"num_tokens": 1583757.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.020220041275024,
|
|
"epoch": 0.07119237502431433,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.6305,
|
|
"mean_token_accuracy": 0.11361563205718994,
|
|
"num_tokens": 1592406.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.9013814449310305,
|
|
"epoch": 0.0715814043960319,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.6107,
|
|
"mean_token_accuracy": 0.11090241372585297,
|
|
"num_tokens": 1601665.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.95518798828125,
|
|
"epoch": 0.07197043376774946,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.6219,
|
|
"mean_token_accuracy": 0.11311167180538177,
|
|
"num_tokens": 1609788.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.954713582992554,
|
|
"epoch": 0.07235946313946703,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.618,
|
|
"mean_token_accuracy": 0.11602962091565132,
|
|
"num_tokens": 1618030.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.909007263183594,
|
|
"epoch": 0.07274849251118459,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.619,
|
|
"mean_token_accuracy": 0.10842904224991798,
|
|
"num_tokens": 1626901.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.836823034286499,
|
|
"epoch": 0.07313752188290217,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.5232,
|
|
"mean_token_accuracy": 0.1104541540145874,
|
|
"num_tokens": 1635372.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.920376491546631,
|
|
"epoch": 0.07352655125461972,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.5485,
|
|
"mean_token_accuracy": 0.11306027993559838,
|
|
"num_tokens": 1643791.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.767651128768921,
|
|
"epoch": 0.07391558062633728,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.518,
|
|
"mean_token_accuracy": 0.1175017923116684,
|
|
"num_tokens": 1652161.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.930508375167847,
|
|
"epoch": 0.07430460999805485,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.5631,
|
|
"mean_token_accuracy": 0.1112576186656952,
|
|
"num_tokens": 1661077.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.823507070541382,
|
|
"epoch": 0.07469363936977241,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.5267,
|
|
"mean_token_accuracy": 0.1152154453098774,
|
|
"num_tokens": 1669010.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.9437110900878904,
|
|
"epoch": 0.07508266874148999,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.6996,
|
|
"mean_token_accuracy": 0.10548838526010514,
|
|
"num_tokens": 1678002.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.970439100265503,
|
|
"epoch": 0.07547169811320754,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.6515,
|
|
"mean_token_accuracy": 0.11191459000110626,
|
|
"num_tokens": 1687403.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.899893045425415,
|
|
"epoch": 0.07586072748492512,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.568,
|
|
"mean_token_accuracy": 0.11637896820902824,
|
|
"num_tokens": 1695512.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.905468416213989,
|
|
"epoch": 0.07624975685664268,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.562,
|
|
"mean_token_accuracy": 0.11065016388893127,
|
|
"num_tokens": 1705116.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.740264987945556,
|
|
"epoch": 0.07663878622836025,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.4647,
|
|
"mean_token_accuracy": 0.11217278465628625,
|
|
"num_tokens": 1713715.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.905466890335083,
|
|
"epoch": 0.0770278156000778,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.534,
|
|
"mean_token_accuracy": 0.11301849856972694,
|
|
"num_tokens": 1721881.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.823386716842651,
|
|
"epoch": 0.07741684497179536,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.5621,
|
|
"mean_token_accuracy": 0.11369865015149117,
|
|
"num_tokens": 1730716.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.003415536880493,
|
|
"epoch": 0.07780587434351294,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.7061,
|
|
"mean_token_accuracy": 0.11018745675683021,
|
|
"num_tokens": 1740257.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.86281156539917,
|
|
"epoch": 0.0781949037152305,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999999989075146,
|
|
"loss": 6.6085,
|
|
"mean_token_accuracy": 0.1118568867444992,
|
|
"num_tokens": 1749071.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.864678907394409,
|
|
"epoch": 0.07858393308694807,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999999944692927,
|
|
"loss": 6.6204,
|
|
"mean_token_accuracy": 0.10326161161065102,
|
|
"num_tokens": 1757952.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.863972473144531,
|
|
"epoch": 0.07897296245866563,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499999986617054,
|
|
"loss": 6.5531,
|
|
"mean_token_accuracy": 0.11324110552668572,
|
|
"num_tokens": 1766027.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.801832294464111,
|
|
"epoch": 0.0793619918303832,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999999753507986,
|
|
"loss": 6.5527,
|
|
"mean_token_accuracy": 0.10727588534355163,
|
|
"num_tokens": 1775039.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.848104572296142,
|
|
"epoch": 0.07975102120210076,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999999606705267,
|
|
"loss": 6.5556,
|
|
"mean_token_accuracy": 0.11754972413182259,
|
|
"num_tokens": 1783971.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.8215718269348145,
|
|
"epoch": 0.08014005057381832,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999999425762385,
|
|
"loss": 6.4753,
|
|
"mean_token_accuracy": 0.11163984313607216,
|
|
"num_tokens": 1792743.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.859644365310669,
|
|
"epoch": 0.08052907994553589,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999999210679344,
|
|
"loss": 6.6316,
|
|
"mean_token_accuracy": 0.10586050003767014,
|
|
"num_tokens": 1801435.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.908881664276123,
|
|
"epoch": 0.08091810931725345,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999998961456145,
|
|
"loss": 6.5221,
|
|
"mean_token_accuracy": 0.10814850106835365,
|
|
"num_tokens": 1810147.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.809201431274414,
|
|
"epoch": 0.08130713868897102,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999998678092794,
|
|
"loss": 6.4526,
|
|
"mean_token_accuracy": 0.11560517325997352,
|
|
"num_tokens": 1818672.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.868528652191162,
|
|
"epoch": 0.08169616806068858,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999998360589293,
|
|
"loss": 6.5984,
|
|
"mean_token_accuracy": 0.11358216851949691,
|
|
"num_tokens": 1827590.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.771164989471435,
|
|
"epoch": 0.08208519743240615,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499999800894565,
|
|
"loss": 6.513,
|
|
"mean_token_accuracy": 0.11691295430064201,
|
|
"num_tokens": 1836467.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.7579442977905275,
|
|
"epoch": 0.08247422680412371,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999997623161866,
|
|
"loss": 6.4583,
|
|
"mean_token_accuracy": 0.11373137831687927,
|
|
"num_tokens": 1845537.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.780694103240966,
|
|
"epoch": 0.08286325617584128,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999997203237951,
|
|
"loss": 6.4658,
|
|
"mean_token_accuracy": 0.12047376260161399,
|
|
"num_tokens": 1854433.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.7921051502227785,
|
|
"epoch": 0.08325228554755884,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499999674917391,
|
|
"loss": 6.5716,
|
|
"mean_token_accuracy": 0.10947082787752152,
|
|
"num_tokens": 1863708.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.810097408294678,
|
|
"epoch": 0.0836413149192764,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999996260969748,
|
|
"loss": 6.4373,
|
|
"mean_token_accuracy": 0.11977095603942871,
|
|
"num_tokens": 1871854.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.711810445785522,
|
|
"epoch": 0.08403034429099397,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999995738625475,
|
|
"loss": 6.4063,
|
|
"mean_token_accuracy": 0.1185697853565216,
|
|
"num_tokens": 1880471.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.751388072967529,
|
|
"epoch": 0.08441937366271153,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999995182141099,
|
|
"loss": 6.4624,
|
|
"mean_token_accuracy": 0.11945423632860183,
|
|
"num_tokens": 1889882.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.6411792755126955,
|
|
"epoch": 0.0848084030344291,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999994591516626,
|
|
"loss": 6.3584,
|
|
"mean_token_accuracy": 0.12587759271264076,
|
|
"num_tokens": 1898701.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.699534511566162,
|
|
"epoch": 0.08519743240614666,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999993966752066,
|
|
"loss": 6.4607,
|
|
"mean_token_accuracy": 0.11258344799280166,
|
|
"num_tokens": 1908165.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.743130016326904,
|
|
"epoch": 0.08558646177786423,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499999330784743,
|
|
"loss": 6.5679,
|
|
"mean_token_accuracy": 0.11548311486840249,
|
|
"num_tokens": 1916295.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.833187913894653,
|
|
"epoch": 0.08597549114958179,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999992614802725,
|
|
"loss": 6.4638,
|
|
"mean_token_accuracy": 0.11991653963923454,
|
|
"num_tokens": 1924643.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.747153854370117,
|
|
"epoch": 0.08636452052129936,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999991887617966,
|
|
"loss": 6.4623,
|
|
"mean_token_accuracy": 0.11614882722496986,
|
|
"num_tokens": 1933822.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.6497047424316404,
|
|
"epoch": 0.08675354989301692,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999991126293158,
|
|
"loss": 6.4652,
|
|
"mean_token_accuracy": 0.11403647363185883,
|
|
"num_tokens": 1943278.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.89057731628418,
|
|
"epoch": 0.08714257926473448,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999990330828318,
|
|
"loss": 6.4991,
|
|
"mean_token_accuracy": 0.11635721921920776,
|
|
"num_tokens": 1951883.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.618956565856934,
|
|
"epoch": 0.08753160863645205,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999989501223456,
|
|
"loss": 6.3814,
|
|
"mean_token_accuracy": 0.12408010512590409,
|
|
"num_tokens": 1959567.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.809039831161499,
|
|
"epoch": 0.08792063800816961,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999988637478584,
|
|
"loss": 6.4599,
|
|
"mean_token_accuracy": 0.11816074550151826,
|
|
"num_tokens": 1968190.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.56049690246582,
|
|
"epoch": 0.08830966737988719,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999987739593716,
|
|
"loss": 6.377,
|
|
"mean_token_accuracy": 0.12225727364420891,
|
|
"num_tokens": 1977519.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.749509620666504,
|
|
"epoch": 0.08869869675160474,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999986807568865,
|
|
"loss": 6.3718,
|
|
"mean_token_accuracy": 0.11851018518209458,
|
|
"num_tokens": 1985796.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.7915668964385985,
|
|
"epoch": 0.08908772612332232,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999985841404045,
|
|
"loss": 6.5103,
|
|
"mean_token_accuracy": 0.1153883047401905,
|
|
"num_tokens": 1993874.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.830569458007813,
|
|
"epoch": 0.08947675549503988,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999984841099271,
|
|
"loss": 6.4631,
|
|
"mean_token_accuracy": 0.12087473869323731,
|
|
"num_tokens": 2001663.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.626487779617309,
|
|
"epoch": 0.08986578486675743,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499998380665456,
|
|
"loss": 6.4341,
|
|
"mean_token_accuracy": 0.12093059793114662,
|
|
"num_tokens": 2010179.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.774807786941528,
|
|
"epoch": 0.090254814238475,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999982738069924,
|
|
"loss": 6.3481,
|
|
"mean_token_accuracy": 0.11917036697268486,
|
|
"num_tokens": 2020013.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.651696872711182,
|
|
"epoch": 0.09064384361019256,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004999981635345382,
|
|
"loss": 6.4849,
|
|
"mean_token_accuracy": 0.12042224928736686,
|
|
"num_tokens": 2028396.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.807629251480103,
|
|
"epoch": 0.09103287298191014,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999980498480949,
|
|
"loss": 6.5699,
|
|
"mean_token_accuracy": 0.11065206825733184,
|
|
"num_tokens": 2036947.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.702048110961914,
|
|
"epoch": 0.0914219023536277,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999979327476644,
|
|
"loss": 6.4087,
|
|
"mean_token_accuracy": 0.11726011484861373,
|
|
"num_tokens": 2045162.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.737331104278565,
|
|
"epoch": 0.09181093172534527,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999978122332485,
|
|
"loss": 6.4986,
|
|
"mean_token_accuracy": 0.11559060364961624,
|
|
"num_tokens": 2054198.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.650309991836548,
|
|
"epoch": 0.09219996109706283,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999976883048487,
|
|
"loss": 6.419,
|
|
"mean_token_accuracy": 0.11779844760894775,
|
|
"num_tokens": 2062558.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.701250696182251,
|
|
"epoch": 0.0925889904687804,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999975609624673,
|
|
"loss": 6.2995,
|
|
"mean_token_accuracy": 0.11358527466654778,
|
|
"num_tokens": 2070816.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.61013011932373,
|
|
"epoch": 0.09297801984049796,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999974302061059,
|
|
"loss": 6.3538,
|
|
"mean_token_accuracy": 0.11822599768638611,
|
|
"num_tokens": 2079058.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.643589496612549,
|
|
"epoch": 0.09336704921221552,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999972960357666,
|
|
"loss": 6.3214,
|
|
"mean_token_accuracy": 0.12255356609821319,
|
|
"num_tokens": 2086679.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.664435195922851,
|
|
"epoch": 0.09375607858393309,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004999971584514516,
|
|
"loss": 6.4264,
|
|
"mean_token_accuracy": 0.11835757493972779,
|
|
"num_tokens": 2095788.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.6650059700012205,
|
|
"epoch": 0.09414510795565065,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999970174531627,
|
|
"loss": 6.4504,
|
|
"mean_token_accuracy": 0.11537863463163375,
|
|
"num_tokens": 2105435.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.69662823677063,
|
|
"epoch": 0.09453413732736822,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999968730409022,
|
|
"loss": 6.3946,
|
|
"mean_token_accuracy": 0.11899836733937263,
|
|
"num_tokens": 2114318.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.603922605514526,
|
|
"epoch": 0.09492316669908578,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999967252146723,
|
|
"loss": 6.319,
|
|
"mean_token_accuracy": 0.1297658160328865,
|
|
"num_tokens": 2122707.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.5683904647827145,
|
|
"epoch": 0.09531219607080335,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999965739744752,
|
|
"loss": 6.4173,
|
|
"mean_token_accuracy": 0.1176735907793045,
|
|
"num_tokens": 2131176.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.759912300109863,
|
|
"epoch": 0.09570122544252091,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999964193203132,
|
|
"loss": 6.4613,
|
|
"mean_token_accuracy": 0.12155932411551476,
|
|
"num_tokens": 2139872.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.643018627166748,
|
|
"epoch": 0.09609025481423847,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999962612521888,
|
|
"loss": 6.3193,
|
|
"mean_token_accuracy": 0.12510446161031724,
|
|
"num_tokens": 2148668.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.589841032028199,
|
|
"epoch": 0.09647928418595604,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999960997701041,
|
|
"loss": 6.3267,
|
|
"mean_token_accuracy": 0.12770092412829398,
|
|
"num_tokens": 2156628.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.672489738464355,
|
|
"epoch": 0.0968683135576736,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999959348740618,
|
|
"loss": 6.4077,
|
|
"mean_token_accuracy": 0.11675584986805916,
|
|
"num_tokens": 2165620.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.6866566181182865,
|
|
"epoch": 0.09725734292939117,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999957665640641,
|
|
"loss": 6.474,
|
|
"mean_token_accuracy": 0.12056236788630485,
|
|
"num_tokens": 2174493.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.706568670272827,
|
|
"epoch": 0.09764637230110873,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499995594840114,
|
|
"loss": 6.3623,
|
|
"mean_token_accuracy": 0.11302633062005044,
|
|
"num_tokens": 2183258.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.616120624542236,
|
|
"epoch": 0.0980354016728263,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999954197022138,
|
|
"loss": 6.4286,
|
|
"mean_token_accuracy": 0.11189185678958893,
|
|
"num_tokens": 2192263.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.736319494247437,
|
|
"epoch": 0.09842443104454386,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999952411503661,
|
|
"loss": 6.4736,
|
|
"mean_token_accuracy": 0.11438293233513833,
|
|
"num_tokens": 2201797.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.494112110137939,
|
|
"epoch": 0.09881346041626143,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999950591845738,
|
|
"loss": 6.2042,
|
|
"mean_token_accuracy": 0.129413703083992,
|
|
"num_tokens": 2209454.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.683527231216431,
|
|
"epoch": 0.09920248978797899,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999948738048397,
|
|
"loss": 6.392,
|
|
"mean_token_accuracy": 0.12001634314656258,
|
|
"num_tokens": 2217761.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.541403865814209,
|
|
"epoch": 0.09959151915969655,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999946850111663,
|
|
"loss": 6.3754,
|
|
"mean_token_accuracy": 0.118533456325531,
|
|
"num_tokens": 2225793.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.716179895401001,
|
|
"epoch": 0.09998054853141412,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999944928035569,
|
|
"loss": 6.263,
|
|
"mean_token_accuracy": 0.12969468906521797,
|
|
"num_tokens": 2234620.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.541376686096191,
|
|
"epoch": 0.10036957790313168,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499994297182014,
|
|
"loss": 6.3484,
|
|
"mean_token_accuracy": 0.11944441497325897,
|
|
"num_tokens": 2242829.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.670366430282593,
|
|
"epoch": 0.10075860727484925,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999940981465408,
|
|
"loss": 6.3704,
|
|
"mean_token_accuracy": 0.11480111479759217,
|
|
"num_tokens": 2251356.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.56609148979187,
|
|
"epoch": 0.10114763664656681,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999938956971404,
|
|
"loss": 6.4409,
|
|
"mean_token_accuracy": 0.11915249675512314,
|
|
"num_tokens": 2259327.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.683287715911865,
|
|
"epoch": 0.10153666601828439,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999936898338156,
|
|
"loss": 6.4538,
|
|
"mean_token_accuracy": 0.11428613439202309,
|
|
"num_tokens": 2267948.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.560197353363037,
|
|
"epoch": 0.10192569539000194,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999934805565698,
|
|
"loss": 6.281,
|
|
"mean_token_accuracy": 0.1233622319996357,
|
|
"num_tokens": 2275828.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.534844875335693,
|
|
"epoch": 0.10231472476171952,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499993267865406,
|
|
"loss": 6.2154,
|
|
"mean_token_accuracy": 0.1286098428070545,
|
|
"num_tokens": 2284246.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.50963945388794,
|
|
"epoch": 0.10270375413343708,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999930517603275,
|
|
"loss": 6.2122,
|
|
"mean_token_accuracy": 0.13067591562867165,
|
|
"num_tokens": 2291837.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.6015325546264645,
|
|
"epoch": 0.10309278350515463,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999928322413374,
|
|
"loss": 6.2854,
|
|
"mean_token_accuracy": 0.12339815348386765,
|
|
"num_tokens": 2299853.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.674331474304199,
|
|
"epoch": 0.1034818128768722,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999926093084394,
|
|
"loss": 6.3807,
|
|
"mean_token_accuracy": 0.11902100816369057,
|
|
"num_tokens": 2308416.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.549804925918579,
|
|
"epoch": 0.10387084224858976,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999923829616365,
|
|
"loss": 6.4127,
|
|
"mean_token_accuracy": 0.11715119779109955,
|
|
"num_tokens": 2318104.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.6144133567810055,
|
|
"epoch": 0.10425987162030734,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999921532009323,
|
|
"loss": 6.3325,
|
|
"mean_token_accuracy": 0.11866103261709213,
|
|
"num_tokens": 2326807.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.590117406845093,
|
|
"epoch": 0.1046489009920249,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999919200263304,
|
|
"loss": 6.3363,
|
|
"mean_token_accuracy": 0.11958926171064377,
|
|
"num_tokens": 2335921.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.594919157028198,
|
|
"epoch": 0.10503793036374247,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999916834378342,
|
|
"loss": 6.3476,
|
|
"mean_token_accuracy": 0.12185617685317993,
|
|
"num_tokens": 2344914.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.542745637893677,
|
|
"epoch": 0.10542695973546003,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999914434354472,
|
|
"loss": 6.2886,
|
|
"mean_token_accuracy": 0.11944291591644288,
|
|
"num_tokens": 2353211.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.57375807762146,
|
|
"epoch": 0.10581598910717759,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999912000191733,
|
|
"loss": 6.4112,
|
|
"mean_token_accuracy": 0.11920397132635116,
|
|
"num_tokens": 2361717.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.566148090362549,
|
|
"epoch": 0.10620501847889516,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499990953189016,
|
|
"loss": 6.346,
|
|
"mean_token_accuracy": 0.12413823828101159,
|
|
"num_tokens": 2370114.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.700903367996216,
|
|
"epoch": 0.10659404785061272,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999907029449791,
|
|
"loss": 6.3374,
|
|
"mean_token_accuracy": 0.11766661703586578,
|
|
"num_tokens": 2378820.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.436738204956055,
|
|
"epoch": 0.10698307722233029,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999904492870663,
|
|
"loss": 6.2537,
|
|
"mean_token_accuracy": 0.12378470376133918,
|
|
"num_tokens": 2387119.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.5843147277832035,
|
|
"epoch": 0.10737210659404785,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999901922152816,
|
|
"loss": 6.3039,
|
|
"mean_token_accuracy": 0.12202484160661697,
|
|
"num_tokens": 2396246.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.51186990737915,
|
|
"epoch": 0.10776113596576542,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999899317296288,
|
|
"loss": 6.3581,
|
|
"mean_token_accuracy": 0.11975730657577514,
|
|
"num_tokens": 2405428.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.566965532302857,
|
|
"epoch": 0.10815016533748298,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999896678301121,
|
|
"loss": 6.3066,
|
|
"mean_token_accuracy": 0.12349836975336075,
|
|
"num_tokens": 2414669.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.655934619903564,
|
|
"epoch": 0.10853919470920055,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999894005167352,
|
|
"loss": 6.3868,
|
|
"mean_token_accuracy": 0.11691371873021125,
|
|
"num_tokens": 2423193.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.565681409835816,
|
|
"epoch": 0.10892822408091811,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499989129789502,
|
|
"loss": 6.3387,
|
|
"mean_token_accuracy": 0.1171958826482296,
|
|
"num_tokens": 2431150.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.56759557723999,
|
|
"epoch": 0.10931725345263567,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999888556484172,
|
|
"loss": 6.3134,
|
|
"mean_token_accuracy": 0.1197988323867321,
|
|
"num_tokens": 2440337.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.470945692062378,
|
|
"epoch": 0.10970628282435324,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999885780934845,
|
|
"loss": 6.2513,
|
|
"mean_token_accuracy": 0.12705043703317642,
|
|
"num_tokens": 2449246.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.516160583496093,
|
|
"epoch": 0.1100953121960708,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999882971247081,
|
|
"loss": 6.2565,
|
|
"mean_token_accuracy": 0.12589537277817725,
|
|
"num_tokens": 2457982.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.5252786636352536,
|
|
"epoch": 0.11048434156778837,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999880127420926,
|
|
"loss": 6.2425,
|
|
"mean_token_accuracy": 0.12535301148891448,
|
|
"num_tokens": 2466697.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.493203258514404,
|
|
"epoch": 0.11087337093950593,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999877249456421,
|
|
"loss": 6.2222,
|
|
"mean_token_accuracy": 0.12576746717095375,
|
|
"num_tokens": 2475457.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.437700080871582,
|
|
"epoch": 0.1112624003112235,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999874337353609,
|
|
"loss": 6.2138,
|
|
"mean_token_accuracy": 0.12601543366909027,
|
|
"num_tokens": 2484753.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.485835027694702,
|
|
"epoch": 0.11165142968294106,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999871391112535,
|
|
"loss": 6.3166,
|
|
"mean_token_accuracy": 0.12342042103409767,
|
|
"num_tokens": 2492921.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.581958627700805,
|
|
"epoch": 0.11204045905465862,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999868410733244,
|
|
"loss": 6.2879,
|
|
"mean_token_accuracy": 0.1212073914706707,
|
|
"num_tokens": 2501371.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.5133496761322025,
|
|
"epoch": 0.11242948842637619,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499986539621578,
|
|
"loss": 6.1714,
|
|
"mean_token_accuracy": 0.12704863548278808,
|
|
"num_tokens": 2509521.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.48231053352356,
|
|
"epoch": 0.11281851779809375,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999862347560191,
|
|
"loss": 6.2989,
|
|
"mean_token_accuracy": 0.12423472106456757,
|
|
"num_tokens": 2518316.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.569843530654907,
|
|
"epoch": 0.11320754716981132,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999859264766521,
|
|
"loss": 6.3733,
|
|
"mean_token_accuracy": 0.1180838830769062,
|
|
"num_tokens": 2527549.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.596394872665405,
|
|
"epoch": 0.11359657654152888,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999856147834817,
|
|
"loss": 6.3999,
|
|
"mean_token_accuracy": 0.12059949561953545,
|
|
"num_tokens": 2536341.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.44488263130188,
|
|
"epoch": 0.11398560591324645,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999852996765129,
|
|
"loss": 6.2924,
|
|
"mean_token_accuracy": 0.13068008571863174,
|
|
"num_tokens": 2544869.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.523885440826416,
|
|
"epoch": 0.11437463528496401,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999849811557502,
|
|
"loss": 6.1793,
|
|
"mean_token_accuracy": 0.13547530099749566,
|
|
"num_tokens": 2553432.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.51270112991333,
|
|
"epoch": 0.11476366465668159,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999846592211984,
|
|
"loss": 6.3122,
|
|
"mean_token_accuracy": 0.11962430030107499,
|
|
"num_tokens": 2561996.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.515383100509643,
|
|
"epoch": 0.11515269402839914,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999843338728626,
|
|
"loss": 6.2467,
|
|
"mean_token_accuracy": 0.12699604406952858,
|
|
"num_tokens": 2571315.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.514121627807617,
|
|
"epoch": 0.1155417234001167,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999840051107476,
|
|
"loss": 6.3579,
|
|
"mean_token_accuracy": 0.12020841464400292,
|
|
"num_tokens": 2579589.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.5186272144317625,
|
|
"epoch": 0.11593075277183428,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999836729348584,
|
|
"loss": 6.1182,
|
|
"mean_token_accuracy": 0.1279861733317375,
|
|
"num_tokens": 2588528.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.421968936920166,
|
|
"epoch": 0.11631978214355183,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999833373452,
|
|
"loss": 6.2575,
|
|
"mean_token_accuracy": 0.12487708628177643,
|
|
"num_tokens": 2596820.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.408306360244751,
|
|
"epoch": 0.1167088115152694,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999829983417778,
|
|
"loss": 6.1765,
|
|
"mean_token_accuracy": 0.12320946007966996,
|
|
"num_tokens": 2605502.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.448068284988404,
|
|
"epoch": 0.11709784088698696,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999826559245965,
|
|
"loss": 6.1834,
|
|
"mean_token_accuracy": 0.13115072697401048,
|
|
"num_tokens": 2613974.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.4151896953582765,
|
|
"epoch": 0.11748687025870454,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999823100936615,
|
|
"loss": 6.2679,
|
|
"mean_token_accuracy": 0.12410511299967766,
|
|
"num_tokens": 2622581.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.444796562194824,
|
|
"epoch": 0.1178758996304221,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999819608489781,
|
|
"loss": 6.1459,
|
|
"mean_token_accuracy": 0.12382340282201768,
|
|
"num_tokens": 2631868.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.3898896217346195,
|
|
"epoch": 0.11826492900213967,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999816081905515,
|
|
"loss": 6.1683,
|
|
"mean_token_accuracy": 0.12991080954670906,
|
|
"num_tokens": 2640501.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.531676197052002,
|
|
"epoch": 0.11865395837385723,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999812521183872,
|
|
"loss": 6.1699,
|
|
"mean_token_accuracy": 0.1317140817642212,
|
|
"num_tokens": 2648916.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.465039777755737,
|
|
"epoch": 0.11904298774557479,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999808926324903,
|
|
"loss": 6.2552,
|
|
"mean_token_accuracy": 0.13165784254670143,
|
|
"num_tokens": 2657725.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.431260061264038,
|
|
"epoch": 0.11943201711729236,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999805297328665,
|
|
"loss": 6.2322,
|
|
"mean_token_accuracy": 0.12672695890069008,
|
|
"num_tokens": 2665983.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.433292293548584,
|
|
"epoch": 0.11982104648900992,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999801634195214,
|
|
"loss": 6.2582,
|
|
"mean_token_accuracy": 0.1332721345126629,
|
|
"num_tokens": 2674546.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.488146877288818,
|
|
"epoch": 0.12021007586072749,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999797936924603,
|
|
"loss": 6.176,
|
|
"mean_token_accuracy": 0.12813623994588852,
|
|
"num_tokens": 2684088.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.44085841178894,
|
|
"epoch": 0.12059910523244505,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499979420551689,
|
|
"loss": 6.2212,
|
|
"mean_token_accuracy": 0.12631620317697526,
|
|
"num_tokens": 2693289.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.404530429840088,
|
|
"epoch": 0.12098813460416262,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499979043997213,
|
|
"loss": 6.1547,
|
|
"mean_token_accuracy": 0.13262817338109018,
|
|
"num_tokens": 2701744.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.463164138793945,
|
|
"epoch": 0.12137716397588018,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999786640290381,
|
|
"loss": 6.2138,
|
|
"mean_token_accuracy": 0.12017801105976104,
|
|
"num_tokens": 2710584.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.473390579223633,
|
|
"epoch": 0.12176619334759774,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999782806471701,
|
|
"loss": 6.221,
|
|
"mean_token_accuracy": 0.12257171049714088,
|
|
"num_tokens": 2719478.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.51469931602478,
|
|
"epoch": 0.12215522271931531,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999778938516147,
|
|
"loss": 6.3018,
|
|
"mean_token_accuracy": 0.11738094314932823,
|
|
"num_tokens": 2729105.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.504203176498413,
|
|
"epoch": 0.12254425209103287,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499977503642378,
|
|
"loss": 6.2567,
|
|
"mean_token_accuracy": 0.12570588439702987,
|
|
"num_tokens": 2738300.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.46259298324585,
|
|
"epoch": 0.12293328146275044,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999771100194656,
|
|
"loss": 6.1997,
|
|
"mean_token_accuracy": 0.12281355112791062,
|
|
"num_tokens": 2747236.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.313042402267456,
|
|
"epoch": 0.123322310834468,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999767129828837,
|
|
"loss": 6.1552,
|
|
"mean_token_accuracy": 0.13333506733179093,
|
|
"num_tokens": 2755919.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.3901971817016605,
|
|
"epoch": 0.12371134020618557,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999763125326383,
|
|
"loss": 6.1311,
|
|
"mean_token_accuracy": 0.13379732444882392,
|
|
"num_tokens": 2764469.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.470418119430542,
|
|
"epoch": 0.12410036957790313,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999759086687355,
|
|
"loss": 6.1465,
|
|
"mean_token_accuracy": 0.13174793347716332,
|
|
"num_tokens": 2772663.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.470247459411621,
|
|
"epoch": 0.1244893989496207,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999755013911813,
|
|
"loss": 6.1849,
|
|
"mean_token_accuracy": 0.12125680297613144,
|
|
"num_tokens": 2780719.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.411885499954224,
|
|
"epoch": 0.12487842832133826,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499975090699982,
|
|
"loss": 6.2373,
|
|
"mean_token_accuracy": 0.12744609639048576,
|
|
"num_tokens": 2789186.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.416819286346436,
|
|
"epoch": 0.12526745769305583,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999746765951438,
|
|
"loss": 6.1496,
|
|
"mean_token_accuracy": 0.12793729454278946,
|
|
"num_tokens": 2797993.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.388448762893677,
|
|
"epoch": 0.1256564870647734,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999742590766729,
|
|
"loss": 6.1015,
|
|
"mean_token_accuracy": 0.12969864159822464,
|
|
"num_tokens": 2806375.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.462837028503418,
|
|
"epoch": 0.12604551643649095,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999738381445757,
|
|
"loss": 6.2504,
|
|
"mean_token_accuracy": 0.1330662988126278,
|
|
"num_tokens": 2814772.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.313505363464356,
|
|
"epoch": 0.1264345458082085,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999734137988586,
|
|
"loss": 6.1229,
|
|
"mean_token_accuracy": 0.1330338940024376,
|
|
"num_tokens": 2824231.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.429342603683471,
|
|
"epoch": 0.1268235751799261,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499972986039528,
|
|
"loss": 6.1851,
|
|
"mean_token_accuracy": 0.12637867406010628,
|
|
"num_tokens": 2833470.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.42327880859375,
|
|
"epoch": 0.12721260455164365,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999725548665904,
|
|
"loss": 6.1914,
|
|
"mean_token_accuracy": 0.1272370584309101,
|
|
"num_tokens": 2843010.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.4151369571685795,
|
|
"epoch": 0.1276016339233612,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999721202800524,
|
|
"loss": 6.0894,
|
|
"mean_token_accuracy": 0.13450721949338912,
|
|
"num_tokens": 2851545.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.322131395339966,
|
|
"epoch": 0.12799066329507877,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999716822799206,
|
|
"loss": 6.2373,
|
|
"mean_token_accuracy": 0.11726373285055161,
|
|
"num_tokens": 2861230.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.472705364227295,
|
|
"epoch": 0.12837969266679633,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999712408662016,
|
|
"loss": 6.1988,
|
|
"mean_token_accuracy": 0.12872418239712716,
|
|
"num_tokens": 2869436.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.349573040008545,
|
|
"epoch": 0.12876872203851392,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999707960389021,
|
|
"loss": 6.0591,
|
|
"mean_token_accuracy": 0.13055680692195892,
|
|
"num_tokens": 2877688.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.446641206741333,
|
|
"epoch": 0.12915775141023147,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999703477980288,
|
|
"loss": 6.2037,
|
|
"mean_token_accuracy": 0.12923076152801513,
|
|
"num_tokens": 2887043.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.349732732772827,
|
|
"epoch": 0.12954678078194903,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999698961435885,
|
|
"loss": 6.1317,
|
|
"mean_token_accuracy": 0.13411349356174468,
|
|
"num_tokens": 2895732.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.334634923934937,
|
|
"epoch": 0.1299358101536666,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999694410755882,
|
|
"loss": 6.0911,
|
|
"mean_token_accuracy": 0.12794594317674637,
|
|
"num_tokens": 2904162.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.453775310516358,
|
|
"epoch": 0.13032483952538418,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999689825940347,
|
|
"loss": 6.2303,
|
|
"mean_token_accuracy": 0.12870074063539505,
|
|
"num_tokens": 2912783.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.386454153060913,
|
|
"epoch": 0.13071386889710174,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999685206989349,
|
|
"loss": 6.128,
|
|
"mean_token_accuracy": 0.13094662353396416,
|
|
"num_tokens": 2921027.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.379840612411499,
|
|
"epoch": 0.1311028982688193,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999680553902959,
|
|
"loss": 6.1558,
|
|
"mean_token_accuracy": 0.13119837194681166,
|
|
"num_tokens": 2930398.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.364923095703125,
|
|
"epoch": 0.13149192764053685,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999675866681247,
|
|
"loss": 6.1767,
|
|
"mean_token_accuracy": 0.12759430408477784,
|
|
"num_tokens": 2938703.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.336649465560913,
|
|
"epoch": 0.1318809570122544,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999671145324286,
|
|
"loss": 6.101,
|
|
"mean_token_accuracy": 0.13444865867495537,
|
|
"num_tokens": 2947007.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.386577987670899,
|
|
"epoch": 0.132269986383972,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999666389832144,
|
|
"loss": 6.2399,
|
|
"mean_token_accuracy": 0.13214273303747176,
|
|
"num_tokens": 2955485.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.432107162475586,
|
|
"epoch": 0.13265901575568956,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999661600204897,
|
|
"loss": 6.0943,
|
|
"mean_token_accuracy": 0.1316603824496269,
|
|
"num_tokens": 2964416.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.345300769805908,
|
|
"epoch": 0.13304804512740712,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999656776442615,
|
|
"loss": 6.0975,
|
|
"mean_token_accuracy": 0.12664629369974137,
|
|
"num_tokens": 2972737.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.319915866851806,
|
|
"epoch": 0.13343707449912467,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999651918545372,
|
|
"loss": 6.138,
|
|
"mean_token_accuracy": 0.12891265898942947,
|
|
"num_tokens": 2981166.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.400096082687378,
|
|
"epoch": 0.13382610387084226,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999647026513243,
|
|
"loss": 6.1841,
|
|
"mean_token_accuracy": 0.1323157973587513,
|
|
"num_tokens": 2989689.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.409255075454712,
|
|
"epoch": 0.13421513324255982,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00049996421003463,
|
|
"loss": 6.0878,
|
|
"mean_token_accuracy": 0.1328970320522785,
|
|
"num_tokens": 2998793.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.303147697448731,
|
|
"epoch": 0.13460416261427738,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999637140044619,
|
|
"loss": 6.2446,
|
|
"mean_token_accuracy": 0.12399912551045418,
|
|
"num_tokens": 3007320.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.372701263427734,
|
|
"epoch": 0.13499319198599494,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999632145608275,
|
|
"loss": 6.1419,
|
|
"mean_token_accuracy": 0.13464085459709169,
|
|
"num_tokens": 3015024.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.392448997497558,
|
|
"epoch": 0.1353822213577125,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999627117037343,
|
|
"loss": 6.2367,
|
|
"mean_token_accuracy": 0.13206600919365882,
|
|
"num_tokens": 3023058.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.42128438949585,
|
|
"epoch": 0.13577125072943008,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00049996220543319,
|
|
"loss": 6.1337,
|
|
"mean_token_accuracy": 0.1343154013156891,
|
|
"num_tokens": 3031308.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.368301248550415,
|
|
"epoch": 0.13616028010114764,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999616957492025,
|
|
"loss": 6.2115,
|
|
"mean_token_accuracy": 0.12576463893055917,
|
|
"num_tokens": 3039598.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.332375144958496,
|
|
"epoch": 0.1365493094728652,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999611826517793,
|
|
"loss": 6.0264,
|
|
"mean_token_accuracy": 0.13993713706731797,
|
|
"num_tokens": 3047598.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.369699382781983,
|
|
"epoch": 0.13693833884458276,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999606661409281,
|
|
"loss": 6.1765,
|
|
"mean_token_accuracy": 0.1314793422818184,
|
|
"num_tokens": 3055702.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.352033996582032,
|
|
"epoch": 0.13732736821630034,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999601462166569,
|
|
"loss": 6.0358,
|
|
"mean_token_accuracy": 0.13761886060237885,
|
|
"num_tokens": 3063908.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.316202020645141,
|
|
"epoch": 0.1377163975880179,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999596228789736,
|
|
"loss": 6.1396,
|
|
"mean_token_accuracy": 0.12727851122617723,
|
|
"num_tokens": 3072077.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.371345472335816,
|
|
"epoch": 0.13810542695973546,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999590961278859,
|
|
"loss": 6.1301,
|
|
"mean_token_accuracy": 0.13236963376402855,
|
|
"num_tokens": 3080498.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.343796157836914,
|
|
"epoch": 0.13849445633145302,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999585659634021,
|
|
"loss": 6.135,
|
|
"mean_token_accuracy": 0.13217933028936385,
|
|
"num_tokens": 3089055.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.314961290359497,
|
|
"epoch": 0.13888348570317058,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999580323855301,
|
|
"loss": 6.1373,
|
|
"mean_token_accuracy": 0.13297785818576813,
|
|
"num_tokens": 3096944.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.29940447807312,
|
|
"epoch": 0.13927251507488816,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999574953942781,
|
|
"loss": 6.0293,
|
|
"mean_token_accuracy": 0.13218909054994582,
|
|
"num_tokens": 3105596.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.27741756439209,
|
|
"epoch": 0.13966154444660572,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999569549896541,
|
|
"loss": 6.0162,
|
|
"mean_token_accuracy": 0.14017163962125778,
|
|
"num_tokens": 3114349.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.2425329208374025,
|
|
"epoch": 0.14005057381832328,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999564111716665,
|
|
"loss": 6.1302,
|
|
"mean_token_accuracy": 0.12543968632817268,
|
|
"num_tokens": 3122490.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.412037658691406,
|
|
"epoch": 0.14043960319004084,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999558639403232,
|
|
"loss": 6.1766,
|
|
"mean_token_accuracy": 0.12949994951486588,
|
|
"num_tokens": 3130988.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.349801778793335,
|
|
"epoch": 0.1408286325617584,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999553132956328,
|
|
"loss": 6.0352,
|
|
"mean_token_accuracy": 0.1310783050954342,
|
|
"num_tokens": 3139488.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.275408506393433,
|
|
"epoch": 0.14121766193347599,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999547592376035,
|
|
"loss": 6.0853,
|
|
"mean_token_accuracy": 0.13912829905748367,
|
|
"num_tokens": 3147955.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.324730014801025,
|
|
"epoch": 0.14160669130519354,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999542017662438,
|
|
"loss": 6.1356,
|
|
"mean_token_accuracy": 0.12387675121426582,
|
|
"num_tokens": 3157608.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.365148973464966,
|
|
"epoch": 0.1419957206769111,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999536408815623,
|
|
"loss": 6.0893,
|
|
"mean_token_accuracy": 0.12791794016957284,
|
|
"num_tokens": 3166124.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.237749290466309,
|
|
"epoch": 0.14238475004862866,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999530765835672,
|
|
"loss": 6.0837,
|
|
"mean_token_accuracy": 0.12821160182356833,
|
|
"num_tokens": 3175069.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.356600522994995,
|
|
"epoch": 0.14277377942034625,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999525088722673,
|
|
"loss": 6.1196,
|
|
"mean_token_accuracy": 0.13117128163576125,
|
|
"num_tokens": 3184259.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.341631460189819,
|
|
"epoch": 0.1431628087920638,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999519377476711,
|
|
"loss": 6.0274,
|
|
"mean_token_accuracy": 0.1311353027820587,
|
|
"num_tokens": 3193015.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.335974597930909,
|
|
"epoch": 0.14355183816378136,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999513632097872,
|
|
"loss": 5.9655,
|
|
"mean_token_accuracy": 0.1419636234641075,
|
|
"num_tokens": 3201624.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.2722913265228275,
|
|
"epoch": 0.14394086753549892,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999507852586245,
|
|
"loss": 6.0784,
|
|
"mean_token_accuracy": 0.13751533553004264,
|
|
"num_tokens": 3209474.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.228673076629638,
|
|
"epoch": 0.14432989690721648,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999502038941917,
|
|
"loss": 6.0466,
|
|
"mean_token_accuracy": 0.13530608788132667,
|
|
"num_tokens": 3218550.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.159630537033081,
|
|
"epoch": 0.14471892627893407,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999496191164975,
|
|
"loss": 6.0135,
|
|
"mean_token_accuracy": 0.13874994069337845,
|
|
"num_tokens": 3227108.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.317847490310669,
|
|
"epoch": 0.14510795565065163,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499949030925551,
|
|
"loss": 6.0647,
|
|
"mean_token_accuracy": 0.13484866991639138,
|
|
"num_tokens": 3235785.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.4040697574615475,
|
|
"epoch": 0.14549698502236919,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999484393213609,
|
|
"loss": 6.0958,
|
|
"mean_token_accuracy": 0.12889099717140198,
|
|
"num_tokens": 3244180.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.206935405731201,
|
|
"epoch": 0.14588601439408674,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999478443039363,
|
|
"loss": 5.966,
|
|
"mean_token_accuracy": 0.13705985099077225,
|
|
"num_tokens": 3253098.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.353375959396362,
|
|
"epoch": 0.14627504376580433,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999472458732862,
|
|
"loss": 6.0139,
|
|
"mean_token_accuracy": 0.1389046587049961,
|
|
"num_tokens": 3261726.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.185830402374267,
|
|
"epoch": 0.1466640731375219,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999466440294198,
|
|
"loss": 5.9819,
|
|
"mean_token_accuracy": 0.13572768047451972,
|
|
"num_tokens": 3270362.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.255965852737427,
|
|
"epoch": 0.14705310250923945,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499946038772346,
|
|
"loss": 5.9745,
|
|
"mean_token_accuracy": 0.13993003964424133,
|
|
"num_tokens": 3278332.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.187082147598266,
|
|
"epoch": 0.147442131880957,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999454301020741,
|
|
"loss": 5.9432,
|
|
"mean_token_accuracy": 0.14198991358280183,
|
|
"num_tokens": 3286800.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.344804382324218,
|
|
"epoch": 0.14783116125267456,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999448180186133,
|
|
"loss": 6.181,
|
|
"mean_token_accuracy": 0.12529000788927078,
|
|
"num_tokens": 3296186.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.254264879226684,
|
|
"epoch": 0.14822019062439215,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499944202521973,
|
|
"loss": 6.0373,
|
|
"mean_token_accuracy": 0.1428308829665184,
|
|
"num_tokens": 3303973.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.188289737701416,
|
|
"epoch": 0.1486092199961097,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999435836121624,
|
|
"loss": 5.9926,
|
|
"mean_token_accuracy": 0.13803835734724998,
|
|
"num_tokens": 3312550.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.331698322296143,
|
|
"epoch": 0.14899824936782727,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499942961289191,
|
|
"loss": 6.0628,
|
|
"mean_token_accuracy": 0.13561255410313605,
|
|
"num_tokens": 3321342.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.1749297142028805,
|
|
"epoch": 0.14938727873954483,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999423355530683,
|
|
"loss": 5.9403,
|
|
"mean_token_accuracy": 0.14343732073903084,
|
|
"num_tokens": 3329293.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.156786012649536,
|
|
"epoch": 0.1497763081112624,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999417064038035,
|
|
"loss": 5.9966,
|
|
"mean_token_accuracy": 0.13348888084292412,
|
|
"num_tokens": 3338278.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.295070505142212,
|
|
"epoch": 0.15016533748297997,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999410738414065,
|
|
"loss": 6.1006,
|
|
"mean_token_accuracy": 0.1349467881023884,
|
|
"num_tokens": 3346757.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.215303182601929,
|
|
"epoch": 0.15055436685469753,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999404378658866,
|
|
"loss": 6.0975,
|
|
"mean_token_accuracy": 0.1362791948020458,
|
|
"num_tokens": 3355903.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.2781799793243405,
|
|
"epoch": 0.1509433962264151,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999397984772536,
|
|
