171de99300
Model: fpadovani/eng-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
42112 lines
1.1 MiB
42112 lines
1.1 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.3585106980400967,
|
|
"eval_steps": 3000,
|
|
"global_step": 21000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 7.055009984970093,
|
|
"epoch": 0.0005615769079575448,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 2e-06,
|
|
"loss": 6.7107,
|
|
"mean_token_accuracy": 0.11852641776204109,
|
|
"num_tokens": 11659.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.089489412307739,
|
|
"epoch": 0.0011231538159150896,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 6.6891,
|
|
"mean_token_accuracy": 0.1258482627570629,
|
|
"num_tokens": 21794.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.030844259262085,
|
|
"epoch": 0.0016847307238726343,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 7e-06,
|
|
"loss": 6.692,
|
|
"mean_token_accuracy": 0.12024398297071456,
|
|
"num_tokens": 33206.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.072840785980224,
|
|
"epoch": 0.0022463076318301792,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 6.7396,
|
|
"mean_token_accuracy": 0.11460101678967476,
|
|
"num_tokens": 44487.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.070654821395874,
|
|
"epoch": 0.002807884539787724,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 6.7794,
|
|
"mean_token_accuracy": 0.12300792410969734,
|
|
"num_tokens": 56062.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.022868919372558,
|
|
"epoch": 0.0033694614477452686,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 6.6531,
|
|
"mean_token_accuracy": 0.12243497297167778,
|
|
"num_tokens": 67453.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.1308962345123295,
|
|
"epoch": 0.003931038355702813,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 6.7718,
|
|
"mean_token_accuracy": 0.12407388612627983,
|
|
"num_tokens": 78527.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 7.098523569107056,
|
|
"epoch": 0.0044926152636603585,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 6.6361,
|
|
"mean_token_accuracy": 0.12737443149089814,
|
|
"num_tokens": 89267.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 7.05347261428833,
|
|
"epoch": 0.005054192171617903,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 6.6533,
|
|
"mean_token_accuracy": 0.12288121953606605,
|
|
"num_tokens": 102035.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.032813835144043,
|
|
"epoch": 0.005615769079575448,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 6.691,
|
|
"mean_token_accuracy": 0.12443716675043107,
|
|
"num_tokens": 112734.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.025327157974243,
|
|
"epoch": 0.006177345987532993,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 6.605,
|
|
"mean_token_accuracy": 0.12701525092124938,
|
|
"num_tokens": 123854.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.010390710830689,
|
|
"epoch": 0.006738922895490537,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 6.6598,
|
|
"mean_token_accuracy": 0.12369369864463806,
|
|
"num_tokens": 133444.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.015805435180664,
|
|
"epoch": 0.007300499803448083,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 6.5399,
|
|
"mean_token_accuracy": 0.13149982020258905,
|
|
"num_tokens": 144678.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 7.051552820205688,
|
|
"epoch": 0.007862076711405626,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 6.6398,
|
|
"mean_token_accuracy": 0.12550251558423042,
|
|
"num_tokens": 155866.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 7.051578426361084,
|
|
"epoch": 0.008423653619363172,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 6.6549,
|
|
"mean_token_accuracy": 0.12591486871242524,
|
|
"num_tokens": 166965.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.005019807815552,
|
|
"epoch": 0.008985230527320717,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 6.6264,
|
|
"mean_token_accuracy": 0.12710528150200845,
|
|
"num_tokens": 177423.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.094327354431153,
|
|
"epoch": 0.00954680743527826,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.6799,
|
|
"mean_token_accuracy": 0.13134793564677238,
|
|
"num_tokens": 188687.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.02366008758545,
|
|
"epoch": 0.010108384343235806,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 6.7402,
|
|
"mean_token_accuracy": 0.12708025872707368,
|
|
"num_tokens": 200173.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.101563358306885,
|
|
"epoch": 0.010669961251193351,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 6.6927,
|
|
"mean_token_accuracy": 0.1279763586819172,
|
|
"num_tokens": 210877.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.070672464370728,
|
|
"epoch": 0.011231538159150897,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.5966,
|
|
"mean_token_accuracy": 0.12734237387776376,
|
|
"num_tokens": 221770.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 7.042833042144776,
|
|
"epoch": 0.01179311506710844,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 6.7053,
|
|
"mean_token_accuracy": 0.13242030143737793,
|
|
"num_tokens": 232140.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.078888416290283,
|
|
"epoch": 0.012354691975065986,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 6.7883,
|
|
"mean_token_accuracy": 0.12373976334929467,
|
|
"num_tokens": 244186.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.088221263885498,
|
|
"epoch": 0.012916268883023531,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 6.6365,
|
|
"mean_token_accuracy": 0.12594474777579306,
|
|
"num_tokens": 254805.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 6.958014631271363,
|
|
"epoch": 0.013477845790981074,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 6.6024,
|
|
"mean_token_accuracy": 0.13206158876419066,
|
|
"num_tokens": 265055.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 6.960734224319458,
|
|
"epoch": 0.01403942269893862,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 6.5299,
|
|
"mean_token_accuracy": 0.13171669095754623,
|
|
"num_tokens": 275850.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 6.957069635391235,
|
|
"epoch": 0.014600999606896165,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 6.573,
|
|
"mean_token_accuracy": 0.12500080540776254,
|
|
"num_tokens": 286802.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 7.044544267654419,
|
|
"epoch": 0.015162576514853709,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 6.6832,
|
|
"mean_token_accuracy": 0.12705129086971284,
|
|
"num_tokens": 297070.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.043524742126465,
|
|
"epoch": 0.015724153422811252,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 6.6043,
|
|
"mean_token_accuracy": 0.12342865765094757,
|
|
"num_tokens": 309617.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.012852001190185,
|
|
"epoch": 0.0162857303307688,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 6.6383,
|
|
"mean_token_accuracy": 0.12594973370432855,
|
|
"num_tokens": 321310.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 6.964358329772949,
|
|
"epoch": 0.016847307238726343,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.5806,
|
|
"mean_token_accuracy": 0.1310770720243454,
|
|
"num_tokens": 332243.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.011226844787598,
|
|
"epoch": 0.017408884146683887,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 6.6,
|
|
"mean_token_accuracy": 0.12499173060059547,
|
|
"num_tokens": 342847.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 6.951114463806152,
|
|
"epoch": 0.017970461054641434,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 6.5329,
|
|
"mean_token_accuracy": 0.1339307375252247,
|
|
"num_tokens": 353570.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.024112272262573,
|
|
"epoch": 0.018532037962598977,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.5861,
|
|
"mean_token_accuracy": 0.1328870877623558,
|
|
"num_tokens": 364330.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 6.923271131515503,
|
|
"epoch": 0.01909361487055652,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.6291,
|
|
"mean_token_accuracy": 0.12735793143510818,
|
|
"num_tokens": 374930.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.001209163665772,
|
|
"epoch": 0.019655191778514068,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.5985,
|
|
"mean_token_accuracy": 0.12637024670839309,
|
|
"num_tokens": 384690.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.093705129623413,
|
|
"epoch": 0.020216768686471612,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.6222,
|
|
"mean_token_accuracy": 0.13092779442667962,
|
|
"num_tokens": 395753.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 6.9514984607696535,
|
|
"epoch": 0.020778345594429155,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.5706,
|
|
"mean_token_accuracy": 0.13586961552500726,
|
|
"num_tokens": 407049.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 6.99260983467102,
|
|
"epoch": 0.021339922502386702,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 6.614,
|
|
"mean_token_accuracy": 0.13324331417679786,
|
|
"num_tokens": 417942.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 6.963890314102173,
|
|
"epoch": 0.021901499410344246,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.6224,
|
|
"mean_token_accuracy": 0.12833026573061942,
|
|
"num_tokens": 428151.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.052244853973389,
|
|
"epoch": 0.022463076318301793,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.7162,
|
|
"mean_token_accuracy": 0.12399227246642112,
|
|
"num_tokens": 439837.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 6.945697355270386,
|
|
"epoch": 0.023024653226259337,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.5155,
|
|
"mean_token_accuracy": 0.1301749385893345,
|
|
"num_tokens": 450357.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.052839756011963,
|
|
"epoch": 0.02358623013421688,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 6.5709,
|
|
"mean_token_accuracy": 0.13226377889513968,
|
|
"num_tokens": 461174.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.019093132019043,
|
|
"epoch": 0.024147807042174427,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 6.6459,
|
|
"mean_token_accuracy": 0.12973417043685914,
|
|
"num_tokens": 472785.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 6.997825956344604,
|
|
"epoch": 0.02470938395013197,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.6406,
|
|
"mean_token_accuracy": 0.13002291321754456,
|
|
"num_tokens": 483248.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 6.945517063140869,
|
|
"epoch": 0.025270960858089515,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.475,
|
|
"mean_token_accuracy": 0.13533480763435363,
|
|
"num_tokens": 494690.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.020949125289917,
|
|
"epoch": 0.025832537766047062,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.7007,
|
|
"mean_token_accuracy": 0.124896689504385,
|
|
"num_tokens": 506192.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.028987121582031,
|
|
"epoch": 0.026394114674004605,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.5915,
|
|
"mean_token_accuracy": 0.12858845070004463,
|
|
"num_tokens": 517152.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 6.942857360839843,
|
|