"loss": 6.0666,
|
|
"mean_token_accuracy": 0.1276647962629795,
|
|
"num_tokens": 3365440.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.2379114627838135,
|
|
"epoch": 0.15133242559813265,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999391556755172,
|
|
"loss": 6.0323,
|
|
"mean_token_accuracy": 0.13651658967137337,
|
|
"num_tokens": 3373672.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.2155702114105225,
|
|
"epoch": 0.15172145496985023,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999385094606872,
|
|
"loss": 6.0032,
|
|
"mean_token_accuracy": 0.1315799042582512,
|
|
"num_tokens": 3382733.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.174511241912842,
|
|
"epoch": 0.1521104843415678,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999378598327733,
|
|
"loss": 5.9656,
|
|
"mean_token_accuracy": 0.13844937980175018,
|
|
"num_tokens": 3390842.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.256609535217285,
|
|
"epoch": 0.15249951371328535,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999372067917854,
|
|
"loss": 6.1149,
|
|
"mean_token_accuracy": 0.1254595175385475,
|
|
"num_tokens": 3399761.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.284492778778076,
|
|
"epoch": 0.1528885430850029,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999365503377335,
|
|
"loss": 6.0315,
|
|
"mean_token_accuracy": 0.13321302980184554,
|
|
"num_tokens": 3408986.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.235216522216797,
|
|
"epoch": 0.1532775724567205,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999358904706273,
|
|
"loss": 5.9892,
|
|
"mean_token_accuracy": 0.1353617176413536,
|
|
"num_tokens": 3418051.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.321955776214599,
|
|
"epoch": 0.15366660182843805,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999352271904771,
|
|
"loss": 6.0986,
|
|
"mean_token_accuracy": 0.13750415220856665,
|
|
"num_tokens": 3427185.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.196172285079956,
|
|
"epoch": 0.1540556312001556,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999345604972928,
|
|
"loss": 5.9939,
|
|
"mean_token_accuracy": 0.13660573363304138,
|
|
"num_tokens": 3435367.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.193881511688232,
|
|
"epoch": 0.15444466057187317,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999338903910846,
|
|
"loss": 6.0341,
|
|
"mean_token_accuracy": 0.1360504299402237,
|
|
"num_tokens": 3443451.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.246865940093994,
|
|
"epoch": 0.15483368994359073,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999332168718626,
|
|
"loss": 6.0401,
|
|
"mean_token_accuracy": 0.1405157931149006,
|
|
"num_tokens": 3451038.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.464015769958496,
|
|
"epoch": 0.15522271931530832,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999325399396371,
|
|
"loss": 6.189,
|
|
"mean_token_accuracy": 0.12317560613155365,
|
|
"num_tokens": 3459693.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.344349575042725,
|
|
"epoch": 0.15561174868702587,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999318595944183,
|
|
"loss": 6.0573,
|
|
"mean_token_accuracy": 0.1302526354789734,
|
|
"num_tokens": 3468347.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.2093932151794435,
|
|
"epoch": 0.15600077805874343,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999311758362166,
|
|
"loss": 6.041,
|
|
"mean_token_accuracy": 0.1344868026673794,
|
|
"num_tokens": 3476030.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.173217630386352,
|
|
"epoch": 0.156389807430461,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999304886650422,
|
|
"loss": 6.0088,
|
|
"mean_token_accuracy": 0.1343566119670868,
|
|
"num_tokens": 3484840.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.339105176925659,
|
|
"epoch": 0.15677883680217858,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999297980809058,
|
|
"loss": 6.1002,
|
|
"mean_token_accuracy": 0.133415899425745,
|
|
"num_tokens": 3492662.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.286862468719482,
|
|
"epoch": 0.15716786617389614,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999291040838176,
|
|
"loss": 6.0174,
|
|
"mean_token_accuracy": 0.13295094966888427,
|
|
"num_tokens": 3501582.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.232885360717773,
|
|
"epoch": 0.1575568955456137,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999284066737884,
|
|
"loss": 6.0275,
|
|
"mean_token_accuracy": 0.1392024390399456,
|
|
"num_tokens": 3510141.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.297137260437012,
|
|
"epoch": 0.15794592491733125,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999277058508285,
|
|
"loss": 6.0623,
|
|
"mean_token_accuracy": 0.13623598217964172,
|
|
"num_tokens": 3518530.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.16064453125,
|
|
"epoch": 0.1583349542890488,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999270016149486,
|
|
"loss": 6.0192,
|
|
"mean_token_accuracy": 0.1363525167107582,
|
|
"num_tokens": 3526815.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.216293525695801,
|
|
"epoch": 0.1587239836607664,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999262939661596,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.13018166050314903,
|
|
"num_tokens": 3535840.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.298702955245972,
|
|
"epoch": 0.15911301303248396,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999255829044721,
|
|
"loss": 6.0981,
|
|
"mean_token_accuracy": 0.13071646615862847,
|
|
"num_tokens": 3544876.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.225747776031494,
|
|
"epoch": 0.15950204240420152,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999248684298968,
|
|
"loss": 5.8578,
|
|
"mean_token_accuracy": 0.1430135577917099,
|
|
"num_tokens": 3553018.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.087709617614746,
|
|
"epoch": 0.15989107177591907,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999241505424447,
|
|
"loss": 5.9005,
|
|
"mean_token_accuracy": 0.13955418467521669,
|
|
"num_tokens": 3560909.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.183088874816894,
|
|
"epoch": 0.16028010114763663,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999234292421265,
|
|
"loss": 6.0498,
|
|
"mean_token_accuracy": 0.13545388653874396,
|
|
"num_tokens": 3569235.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.154008436203003,
|
|
"epoch": 0.16066913051935422,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999227045289535,
|
|
"loss": 5.9139,
|
|
"mean_token_accuracy": 0.13975678011775017,
|
|
"num_tokens": 3577646.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.173991012573242,
|
|
"epoch": 0.16105815989107178,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999219764029363,
|
|
"loss": 6.0213,
|
|
"mean_token_accuracy": 0.13489074483513833,
|
|
"num_tokens": 3586499.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.236517524719238,
|
|
"epoch": 0.16144718926278934,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999212448640861,
|
|
"loss": 6.0194,
|
|
"mean_token_accuracy": 0.13757209926843644,
|
|
"num_tokens": 3595391.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.141875600814819,
|
|
"epoch": 0.1618362186345069,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999205099124141,
|
|
"loss": 5.9667,
|
|
"mean_token_accuracy": 0.1367950737476349,
|
|
"num_tokens": 3603774.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.297803211212158,
|
|
"epoch": 0.16222524800622448,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999197715479313,
|
|
"loss": 6.0216,
|
|
"mean_token_accuracy": 0.13554098531603814,
|
|
"num_tokens": 3611980.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.2039124965667725,
|
|
"epoch": 0.16261427737794204,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999190297706489,
|
|
"loss": 5.942,
|
|
"mean_token_accuracy": 0.13699196204543113,
|
|
"num_tokens": 3620902.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.3155577182769775,
|
|
"epoch": 0.1630033067496596,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999182845805783,
|
|
"loss": 6.2312,
|
|
"mean_token_accuracy": 0.12782860547304153,
|
|
"num_tokens": 3628924.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.297778558731079,
|
|
"epoch": 0.16339233612137716,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999175359777306,
|
|
"loss": 6.0695,
|
|
"mean_token_accuracy": 0.13167304024100304,
|
|
"num_tokens": 3637538.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.203191900253296,
|
|
"epoch": 0.16378136549309472,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999167839621174,
|
|
"loss": 6.0779,
|
|
"mean_token_accuracy": 0.13191662728786469,
|
|
"num_tokens": 3646309.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.213529634475708,
|
|
"epoch": 0.1641703948648123,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999160285337501,
|
|
"loss": 5.9364,
|
|
"mean_token_accuracy": 0.1367933377623558,
|
|
"num_tokens": 3655204.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.21005539894104,
|
|
"epoch": 0.16455942423652986,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999152696926399,
|
|
"loss": 6.0641,
|
|
"mean_token_accuracy": 0.1300017297267914,
|
|
"num_tokens": 3663939.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.262974691390991,
|
|
"epoch": 0.16494845360824742,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999145074387985,
|
|
"loss": 6.0083,
|
|
"mean_token_accuracy": 0.13462101370096208,
|
|
"num_tokens": 3673167.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.195592164993286,
|
|
"epoch": 0.16533748297996498,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999137417722374,
|
|
"loss": 5.9742,
|
|
"mean_token_accuracy": 0.13803649172186852,
|
|
"num_tokens": 3682234.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.130123567581177,
|
|
"epoch": 0.16572651235168256,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999129726929684,
|
|
"loss": 5.9518,
|
|
"mean_token_accuracy": 0.13907736241817475,
|
|
"num_tokens": 3690835.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.220533561706543,
|
|
"epoch": 0.16611554172340012,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999122002010029,
|
|
"loss": 6.0101,
|
|
"mean_token_accuracy": 0.1316205196082592,
|
|
"num_tokens": 3699348.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.122845840454102,
|
|
"epoch": 0.16650457109511768,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999114242963527,
|
|
"loss": 5.924,
|
|
"mean_token_accuracy": 0.1415353387594223,
|
|
"num_tokens": 3708205.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.129640579223633,
|
|
"epoch": 0.16689360046683524,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999106449790298,
|
|
"loss": 5.9912,
|
|
"mean_token_accuracy": 0.14246149584650994,
|
|
"num_tokens": 3717016.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.351011037826538,
|
|
"epoch": 0.1672826298385528,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999098622490458,
|
|
"loss": 6.0016,
|
|
"mean_token_accuracy": 0.13569031432271003,
|
|
"num_tokens": 3725509.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.1818685054779055,
|
|
"epoch": 0.16767165921027039,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999090761064125,
|
|
"loss": 6.0751,
|
|
"mean_token_accuracy": 0.13177148699760438,
|
|
"num_tokens": 3734674.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.140064430236817,
|
|
"epoch": 0.16806068858198794,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499908286551142,
|
|
"loss": 5.9012,
|
|
"mean_token_accuracy": 0.1402728170156479,
|
|
"num_tokens": 3742930.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.204311227798462,
|
|
"epoch": 0.1684497179537055,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999074935832463,
|
|
"loss": 5.9945,
|
|
"mean_token_accuracy": 0.13643383085727692,
|
|
"num_tokens": 3751314.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.266703701019287,
|
|
"epoch": 0.16883874732542306,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999066972027373,
|
|
"loss": 6.1046,
|
|
"mean_token_accuracy": 0.1291274093091488,
|
|
"num_tokens": 3760229.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.350693798065185,
|
|
"epoch": 0.16922777669714065,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999058974096271,
|
|
"loss": 6.1037,
|
|
"mean_token_accuracy": 0.13275526687502862,
|
|
"num_tokens": 3769037.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.075402069091797,
|
|
"epoch": 0.1696168060688582,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499905094203928,
|
|
"loss": 5.9684,
|
|
"mean_token_accuracy": 0.14126176312565802,
|
|
"num_tokens": 3777686.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.287758302688599,
|
|
"epoch": 0.17000583544057576,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499904287585652,
|
|
"loss": 6.0575,
|
|
"mean_token_accuracy": 0.13231970369815826,
|
|
"num_tokens": 3786412.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.2325122356414795,
|
|
"epoch": 0.17039486481229332,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999034775548113,
|
|
"loss": 6.091,
|
|
"mean_token_accuracy": 0.13756789192557334,
|
|
"num_tokens": 3794981.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.184635210037231,
|
|
"epoch": 0.17078389418401088,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999026641114185,
|
|
"loss": 5.9679,
|
|
"mean_token_accuracy": 0.13785844221711158,
|
|
"num_tokens": 3803069.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.228214073181152,
|
|
"epoch": 0.17117292355572847,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999018472554857,
|
|
"loss": 6.0562,
|
|
"mean_token_accuracy": 0.13657879456877708,
|
|
"num_tokens": 3811986.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.255152368545533,
|
|
"epoch": 0.17156195292744603,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999010269870253,
|
|
"loss": 5.9669,
|
|
"mean_token_accuracy": 0.13384350910782813,
|
|
"num_tokens": 3820626.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.168890142440796,
|
|
"epoch": 0.17195098229916359,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999002033060498,
|
|
"loss": 5.9734,
|
|
"mean_token_accuracy": 0.14005149230360986,
|
|
"num_tokens": 3828608.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.115287494659424,
|
|
"epoch": 0.17234001167088114,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998993762125716,
|
|
"loss": 5.9222,
|
|
"mean_token_accuracy": 0.1419154718518257,
|
|
"num_tokens": 3837059.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.196029186248779,
|
|
"epoch": 0.17272904104259873,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998985457066034,
|
|
"loss": 5.9477,
|
|
"mean_token_accuracy": 0.13308243378996848,
|
|
"num_tokens": 3845137.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.161190748214722,
|
|
"epoch": 0.1731180704143163,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998977117881576,
|
|
"loss": 5.9399,
|
|
"mean_token_accuracy": 0.14329548850655555,
|
|
"num_tokens": 3854012.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.076524972915649,
|
|
"epoch": 0.17350709978603385,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998968744572472,
|
|
"loss": 5.8859,
|
|
"mean_token_accuracy": 0.14090772867202758,
|
|
"num_tokens": 3862308.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.084261083602906,
|
|
"epoch": 0.1738961291577514,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998960337138845,
|
|
"loss": 5.8224,
|
|
"mean_token_accuracy": 0.13599667102098464,
|
|
"num_tokens": 3870975.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.172693729400635,
|
|
"epoch": 0.17428515852946896,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998951895580826,
|
|
"loss": 5.9953,
|
|
"mean_token_accuracy": 0.1362786665558815,
|
|
"num_tokens": 3879621.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.119487714767456,
|
|
"epoch": 0.17467418790118655,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998943419898542,
|
|
"loss": 5.9608,
|
|
"mean_token_accuracy": 0.13740068078041076,
|
|
"num_tokens": 3889214.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.195636940002442,
|
|
"epoch": 0.1750632172729041,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998934910092119,
|
|
"loss": 5.9972,
|
|
"mean_token_accuracy": 0.13837300091981888,
|
|
"num_tokens": 3898250.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.189534759521484,
|
|
"epoch": 0.17545224664462167,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998926366161689,
|
|
"loss": 6.0342,
|
|
"mean_token_accuracy": 0.13376041278243064,
|
|
"num_tokens": 3906971.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.193826007843017,
|
|
"epoch": 0.17584127601633923,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998917788107383,
|
|
"loss": 6.0622,
|
|
"mean_token_accuracy": 0.13532394245266915,
|
|
"num_tokens": 3916663.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.125564813613892,
|
|
"epoch": 0.17623030538805678,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998909175929326,
|
|
"loss": 5.9445,
|
|
"mean_token_accuracy": 0.13861310556530954,
|
|
"num_tokens": 3926848.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.110090446472168,
|
|
"epoch": 0.17661933475977437,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998900529627653,
|
|
"loss": 5.9132,
|
|
"mean_token_accuracy": 0.138637275993824,
|
|
"num_tokens": 3935729.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.222514343261719,
|
|
"epoch": 0.17700836413149193,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998891849202495,
|
|
"loss": 5.9225,
|
|
"mean_token_accuracy": 0.13785927072167398,
|
|
"num_tokens": 3943408.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.115485048294067,
|
|
"epoch": 0.1773973935032095,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499888313465398,
|
|
"loss": 5.8904,
|
|
"mean_token_accuracy": 0.13828733041882516,
|
|
"num_tokens": 3952473.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.189030885696411,
|
|
"epoch": 0.17778642287492705,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998874385982247,
|
|
"loss": 6.0584,
|
|
"mean_token_accuracy": 0.1308848187327385,
|
|
"num_tokens": 3960878.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.263873767852783,
|
|
"epoch": 0.17817545224664463,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998865603187421,
|
|
"loss": 6.0012,
|
|
"mean_token_accuracy": 0.13525196462869643,
|
|
"num_tokens": 3969282.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.142105340957642,
|
|
"epoch": 0.1785644816183622,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499885678626964,
|
|
"loss": 5.9793,
|
|
"mean_token_accuracy": 0.1365065097808838,
|
|
"num_tokens": 3978516.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.130709075927735,
|
|
"epoch": 0.17895351099007975,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998847935229038,
|
|
"loss": 5.8469,
|
|
"mean_token_accuracy": 0.14624039083719254,
|
|
"num_tokens": 3986580.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.984261894226075,
|
|
"epoch": 0.1793425403617973,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998839050065746,
|
|
"loss": 5.8505,
|
|
"mean_token_accuracy": 0.1426392376422882,
|
|
"num_tokens": 3995144.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.117937326431274,
|
|
"epoch": 0.17973156973351487,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998830130779902,
|
|
"loss": 5.8539,
|
|
"mean_token_accuracy": 0.13852243572473527,
|
|
"num_tokens": 4003887.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.178174209594727,
|
|
"epoch": 0.18012059910523245,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499882117737164,
|
|
"loss": 5.9577,
|
|
"mean_token_accuracy": 0.13900213465094566,
|
|
"num_tokens": 4012607.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.117289209365845,
|
|
"epoch": 0.18050962847695,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998812189841096,
|
|
"loss": 6.0434,
|
|
"mean_token_accuracy": 0.13420895710587502,
|
|
"num_tokens": 4021950.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.188327360153198,
|
|
"epoch": 0.18089865784866757,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998803168188407,
|
|
"loss": 6.0003,
|
|
"mean_token_accuracy": 0.1396230697631836,
|
|
"num_tokens": 4031076.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.050243377685547,
|
|
"epoch": 0.18128768722038513,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998794112413708,
|
|
"loss": 5.8423,
|
|
"mean_token_accuracy": 0.14782028794288635,
|
|
"num_tokens": 4040414.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.248169994354248,
|
|
"epoch": 0.18167671659210272,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998785022517137,
|
|
"loss": 5.9386,
|
|
"mean_token_accuracy": 0.14150765910744667,
|
|
"num_tokens": 4048931.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.986580514907837,
|
|
"epoch": 0.18206574596382027,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998775898498835,
|
|
"loss": 5.8367,
|
|
"mean_token_accuracy": 0.14155064076185225,
|
|
"num_tokens": 4057688.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.074233341217041,
|
|
"epoch": 0.18245477533553783,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998766740358936,
|
|
"loss": 5.9449,
|
|
"mean_token_accuracy": 0.1420542173087597,
|
|
"num_tokens": 4066365.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.13965334892273,
|
|
"epoch": 0.1828438047072554,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998757548097582,
|
|
"loss": 5.8541,
|
|
"mean_token_accuracy": 0.14332376196980476,
|
|
"num_tokens": 4075136.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.134494304656982,
|
|
"epoch": 0.18323283407897295,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998748321714911,
|
|
"loss": 5.9524,
|
|
"mean_token_accuracy": 0.14317325055599212,
|
|
"num_tokens": 4083337.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.069387912750244,
|
|
"epoch": 0.18362186345069054,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998739061211065,
|
|
"loss": 5.899,
|
|
"mean_token_accuracy": 0.1406087227165699,
|
|
"num_tokens": 4091201.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.1495448589324955,
|
|
"epoch": 0.1840108928224081,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998729766586181,
|
|
"loss": 5.9458,
|
|
"mean_token_accuracy": 0.1404791608452797,
|
|
"num_tokens": 4099480.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.029800033569336,
|
|
"epoch": 0.18439992219412565,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998720437840403,
|
|
"loss": 5.8555,
|
|
"mean_token_accuracy": 0.14272842854261397,
|
|
"num_tokens": 4108151.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.009803676605225,
|
|
"epoch": 0.1847889515658432,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998711074973871,
|
|
"loss": 5.8595,
|
|
"mean_token_accuracy": 0.14537928998470306,
|
|
"num_tokens": 4117380.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.103708982467651,
|
|
"epoch": 0.1851779809375608,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998701677986728,
|
|
"loss": 5.9192,
|
|
"mean_token_accuracy": 0.14413200244307517,
|
|
"num_tokens": 4126757.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.091351890563965,
|
|
"epoch": 0.18556701030927836,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998692246879116,
|
|
"loss": 5.832,
|
|
"mean_token_accuracy": 0.14118036180734633,
|
|
"num_tokens": 4135326.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.083584976196289,
|
|
"epoch": 0.18595603968099592,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998682781651178,
|
|
"loss": 5.8502,
|
|
"mean_token_accuracy": 0.15047699064016343,
|
|
"num_tokens": 4143624.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.039449691772461,
|
|
"epoch": 0.18634506905271347,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998673282303059,
|
|
"loss": 5.8032,
|
|
"mean_token_accuracy": 0.14633125066757202,
|
|
"num_tokens": 4152193.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.093126678466797,
|
|
"epoch": 0.18673409842443103,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998663748834901,
|
|
"loss": 5.9333,
|
|
"mean_token_accuracy": 0.14173089787364007,
|
|
"num_tokens": 4160614.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.195434331893921,
|
|
"epoch": 0.18712312779614862,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998654181246851,
|
|
"loss": 5.9525,
|
|
"mean_token_accuracy": 0.1426502361893654,
|
|
"num_tokens": 4168715.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.14034595489502,
|
|
"epoch": 0.18751215716786618,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998644579539052,
|
|
"loss": 5.9903,
|
|
"mean_token_accuracy": 0.14057205021381378,
|
|
"num_tokens": 4176676.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.11949610710144,
|
|
"epoch": 0.18790118653958374,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499863494371165,
|
|
"loss": 5.9666,
|
|
"mean_token_accuracy": 0.13880052268505097,
|
|
"num_tokens": 4185613.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.10061502456665,
|
|
"epoch": 0.1882902159113013,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998625273764793,
|
|
"loss": 5.9744,
|
|
"mean_token_accuracy": 0.14042351245880128,
|
|
"num_tokens": 4193985.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.119175815582276,
|
|
"epoch": 0.18867924528301888,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998615569698626,
|
|
"loss": 5.8692,
|
|
"mean_token_accuracy": 0.14560523852705956,
|
|
"num_tokens": 4202713.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.20410122871399,
|
|
"epoch": 0.18906827465473644,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998605831513296,
|
|
"loss": 5.9982,
|
|
"mean_token_accuracy": 0.13526586964726448,
|
|
"num_tokens": 4210858.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.077843475341797,
|
|
"epoch": 0.189457304026454,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998596059208953,
|
|
"loss": 5.9232,
|
|
"mean_token_accuracy": 0.1438886322081089,
|
|
"num_tokens": 4219570.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.070500183105469,
|
|
"epoch": 0.18984633339817156,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998586252785743,
|
|
"loss": 5.8362,
|
|
"mean_token_accuracy": 0.14419551193714142,
|
|
"num_tokens": 4228026.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.118373966217041,
|
|
"epoch": 0.19023536276988912,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998576412243816,
|
|
"loss": 5.8484,
|
|
"mean_token_accuracy": 0.14332474917173385,
|
|
"num_tokens": 4235993.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.020765161514282,
|
|
"epoch": 0.1906243921416067,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998566537583321,
|
|
"loss": 5.8452,
|
|
"mean_token_accuracy": 0.1450585328042507,
|
|
"num_tokens": 4244225.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.020392990112304,
|
|
"epoch": 0.19101342151332426,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998556628804408,
|
|
"loss": 5.8412,
|
|
"mean_token_accuracy": 0.14568918645381929,
|
|
"num_tokens": 4252989.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.1407276630401615,
|
|
"epoch": 0.19140245088504182,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998546685907225,
|
|
"loss": 5.8736,
|
|
"mean_token_accuracy": 0.1443709298968315,
|
|
"num_tokens": 4261297.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.14323468208313,
|
|
"epoch": 0.19179148025675938,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998536708891927,
|
|
"loss": 6.0037,
|
|
"mean_token_accuracy": 0.13726148158311843,
|
|
"num_tokens": 4270299.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.137307929992676,
|
|
"epoch": 0.19218050962847694,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998526697758663,
|
|
"loss": 6.0186,
|
|
"mean_token_accuracy": 0.13181870952248573,
|
|
"num_tokens": 4279662.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.12540340423584,
|
|
"epoch": 0.19256953900019452,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998516652507585,
|
|
"loss": 5.8237,
|
|
"mean_token_accuracy": 0.14710504859685897,
|
|
"num_tokens": 4287876.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.082257652282715,
|
|
"epoch": 0.19295856837191208,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998506573138846,
|
|
"loss": 5.9652,
|
|
"mean_token_accuracy": 0.1425960034132004,
|
|
"num_tokens": 4296415.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.0256585597991945,
|
|
"epoch": 0.19334759774362964,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998496459652598,
|
|
"loss": 5.7941,
|
|
"mean_token_accuracy": 0.14723251685500144,
|
|
"num_tokens": 4304434.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.094099235534668,
|
|
"epoch": 0.1937366271153472,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998486312048995,
|
|
"loss": 5.9742,
|
|
"mean_token_accuracy": 0.1384941779077053,
|
|
"num_tokens": 4313266.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.093673992156982,
|
|
"epoch": 0.19412565648706478,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998476130328193,
|
|
"loss": 5.8438,
|
|
"mean_token_accuracy": 0.14551946073770522,
|
|
"num_tokens": 4322121.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.059762907028198,
|
|
"epoch": 0.19451468585878234,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998465914490343,
|
|
"loss": 5.8574,
|
|
"mean_token_accuracy": 0.1456399142742157,
|
|
"num_tokens": 4330596.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.101912212371826,
|
|
"epoch": 0.1949037152304999,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00049984556645356,
|
|
"loss": 5.9538,
|
|
"mean_token_accuracy": 0.14571308046579362,
|
|
"num_tokens": 4337779.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.113310956954956,
|
|
"epoch": 0.19529274460221746,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998445380464124,
|
|
"loss": 5.7871,
|
|
"mean_token_accuracy": 0.14770737588405608,
|
|
"num_tokens": 4346623.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.010924863815307,
|
|
"epoch": 0.19568177397393502,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998435062276066,
|
|
"loss": 5.8965,
|
|
"mean_token_accuracy": 0.14267725944519044,
|
|
"num_tokens": 4355435.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.1819150924682615,
|
|
"epoch": 0.1960708033456526,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998424709971586,
|
|
"loss": 5.9427,
|
|
"mean_token_accuracy": 0.14011435583233833,
|
|
"num_tokens": 4363636.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.994958448410034,
|
|
"epoch": 0.19645983271737016,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998414323550839,
|
|
"loss": 5.7574,
|
|
"mean_token_accuracy": 0.1514812633395195,
|
|
"num_tokens": 4372337.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.082412195205689,
|
|
"epoch": 0.19684886208908772,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998403903013984,
|
|
"loss": 5.8105,
|
|
"mean_token_accuracy": 0.14721191674470901,
|
|
"num_tokens": 4380528.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.050493812561035,
|
|
"epoch": 0.19723789146080528,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998393448361179,
|
|
"loss": 5.8969,
|
|
"mean_token_accuracy": 0.13829589858651162,
|
|
"num_tokens": 4389464.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.092096662521362,
|
|
"epoch": 0.19762692083252287,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499838295959258,
|
|
"loss": 5.9541,
|
|
"mean_token_accuracy": 0.13610536456108094,
|
|
"num_tokens": 4397879.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.115645837783814,
|
|
"epoch": 0.19801595020424043,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499837243670835,
|
|
"loss": 5.965,
|
|
"mean_token_accuracy": 0.14079206734895705,
|
|
"num_tokens": 4406145.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.108259153366089,
|
|
"epoch": 0.19840497957595798,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998361879708646,
|
|
"loss": 5.8727,
|
|
"mean_token_accuracy": 0.1402936451137066,
|
|
"num_tokens": 4415480.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.099182176589966,
|
|
"epoch": 0.19879400894767554,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499835128859363,
|
|
"loss": 5.8755,
|
|
"mean_token_accuracy": 0.1442495122551918,
|
|
"num_tokens": 4423355.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.018963813781738,
|
|
"epoch": 0.1991830383193931,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998340663363461,
|
|
"loss": 5.7746,
|
|
"mean_token_accuracy": 0.14996073246002198,
|
|
"num_tokens": 4432059.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.011700248718261,
|
|
"epoch": 0.1995720676911107,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998330004018301,
|
|
"loss": 5.8663,
|
|
"mean_token_accuracy": 0.13528765514492988,
|
|
"num_tokens": 4441146.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.02707347869873,
|
|
"epoch": 0.19996109706282825,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998319310558312,
|
|
"loss": 5.7046,
|
|
"mean_token_accuracy": 0.1531302809715271,
|
|
"num_tokens": 4448553.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.865385389328003,
|
|
"epoch": 0.2003501264345458,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998308582983657,
|
|
"loss": 5.785,
|
|
"mean_token_accuracy": 0.1515739530324936,
|
|
"num_tokens": 4456930.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.159365510940551,
|
|
"epoch": 0.20073915580626336,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998297821294497,
|
|
"loss": 5.9856,
|
|
"mean_token_accuracy": 0.1445264369249344,
|
|
"num_tokens": 4464932.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.066826963424683,
|
|
"epoch": 0.20112818517798095,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998287025490995,
|
|
"loss": 5.7073,
|
|
"mean_token_accuracy": 0.15195650979876518,
|
|
"num_tokens": 4473695.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.915977334976196,
|
|
"epoch": 0.2015172145496985,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998276195573317,
|
|
"loss": 5.9426,
|
|
"mean_token_accuracy": 0.1366700403392315,
|
|
"num_tokens": 4483375.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.159323358535767,
|
|
"epoch": 0.20190624392141607,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998265331541627,
|
|
"loss": 5.9638,
|
|
"mean_token_accuracy": 0.13707406520843507,
|
|
"num_tokens": 4491695.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.056016826629639,
|
|
"epoch": 0.20229527329313363,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998254433396088,
|
|
"loss": 5.9221,
|
|
"mean_token_accuracy": 0.14026020020246505,
|
|
"num_tokens": 4500361.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.072783470153809,
|
|
"epoch": 0.20268430266485118,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998243501136867,
|
|
"loss": 5.8419,
|
|
"mean_token_accuracy": 0.1397676981985569,
|
|
"num_tokens": 4509368.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.088675785064697,
|
|
"epoch": 0.20307333203656877,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998232534764129,
|
|
"loss": 5.8232,
|
|
"mean_token_accuracy": 0.14180155843496323,
|
|
"num_tokens": 4518146.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.058323574066162,
|
|
"epoch": 0.20346236140828633,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998221534278041,
|
|
"loss": 5.8875,
|
|
"mean_token_accuracy": 0.13800363019108772,
|
|
"num_tokens": 4526128.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.097913789749145,
|
|
"epoch": 0.2038513907800039,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998210499678769,
|
|
"loss": 5.9263,
|
|
"mean_token_accuracy": 0.14337622076272966,
|
|
"num_tokens": 4534724.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.008050632476807,
|
|
"epoch": 0.20424042015172145,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998199430966481,
|
|
"loss": 5.7847,
|
|
"mean_token_accuracy": 0.14045033752918243,
|
|
"num_tokens": 4543725.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.033035039901733,
|
|
"epoch": 0.20462944952343903,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998188328141346,
|
|
"loss": 5.8689,
|
|
"mean_token_accuracy": 0.14495224952697755,
|
|
"num_tokens": 4551758.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.990800094604492,
|
|
"epoch": 0.2050184788951566,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998177191203531,
|
|
"loss": 5.7433,
|
|
"mean_token_accuracy": 0.15320585817098617,
|
|
"num_tokens": 4559990.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.993824911117554,
|
|
"epoch": 0.20540750826687415,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998166020153204,
|
|
"loss": 5.793,
|
|
"mean_token_accuracy": 0.1404377117753029,
|
|
"num_tokens": 4568651.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.941356039047241,
|
|
"epoch": 0.2057965376385917,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998154814990538,
|
|
"loss": 5.722,
|
|
"mean_token_accuracy": 0.15070193260908127,
|
|
"num_tokens": 4577981.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.004185390472412,
|
|
"epoch": 0.20618556701030927,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00049981435757157,
|
|
"loss": 5.882,
|
|
"mean_token_accuracy": 0.1453938066959381,
|
|
"num_tokens": 4586480.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.035228633880616,
|
|
"epoch": 0.20657459638202685,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998132302328862,
|
|
"loss": 5.7768,
|
|
"mean_token_accuracy": 0.1519497200846672,
|
|
"num_tokens": 4595554.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.000116539001465,
|
|
"epoch": 0.2069636257537444,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998120994830195,
|
|
"loss": 5.7928,
|
|
"mean_token_accuracy": 0.14965005293488504,
|
|
"num_tokens": 4604091.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.103025817871094,
|
|
"epoch": 0.20735265512546197,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499810965321987,
|
|
"loss": 5.9041,
|
|
"mean_token_accuracy": 0.14321340918540953,
|
|
"num_tokens": 4612603.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.094974136352539,
|
|
"epoch": 0.20774168449717953,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998098277498059,
|
|
"loss": 5.8089,
|
|
"mean_token_accuracy": 0.14330320209264755,
|
|
"num_tokens": 4621041.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.965013837814331,
|
|
"epoch": 0.2081307138688971,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998086867664934,
|
|
"loss": 5.8381,
|
|
"mean_token_accuracy": 0.1479259341955185,
|
|
"num_tokens": 4629849.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.067577695846557,
|
|
"epoch": 0.20851974324061467,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499807542372067,
|
|
"loss": 5.9079,
|
|
"mean_token_accuracy": 0.14189650267362594,
|
|
"num_tokens": 4639426.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.020753288269043,
|
|
"epoch": 0.20890877261233223,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998063945665439,
|
|
"loss": 5.8312,
|
|
"mean_token_accuracy": 0.14925678074359894,
|
|
"num_tokens": 4647257.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.024092960357666,
|
|
"epoch": 0.2092978019840498,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998052433499416,
|
|
"loss": 5.8148,
|
|
"mean_token_accuracy": 0.14485211595892905,
|
|
"num_tokens": 4655773.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.031063079833984,
|
|
"epoch": 0.20968683135576735,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998040887222776,
|
|
"loss": 5.844,
|
|
"mean_token_accuracy": 0.14211719036102294,
|
|
"num_tokens": 4664292.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.070610380172729,
|
|
"epoch": 0.21007586072748494,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998029306835693,
|
|
"loss": 5.8802,
|
|
"mean_token_accuracy": 0.14487007558345794,
|
|
"num_tokens": 4672774.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.192492723464966,
|
|
"epoch": 0.2104648900992025,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998017692338344,
|
|
"loss": 6.0024,
|
|
"mean_token_accuracy": 0.13652608394622803,
|
|
"num_tokens": 4681855.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.003230619430542,
|
|
"epoch": 0.21085391947092005,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998006043730905,
|
|
"loss": 5.7837,
|
|
"mean_token_accuracy": 0.15081765204668046,
|
|
"num_tokens": 4689771.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.06316032409668,
|
|
"epoch": 0.2112429488426376,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997994361013551,
|
|
"loss": 5.9318,
|
|
"mean_token_accuracy": 0.13612701371312141,
|
|
"num_tokens": 4698808.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.027731704711914,
|
|
"epoch": 0.21163197821435517,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997982644186461,
|
|
"loss": 5.8201,
|
|
"mean_token_accuracy": 0.1442001700401306,
|
|
"num_tokens": 4707627.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.994128227233887,
|
|
"epoch": 0.21202100758607276,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997970893249813,
|
|
"loss": 5.8134,
|
|
"mean_token_accuracy": 0.1453290104866028,
|
|
"num_tokens": 4716091.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.026619577407837,
|
|
"epoch": 0.21241003695779032,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997959108203785,
|
|
"loss": 5.8173,
|
|
"mean_token_accuracy": 0.14737472012639047,
|
|
"num_tokens": 4724042.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.927079200744629,
|
|
"epoch": 0.21279906632950787,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997947289048554,
|
|
"loss": 5.7431,
|
|
"mean_token_accuracy": 0.15547642409801482,
|
|
"num_tokens": 4731745.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.977909660339355,
|
|
"epoch": 0.21318809570122543,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997935435784302,
|
|
"loss": 5.9151,
|
|
"mean_token_accuracy": 0.14134541749954224,
|
|
"num_tokens": 4740386.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.097658681869507,
|
|
"epoch": 0.21357712507294302,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997923548411208,
|
|
"loss": 5.9154,
|
|
"mean_token_accuracy": 0.14041005820035934,
|
|
"num_tokens": 4749809.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.157984495162964,
|
|
"epoch": 0.21396615444466058,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499791162692945,
|
|
"loss": 6.0245,
|
|
"mean_token_accuracy": 0.13882595300674438,
|
|
"num_tokens": 4759507.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.020778369903565,
|
|
"epoch": 0.21435518381637814,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997899671339214,
|
|
"loss": 5.7893,
|
|
"mean_token_accuracy": 0.1458857201039791,
|
|
"num_tokens": 4768793.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.058682203292847,
|
|
"epoch": 0.2147442131880957,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997887681640675,
|
|
"loss": 5.9431,
|
|
"mean_token_accuracy": 0.14112222120165824,
|
|
"num_tokens": 4777344.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.091257619857788,
|
|
"epoch": 0.21513324255981325,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997875657834021,
|
|
"loss": 5.859,
|
|
"mean_token_accuracy": 0.1439730390906334,
|
|
"num_tokens": 4785934.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.021985816955566,
|
|
"epoch": 0.21552227193153084,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997863599919432,
|
|
"loss": 5.8154,
|
|
"mean_token_accuracy": 0.1487823836505413,
|
|
"num_tokens": 4794889.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.963295888900757,
|
|
"epoch": 0.2159113013032484,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997851507897089,
|
|
"loss": 5.9177,
|
|
"mean_token_accuracy": 0.1420752465724945,
|
|
"num_tokens": 4803597.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.021999406814575,
|
|
"epoch": 0.21630033067496596,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997839381767178,
|
|
"loss": 5.7093,
|
|
"mean_token_accuracy": 0.14998439997434615,
|
|
"num_tokens": 4812706.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.942576360702515,
|
|
"epoch": 0.21668936004668352,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997827221529882,
|
|
"loss": 5.7645,
|
|
"mean_token_accuracy": 0.14373311623930932,
|
|
"num_tokens": 4821790.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.044412851333618,
|
|
"epoch": 0.2170783894184011,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997815027185386,
|
|
"loss": 5.8268,
|
|
"mean_token_accuracy": 0.14614877104759216,
|
|
"num_tokens": 4830123.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.031355142593384,
|
|
"epoch": 0.21746741879011866,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997802798733874,
|
|
"loss": 5.7584,
|
|
"mean_token_accuracy": 0.14889259934425353,
|
|
"num_tokens": 4838066.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.985014152526856,
|
|
"epoch": 0.21785644816183622,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997790536175534,
|
|
"loss": 5.8295,
|
|
"mean_token_accuracy": 0.1473879933357239,
|
|
"num_tokens": 4846877.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.0131855487823485,
|
|
"epoch": 0.21824547753355378,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997778239510548,
|
|
"loss": 5.8809,
|
|
"mean_token_accuracy": 0.13904760181903839,
|
|
"num_tokens": 4856960.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.0483003616333,
|
|
"epoch": 0.21863450690527134,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997765908739106,
|
|
"loss": 5.8844,
|
|
"mean_token_accuracy": 0.1458500951528549,
|
|
"num_tokens": 4865440.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.985370063781739,
|
|
"epoch": 0.21902353627698892,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997753543861395,
|
|
"loss": 5.7839,
|
|
"mean_token_accuracy": 0.1455774076282978,
|
|
"num_tokens": 4874187.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.1545000076293945,
|
|
"epoch": 0.21941256564870648,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00049977411448776,
|
|
"loss": 5.9234,
|
|
"mean_token_accuracy": 0.13685425370931625,
|
|
"num_tokens": 4883151.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.033831405639648,
|
|
"epoch": 0.21980159502042404,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997728711787912,
|
|
"loss": 5.8376,
|
|
"mean_token_accuracy": 0.14152983725070953,
|
|
"num_tokens": 4890968.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.948618221282959,
|
|
"epoch": 0.2201906243921416,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997716244592518,
|
|
"loss": 5.7224,
|
|
"mean_token_accuracy": 0.15324778854846954,
|
|
"num_tokens": 4899389.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.957552099227906,
|
|
"epoch": 0.22057965376385918,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997703743291607,
|
|
"loss": 5.7836,
|
|
"mean_token_accuracy": 0.15218881666660308,
|
|
"num_tokens": 4907622.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.971472644805909,
|
|
"epoch": 0.22096868313557674,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499769120788537,
|
|
"loss": 5.7855,
|
|
"mean_token_accuracy": 0.14718300998210906,
|
|
"num_tokens": 4916151.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.953951168060303,
|
|
"epoch": 0.2213577125072943,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997678638373995,
|
|
"loss": 5.6926,
|
|
"mean_token_accuracy": 0.1555492803454399,
|
|
"num_tokens": 4923938.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.977941274642944,
|
|
"epoch": 0.22174674187901186,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997666034757676,
|
|
"loss": 5.8041,
|
|
"mean_token_accuracy": 0.15950555503368377,
|
|
"num_tokens": 4932027.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.992272996902466,
|
|
"epoch": 0.22213577125072942,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997653397036603,
|
|
"loss": 5.8234,
|
|
"mean_token_accuracy": 0.15327517986297606,
|
|
"num_tokens": 4940229.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.946475648880005,
|
|
"epoch": 0.222524800622447,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997640725210965,
|
|
"loss": 5.8766,
|
|
"mean_token_accuracy": 0.1445116177201271,
|
|
"num_tokens": 4948662.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.985954427719117,
|
|
"epoch": 0.22291382999416456,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997628019280958,
|
|
"loss": 5.8304,
|
|
"mean_token_accuracy": 0.14730205610394478,
|
|
"num_tokens": 4956847.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.0246001243591305,
|
|
"epoch": 0.22330285936588212,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997615279246773,
|
|
"loss": 5.7519,
|
|
"mean_token_accuracy": 0.14672646746039392,
|
|
"num_tokens": 4965139.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.093596029281616,
|
|
"epoch": 0.22369188873759968,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997602505108603,
|
|
"loss": 5.9346,
|
|
"mean_token_accuracy": 0.1362128235399723,
|
|
"num_tokens": 4973671.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.992952871322632,
|
|
"epoch": 0.22408091810931724,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997589696866644,
|
|
"loss": 5.7985,
|
|
"mean_token_accuracy": 0.14313325881958008,
|
|
"num_tokens": 4981970.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.994722890853882,
|
|
"epoch": 0.22446994748103483,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997576854521088,
|
|
"loss": 5.8276,
|
|
"mean_token_accuracy": 0.14740151315927505,
|
|
"num_tokens": 4990591.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.008001279830933,
|
|
"epoch": 0.22485897685275238,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499756397807213,
|
|
"loss": 5.8338,
|
|
"mean_token_accuracy": 0.1426657348871231,
|
|
"num_tokens": 4999623.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.0818774700164795,
|
|
"epoch": 0.22524800622446994,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997551067519966,
|
|
"loss": 5.8912,
|
|
"mean_token_accuracy": 0.13916059359908103,
|
|
"num_tokens": 5008387.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.989216756820679,
|
|
"epoch": 0.2256370355961875,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997538122864792,
|
|
"loss": 5.8194,
|
|
"mean_token_accuracy": 0.14748692139983177,
|
|
"num_tokens": 5016788.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.08019700050354,
|
|
"epoch": 0.2260260649679051,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997525144106804,
|
|
"loss": 5.8442,
|
|
"mean_token_accuracy": 0.14615625888109207,
|
|
"num_tokens": 5025508.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.974547910690307,
|
|
"epoch": 0.22641509433962265,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049975121312462,
|
|
"loss": 5.8181,
|
|
"mean_token_accuracy": 0.14417650923132896,
|
|
"num_tokens": 5035081.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.942454242706299,
|
|
"epoch": 0.2268041237113402,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997499084283177,
|
|
"loss": 5.7548,
|
|
"mean_token_accuracy": 0.15317937284708022,
|
|
"num_tokens": 5043655.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.948886728286743,
|
|
"epoch": 0.22719315308305776,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997486003217932,
|
|
"loss": 5.7784,
|
|
"mean_token_accuracy": 0.14860536009073258,
|
|
"num_tokens": 5052080.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.9562623500823975,
|
|
"epoch": 0.22758218245477532,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997472888050664,
|
|
"loss": 5.7576,
|
|
"mean_token_accuracy": 0.15349135398864747,
|
|
"num_tokens": 5061325.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.030727291107178,
|
|
"epoch": 0.2279712118264929,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997459738781573,
|
|
"loss": 5.8539,
|
|
"mean_token_accuracy": 0.14812101200222969,
|
|
"num_tokens": 5069461.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.0146770000457765,
|
|
"epoch": 0.22836024119821047,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997446555410857,
|
|
"loss": 5.8223,
|
|
"mean_token_accuracy": 0.14278532564640045,
|
|
"num_tokens": 5077747.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.042302083969116,
|
|
"epoch": 0.22874927056992803,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997433337938716,
|
|
"loss": 5.8714,
|
|
"mean_token_accuracy": 0.15094365030527115,
|
|
"num_tokens": 5086300.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.889710426330566,
|
|
"epoch": 0.22913829994164558,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997420086365351,
|
|
"loss": 5.639,
|
|
"mean_token_accuracy": 0.1529846578836441,
|
|
"num_tokens": 5094762.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.962165880203247,
|
|
"epoch": 0.22952732931336317,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997406800690966,
|
|
"loss": 5.8148,
|
|
"mean_token_accuracy": 0.14716944992542266,
|
|
"num_tokens": 5103364.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.089474296569824,
|
|
"epoch": 0.22991635868508073,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997393480915758,
|
|
"loss": 5.9175,
|
|
"mean_token_accuracy": 0.14378761649131774,
|
|
"num_tokens": 5111730.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.014431476593018,
|
|
"epoch": 0.2303053880567983,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997380127039931,
|
|
"loss": 5.721,
|
|
"mean_token_accuracy": 0.14942315146327018,
|
|
"num_tokens": 5119878.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.950433588027954,
|
|
"epoch": 0.23069441742851585,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997366739063688,
|
|
"loss": 5.8318,
|
|
"mean_token_accuracy": 0.14808186888694763,
|
|
"num_tokens": 5129146.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.973391675949097,
|
|
"epoch": 0.2310834468002334,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997353316987231,
|
|
"loss": 5.8516,
|
|
"mean_token_accuracy": 0.14153072685003282,
|
|
"num_tokens": 5137989.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.0436218738555905,
|
|
"epoch": 0.231472476171951,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997339860810765,
|
|
"loss": 5.8711,
|
|
"mean_token_accuracy": 0.14632160738110542,
|
|
"num_tokens": 5146722.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.069381904602051,
|
|
"epoch": 0.23186150554366855,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997326370534495,
|
|
"loss": 5.8568,
|
|
"mean_token_accuracy": 0.14624862521886825,
|
|
"num_tokens": 5154902.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.035060167312622,
|
|
"epoch": 0.2322505349153861,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997312846158622,
|
|
"loss": 5.8534,
|
|
"mean_token_accuracy": 0.1460738830268383,
|
|
"num_tokens": 5163594.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.965574455261231,
|
|
"epoch": 0.23263956428710367,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997299287683355,
|
|
"loss": 5.7492,
|
|
"mean_token_accuracy": 0.15077491253614425,
|
|
"num_tokens": 5172139.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.024194145202637,
|
|
"epoch": 0.23302859365882125,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997285695108898,
|
|
"loss": 5.8685,
|
|
"mean_token_accuracy": 0.1467841848731041,
|
|
"num_tokens": 5180077.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.930562591552734,
|
|
"epoch": 0.2334176230305388,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997272068435458,
|
|
"loss": 5.7271,
|
|
"mean_token_accuracy": 0.1471436142921448,
|
|
"num_tokens": 5188500.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2334176230305388,
|
|
"eval_entropy": 5.6941922486115235,
|
|
"eval_loss": 5.846546649932861,
|
|
"eval_mean_token_accuracy": 0.15339850671912067,
|
|
"eval_num_tokens": 5188500.0,
|
|
"eval_runtime": 21.835,
|
|
"eval_samples_per_second": 1903.278,
|
|
"eval_steps_per_second": 237.921,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.961565971374512,
|
|
"epoch": 0.23380665240225637,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499725840766324,
|
|
"loss": 5.8084,
|
|
"mean_token_accuracy": 0.14536137208342553,
|
|
"num_tokens": 5197214.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 6.099143123626709,
|
|
"epoch": 0.23419568177397393,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997244712792453,
|
|
"loss": 5.8902,
|
|
"mean_token_accuracy": 0.1375305250287056,
|
|
"num_tokens": 5206348.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.908238410949707,
|
|
"epoch": 0.2345847111456915,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997230983823305,
|
|
"loss": 5.7049,
|
|
"mean_token_accuracy": 0.1495301440358162,
|
|
"num_tokens": 5215425.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 6.090976285934448,
|
|
"epoch": 0.23497374051740907,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997217220756003,
|
|
"loss": 5.9276,
|
|
"mean_token_accuracy": 0.137629234790802,
|
|
"num_tokens": 5224899.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 6.01672511100769,
|
|
"epoch": 0.23536276988912663,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997203423590757,
|
|
"loss": 5.8561,
|
|
"mean_token_accuracy": 0.1432482309639454,
|
|
"num_tokens": 5233829.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 6.031854343414307,
|
|
"epoch": 0.2357517992608442,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997189592327775,
|
|
"loss": 5.9804,
|
|
"mean_token_accuracy": 0.13744926527142526,
|
|
"num_tokens": 5243144.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 6.057364892959595,
|
|
"epoch": 0.23614082863256175,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997175726967268,
|
|
"loss": 5.8012,
|
|
"mean_token_accuracy": 0.14386512711644173,
|
|
"num_tokens": 5251097.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 6.043510866165161,
|
|
"epoch": 0.23652985800427934,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997161827509447,
|
|
"loss": 5.8739,
|
|
"mean_token_accuracy": 0.14954522103071213,
|
|
"num_tokens": 5260050.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 6.009251642227173,
|
|
"epoch": 0.2369188873759969,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997147893954521,
|
|
"loss": 5.6914,
|
|
"mean_token_accuracy": 0.14883195012807846,
|
|
"num_tokens": 5268363.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.967427968978882,
|
|
"epoch": 0.23730791674771445,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997133926302702,
|
|
"loss": 5.8712,
|
|
"mean_token_accuracy": 0.14183011949062346,
|
|
"num_tokens": 5276821.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.999506711959839,
|
|
"epoch": 0.237696946119432,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997119924554204,
|
|
"loss": 5.7826,
|
|
"mean_token_accuracy": 0.14683904349803925,
|
|
"num_tokens": 5285419.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.9552665710449215,
|
|
"epoch": 0.23808597549114957,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997105888709236,
|
|
"loss": 5.7019,
|
|
"mean_token_accuracy": 0.1541394919157028,
|
|
"num_tokens": 5294004.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.89560899734497,
|
|
"epoch": 0.23847500486286716,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997091818768015,
|
|
"loss": 5.8752,
|
|
"mean_token_accuracy": 0.1477641649544239,
|
|
"num_tokens": 5302699.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.0138801574707035,
|
|
"epoch": 0.23886403423458472,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499707771473075,
|
|
"loss": 5.7971,
|
|
"mean_token_accuracy": 0.14801695495843886,
|
|
"num_tokens": 5311115.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.9761481285095215,
|
|
"epoch": 0.23925306360630227,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997063576597659,
|
|
"loss": 5.7977,
|
|
"mean_token_accuracy": 0.1496265560388565,
|
|
"num_tokens": 5319795.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 6.042915296554566,
|
|
"epoch": 0.23964209297801983,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997049404368954,
|
|
"loss": 5.8341,
|
|
"mean_token_accuracy": 0.14897835552692412,
|
|
"num_tokens": 5328273.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.988575649261475,
|
|
"epoch": 0.2400311223497374,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499703519804485,
|
|
"loss": 5.829,
|
|
"mean_token_accuracy": 0.14671153724193572,
|
|
"num_tokens": 5336394.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.9397519588470455,
|
|
"epoch": 0.24042015172145498,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997020957625564,
|
|
"loss": 5.7769,
|
|
"mean_token_accuracy": 0.15148883908987046,
|
|
"num_tokens": 5344480.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.960248136520386,
|
|
"epoch": 0.24080918109317254,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997006683111312,
|
|
"loss": 5.8344,
|
|
"mean_token_accuracy": 0.13700284957885742,
|
|
"num_tokens": 5353445.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.9557548522949215,
|
|
"epoch": 0.2411982104648901,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499699237450231,
|
|
"loss": 5.7009,
|
|
"mean_token_accuracy": 0.15911950767040253,
|
|
"num_tokens": 5362356.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.96647891998291,
|
|
"epoch": 0.24158723983660765,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996978031798774,
|
|
"loss": 5.8215,
|
|
"mean_token_accuracy": 0.15092627853155136,
|
|
"num_tokens": 5371467.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.874505186080933,
|
|
"epoch": 0.24197626920832524,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996963655000924,
|
|
"loss": 5.698,
|
|
"mean_token_accuracy": 0.15349170416593552,
|
|
"num_tokens": 5380256.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 6.019479560852051,
|
|
"epoch": 0.2423652985800428,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996949244108977,
|
|
"loss": 5.7548,
|
|
"mean_token_accuracy": 0.148537015914917,
|
|
"num_tokens": 5388884.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.934230375289917,
|
|
"epoch": 0.24275432795176036,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499693479912315,
|
|
"loss": 5.7207,
|
|
"mean_token_accuracy": 0.1513214588165283,
|
|
"num_tokens": 5397980.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.915476846694946,
|
|
"epoch": 0.24314335732347792,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996920320043666,
|
|
"loss": 5.8269,
|
|
"mean_token_accuracy": 0.14737921729683875,
|
|
"num_tokens": 5406879.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.97343635559082,
|
|
"epoch": 0.24353238669519547,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996905806870742,
|
|
"loss": 5.8367,
|
|
"mean_token_accuracy": 0.14250106513500213,
|
|
"num_tokens": 5416161.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.952649211883545,
|
|
"epoch": 0.24392141606691306,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996891259604598,
|
|
"loss": 5.7053,
|
|
"mean_token_accuracy": 0.15676204413175582,
|
|
"num_tokens": 5424323.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.9204154968261715,
|
|
"epoch": 0.24431044543863062,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996876678245455,
|
|
"loss": 5.8257,
|
|
"mean_token_accuracy": 0.1389497771859169,
|
|
"num_tokens": 5433750.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 6.035652017593383,
|
|
"epoch": 0.24469947481034818,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996862062793536,
|
|
"loss": 5.8451,
|
|
"mean_token_accuracy": 0.1483545832335949,
|
|
"num_tokens": 5442113.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.946454668045044,
|
|
"epoch": 0.24508850418206574,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996847413249061,
|
|
"loss": 5.7325,
|
|
"mean_token_accuracy": 0.14880170971155166,
|
|
"num_tokens": 5450403.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.944355154037476,
|
|
"epoch": 0.24547753355378332,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996832729612252,
|
|
"loss": 5.8088,
|
|
"mean_token_accuracy": 0.1451127476990223,
|
|
"num_tokens": 5459018.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.953004455566406,
|
|
"epoch": 0.24586656292550088,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996818011883333,
|
|
"loss": 5.8338,
|
|
"mean_token_accuracy": 0.14286485612392424,
|
|
"num_tokens": 5468314.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.988242864608765,
|
|
"epoch": 0.24625559229721844,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996803260062527,
|
|
"loss": 5.8203,
|
|
"mean_token_accuracy": 0.14754107743501663,
|
|
"num_tokens": 5476950.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 6.008144521713257,
|
|
"epoch": 0.246644621668936,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996788474150057,
|
|
"loss": 5.7719,
|
|
"mean_token_accuracy": 0.1521343857049942,
|
|
"num_tokens": 5485201.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 6.0393514156341555,
|
|
"epoch": 0.24703365104065356,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996773654146149,
|
|
"loss": 5.9063,
|
|
"mean_token_accuracy": 0.14898504465818405,
|
|
"num_tokens": 5493096.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.891411304473877,
|
|
"epoch": 0.24742268041237114,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996758800051026,
|
|
"loss": 5.6865,
|
|
"mean_token_accuracy": 0.1497150219976902,
|
|
"num_tokens": 5502413.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.96971640586853,
|
|
"epoch": 0.2478117097840887,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996743911864916,
|
|
"loss": 5.8289,
|
|
"mean_token_accuracy": 0.149935594946146,
|
|
"num_tokens": 5511670.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.96325535774231,
|
|
"epoch": 0.24820073915580626,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996728989588041,
|
|
"loss": 5.7028,
|
|
"mean_token_accuracy": 0.1558322086930275,
|
|
"num_tokens": 5519344.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.896140098571777,
|
|
"epoch": 0.24858976852752382,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996714033220632,
|
|
"loss": 5.7149,
|
|
"mean_token_accuracy": 0.15106671154499055,
|
|
"num_tokens": 5528413.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.9170585632324215,
|
|
"epoch": 0.2489787978992414,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996699042762911,
|
|
"loss": 5.8108,
|
|
"mean_token_accuracy": 0.1454245112836361,
|
|
"num_tokens": 5537201.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.999245262145996,
|
|
"epoch": 0.24936782727095896,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996684018215111,
|
|
"loss": 5.8169,
|
|
"mean_token_accuracy": 0.14384038001298904,
|
|
"num_tokens": 5545975.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.949352216720581,
|
|
"epoch": 0.24975685664267652,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996668959577453,
|
|
"loss": 5.8537,
|
|
"mean_token_accuracy": 0.14289541244506837,
|
|
"num_tokens": 5555237.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.995472574234009,
|
|
"epoch": 0.2501458860143941,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996653866850173,
|
|
"loss": 5.7196,
|
|
"mean_token_accuracy": 0.15133460536599158,
|
|
"num_tokens": 5564048.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.927675676345825,
|
|
"epoch": 0.25053491538611167,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996638740033495,
|
|
"loss": 5.7774,
|
|
"mean_token_accuracy": 0.14800822138786315,
|
|
"num_tokens": 5573615.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.931420469284058,
|
|
"epoch": 0.2509239447578292,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996623579127651,
|
|
"loss": 5.6608,
|
|
"mean_token_accuracy": 0.154579995572567,
|
|
"num_tokens": 5582211.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.98255410194397,
|
|
"epoch": 0.2513129741295468,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996608384132868,
|
|
"loss": 5.8922,
|
|
"mean_token_accuracy": 0.14365677535533905,
|
|
"num_tokens": 5592542.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 6.0203358173370365,
|
|
"epoch": 0.25170200350126437,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499659315504938,
|
|
"loss": 5.8643,
|
|
"mean_token_accuracy": 0.15172575861215593,
|
|
"num_tokens": 5601279.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.95043683052063,
|
|
"epoch": 0.2520910328729819,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996577891877417,
|
|
"loss": 5.7939,
|
|
"mean_token_accuracy": 0.1459869921207428,
|
|
"num_tokens": 5610266.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.979887199401856,
|
|
"epoch": 0.2524800622446995,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996562594617209,
|
|
"loss": 5.8449,
|
|
"mean_token_accuracy": 0.144519080221653,
|
|
"num_tokens": 5618799.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 6.104338645935059,
|
|
"epoch": 0.252869091616417,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996547263268991,
|
|
"loss": 5.798,
|
|
"mean_token_accuracy": 0.1474681720137596,
|
|
"num_tokens": 5627861.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.9928460121154785,
|
|
"epoch": 0.2532581209881346,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996531897832993,
|
|
"loss": 5.7746,
|
|
"mean_token_accuracy": 0.1484766885638237,
|
|
"num_tokens": 5636229.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.9977171421051025,
|
|
"epoch": 0.2536471503598522,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499651649830945,
|
|
"loss": 5.9845,
|
|
"mean_token_accuracy": 0.13543816059827804,
|
|
"num_tokens": 5645828.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.932930946350098,
|
|
"epoch": 0.2540361797315697,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996501064698593,
|
|
"loss": 5.6161,
|
|
"mean_token_accuracy": 0.15123094767332076,
|
|
"num_tokens": 5654750.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.941285562515259,
|
|
"epoch": 0.2544252091032873,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499648559700066,
|
|
"loss": 5.7747,
|
|
"mean_token_accuracy": 0.15008440613746643,
|
|
"num_tokens": 5664017.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.946943283081055,
|
|
"epoch": 0.25481423847500484,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996470095215884,
|
|
"loss": 5.7868,
|
|
"mean_token_accuracy": 0.1457691326737404,
|
|
"num_tokens": 5672220.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.83295087814331,
|
|
"epoch": 0.2552032678467224,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996454559344498,
|
|
"loss": 5.7225,
|
|
"mean_token_accuracy": 0.14943785592913628,
|
|
"num_tokens": 5680921.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 6.023372316360474,
|
|
"epoch": 0.25559229721844,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996438989386741,
|
|
"loss": 5.7338,
|
|
"mean_token_accuracy": 0.14629117920994758,
|
|
"num_tokens": 5689226.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.9807192325592045,
|
|
"epoch": 0.25598132659015754,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996423385342847,
|
|
"loss": 5.87,
|
|
"mean_token_accuracy": 0.14247669130563737,
|
|
"num_tokens": 5698413.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.909314584732056,
|
|
"epoch": 0.25637035596187513,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996407747213055,
|
|
"loss": 5.7584,
|
|
"mean_token_accuracy": 0.14268624037504196,
|
|
"num_tokens": 5707724.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.99248685836792,
|
|
"epoch": 0.25675938533359266,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049963920749976,
|
|
"loss": 5.7555,
|
|
"mean_token_accuracy": 0.14810967147350312,
|
|
"num_tokens": 5716566.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.907137441635132,
|
|
"epoch": 0.25714841470531025,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996376368696721,
|
|
"loss": 5.7048,
|
|
"mean_token_accuracy": 0.14675737172365189,
|
|
"num_tokens": 5725463.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.9448107242584225,
|
|
"epoch": 0.25753744407702783,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996360628310656,
|
|
"loss": 5.7015,
|
|
"mean_token_accuracy": 0.15459197759628296,
|
|
"num_tokens": 5734143.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.9339416980743405,
|
|
"epoch": 0.25792647344874536,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996344853839644,
|
|
"loss": 5.7942,
|
|
"mean_token_accuracy": 0.14937918186187743,
|
|
"num_tokens": 5742981.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.841783332824707,
|
|
"epoch": 0.25831550282046295,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996329045283924,
|
|
"loss": 5.6704,
|
|
"mean_token_accuracy": 0.1587256371974945,
|
|
"num_tokens": 5751294.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.913126373291016,
|
|
"epoch": 0.25870453219218054,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996313202643737,
|
|
"loss": 5.7811,
|
|
"mean_token_accuracy": 0.14709209203720092,
|
|
"num_tokens": 5760958.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 6.002530574798584,
|
|
"epoch": 0.25909356156389807,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996297325919321,
|
|
"loss": 5.8021,
|
|
"mean_token_accuracy": 0.15270253270864487,
|
|
"num_tokens": 5769077.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 6.045363092422486,
|
|
"epoch": 0.25948259093561565,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996281415110919,
|
|
"loss": 5.8305,
|
|
"mean_token_accuracy": 0.1451015964150429,
|
|
"num_tokens": 5778093.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.906732749938965,
|
|
"epoch": 0.2598716203073332,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996265470218773,
|
|
"loss": 5.7761,
|
|
"mean_token_accuracy": 0.15038862004876136,
|
|
"num_tokens": 5786996.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.937571907043457,
|
|
"epoch": 0.26026064967905077,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996249491243122,
|
|
"loss": 5.7874,
|
|
"mean_token_accuracy": 0.1484340101480484,
|
|
"num_tokens": 5794831.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.886205101013184,
|
|
"epoch": 0.26064967905076836,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996233478184211,
|
|
"loss": 5.6179,
|
|
"mean_token_accuracy": 0.1540759265422821,
|
|
"num_tokens": 5802286.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.84423828125,
|
|
"epoch": 0.2610387084224859,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996217431042282,
|
|
"loss": 5.7548,
|
|
"mean_token_accuracy": 0.14987278878688812,
|
|
"num_tokens": 5810985.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.989913988113403,
|
|
"epoch": 0.2614277377942035,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499620134981758,
|
|
"loss": 5.8205,
|
|
"mean_token_accuracy": 0.1478564292192459,
|
|
"num_tokens": 5820037.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.89663553237915,
|
|
"epoch": 0.261816767165921,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996185234510346,
|
|
"loss": 5.6604,
|
|
"mean_token_accuracy": 0.16128647923469544,
|
|
"num_tokens": 5828232.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.934948062896728,
|
|
"epoch": 0.2622057965376386,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996169085120828,
|
|
"loss": 5.8869,
|
|
"mean_token_accuracy": 0.14827670753002167,
|
|
"num_tokens": 5838184.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.9939127445220945,
|
|
"epoch": 0.2625948259093562,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996152901649268,
|
|
"loss": 5.7069,
|
|
"mean_token_accuracy": 0.15314277410507202,
|
|
"num_tokens": 5846705.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.963273620605468,
|
|
"epoch": 0.2629838552810737,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996136684095913,
|
|
"loss": 5.796,
|
|
"mean_token_accuracy": 0.14697006940841675,
|
|
"num_tokens": 5855959.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.930791807174683,
|
|
"epoch": 0.2633728846527913,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996120432461009,
|
|
"loss": 5.7344,
|
|
"mean_token_accuracy": 0.15170250087976456,
|
|
"num_tokens": 5865283.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.922290325164795,
|
|
"epoch": 0.2637619140245088,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996104146744804,
|
|
"loss": 5.7812,
|
|
"mean_token_accuracy": 0.15208776146173478,
|
|
"num_tokens": 5873833.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 6.0046755313873295,
|
|
"epoch": 0.2641509433962264,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996087826947541,
|
|
"loss": 5.7129,
|
|
"mean_token_accuracy": 0.15557411015033723,
|
|
"num_tokens": 5882027.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.759491109848023,
|
|
"epoch": 0.264539972767944,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996071473069471,
|
|
"loss": 5.5875,
|
|
"mean_token_accuracy": 0.16241258680820464,
|
|
"num_tokens": 5890650.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.839728450775146,
|
|
"epoch": 0.26492900213966153,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996055085110842,
|
|
"loss": 5.6511,
|
|
"mean_token_accuracy": 0.15555724650621414,
|
|
"num_tokens": 5898595.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.96372389793396,
|
|
"epoch": 0.2653180315113791,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996038663071902,
|
|
"loss": 5.7441,
|
|
"mean_token_accuracy": 0.15167439579963685,
|
|
"num_tokens": 5907234.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.925133323669433,
|
|
"epoch": 0.26570706088309665,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996022206952901,
|
|
"loss": 5.7027,
|
|
"mean_token_accuracy": 0.15481544137001038,
|
|
"num_tokens": 5915690.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.878487873077392,
|
|
"epoch": 0.26609609025481423,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996005716754086,
|
|
"loss": 5.6507,
|
|
"mean_token_accuracy": 0.15669617652893067,
|
|
"num_tokens": 5924481.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.857667255401611,
|
|
"epoch": 0.2664851196265318,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499598919247571,
|
|
"loss": 5.733,
|
|
"mean_token_accuracy": 0.15500945448875428,
|
|
"num_tokens": 5933059.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.96867036819458,
|
|
"epoch": 0.26687414899824935,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995972634118023,
|
|
"loss": 5.841,
|
|
"mean_token_accuracy": 0.14314620122313498,
|
|
"num_tokens": 5941767.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.908726787567138,
|
|
"epoch": 0.26726317836996694,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995956041681277,
|
|
"loss": 5.7214,
|
|
"mean_token_accuracy": 0.15487033724784852,
|
|
"num_tokens": 5950202.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.880508899688721,
|
|
"epoch": 0.2676522077416845,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995939415165722,
|
|
"loss": 5.7695,
|
|
"mean_token_accuracy": 0.1417275495827198,
|
|
"num_tokens": 5959242.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.897665119171142,
|
|
"epoch": 0.26804123711340205,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004995922754571611,
|
|
"loss": 5.7323,
|
|
"mean_token_accuracy": 0.15200538709759712,
|
|
"num_tokens": 5968404.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.902557420730591,
|
|
"epoch": 0.26843026648511964,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995906059899197,
|
|
"loss": 5.8351,
|
|
"mean_token_accuracy": 0.15149400979280472,
|
|
"num_tokens": 5976711.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.935367488861084,
|
|
"epoch": 0.26881929585683717,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995889331148733,
|
|
"loss": 5.6925,
|
|
"mean_token_accuracy": 0.1482457771897316,
|
|
"num_tokens": 5985049.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.886753368377685,
|
|
"epoch": 0.26920832522855476,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995872568320474,
|
|
"loss": 5.717,
|
|
"mean_token_accuracy": 0.15387479811906815,
|
|
"num_tokens": 5993904.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.962065076828003,
|
|
"epoch": 0.26959735460027234,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995855771414673,
|
|
"loss": 5.7861,
|
|
"mean_token_accuracy": 0.1518370807170868,
|
|
"num_tokens": 6001832.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.872501373291016,
|
|
"epoch": 0.2699863839719899,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995838940431585,
|
|
"loss": 5.7113,
|
|
"mean_token_accuracy": 0.15001548826694489,
|
|
"num_tokens": 6010609.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.925089311599732,
|
|
"epoch": 0.27037541334370746,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995822075371466,
|
|
"loss": 5.7517,
|
|
"mean_token_accuracy": 0.14763056933879853,
|
|
"num_tokens": 6019299.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.982466840744019,
|
|
"epoch": 0.270764442715425,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995805176234571,
|
|
"loss": 5.8002,
|
|
"mean_token_accuracy": 0.14657859951257707,
|
|
"num_tokens": 6028743.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.923907136917114,
|
|
"epoch": 0.2711534720871426,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995788243021158,
|
|
"loss": 5.7007,
|
|
"mean_token_accuracy": 0.1456964671611786,
|
|
"num_tokens": 6038064.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.872335481643677,
|
|
"epoch": 0.27154250145886016,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995771275731483,
|
|
"loss": 5.6945,
|
|
"mean_token_accuracy": 0.1496543303132057,
|
|
"num_tokens": 6047031.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.945437908172607,
|
|
"epoch": 0.2719315308305777,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995754274365802,
|
|
"loss": 5.7919,
|
|
"mean_token_accuracy": 0.14971243888139724,
|
|
"num_tokens": 6056147.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.9183509349823,
|
|
"epoch": 0.2723205602022953,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995737238924376,
|
|
"loss": 5.7057,
|
|
"mean_token_accuracy": 0.15187868028879165,
|
|
"num_tokens": 6064641.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.844458484649659,
|
|
"epoch": 0.2727095895740128,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995720169407461,
|
|
"loss": 5.6144,
|
|
"mean_token_accuracy": 0.1521158903837204,
|
|
"num_tokens": 6073664.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.877747297286987,
|
|
"epoch": 0.2730986189457304,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995703065815317,
|
|
"loss": 5.6149,
|
|
"mean_token_accuracy": 0.15935999006032944,
|
|
"num_tokens": 6081480.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.870375347137451,
|
|
"epoch": 0.273487648317448,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995685928148203,
|
|
"loss": 5.7322,
|
|
"mean_token_accuracy": 0.14783481508493423,
|
|
"num_tokens": 6090408.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.957701301574707,
|
|
"epoch": 0.2738766776891655,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499566875640638,
|
|
"loss": 5.7415,
|
|
"mean_token_accuracy": 0.15329626500606536,
|
|
"num_tokens": 6099076.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.933114671707154,
|
|
"epoch": 0.2742657070608831,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995651550590108,
|
|
"loss": 5.7883,
|
|
"mean_token_accuracy": 0.1436773419380188,
|
|
"num_tokens": 6108346.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.897816848754883,
|
|
"epoch": 0.2746547364326007,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995634310699647,
|
|
"loss": 5.7497,
|
|
"mean_token_accuracy": 0.15223322287201882,
|
|
"num_tokens": 6116974.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.967880916595459,
|
|
"epoch": 0.2750437658043182,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995617036735261,
|
|
"loss": 5.7616,
|
|
"mean_token_accuracy": 0.15204408317804335,
|
|
"num_tokens": 6125510.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.9119133949279785,
|
|
"epoch": 0.2754327951760358,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995599728697211,
|
|
"loss": 5.8049,
|
|
"mean_token_accuracy": 0.14739501252770423,
|
|
"num_tokens": 6134959.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 6.0071333885192875,
|
|
"epoch": 0.27582182454775334,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995582386585759,
|
|
"loss": 5.7453,
|
|
"mean_token_accuracy": 0.14718504920601844,
|
|
"num_tokens": 6144485.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.914857864379883,
|
|
"epoch": 0.2762108539194709,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995565010401167,
|
|
"loss": 5.6867,
|
|
"mean_token_accuracy": 0.15570174753665925,
|
|
"num_tokens": 6153991.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.767222595214844,
|
|
"epoch": 0.2765998832911885,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995547600143702,
|
|
"loss": 5.6895,
|
|
"mean_token_accuracy": 0.1507698953151703,
|
|
"num_tokens": 6162649.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.850847625732422,
|
|
"epoch": 0.27698891266290604,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995530155813625,
|
|
"loss": 5.5856,
|
|
"mean_token_accuracy": 0.16076817810535432,
|
|
"num_tokens": 6171525.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.938121509552002,
|
|
"epoch": 0.2773779420346236,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995512677411203,
|
|
"loss": 5.8146,
|
|
"mean_token_accuracy": 0.15098893493413926,
|
|
"num_tokens": 6180403.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.879735708236694,
|
|
"epoch": 0.27776697140634116,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995495164936698,
|
|
"loss": 5.65,
|
|
"mean_token_accuracy": 0.1596470907330513,
|
|
"num_tokens": 6188361.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.871376180648804,
|
|
"epoch": 0.27815600077805874,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995477618390381,
|
|
"loss": 5.7122,
|
|
"mean_token_accuracy": 0.14880418330430983,
|
|
"num_tokens": 6197418.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.867201614379883,
|
|
"epoch": 0.27854503014977633,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995460037772513,
|
|
"loss": 5.7218,
|
|
"mean_token_accuracy": 0.14871663898229598,
|
|
"num_tokens": 6206040.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.845054197311401,
|
|
"epoch": 0.27893405952149386,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995442423083365,
|
|
"loss": 5.6482,
|
|
"mean_token_accuracy": 0.15263187140226364,
|
|
"num_tokens": 6214433.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.831419801712036,
|
|
"epoch": 0.27932308889321145,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995424774323201,
|
|
"loss": 5.6136,
|
|
"mean_token_accuracy": 0.1577524796128273,
|
|
"num_tokens": 6223375.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.778666973114014,
|
|
"epoch": 0.279712118264929,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499540709149229,
|
|
"loss": 5.7271,
|
|
"mean_token_accuracy": 0.15046759992837905,
|
|
"num_tokens": 6232597.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.874596309661865,
|
|
"epoch": 0.28010114763664656,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995389374590901,
|
|
"loss": 5.5829,
|
|
"mean_token_accuracy": 0.1621890977025032,
|
|
"num_tokens": 6240634.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.842890501022339,
|
|
"epoch": 0.28049017700836415,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995371623619301,
|
|
"loss": 5.5473,
|
|
"mean_token_accuracy": 0.1555539771914482,
|
|
"num_tokens": 6249098.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.764733839035034,
|
|
"epoch": 0.2808792063800817,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499535383857776,
|
|
"loss": 5.5857,
|
|
"mean_token_accuracy": 0.15672399699687958,
|
|
"num_tokens": 6257572.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.914619064331054,
|
|
"epoch": 0.28126823575179927,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499533601946655,
|
|
"loss": 5.8565,
|
|
"mean_token_accuracy": 0.14434114694595337,
|
|
"num_tokens": 6266492.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.921752166748047,
|
|
"epoch": 0.2816572651235168,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995318166285938,
|
|
"loss": 5.7196,
|
|
"mean_token_accuracy": 0.15166337937116622,
|
|
"num_tokens": 6275149.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.916532564163208,
|
|
"epoch": 0.2820462944952344,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995300279036199,
|
|
"loss": 5.7381,
|
|
"mean_token_accuracy": 0.1488499790430069,
|
|
"num_tokens": 6283208.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.901528787612915,
|
|
"epoch": 0.28243532386695197,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049952823577176,
|
|
"loss": 5.6755,
|
|
"mean_token_accuracy": 0.15527186542749405,
|
|
"num_tokens": 6292084.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.869945526123047,
|
|
"epoch": 0.2828243532386695,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004995264402330416,
|
|
"loss": 5.6731,
|
|
"mean_token_accuracy": 0.15194449573755264,
|
|
"num_tokens": 6301855.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.882921409606934,
|
|
"epoch": 0.2832133826103871,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995246412874919,
|
|
"loss": 5.6707,
|
|
"mean_token_accuracy": 0.15566004812717438,
|
|
"num_tokens": 6310166.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.82180552482605,
|
|
"epoch": 0.2836024119821047,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499522838935138,
|
|
"loss": 5.6583,
|
|
"mean_token_accuracy": 0.1585020527243614,
|
|
"num_tokens": 6318928.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.862071371078491,
|
|
"epoch": 0.2839914413538222,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995210331760074,
|
|
"loss": 5.7061,
|
|
"mean_token_accuracy": 0.15993273109197617,
|
|
"num_tokens": 6327790.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.952098655700683,
|
|
"epoch": 0.2843804707255398,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995192240101275,
|
|
"loss": 5.7378,
|
|
"mean_token_accuracy": 0.15206011682748793,
|
|
"num_tokens": 6335517.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.846499061584472,
|
|
"epoch": 0.2847695000972573,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995174114375258,
|
|
"loss": 5.7502,
|
|
"mean_token_accuracy": 0.15136053413152695,
|
|
"num_tokens": 6344218.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.804873752593994,
|
|
"epoch": 0.2851585294689749,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995155954582297,
|
|
"loss": 5.5473,
|
|
"mean_token_accuracy": 0.16678376495838165,
|
|
"num_tokens": 6353125.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.841932868957519,
|
|
"epoch": 0.2855475588406925,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995137760722668,
|
|
"loss": 5.6974,
|
|
"mean_token_accuracy": 0.15368882119655608,
|
|
"num_tokens": 6362113.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.88684115409851,
|
|
"epoch": 0.28593658821241,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995119532796646,
|
|
"loss": 5.7699,
|
|
"mean_token_accuracy": 0.14920303374528884,
|
|
"num_tokens": 6370916.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.927021169662476,
|
|
"epoch": 0.2863256175841276,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499510127080451,
|
|
"loss": 5.6138,
|
|
"mean_token_accuracy": 0.16021920293569564,
|
|
"num_tokens": 6379256.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.855990695953369,
|
|
"epoch": 0.28671464695584514,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995082974746535,
|
|
"loss": 5.7499,
|
|
"mean_token_accuracy": 0.1522106409072876,
|
|
"num_tokens": 6388098.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.802329730987549,
|
|
"epoch": 0.28710367632756273,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995064644622999,
|
|
"loss": 5.5594,
|
|
"mean_token_accuracy": 0.16143814623355865,
|
|
"num_tokens": 6396292.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.849812459945679,
|
|
"epoch": 0.2874927056992803,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995046280434181,
|
|
"loss": 5.5901,
|
|
"mean_token_accuracy": 0.15952554792165757,
|
|
"num_tokens": 6404968.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.730056238174439,
|
|
"epoch": 0.28788173507099785,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995027882180358,
|
|
"loss": 5.6695,
|
|
"mean_token_accuracy": 0.156508731842041,
|
|
"num_tokens": 6412839.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.860387945175171,
|
|
"epoch": 0.28827076444271543,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995009449861812,
|
|
"loss": 5.6814,
|
|
"mean_token_accuracy": 0.14714949131011962,
|
|
"num_tokens": 6421943.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.891568422317505,
|
|
"epoch": 0.28865979381443296,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499499098347882,
|
|
"loss": 5.7659,
|
|
"mean_token_accuracy": 0.14767337441444398,
|
|
"num_tokens": 6430731.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.881146097183228,
|
|
"epoch": 0.28904882318615055,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994972483031662,
|
|
"loss": 5.6965,
|
|
"mean_token_accuracy": 0.15450607240200043,
|
|
"num_tokens": 6439365.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.895514392852784,
|
|
"epoch": 0.28943785255786814,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499495394852062,
|
|
"loss": 5.6478,
|
|
"mean_token_accuracy": 0.16102308481931688,
|
|
"num_tokens": 6448085.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.757776546478271,
|
|
"epoch": 0.28982688192958567,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994935379945977,
|
|
"loss": 5.6973,
|
|
"mean_token_accuracy": 0.14822151511907578,
|
|
"num_tokens": 6457630.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.874344253540039,
|
|
"epoch": 0.29021591130130325,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994916777308012,
|
|
"loss": 5.5632,
|
|
"mean_token_accuracy": 0.16281430721282958,
|
|
"num_tokens": 6465781.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.872119998931884,
|
|
"epoch": 0.29060494067302084,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994898140607007,
|
|
"loss": 5.7428,
|
|
"mean_token_accuracy": 0.15796843618154527,
|
|
"num_tokens": 6473723.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.805860328674316,
|
|
"epoch": 0.29099397004473837,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004994879469843247,
|
|
"loss": 5.6772,
|
|
"mean_token_accuracy": 0.15386528074741362,
|
|
"num_tokens": 6482535.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.893405437469482,
|
|
"epoch": 0.29138299941645596,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994860765017013,
|
|
"loss": 5.7045,
|
|
"mean_token_accuracy": 0.15752176195383072,
|
|
"num_tokens": 6491297.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.846108055114746,
|
|
"epoch": 0.2917720287881735,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499484202612859,
|
|
"loss": 5.6735,
|
|
"mean_token_accuracy": 0.1522021323442459,
|
|
"num_tokens": 6499809.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.867705631256103,
|
|
"epoch": 0.2921610581598911,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994823253178264,
|
|
"loss": 5.6319,
|
|
"mean_token_accuracy": 0.16157492250204086,
|
|
"num_tokens": 6507965.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.846333694458008,
|
|
"epoch": 0.29255008753160866,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004994804446166317,
|
|
"loss": 5.6921,
|
|
"mean_token_accuracy": 0.14701894968748092,
|
|
"num_tokens": 6517106.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.883748531341553,
|
|
"epoch": 0.2929391169033262,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994785605093035,
|
|
"loss": 5.7624,
|
|
"mean_token_accuracy": 0.1514585569500923,
|
|
"num_tokens": 6526663.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 6.009462690353393,
|
|
"epoch": 0.2933281462750438,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994766729958705,
|
|
"loss": 5.808,
|
|
"mean_token_accuracy": 0.14928104281425475,
|
|
"num_tokens": 6535732.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.870941591262818,
|
|
"epoch": 0.2937171756467613,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004994747820763612,
|
|
"loss": 5.6578,
|
|
"mean_token_accuracy": 0.15538851767778397,
|
|
"num_tokens": 6544938.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.857924222946167,
|
|
"epoch": 0.2941062050184789,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994728877508046,
|
|
"loss": 5.6827,
|
|
"mean_token_accuracy": 0.15063629150390626,
|
|
"num_tokens": 6554507.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.892081832885742,
|
|
"epoch": 0.2944952343901965,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994709900192289,
|
|
"loss": 5.7118,
|
|
"mean_token_accuracy": 0.15043701082468033,
|
|
"num_tokens": 6563285.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.798528814315796,
|
|
"epoch": 0.294884263761914,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994690888816635,
|
|
"loss": 5.6014,
|
|
"mean_token_accuracy": 0.15134119018912315,
|
|
"num_tokens": 6572223.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.876222610473633,
|
|
"epoch": 0.2952732931336316,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994671843381367,
|
|
"loss": 5.7841,
|
|
"mean_token_accuracy": 0.14985665529966355,
|
|
"num_tokens": 6580686.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.892121982574463,
|
|
"epoch": 0.29566232250534913,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994652763886778,
|
|
"loss": 5.6401,
|
|
"mean_token_accuracy": 0.15805123150348663,
|
|
"num_tokens": 6589056.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.875431108474731,
|
|
"epoch": 0.2960513518770667,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994633650333155,
|
|
"loss": 5.7144,
|
|
"mean_token_accuracy": 0.15104243978857995,
|
|
"num_tokens": 6598221.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.948964405059814,
|
|
"epoch": 0.2964403812487843,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994614502720792,
|
|
"loss": 5.7493,
|
|
"mean_token_accuracy": 0.15437679290771483,
|
|
"num_tokens": 6606657.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.934873723983765,
|
|
"epoch": 0.29682941062050183,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994595321049974,
|
|
"loss": 5.8543,
|
|
"mean_token_accuracy": 0.143535877764225,
|
|
"num_tokens": 6616203.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.972373390197754,
|
|
"epoch": 0.2972184399922194,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004994576105320994,
|
|
"loss": 5.6997,
|
|
"mean_token_accuracy": 0.15348666310310363,
|
|
"num_tokens": 6624982.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.924484014511108,
|
|
"epoch": 0.29760746936393695,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994556855534146,
|
|
"loss": 5.6617,
|
|
"mean_token_accuracy": 0.15609370917081833,
|
|
"num_tokens": 6632548.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.828466367721558,
|
|
"epoch": 0.29799649873565454,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994537571689719,
|
|
"loss": 5.7896,
|
|
"mean_token_accuracy": 0.14499867409467698,
|
|
"num_tokens": 6641943.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.868363666534424,
|
|
"epoch": 0.2983855281073721,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994518253788007,
|
|
"loss": 5.6382,
|
|
"mean_token_accuracy": 0.15800181329250335,
|
|
"num_tokens": 6650371.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.883022594451904,
|
|
"epoch": 0.29877455747908965,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994498901829304,
|
|
"loss": 5.7198,
|
|
"mean_token_accuracy": 0.1552921250462532,
|
|
"num_tokens": 6659324.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.83655161857605,
|
|
"epoch": 0.29916358685080724,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994479515813903,
|
|
"loss": 5.6879,
|
|
"mean_token_accuracy": 0.15144439041614532,
|
|
"num_tokens": 6668237.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.839875030517578,
|
|
"epoch": 0.2995526162225248,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994460095742096,
|
|
"loss": 5.6073,
|
|
"mean_token_accuracy": 0.1622507467865944,
|
|
"num_tokens": 6677213.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.879772186279297,
|
|
"epoch": 0.29994164559424236,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499444064161418,
|
|
"loss": 5.6328,
|
|
"mean_token_accuracy": 0.1550130233168602,
|
|
"num_tokens": 6686850.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.8478320121765135,
|
|
"epoch": 0.30033067496595994,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499442115343045,
|
|
"loss": 5.6037,
|
|
"mean_token_accuracy": 0.15739710181951522,
|
|
"num_tokens": 6695697.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.793270015716553,
|
|
"epoch": 0.3007197043376775,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994401631191202,
|
|
"loss": 5.6532,
|
|
"mean_token_accuracy": 0.15891365557909012,
|
|
"num_tokens": 6704525.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.806357145309448,
|
|
"epoch": 0.30110873370939506,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994382074896731,
|
|
"loss": 5.5961,
|
|
"mean_token_accuracy": 0.1595403343439102,
|
|
"num_tokens": 6713562.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.90467472076416,
|
|
"epoch": 0.30149776308111265,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994362484547335,
|
|
"loss": 5.6972,
|
|
"mean_token_accuracy": 0.15663892328739165,
|
|
"num_tokens": 6721817.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.8863348960876465,
|
|
"epoch": 0.3018867924528302,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994342860143309,
|
|
"loss": 5.6195,
|
|
"mean_token_accuracy": 0.16563971489667892,
|
|
"num_tokens": 6729757.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.8139941692352295,
|
|
"epoch": 0.30227582182454776,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994323201684953,
|
|
"loss": 5.6991,
|
|
"mean_token_accuracy": 0.14580276012420654,
|
|
"num_tokens": 6738354.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.869457769393921,
|
|
"epoch": 0.3026648511962653,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994303509172566,
|
|
"loss": 5.7431,
|
|
"mean_token_accuracy": 0.15211848467588424,
|
|
"num_tokens": 6746505.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.927693891525268,
|
|
"epoch": 0.3030538805679829,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994283782606444,
|
|
"loss": 5.6525,
|
|
"mean_token_accuracy": 0.15591547936201094,
|
|
"num_tokens": 6754547.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.826806640625,
|
|
"epoch": 0.30344290993970047,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004994264021986888,
|
|
"loss": 5.5634,
|
|
"mean_token_accuracy": 0.15850718766450883,
|
|
"num_tokens": 6763213.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.7963276386260985,
|
|
"epoch": 0.303831939311418,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994244227314197,
|
|
"loss": 5.6212,
|
|
"mean_token_accuracy": 0.15866039842367172,
|
|
"num_tokens": 6771060.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.867762565612793,
|
|
"epoch": 0.3042209686831356,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994224398588672,
|
|
"loss": 5.7616,
|
|
"mean_token_accuracy": 0.15014109760522842,
|
|
"num_tokens": 6779819.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.846722602844238,
|
|
"epoch": 0.3046099980548531,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994204535810615,
|
|
"loss": 5.6614,
|
|
"mean_token_accuracy": 0.1529073566198349,
|
|
"num_tokens": 6788660.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.82415132522583,
|
|
"epoch": 0.3049990274265707,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994184638980326,
|
|
"loss": 5.6009,
|
|
"mean_token_accuracy": 0.1573179095983505,
|
|
"num_tokens": 6797298.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.798014879226685,
|
|
"epoch": 0.3053880567982883,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004994164708098107,
|
|
"loss": 5.6436,
|
|
"mean_token_accuracy": 0.15172264575958253,
|
|
"num_tokens": 6806148.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.843776082992553,
|
|
"epoch": 0.3057770861700058,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499414474316426,
|
|
"loss": 5.697,
|
|
"mean_token_accuracy": 0.15370588451623918,
|
|
"num_tokens": 6815494.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.975485897064209,
|
|
"epoch": 0.3061661155417234,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994124744179088,
|
|
"loss": 5.7473,
|
|
"mean_token_accuracy": 0.15004800111055375,
|
|
"num_tokens": 6824852.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.824012279510498,
|
|
"epoch": 0.306555144913441,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994104711142896,
|
|
"loss": 5.547,
|
|
"mean_token_accuracy": 0.16258234083652495,
|
|
"num_tokens": 6834200.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.8411280632019045,
|
|
"epoch": 0.3069441742851585,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994084644055986,
|
|
"loss": 5.6987,
|
|
"mean_token_accuracy": 0.15020909756422043,
|
|
"num_tokens": 6842869.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.867465353012085,
|
|
"epoch": 0.3073332036568761,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004994064542918664,
|
|
"loss": 5.6554,
|
|
"mean_token_accuracy": 0.15713998079299926,
|
|
"num_tokens": 6851668.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.892431163787842,
|
|
"epoch": 0.30772223302859364,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994044407731235,
|
|
"loss": 5.7414,
|
|
"mean_token_accuracy": 0.15816062390804292,
|
|
"num_tokens": 6860710.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.813387298583985,
|
|
"epoch": 0.3081112624003112,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994024238494002,
|
|
"loss": 5.6588,
|
|
"mean_token_accuracy": 0.15129568427801132,
|
|
"num_tokens": 6869608.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.884786081314087,
|
|
"epoch": 0.3085002917720288,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994004035207274,
|
|
"loss": 5.6702,
|
|
"mean_token_accuracy": 0.1528908684849739,
|
|
"num_tokens": 6878108.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.841224527359008,
|
|
"epoch": 0.30888932114374634,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993983797871356,
|
|
"loss": 5.5901,
|
|
"mean_token_accuracy": 0.1557810366153717,
|
|
"num_tokens": 6886369.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.813205862045288,