"epoch": 0.02695569158196215,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.5168,
|
|
"mean_token_accuracy": 0.133596034348011,
|
|
"num_tokens": 527836.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 6.9801740646362305,
|
|
"epoch": 0.027517268489919696,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.6733,
|
|
"mean_token_accuracy": 0.1276863433420658,
|
|
"num_tokens": 539491.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.092193269729615,
|
|
"epoch": 0.02807884539787724,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.654,
|
|
"mean_token_accuracy": 0.12628911882638932,
|
|
"num_tokens": 550816.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.06174373626709,
|
|
"epoch": 0.028640422305834783,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.7032,
|
|
"mean_token_accuracy": 0.12353009209036828,
|
|
"num_tokens": 561566.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 6.982790279388428,
|
|
"epoch": 0.02920199921379233,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.6345,
|
|
"mean_token_accuracy": 0.12296314612030983,
|
|
"num_tokens": 573032.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.036098527908325,
|
|
"epoch": 0.029763576121749874,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.5545,
|
|
"mean_token_accuracy": 0.13585324659943582,
|
|
"num_tokens": 584140.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 6.972643518447876,
|
|
"epoch": 0.030325153029707418,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.625,
|
|
"mean_token_accuracy": 0.13363742157816888,
|
|
"num_tokens": 595097.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.074052810668945,
|
|
"epoch": 0.030886729937664965,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.6642,
|
|
"mean_token_accuracy": 0.12557960152626038,
|
|
"num_tokens": 606797.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 6.958458995819091,
|
|
"epoch": 0.031448306845622505,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.6346,
|
|
"mean_token_accuracy": 0.1282724417746067,
|
|
"num_tokens": 618187.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.020027160644531,
|
|
"epoch": 0.032009883753580055,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.5731,
|
|
"mean_token_accuracy": 0.13057834804058074,
|
|
"num_tokens": 629829.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 6.9736052513122555,
|
|
"epoch": 0.0325714606615376,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.5896,
|
|
"mean_token_accuracy": 0.1329849384725094,
|
|
"num_tokens": 640914.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 6.921159362792968,
|
|
"epoch": 0.03313303756949514,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.6129,
|
|
"mean_token_accuracy": 0.12800714895129203,
|
|
"num_tokens": 653057.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 6.993884515762329,
|
|
"epoch": 0.033694614477452686,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.5372,
|
|
"mean_token_accuracy": 0.13587351217865945,
|
|
"num_tokens": 663437.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 6.979153728485107,
|
|
"epoch": 0.03425619138541023,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.6207,
|
|
"mean_token_accuracy": 0.12917499542236327,
|
|
"num_tokens": 675416.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 6.811232805252075,
|
|
"epoch": 0.03481776829336777,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.4163,
|
|
"mean_token_accuracy": 0.13696089312434195,
|
|
"num_tokens": 686633.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 6.947882556915284,
|
|
"epoch": 0.035379345201325324,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.5374,
|
|
"mean_token_accuracy": 0.13494077548384667,
|
|
"num_tokens": 698065.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 6.984415197372437,
|
|
"epoch": 0.03594092210928287,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.5488,
|
|
"mean_token_accuracy": 0.13275664299726486,
|
|
"num_tokens": 708652.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.001538467407227,
|
|
"epoch": 0.03650249901724041,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.716,
|
|
"mean_token_accuracy": 0.12674812003970146,
|
|
"num_tokens": 720199.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.04426908493042,
|
|
"epoch": 0.037064075925197955,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.6759,
|
|
"mean_token_accuracy": 0.12783747613430024,
|
|
"num_tokens": 732964.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 6.893573808670044,
|
|
"epoch": 0.0376256528331555,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.4504,
|
|
"mean_token_accuracy": 0.13295350223779678,
|
|
"num_tokens": 743528.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 6.9759503364562985,
|
|
"epoch": 0.03818722974111304,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.5345,
|
|
"mean_token_accuracy": 0.13175515085458755,
|
|
"num_tokens": 754365.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 6.8153159618377686,
|
|
"epoch": 0.03874880664907059,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.4614,
|
|
"mean_token_accuracy": 0.131683911383152,
|
|
"num_tokens": 766094.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 6.927649307250976,
|
|
"epoch": 0.039310383557028136,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.5365,
|
|
"mean_token_accuracy": 0.13060494735836983,
|
|
"num_tokens": 777275.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 6.932587432861328,
|
|
"epoch": 0.03987196046498568,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.6145,
|
|
"mean_token_accuracy": 0.13159823268651963,
|
|
"num_tokens": 789436.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 6.913347625732422,
|
|
"epoch": 0.040433537372943223,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.6299,
|
|
"mean_token_accuracy": 0.13135476037859917,
|
|
"num_tokens": 800164.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 6.842929649353027,
|
|
"epoch": 0.04099511428090077,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.5077,
|
|
"mean_token_accuracy": 0.13295300006866456,
|
|
"num_tokens": 811797.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 6.945403099060059,
|
|
"epoch": 0.04155669118885831,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.5181,
|
|
"mean_token_accuracy": 0.13189431577920913,
|
|
"num_tokens": 824158.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 6.845687580108643,
|
|
"epoch": 0.04211826809681586,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.517,
|
|
"mean_token_accuracy": 0.13648107424378395,
|
|
"num_tokens": 835803.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 6.995227909088134,
|
|
"epoch": 0.042679845004773405,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.6006,
|
|
"mean_token_accuracy": 0.12846365720033645,
|
|
"num_tokens": 848106.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 6.88704137802124,
|
|
"epoch": 0.04324142191273095,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.5878,
|
|
"mean_token_accuracy": 0.12994857951998712,
|
|
"num_tokens": 859101.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 6.8107438564300535,
|
|
"epoch": 0.04380299882068849,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.4562,
|
|
"mean_token_accuracy": 0.1323493629693985,
|
|
"num_tokens": 870309.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 6.995388984680176,
|
|
"epoch": 0.044364575728646036,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.5557,
|
|
"mean_token_accuracy": 0.1317988380789757,
|
|
"num_tokens": 881515.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 6.84275221824646,
|
|
"epoch": 0.044926152636603586,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.5152,
|
|
"mean_token_accuracy": 0.13594210967421533,
|
|
"num_tokens": 892129.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 6.88900990486145,
|
|
"epoch": 0.04548772954456113,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.5348,
|
|
"mean_token_accuracy": 0.1257748119533062,
|
|
"num_tokens": 903186.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 6.874643039703369,
|
|
"epoch": 0.046049306452518673,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.5074,
|
|
"mean_token_accuracy": 0.13315046355128288,
|
|
"num_tokens": 913471.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 6.908110284805298,
|
|
"epoch": 0.04661088336047622,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.5171,
|
|
"mean_token_accuracy": 0.12603104412555693,
|
|
"num_tokens": 924283.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 6.892792367935181,
|
|
"epoch": 0.04717246026843376,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.5449,
|
|
"mean_token_accuracy": 0.13619182109832764,
|
|
"num_tokens": 934975.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 6.853797531127929,
|
|
"epoch": 0.047734037176391304,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.4157,
|
|
"mean_token_accuracy": 0.13784429281949998,
|
|
"num_tokens": 945587.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 6.832434177398682,
|
|
"epoch": 0.048295614084348855,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.4868,
|
|
"mean_token_accuracy": 0.12879071310162543,
|
|
"num_tokens": 955935.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 6.8071524143219,
|
|
"epoch": 0.0488571909923064,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.4581,
|
|
"mean_token_accuracy": 0.13443006500601767,
|
|
"num_tokens": 967960.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.865250539779663,
|
|
"epoch": 0.04941876790026394,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.509,
|
|
"mean_token_accuracy": 0.1331017218530178,
|
|
"num_tokens": 979680.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 6.868223047256469,
|
|
"epoch": 0.049980344808221486,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.5873,
|
|
"mean_token_accuracy": 0.13184501379728317,
|
|
"num_tokens": 990600.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.990716028213501,
|
|
"epoch": 0.05054192171617903,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.6286,
|
|
"mean_token_accuracy": 0.1356397032737732,
|
|
"num_tokens": 1002331.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.83350019454956,
|
|
"epoch": 0.05110349862413657,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.4445,
|
|
"mean_token_accuracy": 0.13236786276102067,
|
|
"num_tokens": 1013473.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.865316438674927,
|
|
"epoch": 0.051665075532094124,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.5207,
|
|
"mean_token_accuracy": 0.13039045557379722,
|
|
"num_tokens": 1024434.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.890588569641113,
|
|
"epoch": 0.05222665244005167,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.5385,
|
|
"mean_token_accuracy": 0.12809760123491287,
|
|
"num_tokens": 1035452.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.826921796798706,
|
|
"epoch": 0.05278822934800921,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.4174,
|
|
"mean_token_accuracy": 0.13453132212162017,
|
|
"num_tokens": 1046213.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.771785497665405,
|
|
"epoch": 0.053349806255966754,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.4467,
|
|
"mean_token_accuracy": 0.13567724153399469,
|
|
"num_tokens": 1057469.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.0101700782775875,
|
|
"epoch": 0.0539113831639243,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.5996,
|
|
"mean_token_accuracy": 0.1290132947266102,
|
|
"num_tokens": 1069543.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.71439380645752,
|
|
"epoch": 0.05447296007188184,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.4728,
|
|
"mean_token_accuracy": 0.13269706442952156,
|
|
"num_tokens": 1080476.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.954592084884643,
|
|
"epoch": 0.05503453697983939,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.5828,
|
|
"mean_token_accuracy": 0.1320900909602642,
|
|
"num_tokens": 1091700.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.786695575714111,
|
|
"epoch": 0.055596113887796936,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.4695,
|
|
"mean_token_accuracy": 0.13233320266008378,
|
|
"num_tokens": 1103056.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.886286687850952,
|
|
"epoch": 0.05615769079575448,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.5359,
|
|
"mean_token_accuracy": 0.13645913898944856,
|
|
"num_tokens": 1114836.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.760018682479858,
|
|
"epoch": 0.05671926770371202,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.447,
|
|
"mean_token_accuracy": 0.13287583217024804,
|
|
"num_tokens": 1125993.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.874892234802246,
|
|
"epoch": 0.05728084461166957,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.5176,
|
|
"mean_token_accuracy": 0.13570363372564315,
|
|
"num_tokens": 1136719.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.795416641235351,
|
|
"epoch": 0.05784242151962711,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.4023,
|
|
"mean_token_accuracy": 0.13578868433833122,
|
|
"num_tokens": 1146947.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.826411437988281,
|
|
"epoch": 0.05840399842758466,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.5302,
|
|
"mean_token_accuracy": 0.13053593188524246,
|
|
"num_tokens": 1157974.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.750731325149536,
|
|
"epoch": 0.058965575335542204,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.4664,
|
|
"mean_token_accuracy": 0.13042562529444696,
|
|
"num_tokens": 1168573.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.815242910385132,
|
|
"epoch": 0.05952715224349975,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.3647,
|
|
"mean_token_accuracy": 0.13693853691220284,
|
|
"num_tokens": 1178446.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.811131572723388,
|
|
"epoch": 0.06008872915145729,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.3944,
|
|
"mean_token_accuracy": 0.13583947718143463,
|
|
"num_tokens": 1190558.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.737180471420288,
|
|
"epoch": 0.060650306059414835,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.5615,
|
|
"mean_token_accuracy": 0.13333362191915513,
|
|
"num_tokens": 1201929.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.711785936355591,
|
|
"epoch": 0.06121188296737238,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.407,
|
|
"mean_token_accuracy": 0.13147006183862686,
|
|
"num_tokens": 1213155.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.913523435592651,
|
|
"epoch": 0.06177345987532993,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.4767,
|
|
"mean_token_accuracy": 0.13126003369688988,
|
|
"num_tokens": 1223961.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.638333320617676,
|
|
"epoch": 0.06233503678328747,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.3667,
|
|
"mean_token_accuracy": 0.1402271084487438,
|
|
"num_tokens": 1233888.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.733293151855468,
|
|
"epoch": 0.06289661369124501,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.4953,
|
|
"mean_token_accuracy": 0.12470907121896743,
|
|
"num_tokens": 1244405.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.823939466476441,
|
|
"epoch": 0.06345819059920256,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.4405,
|
|
"mean_token_accuracy": 0.13227839171886444,
|
|
"num_tokens": 1257099.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.827079486846924,
|
|
"epoch": 0.06401976750716011,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.5325,
|
|
"mean_token_accuracy": 0.13312843218445777,
|
|
"num_tokens": 1267965.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.744953536987305,
|
|
"epoch": 0.06458134441511765,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.4552,
|
|
"mean_token_accuracy": 0.13036884516477584,
|
|
"num_tokens": 1280075.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.849108505249023,
|
|
"epoch": 0.0651429213230752,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.4498,
|
|
"mean_token_accuracy": 0.13528711795806886,
|
|
"num_tokens": 1290574.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.740403699874878,
|
|
"epoch": 0.06570449823103273,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.431,
|
|
"mean_token_accuracy": 0.141810342669487,
|
|
"num_tokens": 1302680.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.773650121688843,
|
|
"epoch": 0.06626607513899029,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.4158,
|
|
"mean_token_accuracy": 0.13916678130626678,
|
|
"num_tokens": 1314577.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.780707979202271,
|
|
"epoch": 0.06682765204694784,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.5412,
|
|
"mean_token_accuracy": 0.1369754306972027,
|
|
"num_tokens": 1326560.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.899291849136352,
|
|
"epoch": 0.06738922895490537,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.6101,
|
|
"mean_token_accuracy": 0.128566275537014,
|
|
"num_tokens": 1339105.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.5432719707489015,
|
|
"epoch": 0.06795080586286292,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.2816,
|
|
"mean_token_accuracy": 0.1405505046248436,
|
|
"num_tokens": 1349914.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.829094409942627,
|
|
"epoch": 0.06851238277082046,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.5035,
|
|
"mean_token_accuracy": 0.1318673647940159,
|
|
"num_tokens": 1361700.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.7323582649230955,
|
|
"epoch": 0.06907395967877801,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.524,
|
|
"mean_token_accuracy": 0.1338668704032898,
|
|
"num_tokens": 1373103.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.701350355148316,
|
|
"epoch": 0.06963553658673555,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.3164,
|
|
"mean_token_accuracy": 0.14012459367513658,
|
|
"num_tokens": 1383742.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.640402126312256,
|
|
"epoch": 0.0701971134946931,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.4778,
|
|
"mean_token_accuracy": 0.1333733394742012,
|
|
"num_tokens": 1396656.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.783367872238159,
|
|
"epoch": 0.07075869040265065,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.3468,
|
|
"mean_token_accuracy": 0.15129355043172837,
|
|
"num_tokens": 1406709.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.7202239513397215,
|
|
"epoch": 0.07132026731060818,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.3802,
|
|
"mean_token_accuracy": 0.14140321388840676,
|
|
"num_tokens": 1417793.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.755014324188233,
|
|
"epoch": 0.07188184421856574,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.4691,
|
|
"mean_token_accuracy": 0.13631825447082518,
|
|
"num_tokens": 1429093.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.677226877212524,
|
|
"epoch": 0.07244342112652327,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.3998,
|
|
"mean_token_accuracy": 0.14246537908911705,
|
|
"num_tokens": 1440907.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.728086280822754,
|
|
"epoch": 0.07300499803448082,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.4661,
|
|
"mean_token_accuracy": 0.1364982731640339,
|
|
"num_tokens": 1452089.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.749984645843506,
|
|
"epoch": 0.07356657494243837,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.4943,
|
|
"mean_token_accuracy": 0.1323855087161064,
|
|
"num_tokens": 1464378.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.694591379165649,
|
|
"epoch": 0.07412815185039591,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.4131,
|
|
"mean_token_accuracy": 0.13516984954476358,
|
|
"num_tokens": 1476678.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.660327816009522,
|
|
"epoch": 0.07468972875835346,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.2587,
|
|
"mean_token_accuracy": 0.1437138944864273,
|
|
"num_tokens": 1486808.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.783201026916504,
|
|
"epoch": 0.075251305666311,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.5481,
|
|
"mean_token_accuracy": 0.12994321286678315,
|
|
"num_tokens": 1499281.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.711549758911133,
|
|
"epoch": 0.07581288257426855,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.4505,
|
|
"mean_token_accuracy": 0.13625041544437408,
|
|
"num_tokens": 1510202.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.67443437576294,
|
|
"epoch": 0.07637445948222608,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.3292,
|
|
"mean_token_accuracy": 0.14246201664209365,
|
|
"num_tokens": 1521492.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.584014463424682,
|
|
"epoch": 0.07693603639018363,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.3419,
|
|
"mean_token_accuracy": 0.14672905653715135,
|
|
"num_tokens": 1532856.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.675293254852295,
|
|
"epoch": 0.07749761329814119,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.3414,
|
|
"mean_token_accuracy": 0.13955900371074675,
|
|
"num_tokens": 1543408.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.606938409805298,
|
|
"epoch": 0.07805919020609872,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.3889,
|
|
"mean_token_accuracy": 0.13311915546655656,
|
|
"num_tokens": 1555474.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.718470048904419,
|
|
"epoch": 0.07862076711405627,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.4749,
|
|
"mean_token_accuracy": 0.13796819001436234,
|
|
"num_tokens": 1567484.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.613565444946289,
|
|
"epoch": 0.07918234402201381,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.3032,
|
|
"mean_token_accuracy": 0.1469588965177536,
|
|
"num_tokens": 1578204.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.695013618469238,
|
|
"epoch": 0.07974392092997136,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.3049,
|
|
"mean_token_accuracy": 0.13991812244057655,
|
|
"num_tokens": 1589012.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.560267734527588,
|
|
"epoch": 0.08030549783792891,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.3206,
|
|
"mean_token_accuracy": 0.139244681596756,
|
|
"num_tokens": 1601099.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.70271053314209,
|
|
"epoch": 0.08086707474588645,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.4769,
|
|
"mean_token_accuracy": 0.13117794394493104,
|
|
"num_tokens": 1612814.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.733196353912353,
|
|
"epoch": 0.081428651653844,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.3706,
|
|
"mean_token_accuracy": 0.13757371306419372,
|
|
"num_tokens": 1624953.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.5949835777282715,