|
|
"epoch": 0.30927835051546393,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993963526486555,
|
|
"loss": 5.6423,
|
|
"mean_token_accuracy": 0.15107669085264205,
|
|
"num_tokens": 6895410.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.855010175704956,
|
|
"epoch": 0.30966737988718146,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499394322105318,
|
|
"loss": 5.6222,
|
|
"mean_token_accuracy": 0.16079719364643097,
|
|
"num_tokens": 6904380.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.888308000564575,
|
|
"epoch": 0.31005640925889905,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993922881571538,
|
|
"loss": 5.6539,
|
|
"mean_token_accuracy": 0.15389953702688217,
|
|
"num_tokens": 6913012.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.815182638168335,
|
|
"epoch": 0.31044543863061663,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004993902508041939,
|
|
"loss": 5.6771,
|
|
"mean_token_accuracy": 0.15611743330955505,
|
|
"num_tokens": 6921696.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.8514533042907715,
|
|
"epoch": 0.31083446800233416,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499388210046469,
|
|
"loss": 5.6059,
|
|
"mean_token_accuracy": 0.15560422986745834,
|
|
"num_tokens": 6930017.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.765750408172607,
|
|
"epoch": 0.31122349737405175,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993861658840102,
|
|
"loss": 5.572,
|
|
"mean_token_accuracy": 0.15584051012992858,
|
|
"num_tokens": 6938410.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.836692142486572,
|
|
"epoch": 0.3116125267457693,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993841183168484,
|
|
"loss": 5.6654,
|
|
"mean_token_accuracy": 0.15382085889577865,
|
|
"num_tokens": 6946227.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.874892997741699,
|
|
"epoch": 0.31200155611748687,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004993820673450148,
|
|
"loss": 5.6478,
|
|
"mean_token_accuracy": 0.15918285697698592,
|
|
"num_tokens": 6954747.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.823175764083862,
|
|
"epoch": 0.31239058548920445,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993800129685404,
|
|
"loss": 5.7146,
|
|
"mean_token_accuracy": 0.15485749244689942,
|
|
"num_tokens": 6962990.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.821749258041382,
|
|
"epoch": 0.312779614860922,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993779551874565,
|
|
"loss": 5.6766,
|
|
"mean_token_accuracy": 0.15734780877828597,
|
|
"num_tokens": 6972351.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.82036509513855,
|
|
"epoch": 0.31316864423263957,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993758940017943,
|
|
"loss": 5.6043,
|
|
"mean_token_accuracy": 0.15843922197818755,
|
|
"num_tokens": 6980387.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.721660137176514,
|
|
"epoch": 0.31355767360435716,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499373829411585,
|
|
"loss": 5.6673,
|
|
"mean_token_accuracy": 0.15660033971071244,
|
|
"num_tokens": 6989388.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.917605304718018,
|
|
"epoch": 0.3139467029760747,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00049937176141686,
|
|
"loss": 5.6171,
|
|
"mean_token_accuracy": 0.16407724171876908,
|
|
"num_tokens": 6997714.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.873993015289306,
|
|
"epoch": 0.3143357323477923,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004993696900176506,
|
|
"loss": 5.6092,
|
|
"mean_token_accuracy": 0.160344497859478,
|
|
"num_tokens": 7006453.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.795370388031006,
|
|
"epoch": 0.3147247617195098,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004993676152139883,
|
|
"loss": 5.6938,
|
|
"mean_token_accuracy": 0.15555773973464965,
|
|
"num_tokens": 7015398.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.8068183898925785,
|
|
"epoch": 0.3151137910912274,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993655370059046,
|
|
"loss": 5.6368,
|
|
"mean_token_accuracy": 0.1559157431125641,
|
|
"num_tokens": 7023796.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.760886287689209,
|
|
"epoch": 0.315502820462945,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004993634553934309,
|
|
"loss": 5.5815,
|
|
"mean_token_accuracy": 0.162422014772892,
|
|
"num_tokens": 7032453.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.805798435211182,
|
|
"epoch": 0.3158918498346625,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993613703765989,
|
|
"loss": 5.7204,
|
|
"mean_token_accuracy": 0.14737134724855422,
|
|
"num_tokens": 7041034.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.924254035949707,
|
|
"epoch": 0.3162808792063801,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993592819554402,
|
|
"loss": 5.8155,
|
|
"mean_token_accuracy": 0.14719487279653548,
|
|
"num_tokens": 7050289.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.8544573307037355,
|
|
"epoch": 0.3166699085780976,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993571901299866,
|
|
"loss": 5.6415,
|
|
"mean_token_accuracy": 0.16184244453907012,
|
|
"num_tokens": 7059638.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.799168491363526,
|
|
"epoch": 0.3170589379498152,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993550949002697,
|
|
"loss": 5.6618,
|
|
"mean_token_accuracy": 0.15811943262815475,
|
|
"num_tokens": 7067763.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.805049800872803,
|
|
"epoch": 0.3174479673215328,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993529962663213,
|
|
"loss": 5.6435,
|
|
"mean_token_accuracy": 0.16328213661909102,
|
|
"num_tokens": 7076126.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.815125751495361,
|
|
"epoch": 0.31783699669325033,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993508942281732,
|
|
"loss": 5.5661,
|
|
"mean_token_accuracy": 0.159896120429039,
|
|
"num_tokens": 7084403.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.687847995758057,
|
|
"epoch": 0.3182260260649679,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004993487887858575,
|
|
"loss": 5.5415,
|
|
"mean_token_accuracy": 0.16261251866817475,
|
|
"num_tokens": 7093450.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.770251321792602,
|
|
"epoch": 0.31861505543668545,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499346679939406,
|
|
"loss": 5.5404,
|
|
"mean_token_accuracy": 0.16247584223747252,
|
|
"num_tokens": 7101722.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.756721687316895,
|
|
"epoch": 0.31900408480840303,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004993445676888507,
|
|
"loss": 5.6337,
|
|
"mean_token_accuracy": 0.15481607466936112,
|
|
"num_tokens": 7111285.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.881993198394776,
|
|
"epoch": 0.3193931141801206,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993424520342236,
|
|
"loss": 5.7005,
|
|
"mean_token_accuracy": 0.15225102454423906,
|
|
"num_tokens": 7120281.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.798208332061767,
|
|
"epoch": 0.31978214355183815,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993403329755569,
|
|
"loss": 5.5741,
|
|
"mean_token_accuracy": 0.1554294690489769,
|
|
"num_tokens": 7128584.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.880425357818604,
|
|
"epoch": 0.32017117292355574,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993382105128828,
|
|
"loss": 5.6783,
|
|
"mean_token_accuracy": 0.15804177671670913,
|
|
"num_tokens": 7137570.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.832143306732178,
|
|
"epoch": 0.32056020229527327,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993360846462333,
|
|
"loss": 5.7214,
|
|
"mean_token_accuracy": 0.15496834367513657,
|
|
"num_tokens": 7146965.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.823439979553223,
|
|
"epoch": 0.32094923166699085,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993339553756408,
|
|
"loss": 5.6592,
|
|
"mean_token_accuracy": 0.15344669073820114,
|
|
"num_tokens": 7155657.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.849871444702148,
|
|
"epoch": 0.32133826103870844,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993318227011378,
|
|
"loss": 5.5982,
|
|
"mean_token_accuracy": 0.15800351351499559,
|
|
"num_tokens": 7164369.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.862731027603149,
|
|
"epoch": 0.32172729041042597,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993296866227562,
|
|
"loss": 5.5761,
|
|
"mean_token_accuracy": 0.16416397988796233,
|
|
"num_tokens": 7172161.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.774852848052978,
|
|
"epoch": 0.32211631978214356,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004993275471405288,
|
|
"loss": 5.6148,
|
|
"mean_token_accuracy": 0.149345500767231,
|
|
"num_tokens": 7180606.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.7628284931182865,
|
|
"epoch": 0.32250534915386114,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993254042544879,
|
|
"loss": 5.6498,
|
|
"mean_token_accuracy": 0.15902409553527833,
|
|
"num_tokens": 7188912.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.808630084991455,
|
|
"epoch": 0.3228943785255787,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499323257964666,
|
|
"loss": 5.6582,
|
|
"mean_token_accuracy": 0.15545909702777863,
|
|
"num_tokens": 7197477.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.859759187698364,
|
|
"epoch": 0.32328340789729626,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993211082710957,
|
|
"loss": 5.6418,
|
|
"mean_token_accuracy": 0.1600700318813324,
|
|
"num_tokens": 7206571.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.824004888534546,
|
|
"epoch": 0.3236724372690138,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993189551738097,
|
|
"loss": 5.4896,
|
|
"mean_token_accuracy": 0.1557634025812149,
|
|
"num_tokens": 7215319.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.779311323165894,
|
|
"epoch": 0.3240614666407314,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993167986728405,
|
|
"loss": 5.6555,
|
|
"mean_token_accuracy": 0.1558437839150429,
|
|
"num_tokens": 7223389.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.818670797348022,
|
|
"epoch": 0.32445049601244896,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499314638768221,
|
|
"loss": 5.6366,
|
|
"mean_token_accuracy": 0.1572311580181122,
|
|
"num_tokens": 7231853.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.805356645584107,
|
|
"epoch": 0.3248395253841665,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004993124754599839,
|
|
"loss": 5.5678,
|
|
"mean_token_accuracy": 0.1613128237426281,
|
|
"num_tokens": 7241081.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.773802375793457,
|
|
"epoch": 0.3252285547558841,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993103087481619,
|
|
"loss": 5.598,
|
|
"mean_token_accuracy": 0.15808786898851396,
|
|
"num_tokens": 7249742.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.8834186553955075,
|
|
"epoch": 0.3256175841276016,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004993081386327881,
|
|
"loss": 5.7046,
|
|
"mean_token_accuracy": 0.15388916730880736,
|
|
"num_tokens": 7258285.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.80883526802063,
|
|
"epoch": 0.3260066134993192,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004993059651138953,
|
|
"loss": 5.5378,
|
|
"mean_token_accuracy": 0.16168167293071747,
|
|
"num_tokens": 7266843.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.761549377441407,
|
|
"epoch": 0.3263956428710368,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993037881915165,
|
|
"loss": 5.6235,
|
|
"mean_token_accuracy": 0.16374704092741013,
|
|
"num_tokens": 7276041.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.801425170898438,
|
|
"epoch": 0.3267846722427543,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993016078656847,
|
|
"loss": 5.6898,
|
|
"mean_token_accuracy": 0.1496354892849922,
|
|
"num_tokens": 7285144.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.701427793502807,
|
|
"epoch": 0.3271737016144719,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499299424136433,
|
|
"loss": 5.5432,
|
|
"mean_token_accuracy": 0.16148447692394258,
|
|
"num_tokens": 7293976.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.813598680496216,
|
|
"epoch": 0.32756273098618943,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992972370037946,
|
|
"loss": 5.5957,
|
|
"mean_token_accuracy": 0.15628974586725236,
|
|
"num_tokens": 7302365.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.853533697128296,
|
|
"epoch": 0.327951760357907,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992950464678026,
|
|
"loss": 5.6728,
|
|
"mean_token_accuracy": 0.1533830374479294,
|
|
"num_tokens": 7310909.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.817704343795777,
|
|
"epoch": 0.3283407897296246,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992928525284903,
|
|
"loss": 5.6304,
|
|
"mean_token_accuracy": 0.1496094822883606,
|
|
"num_tokens": 7319391.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.894934749603271,
|
|
"epoch": 0.32872981910134214,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499290655185891,
|
|
"loss": 5.7032,
|
|
"mean_token_accuracy": 0.15388529300689696,
|
|
"num_tokens": 7328076.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.895980453491211,
|
|
"epoch": 0.3291188484730597,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499288454440038,
|
|
"loss": 5.656,
|
|
"mean_token_accuracy": 0.15448319762945176,
|
|
"num_tokens": 7336833.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.7740541934967045,
|
|
"epoch": 0.3295078778447773,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992862502909645,
|
|
"loss": 5.5709,
|
|
"mean_token_accuracy": 0.16009747087955475,
|
|
"num_tokens": 7344862.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.845920705795288,
|
|
"epoch": 0.32989690721649484,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992840427387043,
|
|
"loss": 5.6108,
|
|
"mean_token_accuracy": 0.1616164118051529,
|
|
"num_tokens": 7354503.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.807738494873047,
|
|
"epoch": 0.3302859365882124,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992818317832908,
|
|
"loss": 5.5924,
|
|
"mean_token_accuracy": 0.15691906362771987,
|
|
"num_tokens": 7363000.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.762190198898315,
|
|
"epoch": 0.33067496595992996,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004992796174247574,
|
|
"loss": 5.6631,
|
|
"mean_token_accuracy": 0.15225939452648163,
|
|
"num_tokens": 7372619.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.859451723098755,
|
|
"epoch": 0.33106399533164754,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992773996631378,
|
|
"loss": 5.5438,
|
|
"mean_token_accuracy": 0.16727319806814195,
|
|
"num_tokens": 7380531.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.779058408737183,
|
|
"epoch": 0.33145302470336513,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992751784984656,
|
|
"loss": 5.6608,
|
|
"mean_token_accuracy": 0.15575532466173173,
|
|
"num_tokens": 7389153.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.766335105895996,
|
|
"epoch": 0.33184205407508266,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004992729539307745,
|
|
"loss": 5.5563,
|
|
"mean_token_accuracy": 0.1592848628759384,
|
|
"num_tokens": 7397880.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.846122121810913,
|
|
"epoch": 0.33223108344680025,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992707259600984,
|
|
"loss": 5.6265,
|
|
"mean_token_accuracy": 0.1536146730184555,
|
|
"num_tokens": 7406180.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.763803863525391,
|
|
"epoch": 0.3326201128185178,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992684945864709,
|
|
"loss": 5.6285,
|
|
"mean_token_accuracy": 0.15639231055974961,
|
|
"num_tokens": 7415069.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.810007476806641,
|
|
"epoch": 0.33300914219023536,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992662598099261,
|
|
"loss": 5.6936,
|
|
"mean_token_accuracy": 0.15463295876979827,
|
|
"num_tokens": 7423921.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.7576460361480715,
|
|
"epoch": 0.33339817156195295,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004992640216304975,
|
|
"loss": 5.4188,
|
|
"mean_token_accuracy": 0.16716092079877853,
|
|
"num_tokens": 7432655.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.829642963409424,
|
|
"epoch": 0.3337872009336705,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992617800482196,
|
|
"loss": 5.6198,
|
|
"mean_token_accuracy": 0.15765354484319688,
|
|
"num_tokens": 7441858.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.723947429656983,
|
|
"epoch": 0.33417623030538807,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499259535063126,
|
|
"loss": 5.5789,
|
|
"mean_token_accuracy": 0.15934376716613768,
|
|
"num_tokens": 7450030.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.808957242965699,
|
|
"epoch": 0.3345652596771056,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499257286675251,
|
|
"loss": 5.6593,
|
|
"mean_token_accuracy": 0.15726078003644944,
|
|
"num_tokens": 7458256.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.867031478881836,
|
|
"epoch": 0.3349542890488232,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992550348846285,
|
|
"loss": 5.6334,
|
|
"mean_token_accuracy": 0.15359683632850646,
|
|
"num_tokens": 7466710.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.773306608200073,
|
|
"epoch": 0.33534331842054077,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004992527796912928,
|
|
"loss": 5.5716,
|
|
"mean_token_accuracy": 0.15899703204631804,
|
|
"num_tokens": 7475445.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.8272724628448485,
|
|
"epoch": 0.3357323477922583,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992505210952782,
|
|
"loss": 5.6566,
|
|
"mean_token_accuracy": 0.15544623732566834,
|
|
"num_tokens": 7484326.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.770163440704346,
|
|
"epoch": 0.3361213771639759,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992482590966188,
|
|
"loss": 5.559,
|
|
"mean_token_accuracy": 0.15421020984649658,
|
|
"num_tokens": 7493028.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.868523788452149,
|
|
"epoch": 0.3365104065356934,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004992459936953489,
|
|
"loss": 5.7285,
|
|
"mean_token_accuracy": 0.14974396377801896,
|
|
"num_tokens": 7502284.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.830294513702393,
|
|
"epoch": 0.336899435907411,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992437248915032,
|
|
"loss": 5.6091,
|
|
"mean_token_accuracy": 0.1528960421681404,
|
|
"num_tokens": 7510728.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.75536732673645,
|
|
"epoch": 0.3372884652791286,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004992414526851157,
|
|
"loss": 5.5634,
|
|
"mean_token_accuracy": 0.16224416494369506,
|
|
"num_tokens": 7519578.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.788976240158081,
|
|
"epoch": 0.3376774946508461,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992391770762212,
|
|
"loss": 5.6893,
|
|
"mean_token_accuracy": 0.15647384971380235,
|
|
"num_tokens": 7528853.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.948878335952759,
|
|
"epoch": 0.3380665240225637,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499236898064854,
|
|
"loss": 5.7347,
|
|
"mean_token_accuracy": 0.15497319251298905,
|
|
"num_tokens": 7537000.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.835531377792359,
|
|
"epoch": 0.3384555533942813,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004992346156510488,
|
|
"loss": 5.6985,
|
|
"mean_token_accuracy": 0.1538426622748375,
|
|
"num_tokens": 7545439.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.821720838546753,
|
|
"epoch": 0.3388445827659988,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992323298348403,
|
|
"loss": 5.5876,
|
|
"mean_token_accuracy": 0.15640681535005568,
|
|
"num_tokens": 7553808.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.844230365753174,
|
|
"epoch": 0.3392336121377164,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499230040616263,
|
|
"loss": 5.6092,
|
|
"mean_token_accuracy": 0.1657412052154541,
|
|
"num_tokens": 7562124.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.876851892471313,
|
|
"epoch": 0.33962264150943394,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004992277479953518,
|
|
"loss": 5.6564,
|
|
"mean_token_accuracy": 0.15803641080856323,
|
|
"num_tokens": 7570692.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.753260946273803,
|
|
"epoch": 0.34001167088115153,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992254519721414,
|
|
"loss": 5.5656,
|
|
"mean_token_accuracy": 0.1561785027384758,
|
|
"num_tokens": 7579380.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.7513867855072025,
|
|
"epoch": 0.3404007002528691,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992231525466666,
|
|
"loss": 5.6143,
|
|
"mean_token_accuracy": 0.1561330333352089,
|
|
"num_tokens": 7587581.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.8919556617736815,
|
|
"epoch": 0.34078972962458665,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004992208497189624,
|
|
"loss": 5.6625,
|
|
"mean_token_accuracy": 0.15787704586982726,
|
|
"num_tokens": 7596373.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.797363567352295,
|
|
"epoch": 0.34117875899630423,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004992185434890637,
|
|
"loss": 5.6715,
|
|
"mean_token_accuracy": 0.15297794640064238,
|
|
"num_tokens": 7605698.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.882697725296021,
|
|
"epoch": 0.34156778836802176,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992162338570055,
|
|
"loss": 5.6975,
|
|
"mean_token_accuracy": 0.14880578219890594,
|
|
"num_tokens": 7614299.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.7781144142150875,
|
|
"epoch": 0.34195681773973935,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992139208228227,
|
|
"loss": 5.6118,
|
|
"mean_token_accuracy": 0.16854615658521652,
|
|
"num_tokens": 7622244.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.8229796409606935,
|
|
"epoch": 0.34234584711145694,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992116043865506,
|
|
"loss": 5.7222,
|
|
"mean_token_accuracy": 0.14495111405849456,
|
|
"num_tokens": 7631421.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.837610483169556,
|
|
"epoch": 0.34273487648317447,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004992092845482244,
|
|
"loss": 5.6514,
|
|
"mean_token_accuracy": 0.16512158513069153,
|
|
"num_tokens": 7640483.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.790783357620239,
|
|
"epoch": 0.34312390585489205,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992069613078791,
|
|
"loss": 5.581,
|
|
"mean_token_accuracy": 0.1600580781698227,
|
|
"num_tokens": 7648928.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.822185516357422,
|
|
"epoch": 0.3435129352266096,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992046346655499,
|
|
"loss": 5.5944,
|
|
"mean_token_accuracy": 0.16028566807508468,
|
|
"num_tokens": 7658158.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.871115207672119,
|
|
"epoch": 0.34390196459832717,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004992023046212723,
|
|
"loss": 5.6718,
|
|
"mean_token_accuracy": 0.16050985604524612,
|
|
"num_tokens": 7666657.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.8094886302947994,
|
|
"epoch": 0.34429099397004476,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991999711750816,
|
|
"loss": 5.6214,
|
|
"mean_token_accuracy": 0.15986572504043578,
|
|
"num_tokens": 7675182.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.760066080093384,
|
|
"epoch": 0.3446800233417623,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004991976343270133,
|
|
"loss": 5.576,
|
|
"mean_token_accuracy": 0.1577327698469162,
|
|
"num_tokens": 7684132.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.778253698348999,
|
|
"epoch": 0.3450690527134799,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004991952940771026,
|
|
"loss": 5.5113,
|
|
"mean_token_accuracy": 0.16556746065616607,
|
|
"num_tokens": 7692574.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.707170486450195,
|
|
"epoch": 0.34545808208519746,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004991929504253852,
|
|
"loss": 5.581,
|
|
"mean_token_accuracy": 0.16168904453516006,
|
|
"num_tokens": 7700969.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.851817226409912,
|
|
"epoch": 0.345847111456915,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991906033718966,
|
|
"loss": 5.7303,
|
|
"mean_token_accuracy": 0.1541138157248497,
|
|
"num_tokens": 7710688.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.875735950469971,
|
|
"epoch": 0.3462361408286326,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991882529166724,
|
|
"loss": 5.684,
|
|
"mean_token_accuracy": 0.15931884944438934,
|
|
"num_tokens": 7720071.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.699068641662597,
|
|
"epoch": 0.3466251702003501,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004991858990597483,
|
|
"loss": 5.4769,
|
|
"mean_token_accuracy": 0.16656545400619507,
|
|
"num_tokens": 7728418.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.807401704788208,
|
|
"epoch": 0.3470141995720677,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004991835418011601,
|
|
"loss": 5.7004,
|
|
"mean_token_accuracy": 0.1571740910410881,
|
|
"num_tokens": 7736849.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.812630748748779,
|
|
"epoch": 0.3474032289437853,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991811811409434,
|
|
"loss": 5.6368,
|
|
"mean_token_accuracy": 0.1612528756260872,
|
|
"num_tokens": 7745730.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.837718725204468,
|
|
"epoch": 0.3477922583155028,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991788170791341,
|
|
"loss": 5.5321,
|
|
"mean_token_accuracy": 0.16686054319143295,
|
|
"num_tokens": 7755040.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.822087287902832,
|
|
"epoch": 0.3481812876872204,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004991764496157682,
|
|
"loss": 5.5675,
|
|
"mean_token_accuracy": 0.16306846141815184,
|
|
"num_tokens": 7763765.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.662372493743897,
|
|
"epoch": 0.34857031705893793,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004991740787508814,
|
|
"loss": 5.5465,
|
|
"mean_token_accuracy": 0.15900719314813613,
|
|
"num_tokens": 7772261.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.890163516998291,
|
|
"epoch": 0.3489593464306555,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991717044845097,
|
|
"loss": 5.6988,
|
|
"mean_token_accuracy": 0.15734705626964568,
|
|
"num_tokens": 7781651.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.793856143951416,
|
|
"epoch": 0.3493483758023731,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991693268166892,
|
|
"loss": 5.5536,
|
|
"mean_token_accuracy": 0.15972345769405366,
|
|
"num_tokens": 7789926.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.799531078338623,
|
|
"epoch": 0.34973740517409063,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004991669457474559,
|
|
"loss": 5.5908,
|
|
"mean_token_accuracy": 0.15855335295200348,
|
|
"num_tokens": 7798435.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.703534173965454,
|
|
"epoch": 0.3501264345458082,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991645612768461,
|
|
"loss": 5.5305,
|
|
"mean_token_accuracy": 0.15555441081523896,
|
|
"num_tokens": 7806674.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.793919277191162,
|
|
"epoch": 0.35051546391752575,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991621734048958,
|
|
"loss": 5.5803,
|
|
"mean_token_accuracy": 0.16211650967597963,
|
|
"num_tokens": 7814774.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.772414875030518,
|
|
"epoch": 0.35090449328924334,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004991597821316415,
|
|
"loss": 5.6327,
|
|
"mean_token_accuracy": 0.16405177861452103,
|
|
"num_tokens": 7822879.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.7185948371887205,
|
|
"epoch": 0.3512935226609609,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004991573874571192,
|
|
"loss": 5.5775,
|
|
"mean_token_accuracy": 0.1566230461001396,
|
|
"num_tokens": 7831418.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.786003923416137,
|
|
"epoch": 0.35168255203267845,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991549893813653,
|
|
"loss": 5.5533,
|
|
"mean_token_accuracy": 0.1591557964682579,
|
|
"num_tokens": 7839513.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.764983367919922,
|
|
"epoch": 0.35207158140439604,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991525879044162,
|
|
"loss": 5.5583,
|
|
"mean_token_accuracy": 0.15838483273983,
|
|
"num_tokens": 7847653.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.786115550994873,
|
|
"epoch": 0.35246061077611357,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991501830263084,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.15774892494082451,
|
|
"num_tokens": 7857093.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.811744642257691,
|
|
"epoch": 0.35284964014783116,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991477747470783,
|
|
"loss": 5.6042,
|
|
"mean_token_accuracy": 0.15566327124834062,
|
|
"num_tokens": 7866129.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.783624172210693,
|
|
"epoch": 0.35323866951954874,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991453630667625,
|
|
"loss": 5.6931,
|
|
"mean_token_accuracy": 0.15737468898296356,
|
|
"num_tokens": 7874613.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.684437322616577,
|
|
"epoch": 0.3536276988912663,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991429479853976,
|
|
"loss": 5.451,
|
|
"mean_token_accuracy": 0.16613204032182693,
|
|
"num_tokens": 7882292.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.772076034545899,
|
|
"epoch": 0.35401672826298386,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991405295030202,
|
|
"loss": 5.4785,
|
|
"mean_token_accuracy": 0.1672605663537979,
|
|
"num_tokens": 7890810.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.796853303909302,
|
|
"epoch": 0.35440575763470145,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004991381076196671,
|
|
"loss": 5.6086,
|
|
"mean_token_accuracy": 0.15777526199817657,
|
|
"num_tokens": 7899964.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.752718496322632,
|
|
"epoch": 0.354794787006419,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004991356823353748,
|
|
"loss": 5.5094,
|
|
"mean_token_accuracy": 0.16097644716501236,
|
|
"num_tokens": 7908600.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.7299388408660885,
|
|
"epoch": 0.35518381637813656,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991332536501804,
|
|
"loss": 5.6318,
|
|
"mean_token_accuracy": 0.1585194870829582,
|
|
"num_tokens": 7916893.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.76154408454895,
|
|
"epoch": 0.3555728457498541,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004991308215641205,
|
|
"loss": 5.4898,
|
|
"mean_token_accuracy": 0.1694232165813446,
|
|
"num_tokens": 7925230.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.790162515640259,
|
|
"epoch": 0.3559618751215717,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991283860772323,
|
|
"loss": 5.5458,
|
|
"mean_token_accuracy": 0.16623237133026122,
|
|
"num_tokens": 7933487.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.7462163925170895,
|
|
"epoch": 0.35635090449328927,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991259471895525,
|
|
"loss": 5.582,
|
|
"mean_token_accuracy": 0.16115867495536804,
|
|
"num_tokens": 7941957.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.762738752365112,
|
|
"epoch": 0.3567399338650068,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004991235049011182,
|
|
"loss": 5.5274,
|
|
"mean_token_accuracy": 0.15829257667064667,
|
|
"num_tokens": 7950912.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.754968738555908,
|
|
"epoch": 0.3571289632367244,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991210592119663,
|
|
"loss": 5.5701,
|
|
"mean_token_accuracy": 0.1587151512503624,
|
|
"num_tokens": 7959724.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.784298467636108,
|
|
"epoch": 0.3575179926084419,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991186101221342,
|
|
"loss": 5.5576,
|
|
"mean_token_accuracy": 0.16696627289056779,
|
|
"num_tokens": 7968683.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.69855260848999,
|
|
"epoch": 0.3579070219801595,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499116157631659,
|
|
"loss": 5.5198,
|
|
"mean_token_accuracy": 0.16008122861385346,
|
|
"num_tokens": 7977004.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.854188108444214,
|
|
"epoch": 0.3582960513518771,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004991137017405777,
|
|
"loss": 5.7284,
|
|
"mean_token_accuracy": 0.15145769119262695,
|
|
"num_tokens": 7985537.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.852160310745239,
|
|
"epoch": 0.3586850807235946,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991112424489277,
|
|
"loss": 5.6282,
|
|
"mean_token_accuracy": 0.15578002780675887,
|
|
"num_tokens": 7994298.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.7363073348999025,
|
|
"epoch": 0.3590741100953122,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004991087797567462,
|
|
"loss": 5.5804,
|
|
"mean_token_accuracy": 0.16114823073148726,
|
|
"num_tokens": 8003145.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.741312026977539,
|
|
"epoch": 0.35946313946702974,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991063136640709,
|
|
"loss": 5.5539,
|
|
"mean_token_accuracy": 0.15820185393095015,
|
|
"num_tokens": 8011839.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.846971559524536,
|
|
"epoch": 0.3598521688387473,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991038441709388,
|
|
"loss": 5.6292,
|
|
"mean_token_accuracy": 0.1515355572104454,
|
|
"num_tokens": 8020248.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.809453773498535,
|
|
"epoch": 0.3602411982104649,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004991013712773877,
|
|
"loss": 5.6502,
|
|
"mean_token_accuracy": 0.15742439329624175,
|
|
"num_tokens": 8029360.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.897890329360962,
|
|
"epoch": 0.36063022758218244,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990988949834549,
|
|
"loss": 5.7066,
|
|
"mean_token_accuracy": 0.1522804707288742,
|
|
"num_tokens": 8037407.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.818277740478516,
|
|
"epoch": 0.3610192569539,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499096415289178,
|
|
"loss": 5.5227,
|
|
"mean_token_accuracy": 0.16456927210092545,
|
|
"num_tokens": 8045935.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.764923477172852,
|
|
"epoch": 0.3614082863256176,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990939321945948,
|
|
"loss": 5.678,
|
|
"mean_token_accuracy": 0.14663905650377274,
|
|
"num_tokens": 8054640.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.881791114807129,
|
|
"epoch": 0.36179731569733514,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990914456997427,
|
|
"loss": 5.664,
|
|
"mean_token_accuracy": 0.16005869060754777,
|
|
"num_tokens": 8063845.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.818548250198364,
|
|
"epoch": 0.36218634506905273,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004990889558046598,
|
|
"loss": 5.5912,
|
|
"mean_token_accuracy": 0.1565910518169403,
|
|
"num_tokens": 8072389.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.706920480728149,
|
|
"epoch": 0.36257537444077026,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004990864625093836,
|
|
"loss": 5.4744,
|
|
"mean_token_accuracy": 0.16084736585617065,
|
|
"num_tokens": 8080683.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.6497913837432865,
|
|
"epoch": 0.36296440381248785,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990839658139519,
|
|
"loss": 5.5024,
|
|
"mean_token_accuracy": 0.1633412852883339,
|
|
"num_tokens": 8088945.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.738694334030152,
|
|
"epoch": 0.36335343318420543,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990814657184028,
|
|
"loss": 5.5617,
|
|
"mean_token_accuracy": 0.15861178040504456,
|
|
"num_tokens": 8097447.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.70173487663269,
|
|
"epoch": 0.36374246255592296,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990789622227741,
|
|
"loss": 5.4118,
|
|
"mean_token_accuracy": 0.17580605000257493,
|
|
"num_tokens": 8105570.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.678836393356323,
|
|
"epoch": 0.36413149192764055,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004990764553271038,
|
|
"loss": 5.5463,
|
|
"mean_token_accuracy": 0.16317810416221618,
|
|
"num_tokens": 8114842.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.748669624328613,
|
|
"epoch": 0.3645205212993581,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004990739450314299,
|
|
"loss": 5.5307,
|
|
"mean_token_accuracy": 0.16124996095895766,
|
|
"num_tokens": 8122960.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.865330505371094,
|
|
"epoch": 0.36490955067107567,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990714313357906,
|
|
"loss": 5.6691,
|
|
"mean_token_accuracy": 0.16008023619651796,
|
|
"num_tokens": 8131850.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.75564661026001,
|
|
"epoch": 0.36529858004279325,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499068914240224,
|
|
"loss": 5.539,
|
|
"mean_token_accuracy": 0.1603344514966011,
|
|
"num_tokens": 8139818.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.679873132705689,
|
|
"epoch": 0.3656876094145108,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004990663937447682,
|
|
"loss": 5.6201,
|
|
"mean_token_accuracy": 0.16053933054208755,
|
|
"num_tokens": 8147995.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.8246174335479735,
|
|
"epoch": 0.36607663878622837,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990638698494615,
|
|
"loss": 5.5967,
|
|
"mean_token_accuracy": 0.15836117267608643,
|
|
"num_tokens": 8156879.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.8064148902893065,
|
|
"epoch": 0.3664656681579459,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990613425543423,
|
|
"loss": 5.5678,
|
|
"mean_token_accuracy": 0.15500140488147734,
|
|
"num_tokens": 8164860.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.691606712341309,
|
|
"epoch": 0.3668546975296635,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004990588118594487,
|
|
"loss": 5.4042,
|
|
"mean_token_accuracy": 0.1723329722881317,
|
|
"num_tokens": 8173319.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.727795028686524,
|
|
"epoch": 0.3672437269013811,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990562777648194,
|
|
"loss": 5.6093,
|
|
"mean_token_accuracy": 0.16026716232299804,
|
|
"num_tokens": 8182385.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.8143706798553465,
|
|
"epoch": 0.3676327562730986,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004990537402704928,
|
|
"loss": 5.5297,
|
|
"mean_token_accuracy": 0.16515245139598847,
|
|
"num_tokens": 8190394.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.759135580062866,
|
|
"epoch": 0.3680217856448162,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004990511993765071,
|
|
"loss": 5.5424,
|
|
"mean_token_accuracy": 0.15767809599637986,
|
|
"num_tokens": 8198532.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.628855466842651,
|
|
"epoch": 0.3684108150165337,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004990486550829011,
|
|
"loss": 5.4953,
|
|
"mean_token_accuracy": 0.168289515376091,
|
|
"num_tokens": 8207436.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.780854320526123,
|
|
"epoch": 0.3687998443882513,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004990461073897134,
|
|
"loss": 5.5408,
|
|
"mean_token_accuracy": 0.16624754965305327,
|
|
"num_tokens": 8216316.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.769868183135986,
|
|
"epoch": 0.3691888737599689,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990435562969827,
|
|
"loss": 5.4902,
|
|
"mean_token_accuracy": 0.1653371199965477,
|
|
"num_tokens": 8224918.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.69854769706726,
|
|
"epoch": 0.3695779031316864,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990410018047475,
|
|
"loss": 5.5301,
|
|
"mean_token_accuracy": 0.1603669047355652,
|
|
"num_tokens": 8233506.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.743416881561279,
|
|
"epoch": 0.369966932503404,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990384439130467,
|
|
"loss": 5.5692,
|
|
"mean_token_accuracy": 0.15842108130455018,
|
|
"num_tokens": 8243122.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.7349554061889645,
|
|
"epoch": 0.3703559618751216,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990358826219192,
|
|
"loss": 5.5439,
|
|
"mean_token_accuracy": 0.16526512950658798,
|
|
"num_tokens": 8251639.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.757761478424072,
|
|
"epoch": 0.37074499124683913,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990333179314038,
|
|
"loss": 5.5815,
|
|
"mean_token_accuracy": 0.1549780011177063,
|
|
"num_tokens": 8260487.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.771208095550537,
|
|
"epoch": 0.3711340206185567,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990307498415393,
|
|
"loss": 5.5617,
|
|
"mean_token_accuracy": 0.16446320563554764,
|
|
"num_tokens": 8270111.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.77273907661438,
|
|
"epoch": 0.37152304999027425,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990281783523648,
|
|
"loss": 5.6953,
|
|
"mean_token_accuracy": 0.15468359738588333,
|
|
"num_tokens": 8278171.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.764896488189697,
|
|
"epoch": 0.37191207936199183,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004990256034639192,
|
|
"loss": 5.5751,
|
|
"mean_token_accuracy": 0.1614871248602867,
|
|
"num_tokens": 8287278.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.859795999526978,
|
|
"epoch": 0.3723011087337094,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990230251762418,
|
|
"loss": 5.6972,
|
|
"mean_token_accuracy": 0.15220141559839248,
|
|
"num_tokens": 8296874.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.758879995346069,
|
|
"epoch": 0.37269013810542695,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004990204434893713,
|
|
"loss": 5.5568,
|
|
"mean_token_accuracy": 0.15907381623983383,
|
|
"num_tokens": 8305375.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.848282766342163,
|
|
"epoch": 0.37307916747714454,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990178584033474,
|
|
"loss": 5.6089,
|
|
"mean_token_accuracy": 0.15528460443019867,
|
|
"num_tokens": 8313960.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.78062481880188,
|
|
"epoch": 0.37346819684886207,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004990152699182089,
|
|
"loss": 5.5427,
|
|
"mean_token_accuracy": 0.16759291887283326,
|
|
"num_tokens": 8321838.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.700754165649414,
|
|
"epoch": 0.37385722622057965,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004990126780339953,
|
|
"loss": 5.5691,
|
|
"mean_token_accuracy": 0.15406242609024048,
|
|
"num_tokens": 8331325.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.801051759719849,
|
|
"epoch": 0.37424625559229724,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990100827507459,
|
|
"loss": 5.6369,
|
|
"mean_token_accuracy": 0.15624383836984634,
|
|
"num_tokens": 8340105.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.731446266174316,
|
|
"epoch": 0.37463528496401477,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004990074840684999,
|
|
"loss": 5.4545,
|
|
"mean_token_accuracy": 0.17317897975444793,
|
|
"num_tokens": 8348256.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.711327409744262,
|
|
"epoch": 0.37502431433573236,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004990048819872969,
|
|
"loss": 5.6361,
|
|
"mean_token_accuracy": 0.1525025933980942,
|
|
"num_tokens": 8357456.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.789103603363037,
|
|
"epoch": 0.3754133437074499,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004990022765071765,
|
|
"loss": 5.4928,
|
|
"mean_token_accuracy": 0.16532201766967775,
|
|
"num_tokens": 8366939.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.888441324234009,
|
|
"epoch": 0.3758023730791675,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000498999667628178,
|
|
"loss": 5.6419,
|
|
"mean_token_accuracy": 0.1552483007311821,
|
|
"num_tokens": 8376062.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.809573221206665,
|
|
"epoch": 0.37619140245088506,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989970553503411,
|
|
"loss": 5.5562,
|
|
"mean_token_accuracy": 0.16382697820663453,
|
|
"num_tokens": 8383803.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.732746553421021,
|
|
"epoch": 0.3765804318226026,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989944396737054,
|
|
"loss": 5.7206,
|
|
"mean_token_accuracy": 0.15485890656709672,
|
|
"num_tokens": 8392844.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.8165699481964115,
|
|
"epoch": 0.3769694611943202,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989918205983106,
|
|
"loss": 5.6137,
|
|
"mean_token_accuracy": 0.16435452401638032,
|
|
"num_tokens": 8401937.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.821778202056885,
|
|
"epoch": 0.37735849056603776,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989891981241964,
|
|
"loss": 5.6275,
|
|
"mean_token_accuracy": 0.15439676195383073,
|
|
"num_tokens": 8410383.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.701949501037598,
|
|
"epoch": 0.3777475199377553,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004989865722514027,
|
|
"loss": 5.5827,
|
|
"mean_token_accuracy": 0.16015864312648773,
|
|
"num_tokens": 8419053.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.770675277709961,
|
|
"epoch": 0.3781365493094729,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004989839429799692,
|
|
"loss": 5.555,
|
|
"mean_token_accuracy": 0.16515738219022752,
|
|
"num_tokens": 8427311.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.7758008480072025,
|
|
"epoch": 0.3785255786811904,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000498981310309936,
|
|
"loss": 5.6006,
|
|
"mean_token_accuracy": 0.16151956021785735,
|
|
"num_tokens": 8436050.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.834692144393921,
|
|
"epoch": 0.378914608052908,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989786742413428,
|
|
"loss": 5.5515,
|
|
"mean_token_accuracy": 0.16113933473825454,
|
|
"num_tokens": 8444579.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.714345455169678,
|
|
"epoch": 0.3793036374246256,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004989760347742298,
|
|
"loss": 5.5676,
|
|
"mean_token_accuracy": 0.16167921125888823,
|
|
"num_tokens": 8454013.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.793581581115722,
|
|
"epoch": 0.3796926667963431,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004989733919086369,
|
|
"loss": 5.6778,
|
|
"mean_token_accuracy": 0.1574169933795929,
|
|
"num_tokens": 8462564.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.823560762405395,
|
|
"epoch": 0.3800816961680607,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004989707456446043,
|
|
"loss": 5.5164,
|
|
"mean_token_accuracy": 0.16610173135995865,
|
|
"num_tokens": 8471035.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.75401349067688,
|
|
"epoch": 0.38047072553977823,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004989680959821721,
|
|
"loss": 5.5071,
|
|
"mean_token_accuracy": 0.16652308106422425,
|
|
"num_tokens": 8479475.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.688182020187378,
|
|
"epoch": 0.3808597549114958,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004989654429213805,
|
|
"loss": 5.5743,
|
|
"mean_token_accuracy": 0.16116372048854827,
|
|
"num_tokens": 8488163.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.868498039245606,
|
|
"epoch": 0.3812487842832134,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004989627864622699,
|
|
"loss": 5.6339,
|
|
"mean_token_accuracy": 0.15791766941547394,
|
|
"num_tokens": 8497735.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.785080194473267,
|
|
"epoch": 0.38163781365493094,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004989601266048804,
|
|
"loss": 5.5745,
|
|
"mean_token_accuracy": 0.15418473482131959,
|
|
"num_tokens": 8506986.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.738870763778687,
|
|
"epoch": 0.3820268430266485,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004989574633492525,
|
|
"loss": 5.6057,
|
|
"mean_token_accuracy": 0.16127151846885682,
|
|
"num_tokens": 8515168.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.783707952499389,
|
|
"epoch": 0.38241587239836605,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004989547966954266,
|
|
"loss": 5.5922,
|
|
"mean_token_accuracy": 0.16000263020396233,
|
|
"num_tokens": 8523980.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.6956686019897464,
|
|
"epoch": 0.38280490177008364,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000498952126643443,
|
|
"loss": 5.5306,
|
|
"mean_token_accuracy": 0.1625279650092125,
|
|
"num_tokens": 8532938.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.7227997303009035,
|
|
"epoch": 0.3831939311418012,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004989494531933424,
|
|
"loss": 5.5089,
|
|
"mean_token_accuracy": 0.16532202064990997,
|
|
"num_tokens": 8541951.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.820029211044312,
|
|
"epoch": 0.38358296051351876,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004989467763451652,
|
|
"loss": 5.6715,
|
|
"mean_token_accuracy": 0.1566024363040924,
|
|
"num_tokens": 8550981.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.753549671173095,
|
|
"epoch": 0.38397198988523634,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004989440960989523,
|
|
"loss": 5.5932,
|
|
"mean_token_accuracy": 0.1530495285987854,
|
|
"num_tokens": 8559711.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.726752090454101,
|
|
"epoch": 0.3843610192569539,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000498941412454744,
|
|
"loss": 5.5194,
|
|
"mean_token_accuracy": 0.15732942000031472,
|
|
"num_tokens": 8567797.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.742764091491699,
|
|
"epoch": 0.38475004862867146,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004989387254125813,
|
|
"loss": 5.6155,
|
|
"mean_token_accuracy": 0.15704205930233,
|
|
"num_tokens": 8576719.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.787147092819214,
|
|
"epoch": 0.38513907800038905,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004989360349725049,
|
|
"loss": 5.6063,
|
|
"mean_token_accuracy": 0.16519807428121566,
|
|
"num_tokens": 8585871.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.770403671264648,
|
|
"epoch": 0.3855281073721066,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989333411345555,
|
|
"loss": 5.5042,
|
|
"mean_token_accuracy": 0.16043488979339598,
|
|
"num_tokens": 8594018.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.7103471755981445,
|
|
"epoch": 0.38591713674382416,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989306438987742,
|
|
"loss": 5.6376,
|
|
"mean_token_accuracy": 0.15529824048280716,
|
|
"num_tokens": 8602788.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.816785144805908,
|
|
"epoch": 0.38630616611554175,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004989279432652018,
|
|
"loss": 5.5795,
|
|
"mean_token_accuracy": 0.16424058228731156,
|
|
"num_tokens": 8611837.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.7558619499206545,
|
|
"epoch": 0.3866951954872593,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989252392338791,
|
|
"loss": 5.5542,
|
|
"mean_token_accuracy": 0.16635178476572038,
|
|
"num_tokens": 8620114.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.8515918254852295,
|
|
"epoch": 0.38708422485897687,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004989225318048475,
|
|
"loss": 5.6735,
|
|
"mean_token_accuracy": 0.15313750207424165,
|
|
"num_tokens": 8628777.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.812920141220093,
|
|
"epoch": 0.3874732542306944,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004989198209781478,
|
|
"loss": 5.5769,
|
|
"mean_token_accuracy": 0.15885705202817918,
|
|
"num_tokens": 8637088.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.802033758163452,
|
|
"epoch": 0.387862283602412,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989171067538211,
|
|
"loss": 5.5898,
|
|
"mean_token_accuracy": 0.16069801449775695,
|
|
"num_tokens": 8645261.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.761074066162109,
|
|