|
|
"epoch": 0.08199022856180153,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.4122,
|
|
"mean_token_accuracy": 0.1355846755206585,
|
|
"num_tokens": 1635673.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.634992599487305,
|
|
"epoch": 0.08255180546975908,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.3149,
|
|
"mean_token_accuracy": 0.14333953484892845,
|
|
"num_tokens": 1647282.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.590029048919678,
|
|
"epoch": 0.08311338237771662,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.3328,
|
|
"mean_token_accuracy": 0.1433751843869686,
|
|
"num_tokens": 1658426.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.614629554748535,
|
|
"epoch": 0.08367495928567417,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.3629,
|
|
"mean_token_accuracy": 0.1389339104294777,
|
|
"num_tokens": 1669958.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.658067321777343,
|
|
"epoch": 0.08423653619363172,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.4213,
|
|
"mean_token_accuracy": 0.13475271239876746,
|
|
"num_tokens": 1682409.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.597114753723145,
|
|
"epoch": 0.08479811310158926,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.3431,
|
|
"mean_token_accuracy": 0.1512242317199707,
|
|
"num_tokens": 1692409.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.711719036102295,
|
|
"epoch": 0.08535969000954681,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.4225,
|
|
"mean_token_accuracy": 0.13909337669610977,
|
|
"num_tokens": 1705018.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.600584983825684,
|
|
"epoch": 0.08592126691750435,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.3506,
|
|
"mean_token_accuracy": 0.1366318315267563,
|
|
"num_tokens": 1715625.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.598914957046508,
|
|
"epoch": 0.0864828438254619,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.4358,
|
|
"mean_token_accuracy": 0.13147977441549302,
|
|
"num_tokens": 1727045.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.7401669979095455,
|
|
"epoch": 0.08704442073341945,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.5042,
|
|
"mean_token_accuracy": 0.13844706639647483,
|
|
"num_tokens": 1737374.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.725053167343139,
|
|
"epoch": 0.08760599764137698,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.484,
|
|
"mean_token_accuracy": 0.1349758803844452,
|
|
"num_tokens": 1747788.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.476839303970337,
|
|
"epoch": 0.08816757454933453,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.1905,
|
|
"mean_token_accuracy": 0.14935870766639708,
|
|
"num_tokens": 1757769.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.5435089588165285,
|
|
"epoch": 0.08872915145729207,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.3098,
|
|
"mean_token_accuracy": 0.13398686051368713,
|
|
"num_tokens": 1769246.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.666951322555542,
|
|
"epoch": 0.08929072836524962,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.4301,
|
|
"mean_token_accuracy": 0.13988927975296975,
|
|
"num_tokens": 1781306.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.621778106689453,
|
|
"epoch": 0.08985230527320717,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.3204,
|
|
"mean_token_accuracy": 0.14044865369796752,
|
|
"num_tokens": 1792888.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.572351598739624,
|
|
"epoch": 0.09041388218116471,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.3445,
|
|
"mean_token_accuracy": 0.146021768450737,
|
|
"num_tokens": 1802938.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.656881046295166,
|
|
"epoch": 0.09097545908912226,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.3536,
|
|
"mean_token_accuracy": 0.13862004801630973,
|
|
"num_tokens": 1814738.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.619713163375854,
|
|
"epoch": 0.0915370359970798,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.4315,
|
|
"mean_token_accuracy": 0.14092215448617934,
|
|
"num_tokens": 1825100.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.440285301208496,
|
|
"epoch": 0.09209861290503735,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.2709,
|
|
"mean_token_accuracy": 0.14654000774025916,
|
|
"num_tokens": 1835879.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.788227272033692,
|
|
"epoch": 0.09266018981299488,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.4236,
|
|
"mean_token_accuracy": 0.13221182823181152,
|
|
"num_tokens": 1848352.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.550888586044311,
|
|
"epoch": 0.09322176672095243,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.3654,
|
|
"mean_token_accuracy": 0.13856692165136336,
|
|
"num_tokens": 1859687.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.565574073791504,
|
|
"epoch": 0.09378334362890998,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.3691,
|
|
"mean_token_accuracy": 0.14064017236232756,
|
|
"num_tokens": 1871438.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.58135290145874,
|
|
"epoch": 0.09434492053686752,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.25,
|
|
"mean_token_accuracy": 0.1493062250316143,
|
|
"num_tokens": 1881519.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.656439733505249,
|
|
"epoch": 0.09490649744482507,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.4275,
|
|
"mean_token_accuracy": 0.13461267650127412,
|
|
"num_tokens": 1892428.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.692960023880005,
|
|
"epoch": 0.09546807435278261,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.3208,
|
|
"mean_token_accuracy": 0.1437561698257923,
|
|
"num_tokens": 1903760.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.522662353515625,
|
|
"epoch": 0.09602965126074016,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.3783,
|
|
"mean_token_accuracy": 0.13410450741648675,
|
|
"num_tokens": 1915430.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.594115972518921,
|
|
"epoch": 0.09659122816869771,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.3324,
|
|
"mean_token_accuracy": 0.1378035582602024,
|
|
"num_tokens": 1925709.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.645199775695801,
|
|
"epoch": 0.09715280507665525,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.3761,
|
|
"mean_token_accuracy": 0.1379880949854851,
|
|
"num_tokens": 1938148.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.36707878112793,
|
|
"epoch": 0.0977143819846128,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.2556,
|
|
"mean_token_accuracy": 0.14044615030288696,
|
|
"num_tokens": 1949028.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.615007495880127,
|
|
"epoch": 0.09827595889257033,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.3155,
|
|
"mean_token_accuracy": 0.14169368892908096,
|
|
"num_tokens": 1960353.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.591008424758911,
|
|
"epoch": 0.09883753580052788,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.4238,
|
|
"mean_token_accuracy": 0.13767419308423995,
|
|
"num_tokens": 1972335.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.504133701324463,
|
|
"epoch": 0.09939911270848542,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.2723,
|
|
"mean_token_accuracy": 0.14177839010953902,
|
|
"num_tokens": 1982851.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.495877361297607,
|
|
"epoch": 0.09996068961644297,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.2433,
|
|
"mean_token_accuracy": 0.14337393641471863,
|
|
"num_tokens": 1993931.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.582594537734986,
|
|
"epoch": 0.10052226652440052,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.381,
|
|
"mean_token_accuracy": 0.1384746566414833,
|
|
"num_tokens": 2004838.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.437647104263306,
|
|
"epoch": 0.10108384343235806,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.1842,
|
|
"mean_token_accuracy": 0.14243700206279755,
|
|
"num_tokens": 2015620.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.569198560714722,
|
|
"epoch": 0.10164542034031561,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.3106,
|
|
"mean_token_accuracy": 0.14497067034244537,
|
|
"num_tokens": 2027489.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.397192287445068,
|
|
"epoch": 0.10220699724827315,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.194,
|
|
"mean_token_accuracy": 0.14697765707969665,
|
|
"num_tokens": 2038475.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.452962160110474,
|
|
"epoch": 0.1027685741562307,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.1966,
|
|
"mean_token_accuracy": 0.14352490305900573,
|
|
"num_tokens": 2048938.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.477091646194458,
|
|
"epoch": 0.10333015106418825,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.2972,
|
|
"mean_token_accuracy": 0.13728735148906707,
|
|
"num_tokens": 2060372.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.470232009887695,
|
|
"epoch": 0.10389172797214578,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.2836,
|
|
"mean_token_accuracy": 0.13895049095153808,
|
|
"num_tokens": 2071558.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.541862058639526,
|
|
"epoch": 0.10445330488010333,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.3173,
|
|
"mean_token_accuracy": 0.13610014989972113,
|
|
"num_tokens": 2082350.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.466197681427002,
|
|
"epoch": 0.10501488178806087,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.37,
|
|
"mean_token_accuracy": 0.14044060856103896,
|
|
"num_tokens": 2093448.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.683929204940796,
|
|
"epoch": 0.10557645869601842,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.3979,
|
|
"mean_token_accuracy": 0.13594734519720078,
|
|
"num_tokens": 2104171.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.433077430725097,
|
|
"epoch": 0.10613803560397596,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.2868,
|
|
"mean_token_accuracy": 0.1391531579196453,
|
|
"num_tokens": 2114496.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.5762317180633545,
|
|
"epoch": 0.10669961251193351,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.2747,
|
|
"mean_token_accuracy": 0.14130542203783988,
|
|
"num_tokens": 2125930.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.492092609405518,
|
|
"epoch": 0.10726118941989106,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.2387,
|
|
"mean_token_accuracy": 0.14300135299563407,
|
|
"num_tokens": 2136452.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.472325229644776,
|
|
"epoch": 0.1078227663278486,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.3419,
|
|
"mean_token_accuracy": 0.13892039209604262,
|
|
"num_tokens": 2148233.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.37879753112793,
|
|
"epoch": 0.10838434323580615,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.1324,
|
|
"mean_token_accuracy": 0.14699541106820108,
|
|
"num_tokens": 2159475.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.397939586639405,
|
|
"epoch": 0.10894592014376368,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.2593,
|
|
"mean_token_accuracy": 0.14171308875083924,
|
|
"num_tokens": 2170042.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.4696125984191895,