"epoch": 0.38825131297412957,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000498914389131909,
|
|
"loss": 5.5961,
|
|
"mean_token_accuracy": 0.16617487221956254,
|
|
"num_tokens": 8653492.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.704293870925904,
|
|
"epoch": 0.3886403423458471,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989116681124523,
|
|
"loss": 5.5388,
|
|
"mean_token_accuracy": 0.1667382687330246,
|
|
"num_tokens": 8661909.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.7351975440979,
|
|
"epoch": 0.3890293717175647,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004989089436954924,
|
|
"loss": 5.5202,
|
|
"mean_token_accuracy": 0.16341256201267243,
|
|
"num_tokens": 8670332.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.7855016708374025,
|
|
"epoch": 0.3894184010892822,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004989062158810706,
|
|
"loss": 5.5536,
|
|
"mean_token_accuracy": 0.16609135121107102,
|
|
"num_tokens": 8678537.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.754712152481079,
|
|
"epoch": 0.3898074304609998,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004989034846692284,
|
|
"loss": 5.5204,
|
|
"mean_token_accuracy": 0.16194988489151002,
|
|
"num_tokens": 8686839.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.751804971694947,
|
|
"epoch": 0.3901964598327174,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004989007500600073,
|
|
"loss": 5.5653,
|
|
"mean_token_accuracy": 0.16205074191093444,
|
|
"num_tokens": 8694407.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.7259783267974855,
|
|
"epoch": 0.3905854892044349,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004988980120534486,
|
|
"loss": 5.5474,
|
|
"mean_token_accuracy": 0.16532619595527648,
|
|
"num_tokens": 8703484.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.849454307556153,
|
|
"epoch": 0.3909745185761525,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000498895270649594,
|
|
"loss": 5.6414,
|
|
"mean_token_accuracy": 0.1563284620642662,
|
|
"num_tokens": 8712634.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.723186922073364,
|
|
"epoch": 0.39136354794787004,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000498892525848485,
|
|
"loss": 5.511,
|
|
"mean_token_accuracy": 0.16109795421361922,
|
|
"num_tokens": 8721229.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.738790845870971,
|
|
"epoch": 0.3917525773195876,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004988897776501633,
|
|
"loss": 5.5689,
|
|
"mean_token_accuracy": 0.1591969385743141,
|
|
"num_tokens": 8730010.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.693630981445312,
|
|
"epoch": 0.3921416066913052,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004988870260546705,
|
|
"loss": 5.5627,
|
|
"mean_token_accuracy": 0.15526820123195648,
|
|
"num_tokens": 8739046.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.772187757492065,
|
|
"epoch": 0.39253063606302274,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004988842710620486,
|
|
"loss": 5.6578,
|
|
"mean_token_accuracy": 0.16027751863002776,
|
|
"num_tokens": 8747650.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.765837001800537,
|
|
"epoch": 0.39291966543474033,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004988815126723391,
|
|
"loss": 5.5568,
|
|
"mean_token_accuracy": 0.15973474085330963,
|
|
"num_tokens": 8756319.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.666419649124146,
|
|
"epoch": 0.3933086948064579,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004988787508855841,
|
|
"loss": 5.5966,
|
|
"mean_token_accuracy": 0.15986263900995254,
|
|
"num_tokens": 8765448.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.743461608886719,
|
|
"epoch": 0.39369772417817545,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004988759857018253,
|
|
"loss": 5.5435,
|
|
"mean_token_accuracy": 0.1569396510720253,
|
|
"num_tokens": 8774146.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.681514263153076,
|
|
"epoch": 0.39408675354989303,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004988732171211048,
|
|
"loss": 5.4283,
|
|
"mean_token_accuracy": 0.16696038842201233,
|
|
"num_tokens": 8782311.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.661603260040283,
|
|
"epoch": 0.39447578292161056,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004988704451434644,
|
|
"loss": 5.4571,
|
|
"mean_token_accuracy": 0.16644057780504226,
|
|
"num_tokens": 8790196.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.73674054145813,
|
|
"epoch": 0.39486481229332815,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988676697689465,
|
|
"loss": 5.5391,
|
|
"mean_token_accuracy": 0.16053062975406646,
|
|
"num_tokens": 8798836.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.671565914154053,
|
|
"epoch": 0.39525384166504574,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000498864890997593,
|
|
"loss": 5.5662,
|
|
"mean_token_accuracy": 0.16028236746788024,
|
|
"num_tokens": 8806942.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.820256471633911,
|
|
"epoch": 0.39564287103676327,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004988621088294461,
|
|
"loss": 5.767,
|
|
"mean_token_accuracy": 0.1528549611568451,
|
|
"num_tokens": 8816354.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.827496862411499,
|
|
"epoch": 0.39603190040848085,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000498859323264548,
|
|
"loss": 5.5447,
|
|
"mean_token_accuracy": 0.1612401783466339,
|
|
"num_tokens": 8824802.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.719425773620605,
|
|
"epoch": 0.3964209297801984,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000498856534302941,
|
|
"loss": 5.5136,
|
|
"mean_token_accuracy": 0.16859235763549804,
|
|
"num_tokens": 8833348.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.708423900604248,
|
|
"epoch": 0.39680995915191597,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004988537419446673,
|
|
"loss": 5.5229,
|
|
"mean_token_accuracy": 0.16232937723398208,
|
|
"num_tokens": 8841131.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.681782531738281,
|
|
"epoch": 0.39719898852363356,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004988509461897694,
|
|
"loss": 5.5274,
|
|
"mean_token_accuracy": 0.16558895707130433,
|
|
"num_tokens": 8849768.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.772430324554444,
|
|
"epoch": 0.3975880178953511,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988481470382897,
|
|
"loss": 5.4992,
|
|
"mean_token_accuracy": 0.1691967472434044,
|
|
"num_tokens": 8858170.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.7239025115966795,
|
|
"epoch": 0.3979770472670687,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004988453444902708,
|
|
"loss": 5.5276,
|
|
"mean_token_accuracy": 0.16111491322517396,
|
|
"num_tokens": 8866720.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.794546890258789,
|
|
"epoch": 0.3983660766387862,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004988425385457549,
|
|
"loss": 5.5474,
|
|
"mean_token_accuracy": 0.1671929106116295,
|
|
"num_tokens": 8875141.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.768686103820801,
|
|
"epoch": 0.3987551060105038,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004988397292047848,
|
|
"loss": 5.5472,
|
|
"mean_token_accuracy": 0.1745615229010582,
|
|
"num_tokens": 8884512.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.797606515884399,
|
|
"epoch": 0.3991441353822214,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004988369164674032,
|
|
"loss": 5.6336,
|
|
"mean_token_accuracy": 0.16130153685808182,
|
|
"num_tokens": 8893487.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.716752338409424,
|
|
"epoch": 0.3995331647539389,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004988341003336526,
|
|
"loss": 5.5614,
|
|
"mean_token_accuracy": 0.16188647747039794,
|
|
"num_tokens": 8902909.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.747018575668335,
|
|
"epoch": 0.3999221941256565,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004988312808035757,
|
|
"loss": 5.4841,
|
|
"mean_token_accuracy": 0.16728559285402297,
|
|
"num_tokens": 8911311.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.66242356300354,
|
|
"epoch": 0.400311223497374,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004988284578772155,
|
|
"loss": 5.5035,
|
|
"mean_token_accuracy": 0.1671609714627266,
|
|
"num_tokens": 8920222.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.690232276916504,
|
|
"epoch": 0.4007002528690916,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004988256315546146,
|
|
"loss": 5.5598,
|
|
"mean_token_accuracy": 0.15787924081087112,
|
|
"num_tokens": 8928763.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.861962509155274,
|
|
"epoch": 0.4010892822408092,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004988228018358161,
|
|
"loss": 5.6159,
|
|
"mean_token_accuracy": 0.1600317895412445,
|
|
"num_tokens": 8937832.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.710369491577149,
|
|
"epoch": 0.40147831161252673,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004988199687208628,
|
|
"loss": 5.4634,
|
|
"mean_token_accuracy": 0.1653993993997574,
|
|
"num_tokens": 8945662.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.673874187469482,
|
|
"epoch": 0.4018673409842443,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004988171322097977,
|
|
"loss": 5.5616,
|
|
"mean_token_accuracy": 0.15639848113059998,
|
|
"num_tokens": 8954570.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.782657146453857,
|
|
"epoch": 0.4022563703559619,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004988142923026638,
|
|
"loss": 5.5409,
|
|
"mean_token_accuracy": 0.16113771945238115,
|
|
"num_tokens": 8962827.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.779515027999878,
|
|
"epoch": 0.40264539972767943,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004988114489995044,
|
|
"loss": 5.573,
|
|
"mean_token_accuracy": 0.1641353115439415,
|
|
"num_tokens": 8972119.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.71273512840271,
|
|
"epoch": 0.403034429099397,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004988086023003624,
|
|
"loss": 5.4792,
|
|
"mean_token_accuracy": 0.16348525732755662,
|
|
"num_tokens": 8980498.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.760009813308716,
|
|
"epoch": 0.40342345847111455,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004988057522052811,
|
|
"loss": 5.6342,
|
|
"mean_token_accuracy": 0.1559661880135536,
|
|
"num_tokens": 8989819.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.809510660171509,
|
|
"epoch": 0.40381248784283214,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004988028987143037,
|
|
"loss": 5.6752,
|
|
"mean_token_accuracy": 0.15571251288056373,
|
|
"num_tokens": 8998884.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.758668708801269,
|
|
"epoch": 0.4042015172145497,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004988000418274736,
|
|
"loss": 5.5387,
|
|
"mean_token_accuracy": 0.16518065482378005,
|
|
"num_tokens": 9007806.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.784484100341797,
|
|
"epoch": 0.40459054658626725,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004987971815448341,
|
|
"loss": 5.6966,
|
|
"mean_token_accuracy": 0.15061777085065842,
|
|
"num_tokens": 9016541.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.721669101715088,
|
|
"epoch": 0.40497957595798484,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004987943178664285,
|
|
"loss": 5.4546,
|
|
"mean_token_accuracy": 0.16586214303970337,
|
|
"num_tokens": 9024503.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.782793283462524,
|
|
"epoch": 0.40536860532970237,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004987914507923004,
|
|
"loss": 5.5505,
|
|
"mean_token_accuracy": 0.16351571083068847,
|
|
"num_tokens": 9033182.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.703962326049805,
|
|
"epoch": 0.40575763470141996,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004987885803224931,
|
|
"loss": 5.5698,
|
|
"mean_token_accuracy": 0.1618541419506073,
|
|
"num_tokens": 9042281.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.786581754684448,
|
|
"epoch": 0.40614666407313754,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004987857064570505,
|
|
"loss": 5.4916,
|
|
"mean_token_accuracy": 0.16629716008901596,
|
|
"num_tokens": 9050570.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.802667093276978,
|
|
"epoch": 0.4065356934448551,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004987828291960158,
|
|
"loss": 5.6534,
|
|
"mean_token_accuracy": 0.15524297803640366,
|
|
"num_tokens": 9059782.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.689572381973266,
|
|
"epoch": 0.40692472281657266,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000498779948539433,
|
|
"loss": 5.4,
|
|
"mean_token_accuracy": 0.17254798114299774,
|
|
"num_tokens": 9067484.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.732696390151977,
|
|
"epoch": 0.4073137521882902,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004987770644873455,
|
|
"loss": 5.6196,
|
|
"mean_token_accuracy": 0.16232876777648925,
|
|
"num_tokens": 9075740.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.819503831863403,
|
|
"epoch": 0.4077027815600078,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004987741770397974,
|
|
"loss": 5.6565,
|
|
"mean_token_accuracy": 0.1580768421292305,
|
|
"num_tokens": 9084137.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.7091607570648195,
|
|
"epoch": 0.40809181093172536,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004987712861968323,
|
|
"loss": 5.4425,
|
|
"mean_token_accuracy": 0.16982385367155076,
|
|
"num_tokens": 9093245.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.642366218566894,
|
|
"epoch": 0.4084808403034429,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000498768391958494,
|
|
"loss": 5.4436,
|
|
"mean_token_accuracy": 0.17219747751951217,
|
|
"num_tokens": 9102837.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.715507888793946,
|
|
"epoch": 0.4088698696751605,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004987654943248266,
|
|
"loss": 5.5094,
|
|
"mean_token_accuracy": 0.1671164534986019,
|
|
"num_tokens": 9111087.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.715580224990845,
|
|
"epoch": 0.40925889904687807,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004987625932958739,
|
|
"loss": 5.5389,
|
|
"mean_token_accuracy": 0.17025153189897538,
|
|
"num_tokens": 9120506.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.793882369995117,
|
|
"epoch": 0.4096479284185956,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004987596888716801,
|
|
"loss": 5.7239,
|
|
"mean_token_accuracy": 0.15377746447920798,
|
|
"num_tokens": 9129637.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.832787895202637,
|
|
"epoch": 0.4100369577903132,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004987567810522892,
|
|
"loss": 5.5138,
|
|
"mean_token_accuracy": 0.16298867911100387,
|
|
"num_tokens": 9139338.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.704374980926514,
|
|
"epoch": 0.4104259871620307,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004987538698377451,
|
|
"loss": 5.549,
|
|
"mean_token_accuracy": 0.1638969212770462,
|
|
"num_tokens": 9148034.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.7266558647155765,
|
|
"epoch": 0.4108150165337483,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004987509552280924,
|
|
"loss": 5.4992,
|
|
"mean_token_accuracy": 0.16262540221214294,
|
|
"num_tokens": 9156744.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.6911859035491945,
|
|
"epoch": 0.4112040459054659,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000498748037223375,
|
|
"loss": 5.4738,
|
|
"mean_token_accuracy": 0.16808437556028366,
|
|
"num_tokens": 9165174.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.6812522411346436,
|
|
"epoch": 0.4115930752771834,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004987451158236372,
|
|
"loss": 5.4909,
|
|
"mean_token_accuracy": 0.16852608770132066,
|
|
"num_tokens": 9173945.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.762362098693847,
|
|
"epoch": 0.411982104648901,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004987421910289234,
|
|
"loss": 5.4926,
|
|
"mean_token_accuracy": 0.16189738661050795,
|
|
"num_tokens": 9182728.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.668687152862549,
|
|
"epoch": 0.41237113402061853,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004987392628392781,
|
|
"loss": 5.5228,
|
|
"mean_token_accuracy": 0.1617294430732727,
|
|
"num_tokens": 9191494.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.738568305969238,
|
|
"epoch": 0.4127601633923361,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004987363312547456,
|
|
"loss": 5.5492,
|
|
"mean_token_accuracy": 0.16261912733316422,
|
|
"num_tokens": 9199190.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.695952987670898,
|
|
"epoch": 0.4131491927640537,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004987333962753703,
|
|
"loss": 5.4777,
|
|
"mean_token_accuracy": 0.1633556604385376,
|
|
"num_tokens": 9208066.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.736075210571289,
|
|
"epoch": 0.41353822213577124,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004987304579011967,
|
|
"loss": 5.4827,
|
|
"mean_token_accuracy": 0.1680247128009796,
|
|
"num_tokens": 9217103.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.719621896743774,
|
|
"epoch": 0.4139272515074888,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004987275161322697,
|
|
"loss": 5.5188,
|
|
"mean_token_accuracy": 0.15984098762273788,
|
|
"num_tokens": 9225786.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.776179695129395,
|
|
"epoch": 0.41431628087920636,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004987245709686337,
|
|
"loss": 5.5301,
|
|
"mean_token_accuracy": 0.16916029453277587,
|
|
"num_tokens": 9234182.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.741197729110718,
|
|
"epoch": 0.41470531025092394,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004987216224103334,
|
|
"loss": 5.5122,
|
|
"mean_token_accuracy": 0.1564493805170059,
|
|
"num_tokens": 9243844.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.711385488510132,
|
|
"epoch": 0.41509433962264153,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004987186704574136,
|
|
"loss": 5.5045,
|
|
"mean_token_accuracy": 0.16829753071069717,
|
|
"num_tokens": 9252901.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.6386919021606445,
|
|
"epoch": 0.41548336899435906,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004987157151099189,
|
|
"loss": 5.4921,
|
|
"mean_token_accuracy": 0.16120805144309996,
|
|
"num_tokens": 9260947.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.762169742584229,
|
|
"epoch": 0.41587239836607665,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004987127563678945,
|
|
"loss": 5.5373,
|
|
"mean_token_accuracy": 0.1641700491309166,
|
|
"num_tokens": 9269249.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.715381860733032,
|
|
"epoch": 0.4162614277377942,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004987097942313852,
|
|
"loss": 5.5476,
|
|
"mean_token_accuracy": 0.16414593309164047,
|
|
"num_tokens": 9277668.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.705289697647094,
|
|
"epoch": 0.41665045710951176,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004987068287004355,
|
|
"loss": 5.5409,
|
|
"mean_token_accuracy": 0.15832844227552414,
|
|
"num_tokens": 9286000.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.742699480056762,
|
|
"epoch": 0.41703948648122935,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004987038597750909,
|
|
"loss": 5.5861,
|
|
"mean_token_accuracy": 0.15789835453033446,
|
|
"num_tokens": 9295090.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.71341724395752,
|
|
"epoch": 0.4174285158529469,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004987008874553964,
|
|
"loss": 5.5016,
|
|
"mean_token_accuracy": 0.16354818493127823,
|
|
"num_tokens": 9302996.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.683341407775879,
|
|
"epoch": 0.41781754522466447,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004986979117413969,
|
|
"loss": 5.4018,
|
|
"mean_token_accuracy": 0.17096701115369797,
|
|
"num_tokens": 9311636.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.694851970672607,
|
|
"epoch": 0.41820657459638205,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004986949326331376,
|
|
"loss": 5.5059,
|
|
"mean_token_accuracy": 0.16198326498270035,
|
|
"num_tokens": 9319884.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.613385772705078,
|
|
"epoch": 0.4185956039680996,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004986919501306638,
|
|
"loss": 5.4534,
|
|
"mean_token_accuracy": 0.16765042394399643,
|
|
"num_tokens": 9328273.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.693991851806641,
|
|
"epoch": 0.41898463333981717,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004986889642340207,
|
|
"loss": 5.5737,
|
|
"mean_token_accuracy": 0.156100807338953,
|
|
"num_tokens": 9337696.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.75873703956604,
|
|
"epoch": 0.4193736627115347,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004986859749432536,
|
|
"loss": 5.5447,
|
|
"mean_token_accuracy": 0.16316066682338715,
|
|
"num_tokens": 9346596.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.716987037658692,
|
|
"epoch": 0.4197626920832523,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004986829822584078,
|
|
"loss": 5.4887,
|
|
"mean_token_accuracy": 0.16210612803697586,
|
|
"num_tokens": 9355480.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.712895011901855,
|
|
"epoch": 0.4201517214549699,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004986799861795289,
|
|
"loss": 5.5305,
|
|
"mean_token_accuracy": 0.16527193188667297,
|
|
"num_tokens": 9364422.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.707545804977417,
|
|
"epoch": 0.4205407508266874,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004986769867066622,
|
|
"loss": 5.4093,
|
|
"mean_token_accuracy": 0.16503172516822814,
|
|
"num_tokens": 9372311.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.682763624191284,
|
|
"epoch": 0.420929780198405,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004986739838398532,
|
|
"loss": 5.5495,
|
|
"mean_token_accuracy": 0.16107411831617355,
|
|
"num_tokens": 9380936.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.683968544006348,
|
|
"epoch": 0.4213188095701225,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004986709775791475,
|
|
"loss": 5.4955,
|
|
"mean_token_accuracy": 0.16949945986270903,
|
|
"num_tokens": 9390008.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.732982110977173,
|
|
"epoch": 0.4217078389418401,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004986679679245907,
|
|
"loss": 5.5721,
|
|
"mean_token_accuracy": 0.16321041733026503,
|
|
"num_tokens": 9398771.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.714467477798462,
|
|
"epoch": 0.4220968683135577,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004986649548762286,
|
|
"loss": 5.5652,
|
|
"mean_token_accuracy": 0.16471161246299743,
|
|
"num_tokens": 9407105.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.720512437820434,
|
|
"epoch": 0.4224858976852752,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004986619384341066,
|
|
"loss": 5.5494,
|
|
"mean_token_accuracy": 0.1671588495373726,
|
|
"num_tokens": 9415737.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.714883708953858,
|
|
"epoch": 0.4228749270569928,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004986589185982708,
|
|
"loss": 5.4964,
|
|
"mean_token_accuracy": 0.16671057492494584,
|
|
"num_tokens": 9424661.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.779036808013916,
|
|
"epoch": 0.42326395642871034,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986558953687671,
|
|
"loss": 5.5689,
|
|
"mean_token_accuracy": 0.1595238134264946,
|
|
"num_tokens": 9433971.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.658939170837402,
|
|
"epoch": 0.42365298580042793,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004986528687456409,
|
|
"loss": 5.5041,
|
|
"mean_token_accuracy": 0.16503361463546753,
|
|
"num_tokens": 9442905.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.674489879608155,
|
|
"epoch": 0.4240420151721455,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004986498387289384,
|
|
"loss": 5.5473,
|
|
"mean_token_accuracy": 0.16705762594938278,
|
|
"num_tokens": 9451258.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.713934373855591,
|
|
"epoch": 0.42443104454386305,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004986468053187058,
|
|
"loss": 5.4969,
|
|
"mean_token_accuracy": 0.16497478485107422,
|
|
"num_tokens": 9460218.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.71204571723938,
|
|
"epoch": 0.42482007391558063,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004986437685149887,
|
|
"loss": 5.5445,
|
|
"mean_token_accuracy": 0.1658524125814438,
|
|
"num_tokens": 9468756.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.725471305847168,
|
|
"epoch": 0.4252091032872982,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004986407283178334,
|
|
"loss": 5.5697,
|
|
"mean_token_accuracy": 0.165852914750576,
|
|
"num_tokens": 9477622.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.699073648452758,
|
|
"epoch": 0.42559813265901575,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004986376847272861,
|
|
"loss": 5.4257,
|
|
"mean_token_accuracy": 0.17033136934041976,
|
|
"num_tokens": 9486332.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.698595094680786,
|
|
"epoch": 0.42598716203073334,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004986346377433929,
|
|
"loss": 5.4375,
|
|
"mean_token_accuracy": 0.17676602452993392,
|
|
"num_tokens": 9494703.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.678912258148193,
|
|
"epoch": 0.42637619140245087,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004986315873661999,
|
|
"loss": 5.3919,
|
|
"mean_token_accuracy": 0.1781506434082985,
|
|
"num_tokens": 9503008.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.712614440917969,
|
|
"epoch": 0.42676522077416845,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004986285335957536,
|
|
"loss": 5.5112,
|
|
"mean_token_accuracy": 0.16455856263637542,
|
|
"num_tokens": 9511752.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.661769199371338,
|
|
"epoch": 0.42715425014588604,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004986254764321002,
|
|
"loss": 5.4136,
|
|
"mean_token_accuracy": 0.16830996423959732,
|
|
"num_tokens": 9520490.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.650809097290039,
|
|
"epoch": 0.42754327951760357,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004986224158752861,
|
|
"loss": 5.4747,
|
|
"mean_token_accuracy": 0.16516461968421936,
|
|
"num_tokens": 9528474.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.742059564590454,
|
|
"epoch": 0.42793230888932116,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004986193519253578,
|
|
"loss": 5.5615,
|
|
"mean_token_accuracy": 0.16216895580291749,
|
|
"num_tokens": 9537747.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.681634855270386,
|
|
"epoch": 0.4283213382610387,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004986162845823618,
|
|
"loss": 5.484,
|
|
"mean_token_accuracy": 0.160535629093647,
|
|
"num_tokens": 9546414.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.689042711257935,
|
|
"epoch": 0.4287103676327563,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004986132138463446,
|
|
"loss": 5.4927,
|
|
"mean_token_accuracy": 0.16490281671285628,
|
|
"num_tokens": 9555166.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.7525488376617435,
|
|
"epoch": 0.42909939700447386,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004986101397173528,
|
|
"loss": 5.5547,
|
|
"mean_token_accuracy": 0.1655886948108673,
|
|
"num_tokens": 9563217.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.717628622055054,
|
|
"epoch": 0.4294884263761914,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498607062195433,
|
|
"loss": 5.5997,
|
|
"mean_token_accuracy": 0.15301982015371324,
|
|
"num_tokens": 9572837.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.757178735733032,
|
|
"epoch": 0.429877455747909,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000498603981280632,
|
|
"loss": 5.4978,
|
|
"mean_token_accuracy": 0.16078530102968216,
|
|
"num_tokens": 9581297.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.6680278301239015,
|
|
"epoch": 0.4302664851196265,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004986008969729964,
|
|
"loss": 5.5719,
|
|
"mean_token_accuracy": 0.16208446323871611,
|
|
"num_tokens": 9590431.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.769735717773438,
|
|
"epoch": 0.4306555144913441,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004985978092725731,
|
|
"loss": 5.6239,
|
|
"mean_token_accuracy": 0.15763482004404067,
|
|
"num_tokens": 9598719.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.775566530227661,
|
|
"epoch": 0.4310445438630617,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498594718179409,
|
|
"loss": 5.6193,
|
|
"mean_token_accuracy": 0.16195805072784425,
|
|
"num_tokens": 9606935.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.778594875335694,
|
|
"epoch": 0.4314335732347792,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004985916236935508,
|
|
"loss": 5.5615,
|
|
"mean_token_accuracy": 0.16631187945604325,
|
|
"num_tokens": 9615104.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.863265514373779,
|
|
"epoch": 0.4318226026064968,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004985885258150458,
|
|
"loss": 5.5879,
|
|
"mean_token_accuracy": 0.15800173580646515,
|
|
"num_tokens": 9623332.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.610420417785645,
|
|
"epoch": 0.43221163197821433,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004985854245439408,
|
|
"loss": 5.4311,
|
|
"mean_token_accuracy": 0.1664763495326042,
|
|
"num_tokens": 9631874.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.634915590286255,
|
|
"epoch": 0.4326006613499319,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004985823198802827,
|
|
"loss": 5.4814,
|
|
"mean_token_accuracy": 0.16169906109571458,
|
|
"num_tokens": 9641150.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.643579006195068,
|
|
"epoch": 0.4329896907216495,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004985792118241188,
|
|
"loss": 5.3094,
|
|
"mean_token_accuracy": 0.17493287473917007,
|
|
"num_tokens": 9649116.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.688484382629395,
|
|
"epoch": 0.43337872009336703,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004985761003754961,
|
|
"loss": 5.5426,
|
|
"mean_token_accuracy": 0.16924417316913604,
|
|
"num_tokens": 9657579.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.6803422451019285,
|
|
"epoch": 0.4337677494650846,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004985729855344622,
|
|
"loss": 5.512,
|
|
"mean_token_accuracy": 0.16509860008955002,
|
|
"num_tokens": 9666242.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.7111921310424805,
|
|
"epoch": 0.4341567788368022,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000498569867301064,
|
|
"loss": 5.5006,
|
|
"mean_token_accuracy": 0.1659751445055008,
|
|
"num_tokens": 9675196.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.700456762313843,
|
|
"epoch": 0.43454580820851973,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004985667456753489,
|
|
"loss": 5.4593,
|
|
"mean_token_accuracy": 0.16661814898252486,
|
|
"num_tokens": 9683681.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.655364751815796,
|
|
"epoch": 0.4349348375802373,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004985636206573642,
|
|
"loss": 5.5346,
|
|
"mean_token_accuracy": 0.16666558384895325,
|
|
"num_tokens": 9692445.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.693232583999634,
|
|
"epoch": 0.43532386695195485,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004985604922471575,
|
|
"loss": 5.4283,
|
|
"mean_token_accuracy": 0.1684398427605629,
|
|
"num_tokens": 9701256.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.690249300003051,
|
|
"epoch": 0.43571289632367244,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004985573604447761,
|
|
"loss": 5.4647,
|
|
"mean_token_accuracy": 0.16726021617650985,
|
|
"num_tokens": 9710351.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.740422916412354,
|
|
"epoch": 0.43610192569539,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004985542252502676,
|
|
"loss": 5.5413,
|
|
"mean_token_accuracy": 0.15877096205949784,
|
|
"num_tokens": 9718795.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.731997489929199,
|
|
"epoch": 0.43649095506710756,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004985510866636796,
|
|
"loss": 5.4606,
|
|
"mean_token_accuracy": 0.16399804949760438,
|
|
"num_tokens": 9727136.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.632516717910766,
|
|
"epoch": 0.43687998443882514,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004985479446850596,
|
|
"loss": 5.4579,
|
|
"mean_token_accuracy": 0.17203980833292007,
|
|
"num_tokens": 9735712.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.69036169052124,
|
|
"epoch": 0.4372690138105427,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004985447993144554,
|
|
"loss": 5.4946,
|
|
"mean_token_accuracy": 0.16453454941511153,
|
|
"num_tokens": 9744027.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.790532541275025,
|
|
"epoch": 0.43765804318226026,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004985416505519147,
|
|
"loss": 5.6184,
|
|
"mean_token_accuracy": 0.1604256197810173,
|
|
"num_tokens": 9753083.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.778309011459351,
|
|
"epoch": 0.43804707255397785,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004985384983974853,
|
|
"loss": 5.551,
|
|
"mean_token_accuracy": 0.16635619699954987,
|
|
"num_tokens": 9762098.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.731233310699463,
|
|
"epoch": 0.4384361019256954,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004985353428512148,
|
|
"loss": 5.495,
|
|
"mean_token_accuracy": 0.16542133092880248,
|
|
"num_tokens": 9770956.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.656954526901245,
|
|
"epoch": 0.43882513129741296,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004985321839131514,
|
|
"loss": 5.4417,
|
|
"mean_token_accuracy": 0.17078006863594056,
|
|
"num_tokens": 9779427.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.718938112258911,
|
|
"epoch": 0.4392141606691305,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004985290215833428,
|
|
"loss": 5.5177,
|
|
"mean_token_accuracy": 0.17064714282751084,
|
|
"num_tokens": 9787655.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.691762399673462,
|
|
"epoch": 0.4396031900408481,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004985258558618372,
|
|
"loss": 5.4529,
|
|
"mean_token_accuracy": 0.17139697521924974,
|
|
"num_tokens": 9796850.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.693294715881348,
|
|
"epoch": 0.43999221941256567,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004985226867486825,
|
|
"loss": 5.5312,
|
|
"mean_token_accuracy": 0.1715284064412117,
|
|
"num_tokens": 9805317.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.686817598342896,
|
|
"epoch": 0.4403812487842832,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004985195142439267,
|
|
"loss": 5.4756,
|
|
"mean_token_accuracy": 0.1679181158542633,
|
|
"num_tokens": 9814249.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.72498722076416,
|
|
"epoch": 0.4407702781560008,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004985163383476181,
|
|
"loss": 5.567,
|
|
"mean_token_accuracy": 0.16245064735412598,
|
|
"num_tokens": 9823122.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.667973136901855,
|
|
"epoch": 0.44115930752771837,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004985131590598048,
|
|
"loss": 5.4305,
|
|
"mean_token_accuracy": 0.17121292799711227,
|
|
"num_tokens": 9831470.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.698353910446167,
|
|
"epoch": 0.4415483368994359,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004985099763805352,
|
|
"loss": 5.5381,
|
|
"mean_token_accuracy": 0.16199323832988738,
|
|
"num_tokens": 9840096.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.7460099220275875,
|
|
"epoch": 0.4419373662711535,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004985067903098574,
|
|
"loss": 5.4881,
|
|
"mean_token_accuracy": 0.16864942610263825,
|
|
"num_tokens": 9848595.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.675258588790894,
|
|
"epoch": 0.442326395642871,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004985036008478197,
|
|
"loss": 5.4416,
|
|
"mean_token_accuracy": 0.1585637226700783,
|
|
"num_tokens": 9857353.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.700889730453492,
|
|
"epoch": 0.4427154250145886,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004985004079944707,
|
|
"loss": 5.4832,
|
|
"mean_token_accuracy": 0.16071876734495164,
|
|
"num_tokens": 9865828.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.6535553455352785,
|
|
"epoch": 0.4431044543863062,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984972117498587,
|
|
"loss": 5.5072,
|
|
"mean_token_accuracy": 0.16214866042137147,
|
|
"num_tokens": 9874540.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.715157461166382,
|
|
"epoch": 0.4434934837580237,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004984940121140323,
|
|
"loss": 5.5008,
|
|
"mean_token_accuracy": 0.16645390838384627,
|
|
"num_tokens": 9883046.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.691306400299072,
|
|
"epoch": 0.4438825131297413,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00049849080908704,
|
|
"loss": 5.4468,
|
|
"mean_token_accuracy": 0.16432710587978364,
|
|
"num_tokens": 9892282.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.697309494018555,
|
|
"epoch": 0.44427154250145884,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984876026689302,
|
|
"loss": 5.3927,
|
|
"mean_token_accuracy": 0.17191525995731355,
|
|
"num_tokens": 9900653.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.603246593475342,
|
|
"epoch": 0.4446605718731764,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000498484392859752,
|
|
"loss": 5.4154,
|
|
"mean_token_accuracy": 0.17437574863433838,
|
|
"num_tokens": 9909323.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.6650214195251465,
|
|
"epoch": 0.445049601244894,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004984811796595538,
|
|
"loss": 5.5474,
|
|
"mean_token_accuracy": 0.1614001512527466,
|
|
"num_tokens": 9918155.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.8071013450622555,
|
|
"epoch": 0.44543863061661154,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004984779630683843,
|
|
"loss": 5.5043,
|
|
"mean_token_accuracy": 0.1654750481247902,
|
|
"num_tokens": 9925977.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.726596021652222,
|
|
"epoch": 0.44582765998832913,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004984747430862924,
|
|
"loss": 5.499,
|
|
"mean_token_accuracy": 0.16687430441379547,
|
|
"num_tokens": 9934606.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.6400782585144045,
|
|
"epoch": 0.44621668936004666,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004984715197133271,
|
|
"loss": 5.4576,
|
|
"mean_token_accuracy": 0.16767924875020981,
|
|
"num_tokens": 9943638.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.678442335128784,
|
|
"epoch": 0.44660571873176425,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004984682929495371,
|
|
"loss": 5.4881,
|
|
"mean_token_accuracy": 0.16466905921697617,
|
|
"num_tokens": 9952686.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.755481910705567,
|
|
"epoch": 0.44699474810348183,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004984650627949715,
|
|
"loss": 5.6655,
|
|
"mean_token_accuracy": 0.1529266878962517,
|
|
"num_tokens": 9961947.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.745148324966431,
|
|
"epoch": 0.44738377747519936,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004984618292496792,
|
|
"loss": 5.4931,
|
|
"mean_token_accuracy": 0.1682150661945343,
|
|
"num_tokens": 9971218.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.724733972549439,
|
|
"epoch": 0.44777280684691695,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004984585923137093,
|
|
"loss": 5.5207,
|
|
"mean_token_accuracy": 0.16295331418514253,
|
|
"num_tokens": 9980741.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.766764783859253,
|
|
"epoch": 0.4481618362186345,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000498455351987111,
|
|
"loss": 5.4972,
|
|
"mean_token_accuracy": 0.16979309171438217,
|
|
"num_tokens": 9989483.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.759484958648682,
|
|
"epoch": 0.44855086559035207,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004984521082699333,
|
|
"loss": 5.5286,
|
|
"mean_token_accuracy": 0.16119166612625122,
|
|
"num_tokens": 9998491.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.612123298645019,
|
|
"epoch": 0.44893989496206965,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004984488611622256,
|
|
"loss": 5.4047,
|
|
"mean_token_accuracy": 0.16882879436016082,
|
|
"num_tokens": 10006276.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.6463076114654545,
|
|
"epoch": 0.4493289243337872,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498445610664037,
|
|
"loss": 5.5013,
|
|
"mean_token_accuracy": 0.1660662427544594,
|
|
"num_tokens": 10015088.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.708720779418945,
|
|
"epoch": 0.44971795370550477,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000498442356775417,
|
|
"loss": 5.4594,
|
|
"mean_token_accuracy": 0.16434096843004226,
|
|
"num_tokens": 10023305.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.618870544433594,
|
|
"epoch": 0.45010698307722236,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004984390994964148,
|
|
"loss": 5.4102,
|
|
"mean_token_accuracy": 0.16594898849725723,
|
|
"num_tokens": 10031540.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.698048686981201,
|
|
"epoch": 0.4504960124489399,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00049843583882708,
|
|
"loss": 5.5067,
|
|
"mean_token_accuracy": 0.16628773510456085,
|
|
"num_tokens": 10040025.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.6761805534362795,
|
|
"epoch": 0.4508850418206575,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000498432574767462,
|
|
"loss": 5.5097,
|
|
"mean_token_accuracy": 0.16497354656457902,
|
|
"num_tokens": 10048904.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.717904853820801,
|
|
"epoch": 0.451274071192375,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004984293073176103,
|
|
"loss": 5.5377,
|
|
"mean_token_accuracy": 0.16159916371107103,
|
|
"num_tokens": 10057608.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.765069532394409,
|
|
"epoch": 0.4516631005640926,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004984260364775744,
|
|
"loss": 5.5017,
|
|
"mean_token_accuracy": 0.16796645820140838,
|
|
"num_tokens": 10066587.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.649991655349732,
|
|
"epoch": 0.4520521299358102,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000498422762247404,
|
|
"loss": 5.4605,
|
|
"mean_token_accuracy": 0.16765116751194,
|
|
"num_tokens": 10075651.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.7269245147705075,
|
|
"epoch": 0.4524411593075277,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004984194846271489,
|
|
"loss": 5.5845,
|
|
"mean_token_accuracy": 0.16291481852531434,
|
|
"num_tokens": 10084158.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.764606714248657,
|
|
"epoch": 0.4528301886792453,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004984162036168586,
|
|
"loss": 5.5048,
|
|
"mean_token_accuracy": 0.1609376475214958,
|
|
"num_tokens": 10093730.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.68165225982666,
|
|
"epoch": 0.4532192180509628,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004984129192165831,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.16802225708961488,
|
|
"num_tokens": 10102457.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.7178566455841064,
|
|
"epoch": 0.4536082474226804,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004984096314263722,
|
|
"loss": 5.5686,
|
|
"mean_token_accuracy": 0.16633791327476502,
|
|
"num_tokens": 10111188.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.749548244476318,
|
|
"epoch": 0.453997276794398,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004984063402462757,
|
|
"loss": 5.469,
|
|
"mean_token_accuracy": 0.16972580403089524,
|
|
"num_tokens": 10120268.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.682277536392212,
|
|
"epoch": 0.45438630616611553,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004984030456763435,
|
|
"loss": 5.5352,
|
|
"mean_token_accuracy": 0.15636064410209655,
|
|
"num_tokens": 10129262.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.6706867694854735,
|
|
"epoch": 0.4547753355378331,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004983997477166257,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.16850547045469283,
|
|
"num_tokens": 10137417.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.656628227233886,
|
|
"epoch": 0.45516436490955064,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004983964463671723,
|
|
"loss": 5.4197,
|
|
"mean_token_accuracy": 0.17263764292001724,
|
|
"num_tokens": 10145804.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.696662950515747,
|
|
"epoch": 0.45555339428126823,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004983931416280334,
|
|
"loss": 5.5474,
|
|
"mean_token_accuracy": 0.16169732064008713,
|
|
"num_tokens": 10154421.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.808199453353882,
|
|
"epoch": 0.4559424236529858,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004983898334992591,
|
|
"loss": 5.564,
|
|
"mean_token_accuracy": 0.16418157368898392,
|
|
"num_tokens": 10163631.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.702952098846436,
|
|
"epoch": 0.45633145302470335,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004983865219808998,
|
|
"loss": 5.479,
|
|
"mean_token_accuracy": 0.17148095816373826,
|
|
"num_tokens": 10172926.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.717158079147339,
|
|
"epoch": 0.45672048239642093,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004983832070730055,
|
|
"loss": 5.5916,
|
|
"mean_token_accuracy": 0.15716312527656556,
|
|
"num_tokens": 10181671.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.646397733688355,
|
|
"epoch": 0.4571095117681385,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004983798887756265,
|
|
"loss": 5.4077,
|
|
"mean_token_accuracy": 0.17208849787712097,
|
|
"num_tokens": 10189626.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.74006757736206,
|
|
"epoch": 0.45749854113985605,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004983765670888133,
|
|
"loss": 5.5492,
|
|
"mean_token_accuracy": 0.16686739027500153,
|
|
"num_tokens": 10198212.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.646033382415771,
|
|
"epoch": 0.45788757051157364,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004983732420126163,
|
|
"loss": 5.4416,
|
|
"mean_token_accuracy": 0.1704038918018341,
|
|
"num_tokens": 10207342.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.748333358764649,
|
|
"epoch": 0.45827659988329117,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004983699135470858,
|
|
"loss": 5.5571,
|
|
"mean_token_accuracy": 0.1590263545513153,
|
|
"num_tokens": 10216413.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.726169633865356,
|
|
"epoch": 0.45866562925500876,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004983665816922723,
|
|
"loss": 5.489,
|
|
"mean_token_accuracy": 0.16571661978960037,
|
|
"num_tokens": 10225889.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.656914520263672,
|
|
"epoch": 0.45905465862672634,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004983632464482267,
|
|
"loss": 5.4281,
|
|
"mean_token_accuracy": 0.16902617514133453,
|
|
"num_tokens": 10234518.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.736385107040405,
|
|
"epoch": 0.4594436879984439,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004983599078149991,
|
|
"loss": 5.5688,
|
|
"mean_token_accuracy": 0.15792535990476608,
|
|
"num_tokens": 10243074.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.8126506328582765,
|
|
"epoch": 0.45983271737016146,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004983565657926405,
|
|
"loss": 5.5234,
|
|
"mean_token_accuracy": 0.16075174808502196,
|
|
"num_tokens": 10253473.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.7456237316131595,
|
|
"epoch": 0.460221746741879,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004983532203812017,
|
|
"loss": 5.5978,
|
|
"mean_token_accuracy": 0.161079540848732,
|
|
"num_tokens": 10261866.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.715584325790405,
|
|
"epoch": 0.4606107761135966,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004983498715807331,
|
|
"loss": 5.4522,
|
|
"mean_token_accuracy": 0.16834707856178283,
|
|
"num_tokens": 10270350.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.687623453140259,
|
|
"epoch": 0.46099980548531416,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004983465193912857,
|
|
"loss": 5.6004,
|
|
"mean_token_accuracy": 0.1558307781815529,
|
|
"num_tokens": 10279556.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.6369805335998535,
|
|
"epoch": 0.4613888348570317,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004983431638129104,
|
|
"loss": 5.3705,
|
|
"mean_token_accuracy": 0.16682921946048737,
|
|
"num_tokens": 10287489.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.647270536422729,
|
|
"epoch": 0.4617778642287493,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004983398048456581,
|
|
"loss": 5.3598,
|
|
"mean_token_accuracy": 0.17038783580064773,
|
|
"num_tokens": 10296280.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.672983312606812,
|
|
"epoch": 0.4621668936004668,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004983364424895796,
|
|
"loss": 5.4964,
|
|
"mean_token_accuracy": 0.16527538746595383,
|
|
"num_tokens": 10304091.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.718464946746826,
|
|
"epoch": 0.4625559229721844,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004983330767447262,
|
|
"loss": 5.5366,
|
|
"mean_token_accuracy": 0.16057891249656678,
|
|
"num_tokens": 10313058.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.695686197280883,
|
|
"epoch": 0.462944952343902,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004983297076111489,
|
|
"loss": 5.5003,
|
|
"mean_token_accuracy": 0.1629731461405754,
|
|
"num_tokens": 10321642.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.663236951828003,
|
|
"epoch": 0.4633339817156195,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004983263350888987,
|
|
"loss": 5.3201,
|
|
"mean_token_accuracy": 0.17207740843296052,
|
|
"num_tokens": 10329829.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.700695466995239,
|
|
"epoch": 0.4637230110873371,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004983229591780268,
|
|
"loss": 5.5593,
|
|
"mean_token_accuracy": 0.16328161358833312,
|
|
"num_tokens": 10338182.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.698422574996949,
|
|
"epoch": 0.46411204045905463,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004983195798785844,
|
|
"loss": 5.451,
|
|
"mean_token_accuracy": 0.16804663538932801,
|
|
"num_tokens": 10346377.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.697450780868531,
|
|
"epoch": 0.4645010698307722,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004983161971906228,
|
|
"loss": 5.4454,
|
|
"mean_token_accuracy": 0.16864902079105376,
|
|
"num_tokens": 10354937.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.609955787658691,
|
|
"epoch": 0.4648900992024898,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004983128111141935,
|
|
"loss": 5.3412,
|
|
"mean_token_accuracy": 0.17436672896146774,
|
|
"num_tokens": 10363706.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.63286337852478,
|
|
"epoch": 0.46527912857420733,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004983094216493475,
|
|
"loss": 5.4905,
|
|
"mean_token_accuracy": 0.16379242837429048,
|
|
"num_tokens": 10372292.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.707705450057984,
|
|
"epoch": 0.4656681579459249,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004983060287961367,
|
|
"loss": 5.464,
|
|
"mean_token_accuracy": 0.1689232751727104,
|
|
"num_tokens": 10381260.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.693024921417236,
|
|
"epoch": 0.4660571873176425,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983026325546123,
|
|
"loss": 5.4842,
|
|
"mean_token_accuracy": 0.161691378057003,
|
|
"num_tokens": 10390646.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.6791528224945065,
|
|
"epoch": 0.46644621668936004,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004982992329248257,
|
|
"loss": 5.5513,
|
|
"mean_token_accuracy": 0.16394535303115845,
|
|