|
|
"epoch": 0.10950749705172123,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.2453,
|
|
"mean_token_accuracy": 0.13840788900852202,
|
|
"num_tokens": 2182234.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.4058380126953125,
|
|
"epoch": 0.11006907395967878,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.2491,
|
|
"mean_token_accuracy": 0.14312953129410744,
|
|
"num_tokens": 2192477.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.388981103897095,
|
|
"epoch": 0.11063065086763632,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.2388,
|
|
"mean_token_accuracy": 0.14177233427762986,
|
|
"num_tokens": 2203082.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.4049492359161375,
|
|
"epoch": 0.11119222777559387,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.2167,
|
|
"mean_token_accuracy": 0.14464509785175322,
|
|
"num_tokens": 2213684.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.415097045898437,
|
|
"epoch": 0.11175380468355141,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.2157,
|
|
"mean_token_accuracy": 0.1419524908065796,
|
|
"num_tokens": 2225524.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.487058210372925,
|
|
"epoch": 0.11231538159150896,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.1869,
|
|
"mean_token_accuracy": 0.1425313711166382,
|
|
"num_tokens": 2236004.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.465081977844238,
|
|
"epoch": 0.1128769584994665,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499999997707492,
|
|
"loss": 6.3333,
|
|
"mean_token_accuracy": 0.13484762981534004,
|
|
"num_tokens": 2247730.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.48140435218811,
|
|
"epoch": 0.11343853540742405,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999999883941787,
|
|
"loss": 6.2913,
|
|
"mean_token_accuracy": 0.14429717510938644,
|
|
"num_tokens": 2260132.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.403030157089233,
|
|
"epoch": 0.1140001123153816,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999999719167785,
|
|
"loss": 6.2629,
|
|
"mean_token_accuracy": 0.1453886643052101,
|
|
"num_tokens": 2270060.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.4181787967681885,
|
|
"epoch": 0.11456168922333913,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999999482752917,
|
|
"loss": 6.2805,
|
|
"mean_token_accuracy": 0.14259432330727578,
|
|
"num_tokens": 2281568.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.476824760437012,
|
|
"epoch": 0.11512326613129668,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999999174697195,
|
|
"loss": 6.2901,
|
|
"mean_token_accuracy": 0.13487386032938958,
|
|
"num_tokens": 2293325.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.481242752075195,
|
|
"epoch": 0.11568484303925422,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999998795000627,
|
|
"loss": 6.293,
|
|
"mean_token_accuracy": 0.14598456174135208,
|
|
"num_tokens": 2304780.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.406403398513794,
|
|
"epoch": 0.11624641994721177,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999998343663223,
|
|
"loss": 6.2363,
|
|
"mean_token_accuracy": 0.13638271912932395,
|
|
"num_tokens": 2315999.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.472362041473389,
|
|
"epoch": 0.11680799685516932,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999997820685,
|
|
"loss": 6.3868,
|
|
"mean_token_accuracy": 0.14324138388037683,
|
|
"num_tokens": 2326695.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.4760270595550535,
|
|
"epoch": 0.11736957376312686,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999997226065974,
|
|
"loss": 6.2064,
|
|
"mean_token_accuracy": 0.15152312070131302,
|
|
"num_tokens": 2336925.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.393593263626099,
|
|
"epoch": 0.11793115067108441,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999996559806163,
|
|
"loss": 6.1246,
|
|
"mean_token_accuracy": 0.1490764707326889,
|
|
"num_tokens": 2347431.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.360946941375732,
|
|
"epoch": 0.11849272757904195,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999995821905589,
|
|
"loss": 6.2297,
|
|
"mean_token_accuracy": 0.14785884395241738,
|
|
"num_tokens": 2359894.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.376661109924316,
|
|
"epoch": 0.1190543044869995,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999995012364276,
|
|
"loss": 6.2571,
|
|
"mean_token_accuracy": 0.14182159453630447,
|
|
"num_tokens": 2371181.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.43308916091919,
|
|
"epoch": 0.11961588139495703,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999994131182248,
|
|
"loss": 6.1609,
|
|
"mean_token_accuracy": 0.14217472076416016,
|
|
"num_tokens": 2381531.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.453187465667725,
|
|
"epoch": 0.12017745830291458,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999993178359535,
|
|
"loss": 6.2808,
|
|
"mean_token_accuracy": 0.1432340309023857,
|
|
"num_tokens": 2391573.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.3629372119903564,
|
|
"epoch": 0.12073903521087213,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999992153896166,
|
|
"loss": 6.2391,
|
|
"mean_token_accuracy": 0.14391963332891464,
|
|
"num_tokens": 2402822.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.405177211761474,
|
|
"epoch": 0.12130061211882967,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999991057792175,
|
|
"loss": 6.1633,
|
|
"mean_token_accuracy": 0.14490702822804452,
|
|
"num_tokens": 2414322.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.475324583053589,
|
|
"epoch": 0.12186218902678722,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999989890047596,
|
|
"loss": 6.347,
|
|
"mean_token_accuracy": 0.1440906621515751,
|
|
"num_tokens": 2426560.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.456641006469726,
|
|
"epoch": 0.12242376593474476,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999988650662467,
|
|
"loss": 6.2586,
|
|
"mean_token_accuracy": 0.1443517878651619,
|
|
"num_tokens": 2437723.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.335519123077392,
|
|
"epoch": 0.12298534284270231,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999987339636825,
|
|
"loss": 6.2082,
|
|
"mean_token_accuracy": 0.14743260070681571,
|
|
"num_tokens": 2448497.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.297663021087646,
|
|
"epoch": 0.12354691975065986,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999985956970713,
|
|
"loss": 6.0868,
|
|
"mean_token_accuracy": 0.15371182709932327,
|
|
"num_tokens": 2459089.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.3653172016143795,
|
|
"epoch": 0.1241084966586174,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999984502664178,
|
|
"loss": 6.1582,
|
|
"mean_token_accuracy": 0.15073663890361785,
|
|
"num_tokens": 2469882.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.339643955230713,
|
|
"epoch": 0.12467007356657495,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999982976717261,
|
|
"loss": 6.1994,
|
|
"mean_token_accuracy": 0.14943020194768905,
|
|
"num_tokens": 2482120.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.432038021087647,
|
|
"epoch": 0.1252316504745325,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999981379130016,
|
|
"loss": 6.215,
|
|
"mean_token_accuracy": 0.1437155120074749,
|
|
"num_tokens": 2492626.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.460601425170898,
|
|
"epoch": 0.12579322738249002,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499997970990249,
|
|
"loss": 6.2638,
|
|
"mean_token_accuracy": 0.14326856955885886,
|
|
"num_tokens": 2506347.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.244403314590454,
|
|
"epoch": 0.12635480429044757,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999977969034737,
|
|
"loss": 6.1527,
|
|
"mean_token_accuracy": 0.15141456723213195,
|
|
"num_tokens": 2516584.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.383342456817627,
|
|
"epoch": 0.12691638119840512,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999976156526814,
|
|
"loss": 6.1966,
|
|
"mean_token_accuracy": 0.1493828549981117,
|
|
"num_tokens": 2526731.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.324274206161499,
|
|
"epoch": 0.12747795810636267,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999974272378776,
|
|
"loss": 6.0998,
|
|
"mean_token_accuracy": 0.15336599498987197,
|
|
"num_tokens": 2537180.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.393867540359497,
|
|
"epoch": 0.12803953501432022,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999972316590685,
|
|
"loss": 6.1904,
|
|
"mean_token_accuracy": 0.14489513039588928,
|
|
"num_tokens": 2547617.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.284448671340942,
|
|
"epoch": 0.12860111192227774,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999970289162604,
|
|
"loss": 6.0558,
|
|
"mean_token_accuracy": 0.15631555318832396,
|
|
"num_tokens": 2557743.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.3023943424224855,
|
|
"epoch": 0.1291626888302353,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999968190094595,
|
|
"loss": 6.1694,
|
|
"mean_token_accuracy": 0.14730207920074462,
|
|
"num_tokens": 2568351.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.266475439071655,
|
|
"epoch": 0.12972426573819285,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999966019386727,
|
|
"loss": 6.2243,
|
|
"mean_token_accuracy": 0.1486775517463684,
|
|
"num_tokens": 2579703.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.48288254737854,
|
|
"epoch": 0.1302858426461504,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999963777039067,
|
|
"loss": 6.202,
|
|
"mean_token_accuracy": 0.1458014190196991,
|
|
"num_tokens": 2591197.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.293277406692505,
|
|
"epoch": 0.13084741955410795,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499996146305169,
|
|
"loss": 6.1625,
|
|
"mean_token_accuracy": 0.14280997961759567,
|
|
"num_tokens": 2601836.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.247816705703736,
|
|
"epoch": 0.13140899646206547,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999959077424665,
|
|
"loss": 6.1171,
|
|
"mean_token_accuracy": 0.14851301163434982,
|
|
"num_tokens": 2613513.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.337481117248535,
|
|
"epoch": 0.13197057337002302,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999956620158072,
|
|
"loss": 6.1561,
|
|
"mean_token_accuracy": 0.14839788228273393,
|
|
"num_tokens": 2625246.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.3013852596282955,
|
|
"epoch": 0.13253215027798057,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999954091251987,
|
|
"loss": 6.1219,
|
|
"mean_token_accuracy": 0.1513855129480362,
|
|
"num_tokens": 2636375.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.3086591243743895,
|
|
"epoch": 0.13309372718593812,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999951490706491,
|
|
"loss": 6.211,
|
|
"mean_token_accuracy": 0.14393428042531015,
|
|
"num_tokens": 2648586.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.401763534545898,
|
|
"epoch": 0.13365530409389567,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999948818521667,
|
|
"loss": 6.2164,
|
|
"mean_token_accuracy": 0.15318685173988342,
|
|
"num_tokens": 2660847.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.29134726524353,
|
|
"epoch": 0.1342168810018532,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00049999460746976,
|
|
"loss": 6.1473,
|
|
"mean_token_accuracy": 0.14875885099172592,
|
|
"num_tokens": 2671160.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.482362604141235,
|
|
"epoch": 0.13477845790981074,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999943259234377,
|
|
"loss": 6.2605,
|
|
"mean_token_accuracy": 0.144464373588562,
|
|
"num_tokens": 2681622.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.207872486114502,
|
|
"epoch": 0.1353400348177683,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999940372132089,
|
|
"loss": 6.0459,
|
|
"mean_token_accuracy": 0.15137153267860412,
|
|
"num_tokens": 2691503.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.269325542449951,
|
|
"epoch": 0.13590161172572585,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999937413390826,
|
|
"loss": 6.1656,
|
|
"mean_token_accuracy": 0.14382996857166291,
|
|
"num_tokens": 2702207.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.334103918075561,
|
|
"epoch": 0.1364631886336834,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999934383010683,
|
|
"loss": 6.155,
|
|
"mean_token_accuracy": 0.1459783896803856,
|
|
"num_tokens": 2713178.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.360417366027832,
|
|
"epoch": 0.13702476554164092,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999931280991757,
|
|
"loss": 6.1601,
|
|
"mean_token_accuracy": 0.15585049539804458,
|
|
"num_tokens": 2723717.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.296167993545533,
|
|
"epoch": 0.13758634244959847,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999928107334146,
|
|
"loss": 6.2208,
|
|
"mean_token_accuracy": 0.142020982503891,
|
|
"num_tokens": 2735669.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.2710144996643065,
|
|
"epoch": 0.13814791935755602,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999924862037952,
|
|
"loss": 6.1297,
|
|
"mean_token_accuracy": 0.14939224869012832,
|
|
"num_tokens": 2746087.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.290295934677124,
|
|
"epoch": 0.13870949626551357,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999921545103278,
|
|
"loss": 6.143,
|
|
"mean_token_accuracy": 0.1474170580506325,
|
|
"num_tokens": 2757143.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.402835416793823,
|
|
"epoch": 0.1392710731734711,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999918156530229,
|
|
"loss": 6.2416,
|
|
"mean_token_accuracy": 0.14436521381139755,
|
|
"num_tokens": 2769340.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.353951168060303,
|
|
"epoch": 0.13983265008142864,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999914696318913,
|
|
"loss": 6.1601,
|
|
"mean_token_accuracy": 0.14525908827781678,
|
|
"num_tokens": 2779514.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.312722253799438,
|
|
"epoch": 0.1403942269893862,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999911164469441,
|
|
"loss": 6.0998,
|
|
"mean_token_accuracy": 0.1497655987739563,
|
|
"num_tokens": 2790801.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.249200296401978,
|
|
"epoch": 0.14095580389734375,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999907560981925,
|
|
"loss": 6.0947,
|
|
"mean_token_accuracy": 0.1503822013735771,
|
|
"num_tokens": 2801082.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.284300231933594,
|
|
"epoch": 0.1415173808053013,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999903885856479,
|
|
"loss": 6.1092,
|
|
"mean_token_accuracy": 0.14815400838851928,
|
|
"num_tokens": 2812719.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.227870082855224,
|
|
"epoch": 0.14207895771325882,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499990013909322,
|
|
"loss": 6.1087,
|
|
"mean_token_accuracy": 0.14787399768829346,
|
|
"num_tokens": 2823766.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.272064590454102,
|
|
"epoch": 0.14264053462121637,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499989632069227,
|
|
"loss": 6.1973,
|
|
"mean_token_accuracy": 0.14443453252315522,
|
|
"num_tokens": 2834801.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.274245309829712,
|
|
"epoch": 0.14320211152917392,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999892430653747,
|
|
"loss": 6.0189,
|
|
"mean_token_accuracy": 0.1519506961107254,
|
|
"num_tokens": 2845769.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.176938724517822,
|
|
"epoch": 0.14376368843713147,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999888468977776,
|
|
"loss": 6.0579,
|
|
"mean_token_accuracy": 0.1528223842382431,
|
|
"num_tokens": 2856001.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.2550255298614506,
|
|
"epoch": 0.14432526534508902,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999884435664485,
|
|
"loss": 6.0874,
|
|
"mean_token_accuracy": 0.15212968960404397,
|
|
"num_tokens": 2867703.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.179595184326172,
|
|
"epoch": 0.14488684225304654,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999880330714,
|
|
"loss": 6.0396,
|
|
"mean_token_accuracy": 0.15258833020925522,
|
|
"num_tokens": 2878671.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.2422667980194095,
|
|
"epoch": 0.1454484191610041,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999876154126453,
|
|
"loss": 6.1536,
|
|
"mean_token_accuracy": 0.1454537458717823,
|
|
"num_tokens": 2890137.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.2193653106689455,
|
|
"epoch": 0.14600999606896164,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999871905901977,
|
|
"loss": 6.0568,
|
|
"mean_token_accuracy": 0.15350484400987624,
|
|
"num_tokens": 2900344.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.197004318237305,
|
|
"epoch": 0.1465715729769192,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999867586040706,
|
|
"loss": 6.0832,
|
|
"mean_token_accuracy": 0.1501095861196518,
|
|
"num_tokens": 2912270.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.325214147567749,
|
|
"epoch": 0.14713314988487675,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999863194542779,
|
|
"loss": 6.1474,
|
|
"mean_token_accuracy": 0.142381751537323,
|
|
"num_tokens": 2924677.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.198146820068359,
|
|
"epoch": 0.14769472679283427,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999858731408336,
|
|
"loss": 6.0754,
|
|
"mean_token_accuracy": 0.1535286396741867,
|
|
"num_tokens": 2935794.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.309402561187744,
|
|
"epoch": 0.14825630370079182,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999854196637518,
|
|
"loss": 6.1807,
|
|
"mean_token_accuracy": 0.1483509808778763,
|
|
"num_tokens": 2945958.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.274414014816284,
|
|
"epoch": 0.14881788060874937,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999849590230469,
|
|
"loss": 6.1433,
|
|
"mean_token_accuracy": 0.14606737792491914,
|
|
"num_tokens": 2957536.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.277726364135742,
|
|
"epoch": 0.14937945751670692,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999844912187336,
|
|
"loss": 6.1094,
|
|
"mean_token_accuracy": 0.15047910585999488,
|
|
"num_tokens": 2967787.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.2430198192596436,
|
|
"epoch": 0.14994103442466447,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499984016250827,
|
|
"loss": 6.1327,
|
|
"mean_token_accuracy": 0.14211324453353882,
|
|
"num_tokens": 2980522.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.135755300521851,
|
|
"epoch": 0.150502611332622,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499983534119342,
|
|
"loss": 6.0791,
|
|
"mean_token_accuracy": 0.15327682048082353,
|
|
"num_tokens": 2990497.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.3184624195098875,
|
|
"epoch": 0.15106418824057954,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999830448242941,
|
|
"loss": 6.1647,
|
|
"mean_token_accuracy": 0.15013931393623353,
|
|
"num_tokens": 3002931.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.258245277404785,
|
|
"epoch": 0.1516257651485371,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999825483656986,
|
|
"loss": 6.0849,
|
|
"mean_token_accuracy": 0.1547642767429352,
|
|
"num_tokens": 3014137.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.369079113006592,
|
|
"epoch": 0.15218734205649465,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999820447435716,
|
|
"loss": 6.2573,
|
|
"mean_token_accuracy": 0.13950591012835503,
|
|
"num_tokens": 3026145.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.16160569190979,
|
|
"epoch": 0.15274891896445217,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999815339579291,
|
|
"loss": 6.1087,
|
|
"mean_token_accuracy": 0.14567982107400895,
|
|
"num_tokens": 3037068.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.293409633636474,
|
|
"epoch": 0.15331049587240972,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999810160087872,
|
|
"loss": 6.0279,
|
|
"mean_token_accuracy": 0.14883914291858674,
|
|
"num_tokens": 3047836.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.2063792705535885,
|
|
"epoch": 0.15387207278036727,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999804908961626,
|
|
"loss": 6.1668,
|
|
"mean_token_accuracy": 0.15080713033676146,
|
|
"num_tokens": 3060309.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.290639400482178,
|
|
"epoch": 0.15443364968832482,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999799586200719,
|
|
"loss": 6.1341,
|
|
"mean_token_accuracy": 0.1524991884827614,
|
|
"num_tokens": 3071789.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.208878803253174,
|
|
"epoch": 0.15499522659628237,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499979419180532,
|
|
"loss": 6.0495,
|
|
"mean_token_accuracy": 0.15470616593956948,
|
|
"num_tokens": 3081756.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.266907453536987,
|
|
"epoch": 0.1555568035042399,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999788725775601,
|
|
"loss": 6.1499,
|
|
"mean_token_accuracy": 0.14703571647405625,
|
|
"num_tokens": 3093456.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.318468141555786,
|
|
"epoch": 0.15611838041219744,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999783188111737,
|
|
"loss": 6.0872,
|
|
"mean_token_accuracy": 0.15315306335687637,
|
|
"num_tokens": 3104565.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.206810712814331,
|
|
"epoch": 0.156679957320155,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999777578813904,
|
|
"loss": 6.1015,
|
|
"mean_token_accuracy": 0.14678023308515548,
|
|
"num_tokens": 3115577.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.182242918014526,
|
|
"epoch": 0.15724153422811254,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499977189788228,
|
|
"loss": 6.0038,
|
|
"mean_token_accuracy": 0.1520043984055519,
|
|
"num_tokens": 3126019.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.278607749938965,
|
|
"epoch": 0.1578031111360701,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999766145317046,
|
|
"loss": 6.1645,
|
|
"mean_token_accuracy": 0.13868181630969048,
|
|
"num_tokens": 3136191.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.29112024307251,
|
|
"epoch": 0.15836468804402762,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999760321118385,
|
|
"loss": 6.0267,
|
|