"num_tokens": 10399056.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.694767427444458,
|
|
"epoch": 0.4668352460610776,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004982958299068289,
|
|
"loss": 5.536,
|
|
"mean_token_accuracy": 0.15566003024578096,
|
|
"num_tokens": 10408746.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.4668352460610776,
|
|
"eval_entropy": 5.526954579376279,
|
|
"eval_loss": 5.511401176452637,
|
|
"eval_mean_token_accuracy": 0.17264520771607858,
|
|
"eval_num_tokens": 10408746.0,
|
|
"eval_runtime": 21.9309,
|
|
"eval_samples_per_second": 1894.95,
|
|
"eval_steps_per_second": 236.88,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.726455783843994,
|
|
"epoch": 0.46722427543279516,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000498292423500673,
|
|
"loss": 5.4587,
|
|
"mean_token_accuracy": 0.16634683459997177,
|
|
"num_tokens": 10416937.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.682621479034424,
|
|
"epoch": 0.46761330480451274,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004982890137064102,
|
|
"loss": 5.4357,
|
|
"mean_token_accuracy": 0.17602696865797043,
|
|
"num_tokens": 10426343.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.652905225753784,
|
|
"epoch": 0.46800233417623033,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000498285600524092,
|
|
"loss": 5.4522,
|
|
"mean_token_accuracy": 0.17078690230846405,
|
|
"num_tokens": 10435014.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.628161239624023,
|
|
"epoch": 0.46839136354794786,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004982821839537701,
|
|
"loss": 5.476,
|
|
"mean_token_accuracy": 0.16416355222463608,
|
|
"num_tokens": 10443522.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.720815229415893,
|
|
"epoch": 0.46878039291966545,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004982787639954966,
|
|
"loss": 5.5215,
|
|
"mean_token_accuracy": 0.16364811658859252,
|
|
"num_tokens": 10452202.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.654162073135376,
|
|
"epoch": 0.469169422291383,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004982753406493232,
|
|
"loss": 5.4953,
|
|
"mean_token_accuracy": 0.15741059929132462,
|
|
"num_tokens": 10462293.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.67516975402832,
|
|
"epoch": 0.46955845166310056,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004982719139153018,
|
|
"loss": 5.4369,
|
|
"mean_token_accuracy": 0.16624483615159988,
|
|
"num_tokens": 10470322.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.719859933853149,
|
|
"epoch": 0.46994748103481815,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004982684837934845,
|
|
"loss": 5.4172,
|
|
"mean_token_accuracy": 0.16623629927635192,
|
|
"num_tokens": 10479581.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.711789560317993,
|
|
"epoch": 0.4703365104065357,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004982650502839234,
|
|
"loss": 5.436,
|
|
"mean_token_accuracy": 0.16731600165367128,
|
|
"num_tokens": 10488207.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.619416332244873,
|
|
"epoch": 0.47072553977825327,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004982616133866705,
|
|
"loss": 5.4435,
|
|
"mean_token_accuracy": 0.16506613194942474,
|
|
"num_tokens": 10497360.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.6212522983551025,
|
|
"epoch": 0.4711145691499708,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004982581731017779,
|
|
"loss": 5.4183,
|
|
"mean_token_accuracy": 0.17101287096738815,
|
|
"num_tokens": 10506131.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.663428783416748,
|
|
"epoch": 0.4715035985216884,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004982547294292979,
|
|
"loss": 5.4653,
|
|
"mean_token_accuracy": 0.16743853986263274,
|
|
"num_tokens": 10514955.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.629032135009766,
|
|
"epoch": 0.47189262789340597,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004982512823692828,
|
|
"loss": 5.4483,
|
|
"mean_token_accuracy": 0.15942414551973344,
|
|
"num_tokens": 10523743.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.652404117584228,
|
|
"epoch": 0.4722816572651235,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004982478319217848,
|
|
"loss": 5.4086,
|
|
"mean_token_accuracy": 0.18121292889118196,
|
|
"num_tokens": 10533149.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.645018529891968,
|
|
"epoch": 0.4726706866368411,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004982443780868562,
|
|
"loss": 5.4459,
|
|
"mean_token_accuracy": 0.1664214089512825,
|
|
"num_tokens": 10541291.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.6984508514404295,
|
|
"epoch": 0.4730597160085587,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004982409208645496,
|
|
"loss": 5.4859,
|
|
"mean_token_accuracy": 0.16808651089668275,
|
|
"num_tokens": 10550005.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.742500305175781,
|
|
"epoch": 0.4734487453802762,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004982374602549173,
|
|
"loss": 5.5135,
|
|
"mean_token_accuracy": 0.16490289494395255,
|
|
"num_tokens": 10558957.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.702150869369507,
|
|
"epoch": 0.4738377747519938,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004982339962580119,
|
|
"loss": 5.3942,
|
|
"mean_token_accuracy": 0.16679285317659379,
|
|
"num_tokens": 10567293.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.614796686172485,
|
|
"epoch": 0.4742268041237113,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004982305288738859,
|
|
"loss": 5.376,
|
|
"mean_token_accuracy": 0.1681532680988312,
|
|
"num_tokens": 10575546.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.5767762660980225,
|
|
"epoch": 0.4746158334954289,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004982270581025919,
|
|
"loss": 5.5016,
|
|
"mean_token_accuracy": 0.17040557861328126,
|
|
"num_tokens": 10584779.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.648759889602661,
|
|
"epoch": 0.4750048628671465,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004982235839441826,
|
|
"loss": 5.4087,
|
|
"mean_token_accuracy": 0.17466698437929154,
|
|
"num_tokens": 10592852.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.704872751235962,
|
|
"epoch": 0.475393892238864,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004982201063987108,
|
|
"loss": 5.5318,
|
|
"mean_token_accuracy": 0.15746946930885314,
|
|
"num_tokens": 10601875.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.662019157409668,
|
|
"epoch": 0.4757829216105816,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004982166254662292,
|
|
"loss": 5.5062,
|
|
"mean_token_accuracy": 0.170045006275177,
|
|
"num_tokens": 10610438.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.711904287338257,
|
|
"epoch": 0.47617195098229914,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004982131411467904,
|
|
"loss": 5.4955,
|
|
"mean_token_accuracy": 0.1645934909582138,
|
|
"num_tokens": 10619479.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.6802596092224125,
|
|
"epoch": 0.4765609803540167,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004982096534404476,
|
|
"loss": 5.4203,
|
|
"mean_token_accuracy": 0.17332687079906464,
|
|
"num_tokens": 10628519.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.679824876785278,
|
|
"epoch": 0.4769500097257343,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004982061623472535,
|
|
"loss": 5.3683,
|
|
"mean_token_accuracy": 0.17489866316318511,
|
|
"num_tokens": 10636522.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.623510885238647,
|
|
"epoch": 0.47733903909745184,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004982026678672612,
|
|
"loss": 5.3928,
|
|
"mean_token_accuracy": 0.16902382373809816,
|
|
"num_tokens": 10645728.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.639240646362305,
|
|
"epoch": 0.47772806846916943,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004981991700005238,
|
|
"loss": 5.5122,
|
|
"mean_token_accuracy": 0.16430457681417465,
|
|
"num_tokens": 10654868.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.620595550537109,
|
|
"epoch": 0.47811709784088696,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000498195668747094,
|
|
"loss": 5.3954,
|
|
"mean_token_accuracy": 0.1706836685538292,
|
|
"num_tokens": 10662958.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.700119161605835,
|
|
"epoch": 0.47850612721260455,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004981921641070254,
|
|
"loss": 5.4064,
|
|
"mean_token_accuracy": 0.16912615299224854,
|
|
"num_tokens": 10671333.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.690384435653686,
|
|
"epoch": 0.47889515658432213,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004981886560803708,
|
|
"loss": 5.4286,
|
|
"mean_token_accuracy": 0.1688441127538681,
|
|
"num_tokens": 10680523.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.661981439590454,
|
|
"epoch": 0.47928418595603967,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004981851446671838,
|
|
"loss": 5.4975,
|
|
"mean_token_accuracy": 0.16414804756641388,
|
|
"num_tokens": 10689656.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.736613702774048,
|
|
"epoch": 0.47967321532775725,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004981816298675173,
|
|
"loss": 5.5691,
|
|
"mean_token_accuracy": 0.15930777937173843,
|
|
"num_tokens": 10698423.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.707890367507934,
|
|
"epoch": 0.4800622446994748,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004981781116814248,
|
|
"loss": 5.4339,
|
|
"mean_token_accuracy": 0.168502140045166,
|
|
"num_tokens": 10706760.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.743547677993774,
|
|
"epoch": 0.48045127407119237,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004981745901089596,
|
|
"loss": 5.5415,
|
|
"mean_token_accuracy": 0.15941269546747208,
|
|
"num_tokens": 10716221.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.601821565628052,
|
|
"epoch": 0.48084030344290996,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004981710651501753,
|
|
"loss": 5.335,
|
|
"mean_token_accuracy": 0.17823495119810104,
|
|
"num_tokens": 10724603.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.692285394668579,
|
|
"epoch": 0.4812293328146275,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004981675368051254,
|
|
"loss": 5.5583,
|
|
"mean_token_accuracy": 0.15886397808790206,
|
|
"num_tokens": 10733577.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.768624019622803,
|
|
"epoch": 0.4816183621863451,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004981640050738633,
|
|
"loss": 5.4769,
|
|
"mean_token_accuracy": 0.1653328873217106,
|
|
"num_tokens": 10743199.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.65557017326355,
|
|
"epoch": 0.48200739155806266,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004981604699564426,
|
|
"loss": 5.3694,
|
|
"mean_token_accuracy": 0.1680201545357704,
|
|
"num_tokens": 10751734.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.677676343917847,
|
|
"epoch": 0.4823964209297802,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004981569314529169,
|
|
"loss": 5.5159,
|
|
"mean_token_accuracy": 0.1653820604085922,
|
|
"num_tokens": 10760194.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.682971811294555,
|
|
"epoch": 0.4827854503014978,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049815338956334,
|
|
"loss": 5.432,
|
|
"mean_token_accuracy": 0.171656933426857,
|
|
"num_tokens": 10768944.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.759762811660766,
|
|
"epoch": 0.4831744796732153,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004981498442877656,
|
|
"loss": 5.5297,
|
|
"mean_token_accuracy": 0.1686689078807831,
|
|
"num_tokens": 10777685.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.672958707809448,
|
|
"epoch": 0.4835635090449329,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004981462956262474,
|
|
"loss": 5.5018,
|
|
"mean_token_accuracy": 0.16606569439172744,
|
|
"num_tokens": 10787264.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.614988517761231,
|
|
"epoch": 0.4839525384166505,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004981427435788396,
|
|
"loss": 5.4717,
|
|
"mean_token_accuracy": 0.16396449953317643,
|
|
"num_tokens": 10796555.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.581253385543823,
|
|
"epoch": 0.484341567788368,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004981391881455957,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.1764609172940254,
|
|
"num_tokens": 10805379.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.64763994216919,
|
|
"epoch": 0.4847305971600856,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004981356293265696,
|
|
"loss": 5.5108,
|
|
"mean_token_accuracy": 0.16001439467072487,
|
|
"num_tokens": 10815406.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.677568054199218,
|
|
"epoch": 0.4851196265318031,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004981320671218157,
|
|
"loss": 5.5539,
|
|
"mean_token_accuracy": 0.16216269880533218,
|
|
"num_tokens": 10824443.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.728261709213257,
|
|
"epoch": 0.4855086559035207,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004981285015313877,
|
|
"loss": 5.4008,
|
|
"mean_token_accuracy": 0.17301271110773087,
|
|
"num_tokens": 10833497.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.604798269271851,
|
|
"epoch": 0.4858976852752383,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004981249325553399,
|
|
"loss": 5.445,
|
|
"mean_token_accuracy": 0.16607270687818526,
|
|
"num_tokens": 10841864.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.6987268924713135,
|
|
"epoch": 0.48628671464695583,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004981213601937264,
|
|
"loss": 5.48,
|
|
"mean_token_accuracy": 0.1666806936264038,
|
|
"num_tokens": 10850887.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.611641502380371,
|
|
"epoch": 0.4866757440186734,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004981177844466013,
|
|
"loss": 5.3722,
|
|
"mean_token_accuracy": 0.1711752250790596,
|
|
"num_tokens": 10859629.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.673368358612061,
|
|
"epoch": 0.48706477339039095,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004981142053140192,
|
|
"loss": 5.56,
|
|
"mean_token_accuracy": 0.1639465093612671,
|
|
"num_tokens": 10868457.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.6619948387146,
|
|
"epoch": 0.48745380276210853,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004981106227960339,
|
|
"loss": 5.4862,
|
|
"mean_token_accuracy": 0.16452796757221222,
|
|
"num_tokens": 10878007.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.792617225646973,
|
|
"epoch": 0.4878428321338261,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004981070368927001,
|
|
"loss": 5.5191,
|
|
"mean_token_accuracy": 0.16553210765123366,
|
|
"num_tokens": 10887689.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.619898319244385,
|
|
"epoch": 0.48823186150554365,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000498103447604072,
|
|
"loss": 5.3206,
|
|
"mean_token_accuracy": 0.1780785247683525,
|
|
"num_tokens": 10896214.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.591894292831421,
|
|
"epoch": 0.48862089087726124,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004980998549302044,
|
|
"loss": 5.447,
|
|
"mean_token_accuracy": 0.16975104808807373,
|
|
"num_tokens": 10904946.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.736668539047241,
|
|
"epoch": 0.4890099202489788,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004980962588711516,
|
|
"loss": 5.5196,
|
|
"mean_token_accuracy": 0.16013508439064025,
|
|
"num_tokens": 10913382.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.737943172454834,
|
|
"epoch": 0.48939894962069636,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000498092659426968,
|
|
"loss": 5.4813,
|
|
"mean_token_accuracy": 0.16893975734710692,
|
|
"num_tokens": 10922055.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.634787368774414,
|
|
"epoch": 0.48978797899241394,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004980890565977085,
|
|
"loss": 5.4651,
|
|
"mean_token_accuracy": 0.16650761067867278,
|
|
"num_tokens": 10930282.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.586604166030884,
|
|
"epoch": 0.4901770083641315,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004980854503834276,
|
|
"loss": 5.4713,
|
|
"mean_token_accuracy": 0.1735634386539459,
|
|
"num_tokens": 10938432.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.7162559032440186,
|
|
"epoch": 0.49056603773584906,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004980818407841802,
|
|
"loss": 5.4661,
|
|
"mean_token_accuracy": 0.1719464674592018,
|
|
"num_tokens": 10946354.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.746575498580933,
|
|
"epoch": 0.49095506710756665,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004980782278000207,
|
|
"loss": 5.5014,
|
|
"mean_token_accuracy": 0.16299327313899994,
|
|
"num_tokens": 10954885.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.643042278289795,
|
|
"epoch": 0.4913440964792842,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004980746114310043,
|
|
"loss": 5.41,
|
|
"mean_token_accuracy": 0.16809043288230896,
|
|
"num_tokens": 10963173.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.665570878982544,
|
|
"epoch": 0.49173312585100176,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004980709916771858,
|
|
"loss": 5.5587,
|
|
"mean_token_accuracy": 0.15590894371271133,
|
|
"num_tokens": 10972264.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.630701541900635,
|
|
"epoch": 0.4921221552227193,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004980673685386198,
|
|
"loss": 5.4065,
|
|
"mean_token_accuracy": 0.1728062614798546,
|
|
"num_tokens": 10980645.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.6020771026611325,
|
|
"epoch": 0.4925111845944369,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004980637420153618,
|
|
"loss": 5.3592,
|
|
"mean_token_accuracy": 0.17097442746162414,
|
|
"num_tokens": 10989121.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.631519365310669,
|
|
"epoch": 0.49290021396615447,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004980601121074664,
|
|
"loss": 5.3605,
|
|
"mean_token_accuracy": 0.17560895383358002,
|
|
"num_tokens": 10998249.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.747340345382691,
|
|
"epoch": 0.493289243337872,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004980564788149889,
|
|
"loss": 5.4755,
|
|
"mean_token_accuracy": 0.16513971388339996,
|
|
"num_tokens": 11007470.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.694008445739746,
|
|
"epoch": 0.4936782727095896,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004980528421379844,
|
|
"loss": 5.4264,
|
|
"mean_token_accuracy": 0.16628471314907073,
|
|
"num_tokens": 11015912.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.634057521820068,
|
|
"epoch": 0.4940673020813071,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000498049202076508,
|
|
"loss": 5.4354,
|
|
"mean_token_accuracy": 0.16697777658700944,
|
|
"num_tokens": 11024629.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.667661046981811,
|
|
"epoch": 0.4944563314530247,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004980455586306149,
|
|
"loss": 5.3787,
|
|
"mean_token_accuracy": 0.17258453518152236,
|
|
"num_tokens": 11033953.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.592496776580811,
|
|
"epoch": 0.4948453608247423,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004980419118003605,
|
|
"loss": 5.4571,
|
|
"mean_token_accuracy": 0.16577280908823014,
|
|
"num_tokens": 11042891.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.643301963806152,
|
|
"epoch": 0.4952343901964598,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004980382615858001,
|
|
"loss": 5.5492,
|
|
"mean_token_accuracy": 0.16074244379997255,
|
|
"num_tokens": 11051262.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.6761993885040285,
|
|
"epoch": 0.4956234195681774,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004980346079869892,
|
|
"loss": 5.3681,
|
|
"mean_token_accuracy": 0.17648585736751557,
|
|
"num_tokens": 11059357.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.651570606231689,
|
|
"epoch": 0.49601244893989493,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000498030951003983,
|
|
"loss": 5.3967,
|
|
"mean_token_accuracy": 0.1678969830274582,
|
|
"num_tokens": 11068076.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.583523178100586,
|
|
"epoch": 0.4964014783116125,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004980272906368371,
|
|
"loss": 5.2748,
|
|
"mean_token_accuracy": 0.18292394280433655,
|
|
"num_tokens": 11076804.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.660397291183472,
|
|
"epoch": 0.4967905076833301,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004980236268856071,
|
|
"loss": 5.4741,
|
|
"mean_token_accuracy": 0.17098617255687715,
|
|
"num_tokens": 11085794.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.5611003875732425,
|
|
"epoch": 0.49717953705504764,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004980199597503487,
|
|
"loss": 5.3755,
|
|
"mean_token_accuracy": 0.16459452956914902,
|
|
"num_tokens": 11094989.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.586446523666382,
|
|
"epoch": 0.4975685664267652,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004980162892311171,
|
|
"loss": 5.3346,
|
|
"mean_token_accuracy": 0.1741299569606781,
|
|
"num_tokens": 11103046.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.5971721649169925,
|
|
"epoch": 0.4979575957984828,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004980126153279684,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.17560217678546905,
|
|
"num_tokens": 11111533.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.650516223907471,
|
|
"epoch": 0.49834662517020034,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004980089380409583,
|
|
"loss": 5.5972,
|
|
"mean_token_accuracy": 0.15618404000997543,
|
|
"num_tokens": 11120534.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.743019437789917,
|
|
"epoch": 0.4987356545419179,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004980052573701424,
|
|
"loss": 5.5348,
|
|
"mean_token_accuracy": 0.17133111208677293,
|
|
"num_tokens": 11128354.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.711576890945435,
|
|
"epoch": 0.49912468391363546,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004980015733155767,
|
|
"loss": 5.4515,
|
|
"mean_token_accuracy": 0.16233282089233397,
|
|
"num_tokens": 11136201.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.7182337760925295,
|
|
"epoch": 0.49951371328535304,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004979978858773171,
|
|
"loss": 5.4175,
|
|
"mean_token_accuracy": 0.1689138561487198,
|
|
"num_tokens": 11145131.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.606427145004273,
|
|
"epoch": 0.49990274265707063,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004979941950554195,
|
|
"loss": 5.3418,
|
|
"mean_token_accuracy": 0.17413055300712585,
|
|
"num_tokens": 11154514.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.723063278198242,
|
|
"epoch": 0.5002917720287882,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004979905008499399,
|
|
"loss": 5.4389,
|
|
"mean_token_accuracy": 0.17316336631774903,
|
|
"num_tokens": 11163160.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.608155727386475,
|
|
"epoch": 0.5006808014005057,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004979868032609344,
|
|
"loss": 5.4122,
|
|
"mean_token_accuracy": 0.17666464745998384,
|
|
"num_tokens": 11171573.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.5990777015686035,
|
|
"epoch": 0.5010698307722233,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004979831022884591,
|
|
"loss": 5.4154,
|
|
"mean_token_accuracy": 0.16636250764131547,
|
|
"num_tokens": 11180028.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.603765964508057,
|
|
"epoch": 0.5014588601439409,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004979793979325701,
|
|
"loss": 5.335,
|
|
"mean_token_accuracy": 0.16556937098503113,
|
|
"num_tokens": 11188403.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.544768857955932,
|
|
"epoch": 0.5018478895156584,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004979756901933236,
|
|
"loss": 5.3314,
|
|
"mean_token_accuracy": 0.1819371610879898,
|
|
"num_tokens": 11196391.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.6223509311676025,
|
|
"epoch": 0.502236918887376,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000497971979070776,
|
|
"loss": 5.4505,
|
|
"mean_token_accuracy": 0.16939201056957245,
|
|
"num_tokens": 11204596.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.639053726196289,
|
|
"epoch": 0.5026259482590936,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004979682645649834,
|
|
"loss": 5.4105,
|
|
"mean_token_accuracy": 0.16829846501350404,
|
|
"num_tokens": 11212629.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.713208293914795,
|
|
"epoch": 0.5030149776308112,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004979645466760025,
|
|
"loss": 5.4737,
|
|
"mean_token_accuracy": 0.1686081901192665,
|
|
"num_tokens": 11221836.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.67520751953125,
|
|
"epoch": 0.5034040070025287,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004979608254038892,
|
|
"loss": 5.5339,
|
|
"mean_token_accuracy": 0.1600072592496872,
|
|
"num_tokens": 11230600.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.7495097637176515,
|
|
"epoch": 0.5037930363742462,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004979571007487003,
|
|
"loss": 5.5228,
|
|
"mean_token_accuracy": 0.15595481544733047,
|
|
"num_tokens": 11239664.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.629716253280639,
|
|
"epoch": 0.5041820657459638,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004979533727104924,
|
|
"loss": 5.4495,
|
|
"mean_token_accuracy": 0.1616964042186737,
|
|
"num_tokens": 11249111.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.6311675071716305,
|
|
"epoch": 0.5045710951176814,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000497949641289322,
|
|
"loss": 5.3395,
|
|
"mean_token_accuracy": 0.1698092058300972,
|
|
"num_tokens": 11257599.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.615521097183228,
|
|
"epoch": 0.504960124489399,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004979459064852456,
|
|
"loss": 5.461,
|
|
"mean_token_accuracy": 0.17805053144693375,
|
|
"num_tokens": 11265586.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.74630331993103,
|
|
"epoch": 0.5053491538611166,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004979421682983197,
|
|
"loss": 5.5854,
|
|
"mean_token_accuracy": 0.1652588278055191,
|
|
"num_tokens": 11274736.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.665422821044922,
|
|
"epoch": 0.505738183232834,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004979384267286015,
|
|
"loss": 5.362,
|
|
"mean_token_accuracy": 0.17337319552898406,
|
|
"num_tokens": 11282596.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.6501696586608885,
|
|
"epoch": 0.5061272126045516,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004979346817761475,
|
|
"loss": 5.4503,
|
|
"mean_token_accuracy": 0.1627633586525917,
|
|
"num_tokens": 11290974.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.5663024425506595,
|
|
"epoch": 0.5065162419762692,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004979309334410144,
|
|
"loss": 5.3334,
|
|
"mean_token_accuracy": 0.17180522680282592,
|
|
"num_tokens": 11299196.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.671379089355469,
|
|
"epoch": 0.5069052713479868,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004979271817232594,
|
|
"loss": 5.47,
|
|
"mean_token_accuracy": 0.1628324031829834,
|
|
"num_tokens": 11308214.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.661998510360718,
|
|
"epoch": 0.5072943007197044,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004979234266229391,
|
|
"loss": 5.4372,
|
|
"mean_token_accuracy": 0.17011113911867143,
|
|
"num_tokens": 11316566.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.654293775558472,
|
|
"epoch": 0.5076833300914219,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004979196681401106,
|
|
"loss": 5.4283,
|
|
"mean_token_accuracy": 0.16879323571920396,
|
|
"num_tokens": 11325079.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.658125495910644,
|
|
"epoch": 0.5080723594631394,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000497915906274831,
|
|
"loss": 5.4441,
|
|
"mean_token_accuracy": 0.1672111839056015,
|
|
"num_tokens": 11333829.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.582587718963623,
|
|
"epoch": 0.508461388834857,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004979121410271574,
|
|
"loss": 5.3905,
|
|
"mean_token_accuracy": 0.1738412469625473,
|
|
"num_tokens": 11343078.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.65086784362793,
|
|
"epoch": 0.5088504182065746,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004979083723971468,
|
|
"loss": 5.4947,
|
|
"mean_token_accuracy": 0.17132056951522828,
|
|
"num_tokens": 11351475.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.619971179962159,
|
|
"epoch": 0.5092394475782922,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004979046003848564,
|
|
"loss": 5.3775,
|
|
"mean_token_accuracy": 0.1698130652308464,
|
|
"num_tokens": 11359810.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.680748701095581,
|
|
"epoch": 0.5096284769500097,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004979008249903435,
|
|
"loss": 5.4326,
|
|
"mean_token_accuracy": 0.17276596873998643,
|
|
"num_tokens": 11368585.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.690910005569458,
|
|
"epoch": 0.5100175063217273,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004978970462136655,
|
|
"loss": 5.4611,
|
|
"mean_token_accuracy": 0.16980846524238585,
|
|
"num_tokens": 11377393.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.670943355560302,
|
|
"epoch": 0.5104065356934449,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004978932640548794,
|
|
"loss": 5.4339,
|
|
"mean_token_accuracy": 0.165023310482502,
|
|
"num_tokens": 11385877.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.602134370803833,
|
|
"epoch": 0.5107955650651624,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004978894785140429,
|
|
"loss": 5.3569,
|
|
"mean_token_accuracy": 0.17920774668455125,
|
|
"num_tokens": 11394457.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.579525470733643,
|
|
"epoch": 0.51118459443688,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004978856895912132,
|
|
"loss": 5.3712,
|
|
"mean_token_accuracy": 0.17652615308761596,
|
|
"num_tokens": 11403007.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.672693061828613,
|
|
"epoch": 0.5115736238085975,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004978818972864481,
|
|
"loss": 5.4376,
|
|
"mean_token_accuracy": 0.1651514306664467,
|
|
"num_tokens": 11412237.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.686287975311279,
|
|
"epoch": 0.5119626531803151,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004978781015998048,
|
|
"loss": 5.4048,
|
|
"mean_token_accuracy": 0.1689675435423851,
|
|
"num_tokens": 11421219.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.66724534034729,
|
|
"epoch": 0.5123516825520327,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004978743025313413,
|
|
"loss": 5.3848,
|
|
"mean_token_accuracy": 0.16759707182645797,
|
|
"num_tokens": 11428933.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.618669319152832,
|
|
"epoch": 0.5127407119237503,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004978705000811148,
|
|
"loss": 5.4909,
|
|
"mean_token_accuracy": 0.16458306163549424,
|
|
"num_tokens": 11437551.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.722258758544922,
|
|
"epoch": 0.5131297412954678,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004978666942491832,
|
|
"loss": 5.5726,
|
|
"mean_token_accuracy": 0.1582800716161728,
|
|
"num_tokens": 11446045.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.761044073104858,
|
|
"epoch": 0.5135187706671853,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004978628850356043,
|
|
"loss": 5.4914,
|
|
"mean_token_accuracy": 0.16513002216815947,
|
|
"num_tokens": 11455159.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.685759687423706,
|
|
"epoch": 0.5139078000389029,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004978590724404358,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.17099089175462723,
|
|
"num_tokens": 11463835.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.648447322845459,
|
|
"epoch": 0.5142968294106205,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004978552564637356,
|
|
"loss": 5.4682,
|
|
"mean_token_accuracy": 0.17038068175315857,
|
|
"num_tokens": 11472439.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.6681715965271,
|
|
"epoch": 0.5146858587823381,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004978514371055616,
|
|
"loss": 5.5086,
|
|
"mean_token_accuracy": 0.16487603187561034,
|
|
"num_tokens": 11481626.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.605358123779297,
|
|
"epoch": 0.5150748881540557,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004978476143659718,
|
|
"loss": 5.3939,
|
|
"mean_token_accuracy": 0.17514775842428207,
|
|
"num_tokens": 11490571.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.734579801559448,
|
|
"epoch": 0.5154639175257731,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004978437882450241,
|
|
"loss": 5.4922,
|
|
"mean_token_accuracy": 0.1654839798808098,
|
|
"num_tokens": 11499145.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.692298221588135,
|
|
"epoch": 0.5158529468974907,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004978399587427766,
|
|
"loss": 5.4143,
|
|
"mean_token_accuracy": 0.17052434980869294,
|
|
"num_tokens": 11508133.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.511624479293824,
|
|
"epoch": 0.5162419762692083,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004978361258592874,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.1742513209581375,
|
|
"num_tokens": 11516790.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.630044412612915,
|
|
"epoch": 0.5166310056409259,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004978322895946147,
|
|
"loss": 5.4068,
|
|
"mean_token_accuracy": 0.16798608154058456,
|
|
"num_tokens": 11525963.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.629098558425904,
|
|
"epoch": 0.5170200350126435,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004978284499488167,
|
|
"loss": 5.3851,
|
|
"mean_token_accuracy": 0.17411332577466965,
|
|
"num_tokens": 11534193.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.653246212005615,
|
|
"epoch": 0.5174090643843611,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004978246069219516,
|
|
"loss": 5.4029,
|
|
"mean_token_accuracy": 0.17116494178771974,
|
|
"num_tokens": 11542517.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.647744750976562,
|
|
"epoch": 0.5177980937560785,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004978207605140777,
|
|
"loss": 5.4669,
|
|
"mean_token_accuracy": 0.16449436247348787,
|
|
"num_tokens": 11550874.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.669667196273804,
|
|
"epoch": 0.5181871231277961,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004978169107252534,
|
|
"loss": 5.4881,
|
|
"mean_token_accuracy": 0.16329788714647292,
|
|
"num_tokens": 11560562.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.643291759490967,
|
|
"epoch": 0.5185761524995137,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004978130575555373,
|
|
"loss": 5.3751,
|
|
"mean_token_accuracy": 0.16976799070835114,
|
|
"num_tokens": 11569887.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.57875690460205,
|
|
"epoch": 0.5189651818712313,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004978092010049877,
|
|
"loss": 5.3054,
|
|
"mean_token_accuracy": 0.17502678334712982,
|
|
"num_tokens": 11578608.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.585260343551636,
|
|
"epoch": 0.5193542112429489,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000497805341073663,
|
|
"loss": 5.4132,
|
|
"mean_token_accuracy": 0.16847770512104035,
|
|
"num_tokens": 11587435.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.6195220947265625,
|
|
"epoch": 0.5197432406146664,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004978014777616219,
|
|
"loss": 5.5123,
|
|
"mean_token_accuracy": 0.16088477224111558,
|
|
"num_tokens": 11596094.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.700346231460571,
|
|
"epoch": 0.520132269986384,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004977976110689229,
|
|
"loss": 5.4643,
|
|
"mean_token_accuracy": 0.1668734520673752,
|
|
"num_tokens": 11604521.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.684550094604492,
|
|
"epoch": 0.5205212993581015,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000497793740995625,
|
|
"loss": 5.4332,
|
|
"mean_token_accuracy": 0.17027366161346436,
|
|
"num_tokens": 11613143.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.665559864044189,
|
|
"epoch": 0.5209103287298191,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004977898675417866,
|
|
"loss": 5.4826,
|
|
"mean_token_accuracy": 0.17012318819761277,
|
|
"num_tokens": 11622667.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.690769147872925,
|
|
"epoch": 0.5212993581015367,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004977859907074664,
|
|
"loss": 5.4405,
|
|
"mean_token_accuracy": 0.1723522961139679,
|
|
"num_tokens": 11632114.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.6664323806762695,
|
|
"epoch": 0.5216883874732542,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004977821104927236,
|
|
"loss": 5.3708,
|
|
"mean_token_accuracy": 0.17163726687431335,
|
|
"num_tokens": 11640731.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.5376856327056885,
|
|
"epoch": 0.5220774168449718,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004977782268976167,
|
|
"loss": 5.347,
|
|
"mean_token_accuracy": 0.17547252923250198,
|
|
"num_tokens": 11648975.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.629901313781739,
|
|
"epoch": 0.5224664462166894,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004977743399222048,
|
|
"loss": 5.397,
|
|
"mean_token_accuracy": 0.17356285601854324,
|
|
"num_tokens": 11657598.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.759890699386597,
|
|
"epoch": 0.522855475588407,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004977704495665471,
|
|
"loss": 5.5537,
|
|
"mean_token_accuracy": 0.17318776845932007,
|
|
"num_tokens": 11665504.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.689238452911377,
|
|
"epoch": 0.5232445049601245,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004977665558307023,
|
|
"loss": 5.4519,
|
|
"mean_token_accuracy": 0.17328019589185714,
|
|
"num_tokens": 11674337.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.540548801422119,
|
|
"epoch": 0.523633534331842,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004977626587147295,
|
|
"loss": 5.3074,
|
|
"mean_token_accuracy": 0.17538170665502548,
|
|
"num_tokens": 11682626.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.613022899627685,
|
|
"epoch": 0.5240225637035596,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000497758758218688,
|
|
"loss": 5.3536,
|
|
"mean_token_accuracy": 0.17512194365262984,
|
|
"num_tokens": 11691403.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.707204675674438,
|
|
"epoch": 0.5244115930752772,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004977548543426368,
|
|
"loss": 5.487,
|
|
"mean_token_accuracy": 0.16559841185808183,
|
|
"num_tokens": 11700590.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.674825811386109,
|
|
"epoch": 0.5248006224469948,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004977509470866353,
|
|
"loss": 5.3849,
|
|
"mean_token_accuracy": 0.1695603162050247,
|
|
"num_tokens": 11708799.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.622507047653198,
|
|
"epoch": 0.5251896518187124,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004977470364507427,
|
|
"loss": 5.3924,
|
|
"mean_token_accuracy": 0.174872525036335,
|
|
"num_tokens": 11716953.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.645905256271362,
|
|
"epoch": 0.5255786811904298,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004977431224350184,
|
|
"loss": 5.4596,
|
|
"mean_token_accuracy": 0.1675609439611435,
|
|
"num_tokens": 11725032.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.671552467346191,
|
|
"epoch": 0.5259677105621474,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004977392050395217,
|
|
"loss": 5.4674,
|
|
"mean_token_accuracy": 0.16827739626169205,
|
|
"num_tokens": 11733359.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.6978929996490475,
|
|
"epoch": 0.526356739933865,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004977352842643121,
|
|
"loss": 5.4447,
|
|
"mean_token_accuracy": 0.17384590953588486,
|
|
"num_tokens": 11740936.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.6561400413513185,
|
|
"epoch": 0.5267457693055826,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000497731360109449,
|
|
"loss": 5.4912,
|
|
"mean_token_accuracy": 0.1654544785618782,
|
|
"num_tokens": 11749764.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.71761384010315,
|
|
"epoch": 0.5271347986773002,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004977274325749922,
|
|
"loss": 5.499,
|
|
"mean_token_accuracy": 0.17246012687683104,
|
|
"num_tokens": 11757945.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.608647632598877,
|
|
"epoch": 0.5275238280490177,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004977235016610011,
|
|
"loss": 5.3704,
|
|
"mean_token_accuracy": 0.17345735132694245,
|
|
"num_tokens": 11766333.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.605227470397949,
|
|
"epoch": 0.5279128574207352,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004977195673675353,
|
|
"loss": 5.4179,
|
|
"mean_token_accuracy": 0.16838252991437913,
|
|
"num_tokens": 11775041.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.657201194763184,
|
|
"epoch": 0.5283018867924528,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004977156296946545,
|
|
"loss": 5.4054,
|
|
"mean_token_accuracy": 0.16645608246326446,
|
|
"num_tokens": 11783958.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.630903053283691,
|
|
"epoch": 0.5286909161641704,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004977116886424187,
|
|
"loss": 5.4613,
|
|
"mean_token_accuracy": 0.16542300283908845,
|
|
"num_tokens": 11792174.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.639910507202148,
|
|
"epoch": 0.529079945535888,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004977077442108873,
|
|
"loss": 5.3807,
|
|
"mean_token_accuracy": 0.17330700159072876,
|
|
"num_tokens": 11800514.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.6459287166595455,
|
|
"epoch": 0.5294689749076055,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004977037964001204,
|
|
"loss": 5.3029,
|
|
"mean_token_accuracy": 0.18221512138843537,
|
|
"num_tokens": 11808918.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.70598258972168,
|
|
"epoch": 0.5298580042793231,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000497699845210178,
|
|
"loss": 5.5537,
|
|
"mean_token_accuracy": 0.16276264637708665,
|
|
"num_tokens": 11818014.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.63267674446106,
|
|
"epoch": 0.5302470336510406,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004976958906411197,
|
|
"loss": 5.4684,
|
|
"mean_token_accuracy": 0.1639823779463768,
|
|
"num_tokens": 11826477.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.735885572433472,
|
|
"epoch": 0.5306360630227582,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004976919326930059,
|
|
"loss": 5.5319,
|
|
"mean_token_accuracy": 0.16284382790327073,
|
|
"num_tokens": 11835513.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.752363300323486,
|
|
"epoch": 0.5310250923944758,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004976879713658964,
|
|
"loss": 5.5148,
|
|
"mean_token_accuracy": 0.16687608808279036,
|
|
"num_tokens": 11844495.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.661299991607666,
|
|
"epoch": 0.5314141217661933,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004976840066598514,
|
|
"loss": 5.4558,
|
|
"mean_token_accuracy": 0.16549880653619767,
|
|
"num_tokens": 11853013.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.566314268112182,
|
|
"epoch": 0.5318031511379109,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004976800385749309,
|
|
"loss": 5.2665,
|
|
"mean_token_accuracy": 0.17524262219667436,
|
|
"num_tokens": 11861899.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.569824314117431,
|
|
"epoch": 0.5321921805096285,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004976760671111954,
|
|
"loss": 5.3419,
|
|
"mean_token_accuracy": 0.17819802314043046,
|
|
"num_tokens": 11870836.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.630034446716309,
|
|
"epoch": 0.532581209881346,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000497672092268705,
|
|
"loss": 5.3942,
|
|
"mean_token_accuracy": 0.16372393667697907,
|
|
"num_tokens": 11879363.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.677461814880371,
|
|
"epoch": 0.5329702392530636,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049766811404752,
|
|
"loss": 5.4007,
|
|
"mean_token_accuracy": 0.16805416345596313,
|
|
"num_tokens": 11887696.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.633221387863159,
|
|
"epoch": 0.5333592686247812,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004976641324477008,
|
|
"loss": 5.4031,
|
|
"mean_token_accuracy": 0.1713561162352562,
|
|
"num_tokens": 11895867.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.662677812576294,
|
|
"epoch": 0.5337482979964987,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004976601474693077,
|
|
"loss": 5.3389,
|
|
"mean_token_accuracy": 0.1717140942811966,
|
|
"num_tokens": 11904537.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.731931447982788,
|
|
"epoch": 0.5341373273682163,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004976561591124014,
|
|
"loss": 5.4686,
|
|
"mean_token_accuracy": 0.17363298535346985,
|
|
"num_tokens": 11913097.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.578159427642822,
|
|
"epoch": 0.5345263567399339,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004976521673770421,
|
|
"loss": 5.2752,
|
|
"mean_token_accuracy": 0.17268597036600114,
|
|
"num_tokens": 11921852.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.627079343795776,
|
|
"epoch": 0.5349153861116515,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004976481722632907,
|
|
"loss": 5.4598,
|
|
"mean_token_accuracy": 0.1650264471769333,
|
|
"num_tokens": 11930836.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.710422945022583,
|
|
"epoch": 0.535304415483369,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004976441737712076,
|
|
"loss": 5.5305,
|
|
"mean_token_accuracy": 0.16050295382738114,
|
|
"num_tokens": 11940069.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.734521436691284,
|
|
"epoch": 0.5356934448550865,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004976401719008536,
|
|
"loss": 5.4401,
|
|
"mean_token_accuracy": 0.17020536661148072,
|
|
"num_tokens": 11948525.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.626850891113281,
|
|
"epoch": 0.5360824742268041,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004976361666522893,
|
|
"loss": 5.4475,
|
|
"mean_token_accuracy": 0.1688174158334732,
|
|
"num_tokens": 11956912.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.539887142181397,
|
|
"epoch": 0.5364715035985217,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004976321580255755,
|
|
"loss": 5.5336,
|
|
"mean_token_accuracy": 0.16634575575590133,
|
|
"num_tokens": 11965782.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.706142091751099,
|
|
"epoch": 0.5368605329702393,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004976281460207731,
|
|
"loss": 5.447,
|
|
"mean_token_accuracy": 0.1684982642531395,
|
|
"num_tokens": 11974889.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.7341108322143555,
|
|
"epoch": 0.5372495623419569,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000497624130637943,
|
|
"loss": 5.4409,
|
|
"mean_token_accuracy": 0.16870606541633607,
|
|
"num_tokens": 11983507.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.570401287078857,
|
|
"epoch": 0.5376385917136743,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000497620111877146,
|
|
"loss": 5.3142,
|
|
"mean_token_accuracy": 0.17675935626029968,
|
|
"num_tokens": 11991646.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.537765407562256,
|
|
"epoch": 0.5380276210853919,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004976160897384431,
|
|
"loss": 5.3447,
|
|
"mean_token_accuracy": 0.17250619679689408,
|
|
"num_tokens": 12000223.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.665034008026123,
|
|
"epoch": 0.5384166504571095,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004976120642218955,
|
|
"loss": 5.4525,
|
|
"mean_token_accuracy": 0.17188968807458876,
|
|
"num_tokens": 12009012.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.750792694091797,
|
|
"epoch": 0.5388056798288271,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000497608035327564,
|
|
"loss": 5.49,
|
|
"mean_token_accuracy": 0.16075368374586105,
|
|
"num_tokens": 12018001.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.598563003540039,
|
|
"epoch": 0.5391947092005447,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049760400305551,
|
|
"loss": 5.3158,
|
|
"mean_token_accuracy": 0.18070554882287979,
|
|
"num_tokens": 12025943.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.616814088821411,
|
|
"epoch": 0.5395837385722622,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004975999674057944,
|
|
"loss": 5.3605,
|
|
"mean_token_accuracy": 0.17010299861431122,
|
|
"num_tokens": 12035073.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.7316052436828615,
|
|
"epoch": 0.5399727679439797,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004975959283784787,
|
|
"loss": 5.5468,
|
|
"mean_token_accuracy": 0.1576745942234993,
|
|
"num_tokens": 12043698.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.634044551849366,
|
|
"epoch": 0.5403617973156973,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004975918859736241,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.17379543036222458,
|
|
"num_tokens": 12052247.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.625600290298462,
|
|
"epoch": 0.5407508266874149,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004975878401912919,
|
|
"loss": 5.4427,
|
|
"mean_token_accuracy": 0.17108741998672486,
|
|
"num_tokens": 12061187.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.646617078781128,
|
|
"epoch": 0.5411398560591325,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004975837910315436,
|
|
"loss": 5.385,
|
|
"mean_token_accuracy": 0.17147762924432755,
|
|
"num_tokens": 12070121.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.657769870758057,
|
|
"epoch": 0.54152888543085,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004975797384944405,
|
|
"loss": 5.339,
|
|
"mean_token_accuracy": 0.18109859973192216,
|
|
"num_tokens": 12078578.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.591638612747192,
|
|
"epoch": 0.5419179148025676,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000497575682580044,
|
|
"loss": 5.4918,
|
|
"mean_token_accuracy": 0.17290250658988954,
|
|
"num_tokens": 12087029.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.745116949081421,
|
|
"epoch": 0.5423069441742852,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000497571623288416,
|
|
"loss": 5.4636,
|
|
"mean_token_accuracy": 0.16208516657352448,
|
|
"num_tokens": 12096105.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.79583044052124,
|
|
"epoch": 0.5426959735460027,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004975675606196177,
|
|
"loss": 5.5419,
|
|
"mean_token_accuracy": 0.1621698871254921,
|
|
"num_tokens": 12105098.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.647582006454468,
|
|
"epoch": 0.5430850029177203,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000497563494573711,
|
|
"loss": 5.3379,
|
|
"mean_token_accuracy": 0.17473508417606354,
|
|
"num_tokens": 12112894.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.59762806892395,
|
|
"epoch": 0.5434740322894378,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004975594251507575,
|
|
"loss": 5.4683,
|
|
"mean_token_accuracy": 0.17303581088781356,
|
|
"num_tokens": 12121457.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.679516887664795,
|
|
"epoch": 0.5438630616611554,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000497555352350819,
|
|
"loss": 5.3393,
|
|
"mean_token_accuracy": 0.17706256955862046,
|
|
"num_tokens": 12129998.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.699892997741699,
|
|
"epoch": 0.544252091032873,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004975512761739572,
|
|
"loss": 5.4123,
|
|
"mean_token_accuracy": 0.16763640493154525,
|
|
"num_tokens": 12137861.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.611218214035034,