"mean_token_accuracy": 0.1518556460738182,
|
|
"num_tokens": 3147737.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.1147044658660885,
|
|
"epoch": 0.15892626495198517,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999754425286483,
|
|
"loss": 6.1018,
|
|
"mean_token_accuracy": 0.14828776121139525,
|
|
"num_tokens": 3158494.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.346787929534912,
|
|
"epoch": 0.15948784185994272,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999748457821529,
|
|
"loss": 6.1186,
|
|
"mean_token_accuracy": 0.15080327838659285,
|
|
"num_tokens": 3170550.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.109242296218872,
|
|
"epoch": 0.16004941876790027,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000499974241872371,
|
|
"loss": 6.1044,
|
|
"mean_token_accuracy": 0.15341940075159072,
|
|
"num_tokens": 3182860.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.2393961429595945,
|
|
"epoch": 0.16061099567585782,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999736307993221,
|
|
"loss": 6.0998,
|
|
"mean_token_accuracy": 0.1468542292714119,
|
|
"num_tokens": 3193807.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.112961626052856,
|
|
"epoch": 0.16117257258381534,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999730125630255,
|
|
"loss": 5.9753,
|
|
"mean_token_accuracy": 0.14808735698461534,
|
|
"num_tokens": 3203959.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.200899696350097,
|
|
"epoch": 0.1617341494917729,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999723871635008,
|
|
"loss": 5.9863,
|
|
"mean_token_accuracy": 0.16002811044454573,
|
|
"num_tokens": 3215416.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.27506537437439,
|
|
"epoch": 0.16229572639973044,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999717546007681,
|
|
"loss": 6.1366,
|
|
"mean_token_accuracy": 0.14617353230714797,
|
|
"num_tokens": 3226938.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.093537378311157,
|
|
"epoch": 0.162857303307688,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999711148748476,
|
|
"loss": 5.9578,
|
|
"mean_token_accuracy": 0.15727282613515853,
|
|
"num_tokens": 3238406.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.092117643356323,
|
|
"epoch": 0.16341888021564555,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999704679857594,
|
|
"loss": 5.9807,
|
|
"mean_token_accuracy": 0.15305008739233017,
|
|
"num_tokens": 3249695.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.300736570358277,
|
|
"epoch": 0.16398045712360307,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999698139335243,
|
|
"loss": 6.1224,
|
|
"mean_token_accuracy": 0.15480272024869918,
|
|
"num_tokens": 3259656.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.161792993545532,
|
|
"epoch": 0.16454203403156062,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999691527181632,
|
|
"loss": 5.9581,
|
|
"mean_token_accuracy": 0.1575998604297638,
|
|
"num_tokens": 3269712.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.017685747146606,
|
|
"epoch": 0.16510361093951817,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999684843396968,
|
|
"loss": 5.9473,
|
|
"mean_token_accuracy": 0.1620100051164627,
|
|
"num_tokens": 3280343.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.132945108413696,
|
|
"epoch": 0.16566518784747572,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999678087981467,
|
|
"loss": 5.9832,
|
|
"mean_token_accuracy": 0.15548000037670134,
|
|
"num_tokens": 3291649.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.260512495040894,
|
|
"epoch": 0.16622676475543324,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999671260935343,
|
|
"loss": 6.1602,
|
|
"mean_token_accuracy": 0.15033089965581894,
|
|
"num_tokens": 3304190.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.118093347549438,
|
|
"epoch": 0.1667883416633908,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999664362258814,
|
|
"loss": 5.8834,
|
|
"mean_token_accuracy": 0.16507079303264618,
|
|
"num_tokens": 3313966.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.124730253219605,
|
|
"epoch": 0.16734991857134834,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999657391952099,
|
|
"loss": 6.1394,
|
|
"mean_token_accuracy": 0.15149711593985557,
|
|
"num_tokens": 3326017.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.235573196411133,
|
|
"epoch": 0.1679114954793059,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000499965035001542,
|
|
"loss": 6.0274,
|
|
"mean_token_accuracy": 0.1512436166405678,
|
|
"num_tokens": 3338264.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.172114086151123,
|
|
"epoch": 0.16847307238726345,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999643236449001,
|
|
"loss": 6.0762,
|
|
"mean_token_accuracy": 0.15923445373773576,
|
|
"num_tokens": 3348901.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.156464338302612,
|
|
"epoch": 0.16903464929522097,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999636051253069,
|
|
"loss": 6.01,
|
|
"mean_token_accuracy": 0.1561951994895935,
|
|
"num_tokens": 3358441.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.230216312408447,
|
|
"epoch": 0.16959622620317852,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999628794427854,
|
|
"loss": 6.0741,
|
|
"mean_token_accuracy": 0.1592329427599907,
|
|
"num_tokens": 3369334.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.171168613433838,
|
|
"epoch": 0.17015780311113607,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999621465973583,
|
|
"loss": 6.0778,
|
|
"mean_token_accuracy": 0.15496481209993362,
|
|
"num_tokens": 3380698.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.309156847000122,
|
|
"epoch": 0.17071938001909362,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999614065890495,
|
|
"loss": 6.0899,
|
|
"mean_token_accuracy": 0.14700602293014525,
|
|
"num_tokens": 3391061.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.197608804702758,
|
|
"epoch": 0.17128095692705117,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999606594178821,
|
|
"loss": 6.1364,
|
|
"mean_token_accuracy": 0.15024443566799164,
|
|
"num_tokens": 3403983.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.244645118713379,
|
|
"epoch": 0.1718425338350087,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00049995990508388,
|
|
"loss": 6.0779,
|
|
"mean_token_accuracy": 0.15672694891691208,
|
|
"num_tokens": 3413838.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.046824502944946,
|
|
"epoch": 0.17240411074296624,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999591435870674,
|
|
"loss": 5.9089,
|
|
"mean_token_accuracy": 0.15403609424829484,
|
|
"num_tokens": 3423978.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.206249952316284,
|
|
"epoch": 0.1729656876509238,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999583749274684,
|
|
"loss": 6.075,
|
|
"mean_token_accuracy": 0.1552916258573532,
|
|
"num_tokens": 3433416.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.05125732421875,
|
|
"epoch": 0.17352726455888134,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999575991051074,
|
|
"loss": 5.9337,
|
|
"mean_token_accuracy": 0.15946417003870011,
|
|
"num_tokens": 3444983.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.104172706604004,
|
|
"epoch": 0.1740888414668389,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999568161200093,
|
|
"loss": 5.9132,
|
|
"mean_token_accuracy": 0.16011491119861604,
|
|
"num_tokens": 3455808.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.068035030364991,
|
|
"epoch": 0.17465041837479642,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999560259721989,
|
|
"loss": 6.0633,
|
|
"mean_token_accuracy": 0.14862860813736917,
|
|
"num_tokens": 3467503.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.333144569396973,
|
|
"epoch": 0.17521199528275397,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999552286617014,
|
|
"loss": 6.2627,
|
|
"mean_token_accuracy": 0.14934148043394088,
|
|
"num_tokens": 3479941.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.0875753402709964,
|
|
"epoch": 0.17577357219071152,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999544241885421,
|
|
"loss": 5.9409,
|
|
"mean_token_accuracy": 0.1608643963932991,
|
|
"num_tokens": 3491069.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.185438203811645,
|
|
"epoch": 0.17633514909866907,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999536125527467,
|
|
"loss": 6.1219,
|
|
"mean_token_accuracy": 0.14819481000304222,
|
|
"num_tokens": 3502065.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.242910718917846,
|
|
"epoch": 0.17689672600662662,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499952793754341,
|
|
"loss": 6.0773,
|
|
"mean_token_accuracy": 0.15577124506235124,
|
|
"num_tokens": 3514228.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.135730504989624,
|
|
"epoch": 0.17745830291458414,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999519677933512,
|
|
"loss": 6.0138,
|
|
"mean_token_accuracy": 0.1518117979168892,
|
|
"num_tokens": 3525801.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.129576301574707,
|
|
"epoch": 0.1780198798225417,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999511346698035,
|
|
"loss": 5.9359,
|
|
"mean_token_accuracy": 0.1553277626633644,
|
|
"num_tokens": 3536431.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.099354934692383,
|
|
"epoch": 0.17858145673049924,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999502943837244,
|
|
"loss": 6.051,
|
|
"mean_token_accuracy": 0.15079501271247864,
|
|
"num_tokens": 3549098.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.210941171646118,
|
|
"epoch": 0.1791430336384568,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999494469351406,
|
|
"loss": 6.0178,
|
|
"mean_token_accuracy": 0.14901258572936057,
|
|
"num_tokens": 3560532.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.065124273300171,
|
|
"epoch": 0.17970461054641435,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999485923240793,
|
|
"loss": 6.0173,
|
|
"mean_token_accuracy": 0.1576265998184681,
|
|
"num_tokens": 3572175.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.19850378036499,
|
|
"epoch": 0.18026618745437187,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999477305505675,
|
|
"loss": 5.9437,
|
|
"mean_token_accuracy": 0.17433226928114892,
|
|
"num_tokens": 3582862.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.204102182388306,
|
|
"epoch": 0.18082776436232942,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999468616146328,
|
|
"loss": 6.1143,
|
|
"mean_token_accuracy": 0.15742965340614318,
|
|
"num_tokens": 3594685.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.077350044250489,
|
|
"epoch": 0.18138934127028697,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999459855163026,
|
|
"loss": 5.9041,
|
|
"mean_token_accuracy": 0.16472332179546356,
|
|
"num_tokens": 3604847.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.121081256866455,
|
|
"epoch": 0.18195091817824452,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499945102255605,
|
|
"loss": 6.0043,
|
|
"mean_token_accuracy": 0.1578712470829487,
|
|
"num_tokens": 3615549.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.102070951461792,
|
|
"epoch": 0.18251249508620204,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999442118325682,
|
|
"loss": 5.9327,
|
|
"mean_token_accuracy": 0.16479116231203078,
|
|
"num_tokens": 3626300.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.038302087783814,
|
|