|
|
"epoch": 0.5446411204045906,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000497547196620234,
|
|
"loss": 5.4202,
|
|
"mean_token_accuracy": 0.16736047565937043,
|
|
"num_tokens": 12146294.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.6113814353942875,
|
|
"epoch": 0.5450301497763081,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004975431136897114,
|
|
"loss": 5.4225,
|
|
"mean_token_accuracy": 0.17288087606430053,
|
|
"num_tokens": 12155642.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.781958055496216,
|
|
"epoch": 0.5454191791480256,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004975390273824512,
|
|
"loss": 5.5223,
|
|
"mean_token_accuracy": 0.16702488213777542,
|
|
"num_tokens": 12164709.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.67509708404541,
|
|
"epoch": 0.5458082085197432,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004975349376985155,
|
|
"loss": 5.3927,
|
|
"mean_token_accuracy": 0.1752987876534462,
|
|
"num_tokens": 12173591.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.636157035827637,
|
|
"epoch": 0.5461972378914608,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004975308446379663,
|
|
"loss": 5.4468,
|
|
"mean_token_accuracy": 0.16483746767044066,
|
|
"num_tokens": 12182050.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.717999887466431,
|
|
"epoch": 0.5465862672631784,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004975267482008657,
|
|
"loss": 5.4951,
|
|
"mean_token_accuracy": 0.16928022503852844,
|
|
"num_tokens": 12190870.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.554836845397949,
|
|
"epoch": 0.546975296634896,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000497522648387276,
|
|
"loss": 5.2444,
|
|
"mean_token_accuracy": 0.1796307697892189,
|
|
"num_tokens": 12199624.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.671341228485107,
|
|
"epoch": 0.5473643260066134,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004975185451972592,
|
|
"loss": 5.4989,
|
|
"mean_token_accuracy": 0.16450446844100952,
|
|
"num_tokens": 12208087.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.74378662109375,
|
|
"epoch": 0.547753355378331,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004975144386308776,
|
|
"loss": 5.4587,
|
|
"mean_token_accuracy": 0.16939086616039276,
|
|
"num_tokens": 12216531.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.673602485656739,
|
|
"epoch": 0.5481423847500486,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004975103286881936,
|
|
"loss": 5.4118,
|
|
"mean_token_accuracy": 0.17153862565755845,
|
|
"num_tokens": 12225094.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.593559598922729,
|
|
"epoch": 0.5485314141217662,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004975062153692696,
|
|
"loss": 5.4089,
|
|
"mean_token_accuracy": 0.1735567644238472,
|
|
"num_tokens": 12233824.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.611363554000855,
|
|
"epoch": 0.5489204434934838,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004975020986741678,
|
|
"loss": 5.2983,
|
|
"mean_token_accuracy": 0.17281068861484528,
|
|
"num_tokens": 12242923.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.636492395401001,
|
|
"epoch": 0.5493094728652014,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004974979786029509,
|
|
"loss": 5.3389,
|
|
"mean_token_accuracy": 0.1716264933347702,
|
|
"num_tokens": 12251963.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.64126033782959,
|
|
"epoch": 0.5496985022369189,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004974938551556814,
|
|
"loss": 5.4726,
|
|
"mean_token_accuracy": 0.16598251461982727,
|
|
"num_tokens": 12260347.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.616513633728028,
|
|
"epoch": 0.5500875316086364,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004974897283324217,
|
|
"loss": 5.5112,
|
|
"mean_token_accuracy": 0.16583890169858934,
|
|
"num_tokens": 12269156.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.669668912887573,
|
|
"epoch": 0.550476560980354,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004974855981332343,
|
|
"loss": 5.4022,
|
|
"mean_token_accuracy": 0.1681751862168312,
|
|
"num_tokens": 12277636.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.690270805358887,
|
|
"epoch": 0.5508655903520716,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004974814645581823,
|
|
"loss": 5.3897,
|
|
"mean_token_accuracy": 0.1771720752120018,
|
|
"num_tokens": 12286027.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.684526968002319,
|
|
"epoch": 0.5512546197237892,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004974773276073282,
|
|
"loss": 5.5215,
|
|
"mean_token_accuracy": 0.16352718994021415,
|
|
"num_tokens": 12295085.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.726123046875,
|
|
"epoch": 0.5516436490955067,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004974731872807347,
|
|
"loss": 5.4854,
|
|
"mean_token_accuracy": 0.16884510070085526,
|
|
"num_tokens": 12304275.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.619599103927612,
|
|
"epoch": 0.5520326784672243,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004974690435784647,
|
|
"loss": 5.2908,
|
|
"mean_token_accuracy": 0.18858238458633422,
|
|
"num_tokens": 12312841.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.610299396514892,
|
|
"epoch": 0.5524217078389418,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004974648965005811,
|
|
"loss": 5.4071,
|
|
"mean_token_accuracy": 0.16392343640327453,
|
|
"num_tokens": 12322133.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.631564426422119,
|
|
"epoch": 0.5528107372106594,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004974607460471466,
|
|
"loss": 5.3802,
|
|
"mean_token_accuracy": 0.1664992719888687,
|
|
"num_tokens": 12330502.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.684219026565552,
|
|
"epoch": 0.553199766582377,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004974565922182246,
|
|
"loss": 5.4068,
|
|
"mean_token_accuracy": 0.16999222934246064,
|
|
"num_tokens": 12338899.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.597611713409424,
|
|
"epoch": 0.5535887959540945,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004974524350138777,
|
|
"loss": 5.3952,
|
|
"mean_token_accuracy": 0.17126004546880721,
|
|
"num_tokens": 12348299.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.651516532897949,
|
|
"epoch": 0.5539778253258121,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004974482744341693,
|
|
"loss": 5.4134,
|
|
"mean_token_accuracy": 0.17356518805027008,
|
|
"num_tokens": 12356582.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.7098452091217045,
|
|
"epoch": 0.5543668546975297,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004974441104791624,
|
|
"loss": 5.5207,
|
|
"mean_token_accuracy": 0.15875308513641356,
|
|
"num_tokens": 12366209.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.678668260574341,
|
|
"epoch": 0.5547558840692473,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004974399431489201,
|
|
"loss": 5.4401,
|
|
"mean_token_accuracy": 0.16072257608175278,
|
|
"num_tokens": 12374777.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.606429815292358,
|
|
"epoch": 0.5551449134409648,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004974357724435057,
|
|
"loss": 5.4001,
|
|
"mean_token_accuracy": 0.16457735896110534,
|
|
"num_tokens": 12384405.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.732188034057617,
|
|
"epoch": 0.5555339428126823,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004974315983629825,
|
|
"loss": 5.4806,
|
|
"mean_token_accuracy": 0.1655801698565483,
|
|
"num_tokens": 12393464.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.757658910751343,
|
|
"epoch": 0.5559229721843999,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004974274209074139,
|
|
"loss": 5.5011,
|
|
"mean_token_accuracy": 0.16627497524023055,
|
|
"num_tokens": 12401917.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.531997394561768,
|
|
"epoch": 0.5563120015561175,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004974232400768632,
|
|
"loss": 5.2958,
|
|
"mean_token_accuracy": 0.17810201048851013,
|
|
"num_tokens": 12410928.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.60371584892273,
|
|
"epoch": 0.5567010309278351,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004974190558713939,
|
|
"loss": 5.3569,
|
|
"mean_token_accuracy": 0.17425443083047867,
|
|
"num_tokens": 12419747.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.684228324890137,
|
|
"epoch": 0.5570900602995527,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004974148682910694,
|
|
"loss": 5.3857,
|
|
"mean_token_accuracy": 0.17257120013236998,
|
|
"num_tokens": 12428608.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.744918441772461,
|
|
"epoch": 0.5574790896712701,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004974106773359533,
|
|
"loss": 5.4851,
|
|
"mean_token_accuracy": 0.1652093231678009,
|
|
"num_tokens": 12437101.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.602647924423218,
|
|
"epoch": 0.5578681190429877,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004974064830061091,
|
|
"loss": 5.4446,
|
|
"mean_token_accuracy": 0.16767866313457488,
|
|
"num_tokens": 12446813.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.681476163864136,
|
|
"epoch": 0.5582571484147053,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004974022853016006,
|
|
"loss": 5.3904,
|
|
"mean_token_accuracy": 0.17777819335460662,
|
|
"num_tokens": 12455931.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.664216613769531,
|
|
"epoch": 0.5586461777864229,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004973980842224913,
|
|
"loss": 5.3739,
|
|
"mean_token_accuracy": 0.17391000241041182,
|
|
"num_tokens": 12463586.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.597675848007202,
|
|
"epoch": 0.5590352071581405,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004973938797688452,
|
|
"loss": 5.3906,
|
|
"mean_token_accuracy": 0.17691944986581803,
|
|
"num_tokens": 12472063.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.641227197647095,
|
|
"epoch": 0.559424236529858,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004973896719407259,
|
|
"loss": 5.406,
|
|
"mean_token_accuracy": 0.1692581966519356,
|
|
"num_tokens": 12480763.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.675350046157837,
|
|
"epoch": 0.5598132659015755,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004973854607381972,
|
|
"loss": 5.3448,
|
|
"mean_token_accuracy": 0.1801315128803253,
|
|
"num_tokens": 12488757.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.569622135162353,
|
|
"epoch": 0.5602022952732931,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004973812461613232,
|
|
"loss": 5.4064,
|
|
"mean_token_accuracy": 0.17317397892475128,
|
|
"num_tokens": 12497030.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.64783296585083,
|
|
"epoch": 0.5605913246450107,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004973770282101677,
|
|
"loss": 5.4266,
|
|
"mean_token_accuracy": 0.16664355844259263,
|
|
"num_tokens": 12506067.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.651951456069947,
|
|
"epoch": 0.5609803540167283,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004973728068847947,
|
|
"loss": 5.3611,
|
|
"mean_token_accuracy": 0.16840779185295104,
|
|
"num_tokens": 12514246.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.657790565490723,
|
|
"epoch": 0.5613693833884458,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004973685821852684,
|
|
"loss": 5.4019,
|
|
"mean_token_accuracy": 0.171301032602787,
|
|
"num_tokens": 12523523.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.682505464553833,
|
|
"epoch": 0.5617584127601634,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004973643541116528,
|
|
"loss": 5.3957,
|
|
"mean_token_accuracy": 0.17163693606853486,
|
|
"num_tokens": 12532142.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.6058187007904055,
|
|
"epoch": 0.562147442131881,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000497360122664012,
|
|
"loss": 5.4397,
|
|
"mean_token_accuracy": 0.17028565406799318,
|
|
"num_tokens": 12540647.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.576866817474365,
|
|
"epoch": 0.5625364715035985,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004973558878424104,
|
|
"loss": 5.3439,
|
|
"mean_token_accuracy": 0.17291397452354432,
|
|
"num_tokens": 12549010.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.611696720123291,
|
|
"epoch": 0.5629255008753161,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004973516496469119,
|
|
"loss": 5.3486,
|
|
"mean_token_accuracy": 0.17193022966384888,
|
|
"num_tokens": 12557428.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.569612216949463,
|
|
"epoch": 0.5633145302470336,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004973474080775811,
|
|
"loss": 5.29,
|
|
"mean_token_accuracy": 0.16920455694198608,
|
|
"num_tokens": 12566610.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.57372350692749,
|
|
"epoch": 0.5637035596187512,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004973431631344824,
|
|
"loss": 5.4097,
|
|
"mean_token_accuracy": 0.17289151400327682,
|
|
"num_tokens": 12576016.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.51690640449524,
|
|
"epoch": 0.5640925889904688,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049733891481768,
|
|
"loss": 5.2215,
|
|
"mean_token_accuracy": 0.184297177195549,
|
|
"num_tokens": 12584033.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.668150424957275,
|
|
"epoch": 0.5644816183621864,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004973346631272384,
|
|
"loss": 5.3633,
|
|
"mean_token_accuracy": 0.17918503582477568,
|
|
"num_tokens": 12592784.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.647518110275269,
|
|
"epoch": 0.5648706477339039,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004973304080632222,
|
|
"loss": 5.5028,
|
|
"mean_token_accuracy": 0.16309709548950196,
|
|
"num_tokens": 12601259.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.603525066375733,
|
|
"epoch": 0.5652596771056215,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000497326149625696,
|
|
"loss": 5.3313,
|
|
"mean_token_accuracy": 0.16406858563423157,
|
|
"num_tokens": 12610264.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.650942134857178,
|
|
"epoch": 0.565648706477339,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004973218878147244,
|
|
"loss": 5.3415,
|
|
"mean_token_accuracy": 0.17269101589918137,
|
|
"num_tokens": 12618817.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.611858224868774,
|
|
"epoch": 0.5660377358490566,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004973176226303719,
|
|
"loss": 5.3587,
|
|
"mean_token_accuracy": 0.1739836424589157,
|
|
"num_tokens": 12627224.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.689392852783203,
|
|
"epoch": 0.5664267652207742,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004973133540727033,
|
|
"loss": 5.3732,
|
|
"mean_token_accuracy": 0.18202139139175416,
|
|
"num_tokens": 12635020.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.637719821929932,
|
|
"epoch": 0.5668157945924918,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004973090821417835,
|
|
"loss": 5.4898,
|
|
"mean_token_accuracy": 0.16954613626003265,
|
|
"num_tokens": 12643821.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.730007171630859,
|
|
"epoch": 0.5672048239642093,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004973048068376772,
|
|
"loss": 5.4368,
|
|
"mean_token_accuracy": 0.16947726905345917,
|
|
"num_tokens": 12652091.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.700078010559082,
|
|
"epoch": 0.5675938533359268,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004973005281604492,
|
|
"loss": 5.4492,
|
|
"mean_token_accuracy": 0.17107911556959152,
|
|
"num_tokens": 12661389.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.667845392227173,
|
|
"epoch": 0.5679828827076444,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004972962461101646,
|
|
"loss": 5.4683,
|
|
"mean_token_accuracy": 0.17340354472398758,
|
|
"num_tokens": 12670361.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.5832093238830565,
|
|
"epoch": 0.568371912079362,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004972919606868883,
|
|
"loss": 5.2721,
|
|
"mean_token_accuracy": 0.17934520542621613,
|
|
"num_tokens": 12677765.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.60428409576416,
|
|
"epoch": 0.5687609414510796,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004972876718906852,
|
|
"loss": 5.3411,
|
|
"mean_token_accuracy": 0.18018452525138856,
|
|
"num_tokens": 12686461.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.603921890258789,
|
|
"epoch": 0.5691499708227972,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004972833797216206,
|
|
"loss": 5.341,
|
|
"mean_token_accuracy": 0.1742023929953575,
|
|
"num_tokens": 12694663.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.609700298309326,
|
|
"epoch": 0.5695390001945146,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004972790841797595,
|
|
"loss": 5.4034,
|
|
"mean_token_accuracy": 0.17165356129407883,
|
|
"num_tokens": 12703659.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.626158809661865,
|
|
"epoch": 0.5699280295662322,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000497274785265167,
|
|
"loss": 5.3696,
|
|
"mean_token_accuracy": 0.17114897072315216,
|
|
"num_tokens": 12711402.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.634340906143189,
|
|
"epoch": 0.5703170589379498,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004972704829779086,
|
|
"loss": 5.4383,
|
|
"mean_token_accuracy": 0.16824499964714051,
|
|
"num_tokens": 12720500.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.682785940170288,
|
|
"epoch": 0.5707060883096674,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004972661773180492,
|
|
"loss": 5.4586,
|
|
"mean_token_accuracy": 0.166053406894207,
|
|
"num_tokens": 12729325.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.658143758773804,
|
|
"epoch": 0.571095117681385,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004972618682856545,
|
|
"loss": 5.493,
|
|
"mean_token_accuracy": 0.16307419836521148,
|
|
"num_tokens": 12738573.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.609912347793579,
|
|
"epoch": 0.5714841470531025,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004972575558807896,
|
|
"loss": 5.3501,
|
|
"mean_token_accuracy": 0.17531950622797013,
|
|
"num_tokens": 12746608.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.625151872634888,
|
|
"epoch": 0.57187317642482,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004972532401035201,
|
|
"loss": 5.3221,
|
|
"mean_token_accuracy": 0.17489213049411773,
|
|
"num_tokens": 12754724.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.586040687561035,
|
|
"epoch": 0.5722622057965376,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004972489209539114,
|
|
"loss": 5.4132,
|
|
"mean_token_accuracy": 0.1737084284424782,
|
|
"num_tokens": 12762654.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.6631756782531735,
|
|
"epoch": 0.5726512351682552,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004972445984320292,
|
|
"loss": 5.4233,
|
|
"mean_token_accuracy": 0.16429337859153748,
|
|
"num_tokens": 12771615.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.741293478012085,
|
|
"epoch": 0.5730402645399728,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004972402725379388,
|
|
"loss": 5.5056,
|
|
"mean_token_accuracy": 0.16832784414291382,
|
|
"num_tokens": 12780991.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.674177169799805,
|
|
"epoch": 0.5734292939116903,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000497235943271706,
|
|
"loss": 5.361,
|
|
"mean_token_accuracy": 0.1768481969833374,
|
|
"num_tokens": 12789402.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.60377950668335,
|
|
"epoch": 0.5738183232834079,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004972316106333966,
|
|
"loss": 5.346,
|
|
"mean_token_accuracy": 0.17487386167049407,
|
|
"num_tokens": 12798095.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.687059211730957,
|
|
"epoch": 0.5742073526551255,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004972272746230761,
|
|
"loss": 5.4274,
|
|
"mean_token_accuracy": 0.1711514785885811,
|
|
"num_tokens": 12806976.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.642342758178711,
|
|
"epoch": 0.574596382026843,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004972229352408104,
|
|
"loss": 5.3528,
|
|
"mean_token_accuracy": 0.1776340425014496,
|
|
"num_tokens": 12815228.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.621855211257935,
|
|
"epoch": 0.5749854113985606,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004972185924866655,
|
|
"loss": 5.4484,
|
|
"mean_token_accuracy": 0.16927571296691896,
|
|
"num_tokens": 12823674.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.6601160049438475,
|
|
"epoch": 0.5753744407702781,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004972142463607071,
|
|
"loss": 5.5345,
|
|
"mean_token_accuracy": 0.16644566655158996,
|
|
"num_tokens": 12832810.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.722142553329467,
|
|
"epoch": 0.5757634701419957,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004972098968630012,
|
|
"loss": 5.475,
|
|
"mean_token_accuracy": 0.16008357405662538,
|
|
"num_tokens": 12841430.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.658217716217041,
|
|
"epoch": 0.5761524995137133,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004972055439936137,
|
|
"loss": 5.3609,
|
|
"mean_token_accuracy": 0.17402588129043578,
|
|
"num_tokens": 12850539.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.650355625152588,
|
|
"epoch": 0.5765415288854309,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004972011877526109,
|
|
"loss": 5.4717,
|
|
"mean_token_accuracy": 0.16799556314945222,
|
|
"num_tokens": 12859066.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.601924276351928,
|
|
"epoch": 0.5769305582571485,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004971968281400587,
|
|
"loss": 5.3651,
|
|
"mean_token_accuracy": 0.17659385800361632,
|
|
"num_tokens": 12867603.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.548606729507446,
|
|
"epoch": 0.5773195876288659,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004971924651560233,
|
|
"loss": 5.2208,
|
|
"mean_token_accuracy": 0.18172995299100875,
|
|
"num_tokens": 12875950.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.655488729476929,
|
|
"epoch": 0.5777086170005835,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004971880988005709,
|
|
"loss": 5.4785,
|
|
"mean_token_accuracy": 0.16646626889705657,
|
|
"num_tokens": 12884154.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.691912269592285,
|
|
"epoch": 0.5780976463723011,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004971837290737677,
|
|
"loss": 5.5349,
|
|
"mean_token_accuracy": 0.1615962192416191,
|
|
"num_tokens": 12892515.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.619197607040405,
|
|
"epoch": 0.5784866757440187,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004971793559756801,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.17720565050840378,
|
|
"num_tokens": 12900919.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.578056859970093,
|
|
"epoch": 0.5788757051157363,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004971749795063744,
|
|
"loss": 5.3283,
|
|
"mean_token_accuracy": 0.18330039083957672,
|
|
"num_tokens": 12909338.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.694128847122192,
|
|
"epoch": 0.5792647344874537,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000497170599665917,
|
|
"loss": 5.4366,
|
|
"mean_token_accuracy": 0.16502223312854766,
|
|
"num_tokens": 12918118.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.669711685180664,
|
|
"epoch": 0.5796537638591713,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004971662164543743,
|
|
"loss": 5.466,
|
|
"mean_token_accuracy": 0.1676119551062584,
|
|
"num_tokens": 12926878.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.607919597625733,
|
|
"epoch": 0.5800427932308889,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004971618298718131,
|
|
"loss": 5.3358,
|
|
"mean_token_accuracy": 0.17631906270980835,
|
|
"num_tokens": 12934869.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.546912050247192,
|
|
"epoch": 0.5804318226026065,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004971574399182995,
|
|
"loss": 5.394,
|
|
"mean_token_accuracy": 0.16879130452871322,
|
|
"num_tokens": 12944281.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.6653515815734865,
|
|
"epoch": 0.5808208519743241,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004971530465939005,
|
|
"loss": 5.4149,
|
|
"mean_token_accuracy": 0.16727388203144072,
|
|
"num_tokens": 12953281.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.673875236511231,
|
|
"epoch": 0.5812098813460417,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004971486498986825,
|
|
"loss": 5.3931,
|
|
"mean_token_accuracy": 0.17328910380601883,
|
|
"num_tokens": 12962136.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.563898420333862,
|
|
"epoch": 0.5815989107177592,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004971442498327124,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.1756136193871498,
|
|
"num_tokens": 12971288.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.5823845863342285,
|
|
"epoch": 0.5819879400894767,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004971398463960568,
|
|
"loss": 5.3155,
|
|
"mean_token_accuracy": 0.17655461132526398,
|
|
"num_tokens": 12979836.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.6288878440856935,
|
|
"epoch": 0.5823769694611943,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004971354395887827,
|
|
"loss": 5.3323,
|
|
"mean_token_accuracy": 0.18374994695186614,
|
|
"num_tokens": 12988233.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.601915407180786,
|
|
"epoch": 0.5827659988329119,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004971310294109569,
|
|
"loss": 5.3405,
|
|
"mean_token_accuracy": 0.17222541123628615,
|
|
"num_tokens": 12997077.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.580870151519775,
|
|
"epoch": 0.5831550282046295,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004971266158626461,
|
|
"loss": 5.375,
|
|
"mean_token_accuracy": 0.17703234851360322,
|
|
"num_tokens": 13005058.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.693687486648559,
|
|
"epoch": 0.583544057576347,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004971221989439177,
|
|
"loss": 5.4284,
|
|
"mean_token_accuracy": 0.17557696402072906,
|
|
"num_tokens": 13013347.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.691101169586181,
|
|
"epoch": 0.5839330869480646,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004971177786548384,
|
|
"loss": 5.3588,
|
|
"mean_token_accuracy": 0.17577131390571593,
|
|
"num_tokens": 13021555.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.6124955177307125,
|
|
"epoch": 0.5843221163197821,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004971133549954753,
|
|
"loss": 5.4529,
|
|
"mean_token_accuracy": 0.16763664335012435,
|
|
"num_tokens": 13029817.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.641552066802978,
|
|
"epoch": 0.5847111456914997,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004971089279658954,
|
|
"loss": 5.4125,
|
|
"mean_token_accuracy": 0.1687588334083557,
|
|
"num_tokens": 13038119.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.628887176513672,
|
|
"epoch": 0.5851001750632173,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004971044975661663,
|
|
"loss": 5.3371,
|
|
"mean_token_accuracy": 0.1777610197663307,
|
|
"num_tokens": 13047004.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.627340459823609,
|
|
"epoch": 0.5854892044349348,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004971000637963549,
|
|
"loss": 5.3279,
|
|
"mean_token_accuracy": 0.17624397277832032,
|
|
"num_tokens": 13055045.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.672088670730591,
|
|
"epoch": 0.5858782338066524,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004970956266565285,
|
|
"loss": 5.4151,
|
|
"mean_token_accuracy": 0.17066693305969238,
|
|
"num_tokens": 13064535.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.67555799484253,
|
|
"epoch": 0.58626726317837,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004970911861467544,
|
|
"loss": 5.478,
|
|
"mean_token_accuracy": 0.16494464576244355,
|
|
"num_tokens": 13073089.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.606437253952026,
|
|
"epoch": 0.5866562925500876,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004970867422671002,
|
|
"loss": 5.4175,
|
|
"mean_token_accuracy": 0.17264879643917083,
|
|
"num_tokens": 13082161.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.583182430267334,
|
|
"epoch": 0.5870453219218051,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000497082295017633,
|
|
"loss": 5.2945,
|
|
"mean_token_accuracy": 0.1763348251581192,
|
|
"num_tokens": 13090632.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.688999652862549,
|
|
"epoch": 0.5874343512935226,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004970778443984206,
|
|
"loss": 5.3461,
|
|
"mean_token_accuracy": 0.17180395275354385,
|
|
"num_tokens": 13098825.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.677446794509888,
|
|
"epoch": 0.5878233806652402,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004970733904095303,
|
|
"loss": 5.4275,
|
|
"mean_token_accuracy": 0.1757938951253891,
|
|
"num_tokens": 13107059.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.673526430130005,
|
|
"epoch": 0.5882124100369578,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004970689330510298,
|
|
"loss": 5.4427,
|
|
"mean_token_accuracy": 0.16199443265795707,
|
|
"num_tokens": 13116783.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.668778133392334,
|
|
"epoch": 0.5886014394086754,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004970644723229868,
|
|
"loss": 5.3879,
|
|
"mean_token_accuracy": 0.1710350438952446,
|
|
"num_tokens": 13124998.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.68775486946106,
|
|
"epoch": 0.588990468780393,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004970600082254687,
|
|
"loss": 5.4419,
|
|
"mean_token_accuracy": 0.17209930419921876,
|
|
"num_tokens": 13134507.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.571299934387207,
|
|
"epoch": 0.5893794981521104,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004970555407585436,
|
|
"loss": 5.351,
|
|
"mean_token_accuracy": 0.17083754092454911,
|
|
"num_tokens": 13143682.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.632481050491333,
|
|
"epoch": 0.589768527523828,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000497051069922279,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.17508520185947418,
|
|
"num_tokens": 13151924.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.6247814178466795,
|
|
"epoch": 0.5901575568955456,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004970465957167429,
|
|
"loss": 5.3596,
|
|
"mean_token_accuracy": 0.17801107764244078,
|
|
"num_tokens": 13160853.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.689409399032593,
|
|
"epoch": 0.5905465862672632,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000497042118142003,
|
|
"loss": 5.4113,
|
|
"mean_token_accuracy": 0.18122035413980483,
|
|
"num_tokens": 13168993.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.616657495498657,
|
|
"epoch": 0.5909356156389808,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004970376371981275,
|
|
"loss": 5.3321,
|
|
"mean_token_accuracy": 0.17255890220403672,
|
|
"num_tokens": 13177266.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.6668929100036625,
|
|
"epoch": 0.5913246450106983,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004970331528851842,
|
|
"loss": 5.4032,
|
|
"mean_token_accuracy": 0.16720218807458878,
|
|
"num_tokens": 13185328.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.574369049072265,
|
|
"epoch": 0.5917136743824158,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004970286652032412,
|
|
"loss": 5.2853,
|
|
"mean_token_accuracy": 0.179343780875206,
|
|
"num_tokens": 13194502.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.617265462875366,
|
|
"epoch": 0.5921027037541334,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004970241741523667,
|
|
"loss": 5.4346,
|
|
"mean_token_accuracy": 0.16966428309679032,
|
|
"num_tokens": 13203745.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.68468222618103,
|
|
"epoch": 0.592491733125851,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004970196797326286,
|
|
"loss": 5.4815,
|
|
"mean_token_accuracy": 0.17039461582899093,
|
|
"num_tokens": 13213115.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.727099227905273,
|
|
"epoch": 0.5928807624975686,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004970151819440955,
|
|
"loss": 5.5165,
|
|
"mean_token_accuracy": 0.16375751942396163,
|
|
"num_tokens": 13222231.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.634699535369873,
|
|
"epoch": 0.5932697918692861,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004970106807868351,
|
|
"loss": 5.32,
|
|
"mean_token_accuracy": 0.169417604804039,
|
|
"num_tokens": 13231346.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.6288862228393555,
|
|
"epoch": 0.5936588212410037,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000497006176260916,
|
|
"loss": 5.4368,
|
|
"mean_token_accuracy": 0.16189672350883483,
|
|
"num_tokens": 13240436.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.679306936264038,
|
|
"epoch": 0.5940478506127213,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004970016683664068,
|
|
"loss": 5.3609,
|
|
"mean_token_accuracy": 0.17597733438014984,
|
|
"num_tokens": 13249501.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.523988151550293,
|
|
"epoch": 0.5944368799844388,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004969971571033754,
|
|
"loss": 5.2859,
|
|
"mean_token_accuracy": 0.17960336953401565,
|
|
"num_tokens": 13258322.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.615015316009521,
|
|
"epoch": 0.5948259093561564,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004969926424718906,
|
|
"loss": 5.4555,
|
|
"mean_token_accuracy": 0.1687053233385086,
|
|
"num_tokens": 13267418.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.734052753448486,
|
|
"epoch": 0.5952149387278739,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004969881244720207,
|
|
"loss": 5.4526,
|
|
"mean_token_accuracy": 0.16670702248811722,
|
|
"num_tokens": 13276243.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.564925861358643,
|
|
"epoch": 0.5956039680995915,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004969836031038343,
|
|
"loss": 5.3258,
|
|
"mean_token_accuracy": 0.17064776122570038,
|
|
"num_tokens": 13285611.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.642630195617675,
|
|
"epoch": 0.5959929974713091,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004969790783674002,
|
|
"loss": 5.4318,
|
|
"mean_token_accuracy": 0.16857724040746688,
|
|
"num_tokens": 13293949.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.599985218048095,
|
|
"epoch": 0.5963820268430267,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004969745502627868,
|
|
"loss": 5.3695,
|
|
"mean_token_accuracy": 0.1733701005578041,
|
|
"num_tokens": 13302593.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.637280797958374,
|
|
"epoch": 0.5967710562147442,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004969700187900629,
|
|
"loss": 5.4221,
|
|
"mean_token_accuracy": 0.16763776838779448,
|
|
"num_tokens": 13310947.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.662697505950928,
|
|
"epoch": 0.5971600855864618,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004969654839492973,
|
|
"loss": 5.3961,
|
|
"mean_token_accuracy": 0.16570455729961395,
|
|
"num_tokens": 13319233.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.699293565750122,
|
|
"epoch": 0.5975491149581793,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004969609457405588,
|
|
"loss": 5.4885,
|
|
"mean_token_accuracy": 0.16623993068933487,
|
|
"num_tokens": 13327979.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.654090070724488,
|
|
"epoch": 0.5979381443298969,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004969564041639163,
|
|
"loss": 5.4484,
|
|
"mean_token_accuracy": 0.16742156594991683,
|
|
"num_tokens": 13336699.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.631342220306396,
|
|
"epoch": 0.5983271737016145,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004969518592194386,
|
|
"loss": 5.3197,
|
|
"mean_token_accuracy": 0.17523644715547562,
|
|
"num_tokens": 13344688.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.580789470672608,
|
|
"epoch": 0.5987162030733321,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004969473109071946,
|
|
"loss": 5.3484,
|
|
"mean_token_accuracy": 0.1745481461286545,
|
|
"num_tokens": 13353442.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.679361963272095,
|
|
"epoch": 0.5991052324450497,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004969427592272535,
|
|
"loss": 5.4164,
|
|
"mean_token_accuracy": 0.1679532617330551,
|
|
"num_tokens": 13362388.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.566020679473877,
|
|
"epoch": 0.5994942618167671,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004969382041796843,
|
|
"loss": 5.2315,
|
|
"mean_token_accuracy": 0.1839941531419754,
|
|
"num_tokens": 13370796.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.542946290969849,
|
|
"epoch": 0.5998832911884847,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000496933645764556,
|
|
"loss": 5.3832,
|
|
"mean_token_accuracy": 0.17174575924873353,
|
|
"num_tokens": 13379733.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.56348443031311,
|
|
"epoch": 0.6002723205602023,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004969290839819381,
|
|
"loss": 5.2844,
|
|
"mean_token_accuracy": 0.1811760276556015,
|
|
"num_tokens": 13388278.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.702648782730103,
|
|
"epoch": 0.6006613499319199,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004969245188318994,
|
|
"loss": 5.4611,
|
|
"mean_token_accuracy": 0.16957978755235673,
|
|
"num_tokens": 13397461.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.591643238067627,
|
|
"epoch": 0.6010503793036375,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004969199503145093,
|
|
"loss": 5.3271,
|
|
"mean_token_accuracy": 0.17207611352205276,
|
|
"num_tokens": 13406087.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.621450567245484,
|
|
"epoch": 0.601439408675355,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004969153784298374,
|
|
"loss": 5.3155,
|
|
"mean_token_accuracy": 0.176591220498085,
|
|
"num_tokens": 13414760.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.573680639266968,
|
|
"epoch": 0.6018284380470725,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004969108031779527,
|
|
"loss": 5.3811,
|
|
"mean_token_accuracy": 0.16772215068340302,
|
|
"num_tokens": 13423574.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.587210941314697,
|
|
"epoch": 0.6022174674187901,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004969062245589247,
|
|
"loss": 5.3116,
|
|
"mean_token_accuracy": 0.17736600041389466,
|
|
"num_tokens": 13431799.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.611669635772705,
|
|
"epoch": 0.6026064967905077,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004969016425728231,
|
|
"loss": 5.3605,
|
|
"mean_token_accuracy": 0.172268782556057,
|
|
"num_tokens": 13440436.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.628948020935058,
|
|
"epoch": 0.6029955261622253,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004968970572197172,
|
|
"loss": 5.3231,
|
|
"mean_token_accuracy": 0.17577793151140214,
|
|
"num_tokens": 13449236.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.538338327407837,
|
|
"epoch": 0.6033845555339428,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004968924684996765,
|
|
"loss": 5.2873,
|
|
"mean_token_accuracy": 0.17633422166109086,
|
|
"num_tokens": 13457697.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.571261692047119,
|
|
"epoch": 0.6037735849056604,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000496887876412771,
|
|
"loss": 5.3902,
|
|
"mean_token_accuracy": 0.1738929882645607,
|
|
"num_tokens": 13465939.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.601704931259155,
|
|
"epoch": 0.6041626142773779,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004968832809590701,
|
|
"loss": 5.3144,
|
|
"mean_token_accuracy": 0.17881613671779634,
|
|
"num_tokens": 13474154.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.676210689544678,
|
|
"epoch": 0.6045516436490955,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004968786821386435,
|
|
"loss": 5.3248,
|
|
"mean_token_accuracy": 0.17638793736696243,
|
|
"num_tokens": 13482943.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.658667278289795,
|
|
"epoch": 0.6049406730208131,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004968740799515611,
|
|
"loss": 5.4678,
|
|
"mean_token_accuracy": 0.1693929485976696,
|
|
"num_tokens": 13491945.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.58949909210205,
|
|
"epoch": 0.6053297023925306,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004968694743978926,
|
|
"loss": 5.3955,
|
|
"mean_token_accuracy": 0.16946269124746322,
|
|
"num_tokens": 13501277.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.675701999664307,
|
|
"epoch": 0.6057187317642482,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004968648654777081,
|
|
"loss": 5.4113,
|
|
"mean_token_accuracy": 0.1756986677646637,
|
|
"num_tokens": 13509609.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.638581466674805,
|
|
"epoch": 0.6061077611359658,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004968602531910773,
|
|
"loss": 5.4149,
|
|
"mean_token_accuracy": 0.16470842212438583,
|
|
"num_tokens": 13518707.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.616470909118652,
|
|
"epoch": 0.6064967905076833,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004968556375380704,
|
|
"loss": 5.3725,
|
|
"mean_token_accuracy": 0.1771175593137741,
|
|
"num_tokens": 13527973.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.62437891960144,
|
|
"epoch": 0.6068858198794009,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004968510185187571,
|
|
"loss": 5.3276,
|
|
"mean_token_accuracy": 0.17454253733158112,
|
|
"num_tokens": 13536580.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.545835494995117,
|
|
"epoch": 0.6072748492511184,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000496846396133208,
|
|
"loss": 5.3476,
|
|
"mean_token_accuracy": 0.1735129788517952,
|
|
"num_tokens": 13544826.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.645089244842529,
|
|
"epoch": 0.607663878622836,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004968417703814928,
|
|
"loss": 5.4022,
|
|
"mean_token_accuracy": 0.1816071629524231,
|
|
"num_tokens": 13552821.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.557252311706543,
|
|
"epoch": 0.6080529079945536,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004968371412636818,
|
|
"loss": 5.2805,
|
|
"mean_token_accuracy": 0.1728936955332756,
|
|
"num_tokens": 13560827.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.5799144268035885,
|
|
"epoch": 0.6084419373662712,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004968325087798453,
|
|
"loss": 5.4428,
|
|
"mean_token_accuracy": 0.1673152282834053,
|
|
"num_tokens": 13569311.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.692161798477173,
|
|
"epoch": 0.6088309667379888,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004968278729300536,
|
|
"loss": 5.4276,
|
|
"mean_token_accuracy": 0.16603073477745056,
|
|
"num_tokens": 13579035.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.6686742305755615,
|
|
"epoch": 0.6092199961097062,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004968232337143769,
|
|
"loss": 5.3938,
|
|
"mean_token_accuracy": 0.17486062049865722,
|
|
"num_tokens": 13587508.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.578818464279175,
|
|
"epoch": 0.6096090254814238,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004968185911328858,
|
|
"loss": 5.4287,
|
|
"mean_token_accuracy": 0.17448496222496032,
|
|
"num_tokens": 13596515.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.592710494995117,
|
|
"epoch": 0.6099980548531414,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004968139451856506,
|
|
"loss": 5.3312,
|
|
"mean_token_accuracy": 0.17864641845226287,
|
|
"num_tokens": 13605162.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.625046300888061,
|
|
"epoch": 0.610387084224859,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004968092958727419,
|
|
"loss": 5.323,
|
|
"mean_token_accuracy": 0.17763691395521164,
|
|
"num_tokens": 13614398.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.578223323822021,
|
|
"epoch": 0.6107761135965766,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049680464319423,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.17352614998817445,
|
|
"num_tokens": 13622347.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.541752862930298,
|
|
"epoch": 0.6111651429682942,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004967999871501858,
|
|
"loss": 5.2962,
|
|
"mean_token_accuracy": 0.17698583900928497,
|
|
"num_tokens": 13630773.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.588369226455688,
|
|
"epoch": 0.6115541723400116,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004967953277406798,
|
|
"loss": 5.3115,
|
|
"mean_token_accuracy": 0.17603595554828644,
|
|
"num_tokens": 13639857.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.660149669647216,
|
|
"epoch": 0.6119432017117292,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004967906649657828,
|
|
"loss": 5.4013,
|
|
"mean_token_accuracy": 0.1743709772825241,
|
|
"num_tokens": 13649959.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.677736425399781,
|
|
"epoch": 0.6123322310834468,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004967859988255655,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.17269433289766312,
|
|
"num_tokens": 13658072.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.550423526763916,
|
|
"epoch": 0.6127212604551644,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004967813293200985,
|
|
"loss": 5.3686,
|
|
"mean_token_accuracy": 0.17952707409858704,
|
|
"num_tokens": 13666816.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.563448524475097,
|
|
"epoch": 0.613110289826882,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004967766564494529,
|
|
"loss": 5.2309,
|
|
"mean_token_accuracy": 0.18123821616172792,
|
|
"num_tokens": 13675415.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.579014158248901,
|
|
"epoch": 0.6134993191985995,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004967719802136996,
|
|
"loss": 5.2656,
|
|
"mean_token_accuracy": 0.18457305133342744,
|
|
"num_tokens": 13684090.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.569391775131225,
|
|
"epoch": 0.613888348570317,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004967673006129094,
|
|
"loss": 5.3269,
|
|
"mean_token_accuracy": 0.17646651118993759,
|
|
"num_tokens": 13692515.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.5889660835266115,
|
|
"epoch": 0.6142773779420346,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004967626176471536,
|
|
"loss": 5.385,
|
|
"mean_token_accuracy": 0.18018435090780258,
|
|
"num_tokens": 13700780.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.681959104537964,
|
|
"epoch": 0.6146664073137522,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004967579313165028,
|
|
"loss": 5.3926,
|
|
"mean_token_accuracy": 0.17503927946090697,
|
|
"num_tokens": 13708638.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.638011789321899,
|
|
"epoch": 0.6150554366854698,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004967532416210284,
|
|
"loss": 5.4016,
|
|
"mean_token_accuracy": 0.16409457921981813,
|
|
"num_tokens": 13717867.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.6005606174469,
|
|
"epoch": 0.6154444660571873,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004967485485608016,
|
|
"loss": 5.3318,
|
|
"mean_token_accuracy": 0.17787362337112428,
|
|
"num_tokens": 13727280.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.643619108200073,
|
|
"epoch": 0.6158334954289049,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004967438521358934,
|
|
"loss": 5.3688,
|
|
"mean_token_accuracy": 0.17395887821912764,
|
|
"num_tokens": 13735255.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.580457782745361,
|
|
"epoch": 0.6162225248006225,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004967391523463754,
|
|
"loss": 5.4155,
|
|
"mean_token_accuracy": 0.17740168571472167,
|
|
"num_tokens": 13743418.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.5950559139251705,
|
|
"epoch": 0.61661155417234,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004967344491923185,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.17605132162570952,
|
|
"num_tokens": 13752714.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.718257808685303,
|
|
"epoch": 0.6170005835440576,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004967297426737943,
|
|
"loss": 5.4811,
|
|
"mean_token_accuracy": 0.16137529909610748,
|
|
"num_tokens": 13761350.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.602125358581543,
|
|
"epoch": 0.6173896129157751,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004967250327908742,
|
|
"loss": 5.3078,
|
|
"mean_token_accuracy": 0.1830330014228821,
|
|
"num_tokens": 13769769.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.6028557300567625,
|
|
"epoch": 0.6177786422874927,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004967203195436297,
|
|
"loss": 5.3293,
|
|
"mean_token_accuracy": 0.16973882168531418,
|
|
"num_tokens": 13778432.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.568603801727295,
|
|
"epoch": 0.6181676716592103,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004967156029321322,
|
|
"loss": 5.3556,
|
|
"mean_token_accuracy": 0.17310213148593903,
|
|
"num_tokens": 13786968.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.662762260437011,
|
|
"epoch": 0.6185567010309279,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004967108829564532,
|
|
"loss": 5.4562,
|
|
"mean_token_accuracy": 0.16001710295677185,
|
|
"num_tokens": 13795824.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.709210157394409,
|
|
"epoch": 0.6189457304026454,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004967061596166646,
|
|
"loss": 5.378,
|
|
"mean_token_accuracy": 0.1731061264872551,
|
|
"num_tokens": 13804748.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.565902137756348,
|
|
"epoch": 0.6193347597743629,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004967014329128378,
|
|
"loss": 5.3689,
|
|
"mean_token_accuracy": 0.17446858137845994,
|
|
"num_tokens": 13813106.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.563230276107788,
|
|
"epoch": 0.6197237891460805,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004966967028450448,
|
|
"loss": 5.3809,
|
|
"mean_token_accuracy": 0.1709654837846756,
|
|
"num_tokens": 13821787.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.6630446434021,
|
|
"epoch": 0.6201128185177981,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000496691969413357,
|
|
"loss": 5.3837,
|
|
"mean_token_accuracy": 0.1775362342596054,
|
|
"num_tokens": 13830275.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.560218715667725,
|
|
"epoch": 0.6205018478895157,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004966872326178466,
|
|
"loss": 5.2988,
|
|
"mean_token_accuracy": 0.17748090475797654,
|
|
"num_tokens": 13838868.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.585489797592163,
|
|
"epoch": 0.6208908772612333,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004966824924585851,
|
|
"loss": 5.3781,
|
|
"mean_token_accuracy": 0.17652124613523484,
|
|
"num_tokens": 13846970.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.6828413009643555,
|
|
"epoch": 0.6212799066329507,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004966777489356448,
|
|
"loss": 5.4504,
|
|
"mean_token_accuracy": 0.1693106934428215,
|
|
"num_tokens": 13856059.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.636405324935913,
|
|
"epoch": 0.6216689360046683,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004966730020490975,
|
|
"loss": 5.3278,
|
|
"mean_token_accuracy": 0.1738095223903656,
|
|
"num_tokens": 13865461.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.603222417831421,
|
|
"epoch": 0.6220579653763859,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000496668251799015,
|
|
"loss": 5.2961,
|
|
"mean_token_accuracy": 0.17080867439508438,
|
|
"num_tokens": 13874124.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.6592529296875,
|
|
"epoch": 0.6224469947481035,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004966634981854699,
|
|
"loss": 5.3958,
|
|
"mean_token_accuracy": 0.17301683127880096,
|
|
"num_tokens": 13882952.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.627367830276489,
|
|
"epoch": 0.6228360241198211,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004966587412085339,
|
|
"loss": 5.3582,
|
|
"mean_token_accuracy": 0.1702231466770172,
|
|
"num_tokens": 13890687.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.616464519500733,
|
|
"epoch": 0.6232250534915386,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004966539808682793,
|
|
"loss": 5.4369,
|
|
"mean_token_accuracy": 0.16845882385969163,
|
|
"num_tokens": 13899773.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.523895645141602,
|
|
"epoch": 0.6236140828632561,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004966492171647783,
|
|
"loss": 5.2276,
|
|
"mean_token_accuracy": 0.17931140959262848,
|
|
"num_tokens": 13908313.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.580318784713745,
|
|
"epoch": 0.6240031122349737,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004966444500981032,
|
|
"loss": 5.3204,
|
|
"mean_token_accuracy": 0.1795070141553879,
|
|
"num_tokens": 13916422.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.62486834526062,
|
|
"epoch": 0.6243921416066913,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004966396796683265,
|
|
"loss": 5.39,
|
|
"mean_token_accuracy": 0.17168170511722564,
|
|
"num_tokens": 13924971.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.589680099487305,
|
|
"epoch": 0.6247811709784089,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004966349058755204,
|
|
"loss": 5.3006,
|
|
"mean_token_accuracy": 0.1775197058916092,
|
|
"num_tokens": 13933016.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.687878561019898,
|
|
"epoch": 0.6251702003501264,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004966301287197573,
|
|
"loss": 5.4062,
|
|
"mean_token_accuracy": 0.174251052737236,
|
|
"num_tokens": 13941814.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.5712274551391605,
|
|
"epoch": 0.625559229721844,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004966253482011098,
|
|
"loss": 5.2186,
|
|
"mean_token_accuracy": 0.18083521276712416,
|
|
"num_tokens": 13950344.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.61683030128479,
|
|
"epoch": 0.6259482590935616,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004966205643196503,
|
|
"loss": 5.4512,
|
|
"mean_token_accuracy": 0.1689373105764389,
|
|
"num_tokens": 13959456.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.607648944854736,
|
|
"epoch": 0.6263372884652791,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004966157770754516,
|
|
"loss": 5.3463,
|
|
"mean_token_accuracy": 0.17657203674316407,
|
|
"num_tokens": 13967303.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.602029705047608,
|
|
"epoch": 0.6267263178369967,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000496610986468586,
|
|
"loss": 5.3874,
|
|
"mean_token_accuracy": 0.16966375559568406,
|
|
"num_tokens": 13977138.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.693867492675781,
|
|
"epoch": 0.6271153472087143,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004966061924991267,
|
|
"loss": 5.4482,
|
|
"mean_token_accuracy": 0.16907818615436554,
|
|
"num_tokens": 13985062.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.702310848236084,
|
|
"epoch": 0.6275043765804318,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000496601395167146,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.17101518511772157,
|
|
"num_tokens": 13992923.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.5685851097106935,
|
|
"epoch": 0.6278934059521494,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004965965944727168,
|
|
"loss": 5.4363,
|
|
"mean_token_accuracy": 0.16952479034662246,
|
|
"num_tokens": 14002116.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.623130464553833,
|
|
"epoch": 0.628282435323867,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004965917904159121,
|
|
"loss": 5.4253,
|
|
"mean_token_accuracy": 0.17172393202781677,
|
|
"num_tokens": 14011053.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.683843469619751,
|
|
"epoch": 0.6286714646955845,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004965869829968046,
|
|
"loss": 5.3597,
|
|
"mean_token_accuracy": 0.1773932620882988,
|
|
"num_tokens": 14019226.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.5199493885040285,
|
|
"epoch": 0.6290604940673021,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004965821722154674,
|
|
"loss": 5.3672,
|
|
"mean_token_accuracy": 0.17195230424404145,
|
|
"num_tokens": 14027630.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.5660515308380125,
|
|
"epoch": 0.6294495234390196,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004965773580719734,
|
|
"loss": 5.2842,
|
|
"mean_token_accuracy": 0.1818663462996483,
|
|
"num_tokens": 14036004.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.621400690078735,
|
|
"epoch": 0.6298385528107372,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004965725405663957,
|
|
"loss": 5.3658,
|
|
"mean_token_accuracy": 0.17055777907371522,
|
|
"num_tokens": 14045359.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.578890037536621,
|
|
"epoch": 0.6302275821824548,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004965677196988073,
|
|
"loss": 5.3267,
|
|
"mean_token_accuracy": 0.17336366176605225,
|
|
"num_tokens": 14054099.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.610009479522705,
|
|
"epoch": 0.6306166115541724,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004965628954692815,
|
|
"loss": 5.3416,
|
|
"mean_token_accuracy": 0.17796404361724855,
|
|
"num_tokens": 14062414.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.611399984359741,
|
|
"epoch": 0.63100564092589,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004965580678778913,
|
|
"loss": 5.3756,
|
|
"mean_token_accuracy": 0.18041929900646209,
|
|
"num_tokens": 14071016.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.575746250152588,
|
|
"epoch": 0.6313946702976074,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004965532369247102,
|
|
"loss": 5.3672,
|
|
"mean_token_accuracy": 0.1708708330988884,
|
|
"num_tokens": 14080622.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.586710786819458,
|
|
"epoch": 0.631783699669325,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004965484026098111,
|
|
"loss": 5.1892,
|
|
"mean_token_accuracy": 0.1801120385527611,
|
|
"num_tokens": 14089500.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.6284722805023195,
|
|
"epoch": 0.6321727290410426,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004965435649332679,
|
|
"loss": 5.4488,
|
|
"mean_token_accuracy": 0.17494778335094452,
|
|
"num_tokens": 14098260.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.5814660549163815,
|
|
"epoch": 0.6325617584127602,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004965387238951536,
|
|
"loss": 5.2688,
|
|
"mean_token_accuracy": 0.18584552854299546,
|
|
"num_tokens": 14106561.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.624522876739502,
|
|
"epoch": 0.6329507877844778,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004965338794955418,
|
|
"loss": 5.3657,
|
|
"mean_token_accuracy": 0.1758665293455124,
|
|
"num_tokens": 14115049.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.58734016418457,
|
|
"epoch": 0.6333398171561953,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004965290317345061,
|
|
"loss": 5.2659,
|
|
"mean_token_accuracy": 0.17704775631427766,
|
|
"num_tokens": 14123204.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.509800910949707,
|
|
"epoch": 0.6337288465279128,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004965241806121198,
|
|
"loss": 5.3179,
|
|
"mean_token_accuracy": 0.17927377671003342,
|
|
"num_tokens": 14132146.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.698159313201904,
|
|
"epoch": 0.6341178758996304,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004965193261284567,
|
|
"loss": 5.4171,
|
|
"mean_token_accuracy": 0.1724001497030258,
|
|
"num_tokens": 14140839.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.650271606445313,
|
|
"epoch": 0.634506905271348,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004965144682835904,
|
|
"loss": 5.401,
|
|
"mean_token_accuracy": 0.17262654453516008,
|
|
"num_tokens": 14149551.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.561512613296509,
|
|
"epoch": 0.6348959346430656,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004965096070775946,
|
|
"loss": 5.3728,
|
|
"mean_token_accuracy": 0.17555071115493776,
|
|
"num_tokens": 14158414.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.61464114189148,
|
|
"epoch": 0.6352849640147831,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004965047425105431,
|
|
"loss": 5.4119,
|
|
"mean_token_accuracy": 0.175685316324234,
|
|
"num_tokens": 14167984.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.608136701583862,
|
|
"epoch": 0.6356739933865007,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004964998745825097,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.17503494620323182,
|
|
"num_tokens": 14177244.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.659901666641235,
|
|
"epoch": 0.6360630227582182,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004964950032935682,
|
|
"loss": 5.2722,
|
|
"mean_token_accuracy": 0.17545693665742873,
|
|
"num_tokens": 14185754.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.571230077743531,
|
|
"epoch": 0.6364520521299358,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004964901286437927,
|
|
"loss": 5.3131,
|
|
"mean_token_accuracy": 0.18276117295026778,
|
|
"num_tokens": 14194242.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.556791353225708,
|
|
"epoch": 0.6368410815016534,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004964852506332568,
|
|
"loss": 5.2478,
|
|
"mean_token_accuracy": 0.18441312611103058,
|
|
"num_tokens": 14202496.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.6668861389160154,
|
|
"epoch": 0.6372301108733709,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000496480369262035,
|
|
"loss": 5.4665,
|
|
"mean_token_accuracy": 0.1682458072900772,
|
|
"num_tokens": 14210510.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.661225461959839,
|
|
"epoch": 0.6376191402450885,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000496475484530201,
|
|
"loss": 5.4667,
|
|
"mean_token_accuracy": 0.16263825446367264,
|
|
"num_tokens": 14219238.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.536808347702026,
|
|
"epoch": 0.6380081696168061,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004964705964378292,
|
|
"loss": 5.2704,
|
|
"mean_token_accuracy": 0.18453190624713897,
|
|
"num_tokens": 14227651.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.550085401535034,
|
|
"epoch": 0.6383971989885237,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004964657049849934,
|
|
"loss": 5.2368,
|
|
"mean_token_accuracy": 0.18380049616098404,
|
|
"num_tokens": 14236144.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.691999387741089,
|
|
"epoch": 0.6387862283602412,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004964608101717681,
|
|
"loss": 5.4072,
|
|
"mean_token_accuracy": 0.16639018803834915,
|
|
"num_tokens": 14244706.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.613128805160523,
|
|
"epoch": 0.6391752577319587,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004964559119982275,
|
|
"loss": 5.3459,
|
|
"mean_token_accuracy": 0.1780515119433403,
|
|
"num_tokens": 14252873.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.610724401473999,
|
|
"epoch": 0.6395642871036763,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000496451010464446,
|
|
"loss": 5.4295,
|
|
"mean_token_accuracy": 0.17149174213409424,
|
|
"num_tokens": 14261383.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.531325197219848,
|
|
"epoch": 0.6399533164753939,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004964461055704978,
|
|
"loss": 5.2255,
|
|
"mean_token_accuracy": 0.18431342244148255,
|
|
"num_tokens": 14270087.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.668795442581176,
|
|
"epoch": 0.6403423458471115,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004964411973164574,
|
|
"loss": 5.3874,
|
|
"mean_token_accuracy": 0.17765944749116896,
|
|
"num_tokens": 14278826.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.591124486923218,
|
|
"epoch": 0.6407313752188291,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004964362857023993,
|
|
"loss": 5.3041,
|
|
"mean_token_accuracy": 0.17893550395965577,
|
|
"num_tokens": 14287554.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.6133569240570065,
|
|
"epoch": 0.6411204045905465,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000496431370728398,
|
|
"loss": 5.2963,
|
|
"mean_token_accuracy": 0.17880027294158934,
|
|
"num_tokens": 14295839.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.571751594543457,
|
|
"epoch": 0.6415094339622641,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004964264523945281,
|
|
"loss": 5.3406,
|
|
"mean_token_accuracy": 0.18072520494461058,
|
|
"num_tokens": 14304831.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.628354072570801,
|
|
"epoch": 0.6418984633339817,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004964215307008643,
|
|
"loss": 5.296,
|
|
"mean_token_accuracy": 0.17758952379226683,
|
|
"num_tokens": 14313249.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.640737628936767,
|
|
"epoch": 0.6422874927056993,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004964166056474811,
|
|
"loss": 5.3649,
|
|
"mean_token_accuracy": 0.17237574011087417,
|
|
"num_tokens": 14321978.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.53292145729065,
|
|
"epoch": 0.6426765220774169,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004964116772344534,
|
|
"loss": 5.2691,
|
|
"mean_token_accuracy": 0.1784036248922348,
|
|
"num_tokens": 14330379.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.549371385574341,
|
|
"epoch": 0.6430655514491345,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004964067454618559,
|
|
"loss": 5.3233,
|
|
"mean_token_accuracy": 0.18185826987028123,
|
|
"num_tokens": 14339121.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.548624753952026,
|
|
"epoch": 0.6434545808208519,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004964018103297634,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.18576613664627076,
|
|
"num_tokens": 14347443.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.636929130554199,
|
|
"epoch": 0.6438436101925695,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004963968718382509,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.16972884237766267,
|
|
"num_tokens": 14356459.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.609857177734375,
|
|
"epoch": 0.6442326395642871,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004963919299873931,
|
|
"loss": 5.301,
|
|
"mean_token_accuracy": 0.17383714765310287,
|
|
"num_tokens": 14365359.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.5062110900878904,
|
|
"epoch": 0.6446216689360047,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004963869847772653,
|
|
"loss": 5.2143,
|
|
"mean_token_accuracy": 0.1847106158733368,
|
|
"num_tokens": 14373345.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.580478239059448,
|
|
"epoch": 0.6450106983077223,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004963820362079423,
|
|
"loss": 5.3098,
|
|
"mean_token_accuracy": 0.1742485374212265,
|
|
"num_tokens": 14381977.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.520681095123291,
|
|
"epoch": 0.6453997276794398,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004963770842794994,
|
|
"loss": 5.2127,
|
|
"mean_token_accuracy": 0.1802786186337471,
|
|
"num_tokens": 14390486.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.5776502132415775,
|
|
"epoch": 0.6457887570511573,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004963721289920115,
|
|
"loss": 5.3947,
|
|
"mean_token_accuracy": 0.17295217216014863,
|
|
"num_tokens": 14399064.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.580191516876221,
|
|
"epoch": 0.6461777864228749,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004963671703455538,
|
|
"loss": 5.2448,
|
|
"mean_token_accuracy": 0.17858138233423232,
|
|
"num_tokens": 14406965.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.544788074493408,
|
|
"epoch": 0.6465668157945925,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004963622083402018,
|
|
"loss": 5.3934,
|
|
"mean_token_accuracy": 0.17124493718147277,
|
|
"num_tokens": 14416293.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.635854053497314,
|
|
"epoch": 0.6469558451663101,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004963572429760305,
|
|
"loss": 5.3733,
|
|
"mean_token_accuracy": 0.1732726901769638,
|
|
"num_tokens": 14424515.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.58670449256897,
|
|
"epoch": 0.6473448745380276,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004963522742531155,
|
|
"loss": 5.2032,
|
|
"mean_token_accuracy": 0.17925521731376648,
|
|
"num_tokens": 14432706.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.540876770019532,
|
|
"epoch": 0.6477339039097452,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000496347302171532,
|
|
"loss": 5.3134,
|
|
"mean_token_accuracy": 0.17976702898740768,
|
|
"num_tokens": 14441462.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.52711968421936,
|
|
"epoch": 0.6481229332814628,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004963423267313554,
|
|
"loss": 5.2796,
|
|
"mean_token_accuracy": 0.17967983931303025,
|
|
"num_tokens": 14450218.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.620292043685913,
|
|
"epoch": 0.6485119626531803,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004963373479326614,
|
|
"loss": 5.4752,
|
|
"mean_token_accuracy": 0.1684851676225662,
|
|
"num_tokens": 14459825.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.616681241989136,
|
|
"epoch": 0.6489009920248979,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004963323657755255,
|
|
"loss": 5.307,
|
|
"mean_token_accuracy": 0.17906863242387772,
|
|
"num_tokens": 14468647.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.54473352432251,
|
|
"epoch": 0.6492900213966154,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004963273802600231,
|
|
"loss": 5.1997,
|
|
"mean_token_accuracy": 0.18291590511798858,
|
|
"num_tokens": 14476892.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.655897998809815,
|
|
"epoch": 0.649679050768333,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00049632239138623,
|
|
"loss": 5.4402,
|
|
"mean_token_accuracy": 0.1732370838522911,
|
|
"num_tokens": 14485541.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.548528242111206,
|
|
"epoch": 0.6500680801400506,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004963173991542219,
|
|
"loss": 5.2786,
|
|
"mean_token_accuracy": 0.1823086842894554,
|
|
"num_tokens": 14494184.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.670836544036865,
|
|
"epoch": 0.6504571095117682,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004963124035640746,
|
|
"loss": 5.4022,
|
|
"mean_token_accuracy": 0.1653965264558792,
|
|
"num_tokens": 14502151.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.59298038482666,
|
|
"epoch": 0.6508461388834857,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004963074046158637,
|
|
"loss": 5.3839,
|
|
"mean_token_accuracy": 0.17655687034130096,
|
|
"num_tokens": 14511254.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.675338935852051,
|
|
"epoch": 0.6512351682552032,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004963024023096652,
|
|
"loss": 5.4396,
|
|
"mean_token_accuracy": 0.16882770955562593,
|
|
"num_tokens": 14520492.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.685335683822632,
|
|
"epoch": 0.6516241976269208,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004962973966455551,
|
|
"loss": 5.3927,
|
|
"mean_token_accuracy": 0.16695061028003694,
|
|
"num_tokens": 14530082.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.592555570602417,
|
|
"epoch": 0.6520132269986384,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004962923876236092,
|
|
"loss": 5.3558,
|
|
"mean_token_accuracy": 0.1753413200378418,
|
|
"num_tokens": 14539124.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.632155990600586,
|
|
"epoch": 0.652402256370356,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004962873752439035,
|
|
"loss": 5.3377,
|
|
"mean_token_accuracy": 0.17932512909173964,
|
|
"num_tokens": 14547780.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.576566505432129,
|
|
"epoch": 0.6527912857420736,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004962823595065141,
|
|
"loss": 5.2595,
|
|
"mean_token_accuracy": 0.17745744287967682,
|
|
"num_tokens": 14556225.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.634925127029419,
|
|
"epoch": 0.653180315113791,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004962773404115172,
|
|
"loss": 5.3435,
|
|
"mean_token_accuracy": 0.17520466893911363,
|
|
"num_tokens": 14564147.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.601422357559204,
|
|
"epoch": 0.6535693444855086,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004962723179589886,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.1706002101302147,
|
|
"num_tokens": 14573519.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.640968894958496,
|
|
"epoch": 0.6539583738572262,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000496267292149005,
|
|
"loss": 5.4625,
|
|
"mean_token_accuracy": 0.16425798386335372,
|
|
"num_tokens": 14582806.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.5813973903656,
|
|
"epoch": 0.6543474032289438,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004962622629816423,
|
|
"loss": 5.343,
|
|
"mean_token_accuracy": 0.168157197535038,
|
|
"num_tokens": 14591274.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.570907878875732,
|
|
"epoch": 0.6547364326006614,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000496257230456977,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.17347589135169983,
|
|
"num_tokens": 14599902.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.546425914764404,
|
|
"epoch": 0.6551254619723789,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004962521945750855,
|
|
"loss": 5.2911,
|
|
"mean_token_accuracy": 0.1729225903749466,
|
|
"num_tokens": 14608931.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.573162841796875,
|
|
"epoch": 0.6555144913440965,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000496247155336044,
|
|
"loss": 5.2474,
|
|
"mean_token_accuracy": 0.17821999341249467,
|
|
"num_tokens": 14617547.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.614056253433228,
|
|
"epoch": 0.655903520715814,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004962421127399291,
|
|
"loss": 5.3825,
|
|
"mean_token_accuracy": 0.1722403198480606,
|
|
"num_tokens": 14626523.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.625966262817383,
|
|
"epoch": 0.6562925500875316,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004962370667868172,
|
|
"loss": 5.3203,
|
|
"mean_token_accuracy": 0.1793544590473175,
|
|
"num_tokens": 14634846.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.571551084518433,
|
|
"epoch": 0.6566815794592492,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004962320174767851,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.17367968261241912,
|
|
"num_tokens": 14643092.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.633761548995972,
|
|
"epoch": 0.6570706088309667,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000496226964809909,
|
|
"loss": 5.4057,
|
|
"mean_token_accuracy": 0.17658709585666657,
|
|
"num_tokens": 14651456.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.580606842041016,
|
|
"epoch": 0.6574596382026843,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000496221908786266,
|
|
"loss": 5.2845,
|
|
"mean_token_accuracy": 0.17938428670167922,
|
|
"num_tokens": 14660488.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.684810447692871,
|
|
"epoch": 0.6578486675744019,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004962168494059327,
|
|
"loss": 5.4868,
|
|
"mean_token_accuracy": 0.17089286744594573,
|
|
"num_tokens": 14670131.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.642894077301025,
|
|
"epoch": 0.6582376969461194,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004962117866689857,
|
|
"loss": 5.2878,
|
|
"mean_token_accuracy": 0.1739628404378891,
|
|
"num_tokens": 14678402.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.582067584991455,
|
|
"epoch": 0.658626726317837,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000496206720575502,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.1687963843345642,
|
|
"num_tokens": 14687589.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.644313478469849,
|
|
"epoch": 0.6590157556895546,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004962016511255584,
|
|
"loss": 5.4557,
|
|
"mean_token_accuracy": 0.16937474608421327,
|
|
"num_tokens": 14696288.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.685591173171997,
|
|
"epoch": 0.6594047850612721,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004961965783192318,
|
|
"loss": 5.3616,
|
|
"mean_token_accuracy": 0.17366212159395217,
|
|
"num_tokens": 14705269.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.591137266159057,
|
|
"epoch": 0.6597938144329897,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004961915021565992,
|
|
"loss": 5.3471,
|
|
"mean_token_accuracy": 0.17597121000289917,
|
|
"num_tokens": 14713669.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.532935047149659,
|
|
"epoch": 0.6601828438047073,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004961864226377377,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.17643194645643234,
|
|
"num_tokens": 14722529.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.6268493175506595,
|
|
"epoch": 0.6605718731764249,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004961813397627241,
|
|
"loss": 5.384,
|
|
"mean_token_accuracy": 0.17761731743812562,
|
|
"num_tokens": 14730956.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.632120513916016,
|
|
"epoch": 0.6609609025481424,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004961762535316358,
|
|
"loss": 5.3345,
|
|
"mean_token_accuracy": 0.1788095787167549,
|
|
"num_tokens": 14739320.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.571344614028931,
|
|
"epoch": 0.6613499319198599,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004961711639445499,
|
|
"loss": 5.3879,
|
|
"mean_token_accuracy": 0.17722497433423995,
|
|
"num_tokens": 14748030.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.608709764480591,
|
|
"epoch": 0.6617389612915775,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004961660710015435,
|
|
"loss": 5.2843,
|
|
"mean_token_accuracy": 0.18021600544452668,
|
|
"num_tokens": 14756786.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.604683494567871,
|
|
"epoch": 0.6621279906632951,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004961609747026943,
|
|
"loss": 5.3535,
|
|
"mean_token_accuracy": 0.17999780774116517,
|
|
"num_tokens": 14765538.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.608538436889648,
|
|
"epoch": 0.6625170200350127,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004961558750480791,
|
|
"loss": 5.2726,
|
|
"mean_token_accuracy": 0.18049169331789017,
|
|
"num_tokens": 14773845.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.560791444778443,
|
|
"epoch": 0.6629060494067303,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004961507720377756,
|
|
"loss": 5.2237,
|
|
"mean_token_accuracy": 0.1844485729932785,
|
|
"num_tokens": 14782022.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.610558032989502,
|
|
"epoch": 0.6632950787784477,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004961456656718611,
|
|
"loss": 5.3717,
|
|
"mean_token_accuracy": 0.17913725674152375,
|
|
"num_tokens": 14790150.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.59845461845398,
|
|
"epoch": 0.6636841081501653,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000496140555950413,
|
|
"loss": 5.4119,
|
|
"mean_token_accuracy": 0.17195657938718795,
|
|
"num_tokens": 14799239.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.560660743713379,
|
|
"epoch": 0.6640731375218829,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004961354428735091,
|
|
"loss": 5.3272,
|
|
"mean_token_accuracy": 0.16718420684337615,
|
|
"num_tokens": 14808740.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.73283896446228,
|
|
"epoch": 0.6644621668936005,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004961303264412267,
|
|
"loss": 5.4618,
|
|
"mean_token_accuracy": 0.1692821726202965,
|
|
"num_tokens": 14817329.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.624889326095581,
|
|
"epoch": 0.6648511962653181,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004961252066536437,
|
|
"loss": 5.3031,
|
|
"mean_token_accuracy": 0.17418562173843383,
|
|
"num_tokens": 14826240.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.602689266204834,
|
|
"epoch": 0.6652402256370356,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004961200835108375,
|
|
"loss": 5.32,
|
|
"mean_token_accuracy": 0.17306315898895264,
|
|
"num_tokens": 14834471.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.612128400802613,
|
|
"epoch": 0.6656292550087531,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000496114957012886,
|
|
"loss": 5.3241,
|
|
"mean_token_accuracy": 0.1665057823061943,
|
|
"num_tokens": 14842724.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.543188428878784,
|
|
"epoch": 0.6660182843804707,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004961098271598671,
|
|
"loss": 5.2522,
|
|
"mean_token_accuracy": 0.1831625521183014,
|
|
"num_tokens": 14850725.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.5301573276519775,
|
|
"epoch": 0.6664073137521883,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004961046939518585,
|
|
"loss": 5.2167,
|
|
"mean_token_accuracy": 0.18281251490116118,
|
|
"num_tokens": 14859412.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.659323358535767,
|
|
"epoch": 0.6667963431239059,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004960995573889379,
|
|
"loss": 5.3212,
|
|
"mean_token_accuracy": 0.1752857342362404,
|
|
"num_tokens": 14867526.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.532819938659668,
|
|
"epoch": 0.6671853724956234,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004960944174711836,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.17377183735370635,
|
|
"num_tokens": 14875770.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.558029127120972,
|
|
"epoch": 0.667574401867341,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004960892741986734,
|
|
"loss": 5.3095,
|
|
"mean_token_accuracy": 0.18255508840084075,
|
|
"num_tokens": 14883872.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.550190544128418,
|
|
"epoch": 0.6679634312390585,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004960841275714853,
|
|
"loss": 5.3322,
|
|
"mean_token_accuracy": 0.1733739659190178,
|
|
"num_tokens": 14891526.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.6118604183197025,
|
|
"epoch": 0.6683524606107761,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004960789775896975,
|
|
"loss": 5.3753,
|
|
"mean_token_accuracy": 0.1733969748020172,
|
|
"num_tokens": 14900171.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.628033113479614,
|
|
"epoch": 0.6687414899824937,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004960738242533881,
|
|
"loss": 5.3365,
|
|
"mean_token_accuracy": 0.17448588013648986,
|
|
"num_tokens": 14908537.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.554285907745362,
|
|
"epoch": 0.6691305193542112,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004960686675626353,
|
|
"loss": 5.2722,
|
|
"mean_token_accuracy": 0.18086651861667633,
|
|
"num_tokens": 14917387.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.609855794906617,
|
|
"epoch": 0.6695195487259288,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004960635075175173,
|
|
"loss": 5.2943,
|
|
"mean_token_accuracy": 0.17782697677612305,
|
|
"num_tokens": 14925945.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.58464412689209,
|
|
"epoch": 0.6699085780976464,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004960583441181124,
|
|
"loss": 5.3051,
|
|
"mean_token_accuracy": 0.18012278228998185,
|
|
"num_tokens": 14934002.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.583852672576905,
|
|
"epoch": 0.670297607469364,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004960531773644992,
|
|
"loss": 5.3366,
|
|
"mean_token_accuracy": 0.16810405403375625,
|
|
"num_tokens": 14942658.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.669387340545654,
|
|
"epoch": 0.6706866368410815,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004960480072567557,
|
|
"loss": 5.4096,
|
|
"mean_token_accuracy": 0.16790317744016647,
|
|
"num_tokens": 14952324.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.6801048755645756,
|
|
"epoch": 0.671075666212799,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004960428337949604,
|
|
"loss": 5.4406,
|
|
"mean_token_accuracy": 0.17223362624645233,
|
|
"num_tokens": 14961964.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.679262447357178,
|
|
"epoch": 0.6714646955845166,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004960376569791921,
|
|
"loss": 5.3774,
|
|
"mean_token_accuracy": 0.1753703996539116,
|
|
"num_tokens": 14970267.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.55751485824585,
|
|
"epoch": 0.6718537249562342,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004960324768095291,
|
|
"loss": 5.2475,
|
|
"mean_token_accuracy": 0.17541256844997405,
|
|
"num_tokens": 14978546.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.644605398178101,
|
|
"epoch": 0.6722427543279518,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004960272932860502,
|
|
"loss": 5.3149,
|
|
"mean_token_accuracy": 0.17382394820451735,
|
|
"num_tokens": 14986785.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.61287407875061,
|
|
"epoch": 0.6726317836996694,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004960221064088338,
|
|
"loss": 5.235,
|
|
"mean_token_accuracy": 0.17687039226293563,
|
|
"num_tokens": 14994873.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.554454326629639,
|
|
"epoch": 0.6730208130713868,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004960169161779588,
|
|
"loss": 5.2792,
|
|
"mean_token_accuracy": 0.18262446224689483,
|
|
"num_tokens": 15003108.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.453991985321045,
|
|
"epoch": 0.6734098424431044,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004960117225935038,
|
|
"loss": 5.1857,
|
|
"mean_token_accuracy": 0.180227230489254,
|
|
"num_tokens": 15011802.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.598253011703491,
|
|
"epoch": 0.673798871814822,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004960065256555477,
|
|
"loss": 5.3383,
|
|
"mean_token_accuracy": 0.17591814398765565,
|
|
"num_tokens": 15020785.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.674804973602295,
|
|
"epoch": 0.6741879011865396,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004960013253641695,
|
|
"loss": 5.4264,
|
|
"mean_token_accuracy": 0.1727169021964073,
|
|
"num_tokens": 15029218.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.6443077564239506,
|
|
"epoch": 0.6745769305582572,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004959961217194477,
|
|
"loss": 5.3742,
|
|
"mean_token_accuracy": 0.16470756381750107,
|
|
"num_tokens": 15037843.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.554808759689331,
|
|
"epoch": 0.6749659599299748,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004959909147214615,
|
|
"loss": 5.3013,
|
|
"mean_token_accuracy": 0.17953749299049376,
|
|
"num_tokens": 15047053.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.629379653930664,
|
|
"epoch": 0.6753549893016922,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004959857043702902,
|
|
"loss": 5.4161,
|
|
"mean_token_accuracy": 0.17055174857378005,
|
|
"num_tokens": 15056159.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.623338031768799,
|
|
"epoch": 0.6757440186734098,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004959804906660124,
|
|
"loss": 5.36,
|
|
"mean_token_accuracy": 0.17230446636676788,
|
|
"num_tokens": 15064853.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.624137306213379,
|
|
"epoch": 0.6761330480451274,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004959752736087073,
|
|
"loss": 5.3679,
|
|
"mean_token_accuracy": 0.17369776517152785,
|
|
"num_tokens": 15072671.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.566968774795532,
|
|
"epoch": 0.676522077416845,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004959700531984543,
|
|
"loss": 5.2846,
|
|
"mean_token_accuracy": 0.18115321844816207,
|
|
"num_tokens": 15080787.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.59602575302124,
|
|
"epoch": 0.6769111067885626,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004959648294353324,
|
|
"loss": 5.3639,
|
|
"mean_token_accuracy": 0.17051270008087158,
|
|
"num_tokens": 15089906.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.610385417938232,
|
|
"epoch": 0.6773001361602801,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004959596023194208,
|
|
"loss": 5.411,
|
|
"mean_token_accuracy": 0.1748563304543495,
|
|
"num_tokens": 15099329.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.606177234649659,
|
|
"epoch": 0.6776891655319977,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000495954371850799,
|
|
"loss": 5.406,
|
|
"mean_token_accuracy": 0.16943833082914353,
|
|
"num_tokens": 15107744.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.659435749053955,
|
|
"epoch": 0.6780781949037152,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004959491380295463,
|
|
"loss": 5.4144,
|
|
"mean_token_accuracy": 0.17236348092556,
|
|
"num_tokens": 15115918.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.630734920501709,
|
|
"epoch": 0.6784672242754328,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004959439008557422,
|
|
"loss": 5.2683,
|
|
"mean_token_accuracy": 0.18021719306707382,
|
|
"num_tokens": 15124074.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.583794355392456,
|
|
"epoch": 0.6788562536471504,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000495938660329466,
|
|
"loss": 5.2878,
|
|
"mean_token_accuracy": 0.18511537164449693,
|
|
"num_tokens": 15132402.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.593100309371948,
|
|
"epoch": 0.6792452830188679,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004959334164507973,
|
|
"loss": 5.4042,
|
|
"mean_token_accuracy": 0.17148813158273696,
|
|
"num_tokens": 15141640.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.616944646835327,
|
|
"epoch": 0.6796343123905855,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004959281692198155,
|
|
"loss": 5.2823,
|
|
"mean_token_accuracy": 0.18312946259975432,
|
|
"num_tokens": 15149919.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.519328165054321,
|
|
"epoch": 0.6800233417623031,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004959229186366007,
|
|
"loss": 5.136,
|
|
"mean_token_accuracy": 0.18960692137479782,
|
|
"num_tokens": 15157536.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.496883392333984,
|
|
"epoch": 0.6804123711340206,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000495917664701232,
|
|
"loss": 5.3749,
|
|
"mean_token_accuracy": 0.169368739426136,
|
|
"num_tokens": 15165848.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.6310648918151855,
|
|
"epoch": 0.6808014005057382,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004959124074137894,
|
|
"loss": 5.3512,
|
|
"mean_token_accuracy": 0.17456937730312347,
|
|
"num_tokens": 15174799.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.683430242538452,
|
|
"epoch": 0.6811904298774557,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004959071467743526,
|
|
"loss": 5.4544,
|
|
"mean_token_accuracy": 0.16898835003376006,
|
|
"num_tokens": 15183695.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.68021068572998,
|
|
"epoch": 0.6815794592491733,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004959018827830016,
|
|
"loss": 5.4602,
|
|
"mean_token_accuracy": 0.16695004254579543,
|
|
"num_tokens": 15193620.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.634642314910889,
|
|
"epoch": 0.6819684886208909,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000495896615439816,
|
|
"loss": 5.2843,
|
|
"mean_token_accuracy": 0.1768329083919525,
|
|
"num_tokens": 15201535.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.704289817810059,
|
|
"epoch": 0.6823575179926085,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004958913447448759,
|
|
"loss": 5.4164,
|
|
"mean_token_accuracy": 0.1670977532863617,
|
|
"num_tokens": 15209678.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.544375801086426,
|
|
"epoch": 0.682746547364326,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004958860706982613,
|
|
"loss": 5.3324,
|
|
"mean_token_accuracy": 0.1766015887260437,
|
|
"num_tokens": 15218579.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.487669229507446,
|
|
"epoch": 0.6831355767360435,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000495880793300052,
|
|
"loss": 5.2377,
|
|
"mean_token_accuracy": 0.18537399917840958,
|
|
"num_tokens": 15227225.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.6388014793396,
|
|
"epoch": 0.6835246061077611,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004958755125503284,
|
|
"loss": 5.3557,
|
|
"mean_token_accuracy": 0.17073596119880677,
|
|
"num_tokens": 15235900.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.697755146026611,
|
|
"epoch": 0.6839136354794787,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004958702284491703,
|
|
"loss": 5.3068,
|
|
"mean_token_accuracy": 0.18236736655235292,
|
|
"num_tokens": 15244538.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.540953350067139,
|
|
"epoch": 0.6843026648511963,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004958649409966581,
|
|
"loss": 5.2775,
|
|
"mean_token_accuracy": 0.17999098300933838,
|
|
"num_tokens": 15252902.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.589314413070679,
|
|
"epoch": 0.6846916942229139,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000495859650192872,
|
|
"loss": 5.4365,
|
|
"mean_token_accuracy": 0.16840124875307083,
|
|
"num_tokens": 15261514.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.634120941162109,
|
|
"epoch": 0.6850807235946313,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004958543560378922,
|
|
"loss": 5.3649,
|
|
"mean_token_accuracy": 0.17663902938365936,
|
|
"num_tokens": 15270140.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.604912900924683,
|
|
"epoch": 0.6854697529663489,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004958490585317991,
|
|
"loss": 5.3105,
|
|
"mean_token_accuracy": 0.17741454839706422,
|
|
"num_tokens": 15279551.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.542202186584473,
|
|
"epoch": 0.6858587823380665,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000495843757674673,
|
|
"loss": 5.2981,
|
|
"mean_token_accuracy": 0.18478564769029618,
|
|
"num_tokens": 15288767.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.597590923309326,
|
|
"epoch": 0.6862478117097841,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004958384534665945,
|
|
"loss": 5.3255,
|
|
"mean_token_accuracy": 0.18024711757898332,
|
|
"num_tokens": 15297713.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.648599481582641,
|
|
"epoch": 0.6866368410815017,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004958331459076438,
|
|
"loss": 5.3241,
|
|
"mean_token_accuracy": 0.17295677661895753,
|
|
"num_tokens": 15306139.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.661116123199463,
|
|
"epoch": 0.6870258704532192,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004958278349979018,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.18049405366182328,
|
|
"num_tokens": 15315015.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.597526264190674,
|
|
"epoch": 0.6874148998249368,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004958225207374488,
|
|
"loss": 5.2576,
|
|
"mean_token_accuracy": 0.17740098237991334,
|
|
"num_tokens": 15323366.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.534605646133423,
|
|
"epoch": 0.6878039291966543,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004958172031263655,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.19066004008054732,
|
|
"num_tokens": 15331135.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.533976030349732,
|
|
"epoch": 0.6881929585683719,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004958118821647326,
|
|
"loss": 5.2701,
|
|
"mean_token_accuracy": 0.1801069885492325,
|
|
"num_tokens": 15339561.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.642655992507935,
|
|
"epoch": 0.6885819879400895,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004958065578526308,
|
|
"loss": 5.1835,
|
|
"mean_token_accuracy": 0.18612721860408782,
|
|
"num_tokens": 15348000.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.660510301589966,
|
|
"epoch": 0.688971017311807,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000495801230190141,
|
|
"loss": 5.3766,
|
|
"mean_token_accuracy": 0.17496137619018554,
|
|
"num_tokens": 15355916.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.48637022972107,
|
|
"epoch": 0.6893600466835246,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004957958991773441,
|
|
"loss": 5.2261,
|
|
"mean_token_accuracy": 0.18035848140716554,
|
|
"num_tokens": 15364561.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.592615604400635,
|
|
"epoch": 0.6897490760552422,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004957905648143206,
|
|
"loss": 5.2593,
|
|
"mean_token_accuracy": 0.17427134960889817,
|
|
"num_tokens": 15372582.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.594068765640259,
|
|
"epoch": 0.6901381054269597,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004957852271011519,
|
|
"loss": 5.3502,
|
|
"mean_token_accuracy": 0.17120631635189057,
|
|
"num_tokens": 15381684.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.68618335723877,
|
|
"epoch": 0.6905271347986773,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004957798860379187,
|
|
"loss": 5.3811,
|
|
"mean_token_accuracy": 0.17104661464691162,
|
|
"num_tokens": 15390858.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.58775110244751,
|
|
"epoch": 0.6909161641703949,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004957745416247022,
|
|
"loss": 5.2122,
|
|
"mean_token_accuracy": 0.17857923805713655,
|
|
"num_tokens": 15399439.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.515638208389282,
|
|
"epoch": 0.6913051935421124,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004957691938615833,
|
|
"loss": 5.2838,
|
|
"mean_token_accuracy": 0.18353706151247023,
|
|
"num_tokens": 15407784.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.6534748554229735,
|
|
"epoch": 0.69169422291383,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004957638427486434,
|
|
"loss": 5.406,
|
|
"mean_token_accuracy": 0.17561437338590621,
|
|
"num_tokens": 15415985.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.59408802986145,
|
|
"epoch": 0.6920832522855476,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004957584882859636,
|
|
"loss": 5.2927,
|
|
"mean_token_accuracy": 0.17846294939517976,
|
|
"num_tokens": 15424433.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.611450719833374,
|
|
"epoch": 0.6924722816572652,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004957531304736251,
|
|
"loss": 5.3841,
|
|
"mean_token_accuracy": 0.1786998599767685,
|
|
"num_tokens": 15433041.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.536662006378174,
|
|
"epoch": 0.6928613110289827,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004957477693117091,
|
|
"loss": 5.2136,
|
|
"mean_token_accuracy": 0.1760414347052574,
|
|
"num_tokens": 15441159.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.707674503326416,
|
|
"epoch": 0.6932503404007002,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004957424048002971,
|
|
"loss": 5.5292,
|
|
"mean_token_accuracy": 0.16542596071958543,
|
|
"num_tokens": 15450687.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.550708436965943,
|
|
"epoch": 0.6936393697724178,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004957370369394706,
|
|
"loss": 5.2337,
|
|
"mean_token_accuracy": 0.17625031620264053,
|
|
"num_tokens": 15460450.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.545779085159301,
|
|
"epoch": 0.6940283991441354,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004957316657293107,
|
|
"loss": 5.2543,
|
|
"mean_token_accuracy": 0.18371557593345642,
|
|
"num_tokens": 15468435.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.551118421554565,
|
|
"epoch": 0.694417428515853,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004957262911698992,
|
|
"loss": 5.2276,
|
|
"mean_token_accuracy": 0.185743547976017,
|
|
"num_tokens": 15476232.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.650556516647339,
|
|
"epoch": 0.6948064578875706,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004957209132613175,
|
|
"loss": 5.3467,
|
|
"mean_token_accuracy": 0.17577973306179046,
|
|
"num_tokens": 15484569.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.580010795593262,
|
|
"epoch": 0.695195487259288,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004957155320036473,
|
|
"loss": 5.2563,
|
|
"mean_token_accuracy": 0.18059066087007522,
|
|
"num_tokens": 15492583.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.60004186630249,
|
|
"epoch": 0.6955845166310056,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004957101473969702,
|
|
"loss": 5.4014,
|
|
"mean_token_accuracy": 0.17439007014036179,
|
|
"num_tokens": 15501722.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.652395629882813,
|
|
"epoch": 0.6959735460027232,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000495704759441368,
|
|
"loss": 5.3445,
|
|
"mean_token_accuracy": 0.17423500567674638,
|
|
"num_tokens": 15509682.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.620736122131348,
|
|
"epoch": 0.6963625753744408,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004956993681369221,
|
|
"loss": 5.3274,
|
|
"mean_token_accuracy": 0.17697353959083556,
|
|
"num_tokens": 15518971.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.606459903717041,
|
|
"epoch": 0.6967516047461584,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004956939734837148,
|
|
"loss": 5.3077,
|
|
"mean_token_accuracy": 0.1726076379418373,
|
|
"num_tokens": 15527385.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.631381511688232,
|
|
"epoch": 0.6971406341178759,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004956885754818277,
|
|
"loss": 5.4182,
|
|
"mean_token_accuracy": 0.17595664858818055,
|
|
"num_tokens": 15535325.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.659246206283569,
|
|
"epoch": 0.6975296634895934,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004956831741313427,
|
|
"loss": 5.3941,
|
|
"mean_token_accuracy": 0.17625509798526764,
|
|
"num_tokens": 15544098.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.628655052185058,
|
|
"epoch": 0.697918692861311,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004956777694323418,
|
|
"loss": 5.2748,
|
|
"mean_token_accuracy": 0.17389642000198363,
|
|
"num_tokens": 15552547.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.544471740722656,
|
|
"epoch": 0.6983077222330286,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000495672361384907,
|
|
"loss": 5.2914,
|
|
"mean_token_accuracy": 0.1741619199514389,
|
|
"num_tokens": 15561044.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.609742021560669,
|
|
"epoch": 0.6986967516047462,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004956669499891202,
|
|
"loss": 5.3516,
|
|
"mean_token_accuracy": 0.16445284485816955,
|
|
"num_tokens": 15569379.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.62983021736145,
|
|
"epoch": 0.6990857809764637,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004956615352450639,
|
|
"loss": 5.371,
|
|
"mean_token_accuracy": 0.17524835020303725,
|
|
"num_tokens": 15578535.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.523656272888184,
|
|
"epoch": 0.6994748103481813,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004956561171528198,
|
|
"loss": 5.2201,
|
|
"mean_token_accuracy": 0.1841176375746727,
|
|
"num_tokens": 15586972.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.486569213867187,
|
|
"epoch": 0.6998638397198989,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004956506957124704,
|
|
"loss": 5.183,
|
|
"mean_token_accuracy": 0.19105131179094315,
|
|
"num_tokens": 15595092.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.652354097366333,
|
|
"epoch": 0.7002528690916164,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000495645270924098,
|
|
"loss": 5.4934,
|
|
"mean_token_accuracy": 0.17323615550994872,
|
|
"num_tokens": 15604348.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.7002528690916164,
|
|
"eval_entropy": 5.426626439135848,
|
|
"eval_loss": 5.354678153991699,
|
|
"eval_mean_token_accuracy": 0.1833029387344869,
|
|
"eval_num_tokens": 15604348.0,
|
|
"eval_runtime": 21.8814,
|
|
"eval_samples_per_second": 1899.238,
|
|
"eval_steps_per_second": 237.416,
|
|
"step": 9000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 128520,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 3139451977236480.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|