"epoch": 0.1830740719941596,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999433142472205,
|
|
"loss": 5.9514,
|
|
"mean_token_accuracy": 0.15335373133420943,
|
|
"num_tokens": 3637832.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.115744400024414,
|
|
"epoch": 0.18363564890211714,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999424094995902,
|
|
"loss": 5.9789,
|
|
"mean_token_accuracy": 0.15215082317590714,
|
|
"num_tokens": 3649179.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.125009965896607,
|
|
"epoch": 0.1841972258100747,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999414975897066,
|
|
"loss": 6.0199,
|
|
"mean_token_accuracy": 0.1541282758116722,
|
|
"num_tokens": 3660011.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.208988380432129,
|
|
"epoch": 0.18475880271803224,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999405785175983,
|
|
"loss": 6.0967,
|
|
"mean_token_accuracy": 0.1505162686109543,
|
|
"num_tokens": 3672791.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.054459905624389,
|
|
"epoch": 0.18532037962598977,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999396522832949,
|
|
"loss": 5.9203,
|
|
"mean_token_accuracy": 0.15148744434118272,
|
|
"num_tokens": 3684709.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.075024271011353,
|
|
"epoch": 0.18588195653394732,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999387188868256,
|
|
"loss": 5.8949,
|
|
"mean_token_accuracy": 0.15390077084302903,
|
|
"num_tokens": 3694675.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.017467975616455,
|
|
"epoch": 0.18644353344190487,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999377783282203,
|
|
"loss": 5.8928,
|
|
"mean_token_accuracy": 0.1555798292160034,
|
|
"num_tokens": 3706384.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.1620267868042,
|
|
"epoch": 0.18700511034986242,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999368306075089,
|
|
"loss": 5.9712,
|
|
"mean_token_accuracy": 0.15607626289129256,
|
|
"num_tokens": 3717419.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.114587497711182,
|
|
"epoch": 0.18756668725781997,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999358757247215,
|
|
"loss": 6.0022,
|
|
"mean_token_accuracy": 0.15720313042402267,
|
|
"num_tokens": 3727306.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.247707271575928,
|
|
"epoch": 0.1881282641657775,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999349136798886,
|
|
"loss": 6.1246,
|
|
"mean_token_accuracy": 0.14902206510305405,
|
|
"num_tokens": 3739476.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.045167350769043,
|
|
"epoch": 0.18868984107373504,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999339444730409,
|
|
"loss": 5.8815,
|
|
"mean_token_accuracy": 0.16054750233888626,
|
|
"num_tokens": 3751035.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.094293832778931,
|
|
"epoch": 0.1892514179816926,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999329681042092,
|
|
"loss": 5.9816,
|
|
"mean_token_accuracy": 0.15803841948509217,
|
|
"num_tokens": 3762881.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.10405535697937,
|
|
"epoch": 0.18981299488965014,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999319845734243,
|
|
"loss": 5.9942,
|
|
"mean_token_accuracy": 0.15585220605134964,
|
|
"num_tokens": 3774180.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.085261487960816,
|
|
"epoch": 0.1903745717976077,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999309938807181,
|
|
"loss": 5.9852,
|
|
"mean_token_accuracy": 0.1583825647830963,
|
|
"num_tokens": 3784864.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.159953594207764,
|
|
"epoch": 0.19093614870556522,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999299960261216,
|
|
"loss": 5.9661,
|
|
"mean_token_accuracy": 0.15621330142021178,
|
|
"num_tokens": 3797693.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.121345901489258,
|
|
"epoch": 0.19149772561352277,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999289910096669,
|
|
"loss": 5.9815,
|
|
"mean_token_accuracy": 0.1569610618054867,
|
|
"num_tokens": 3809379.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.980222129821778,
|
|
"epoch": 0.19205930252148032,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999279788313858,
|
|
"loss": 5.8466,
|
|
"mean_token_accuracy": 0.16340151876211167,
|
|
"num_tokens": 3819473.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.951950740814209,
|
|
"epoch": 0.19262087942943787,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999269594913107,
|
|
"loss": 5.8416,
|
|
"mean_token_accuracy": 0.16119720190763473,
|
|
"num_tokens": 3831037.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.028258419036865,
|
|
"epoch": 0.19318245633739542,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999259329894739,
|
|
"loss": 5.9828,
|
|
"mean_token_accuracy": 0.1525442384183407,
|
|
"num_tokens": 3841767.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.972176122665405,
|
|
"epoch": 0.19374403324535294,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999248993259081,
|
|
"loss": 5.8144,
|
|
"mean_token_accuracy": 0.16172564327716826,
|
|
"num_tokens": 3851629.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.02704439163208,
|
|
"epoch": 0.1943056101533105,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999238585006463,
|
|
"loss": 5.888,
|
|
"mean_token_accuracy": 0.15862395614385605,
|
|
"num_tokens": 3863247.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.070574378967285,
|
|
"epoch": 0.19486718706126804,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999228105137218,
|
|
"loss": 5.8708,
|
|
"mean_token_accuracy": 0.15669515430927278,
|
|
"num_tokens": 3873949.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.089202356338501,
|
|
"epoch": 0.1954287639692256,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999217553651676,
|
|
"loss": 5.9734,
|
|
"mean_token_accuracy": 0.1567447692155838,
|
|
"num_tokens": 3884992.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.181120681762695,
|
|
"epoch": 0.19599034087718312,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999206930550175,
|
|
"loss": 6.0919,
|
|
"mean_token_accuracy": 0.16048870831727982,
|
|
"num_tokens": 3897029.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.045256233215332,
|
|
"epoch": 0.19655191778514067,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999196235833054,
|
|
"loss": 5.9408,
|
|
"mean_token_accuracy": 0.1560034304857254,
|
|
"num_tokens": 3909510.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.065906572341919,
|
|
"epoch": 0.19711349469309822,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999185469500651,
|
|
"loss": 5.8437,
|
|
"mean_token_accuracy": 0.1581835687160492,
|
|
"num_tokens": 3920593.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.056929016113282,
|
|
"epoch": 0.19767507160105577,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499917463155331,
|
|
"loss": 5.9727,
|
|
"mean_token_accuracy": 0.15137458369135856,
|
|
"num_tokens": 3932215.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.078279876708985,
|
|
"epoch": 0.19823664850901332,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999163721991378,
|
|
"loss": 5.9258,
|
|
"mean_token_accuracy": 0.1602189153432846,
|
|
"num_tokens": 3943876.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.983368635177612,
|
|
"epoch": 0.19879822541697084,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00049991527408152,
|
|
"loss": 5.9166,
|
|
"mean_token_accuracy": 0.1628502070903778,
|
|
"num_tokens": 3954533.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.112651348114014,
|
|
"epoch": 0.1993598023249284,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999141688025127,
|
|
"loss": 5.9763,
|
|
"mean_token_accuracy": 0.16206707656383515,
|
|
"num_tokens": 3965722.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.054543972015381,
|
|
"epoch": 0.19992137923288594,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499913056362151,
|
|
"loss": 5.9075,
|
|
"mean_token_accuracy": 0.1556747227907181,
|
|
"num_tokens": 3976737.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.070246934890747,
|
|
"epoch": 0.2004829561408435,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999119367604703,
|
|
"loss": 5.9879,
|
|
"mean_token_accuracy": 0.16562585681676864,
|
|
"num_tokens": 3986102.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.096411323547363,
|
|
"epoch": 0.20104453304880104,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999108099975064,
|
|
"loss": 5.9518,
|
|
"mean_token_accuracy": 0.15884745121002197,
|
|
"num_tokens": 3996534.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.006507396697998,
|
|
"epoch": 0.20160610995675857,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499909676073295,
|
|
"loss": 5.8641,
|
|
"mean_token_accuracy": 0.15670980811119078,
|
|
"num_tokens": 4006947.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.010478734970093,
|
|
"epoch": 0.20216768686471612,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999085349878723,
|
|
"loss": 5.9085,
|
|
"mean_token_accuracy": 0.16509864330291749,
|
|
"num_tokens": 4017723.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.017948055267334,
|
|
"epoch": 0.20272926377267367,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999073867412746,
|
|
"loss": 5.9857,
|
|
"mean_token_accuracy": 0.1533601000905037,
|
|
"num_tokens": 4028347.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.06327452659607,
|
|
"epoch": 0.20329084068063122,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999062313335385,
|
|
"loss": 5.846,
|
|
"mean_token_accuracy": 0.16621426939964296,
|
|
"num_tokens": 4039648.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.054847764968872,
|
|
"epoch": 0.20385241758858877,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999050687647008,
|
|
"loss": 5.9093,
|
|
"mean_token_accuracy": 0.15702853202819825,
|
|
"num_tokens": 4050786.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.053362274169922,
|
|
"epoch": 0.2044139944965463,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999038990347984,
|
|
"loss": 5.9447,
|
|
"mean_token_accuracy": 0.16274867802858353,
|
|
"num_tokens": 4061184.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.157382345199585,
|
|
"epoch": 0.20497557140450384,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999027221438688,
|
|
"loss": 6.0754,
|
|
"mean_token_accuracy": 0.15608905404806137,
|
|
"num_tokens": 4073607.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.970077323913574,
|
|
"epoch": 0.2055371483124614,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499901538091949,
|
|
"loss": 5.8927,
|
|
"mean_token_accuracy": 0.1595301076769829,
|
|
"num_tokens": 4083924.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.023391008377075,
|
|
"epoch": 0.20609872522041894,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999003468790773,
|
|
"loss": 5.8918,
|
|
"mean_token_accuracy": 0.16054748892784118,
|
|
"num_tokens": 4094083.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.0351855754852295,
|
|
"epoch": 0.2066603021283765,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998991485052911,
|
|
"loss": 5.9218,
|
|
"mean_token_accuracy": 0.16628677994012833,
|
|
"num_tokens": 4105124.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.1698376655578615,
|
|
"epoch": 0.20722187903633402,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499897942970629,
|
|
"loss": 6.0908,
|
|
"mean_token_accuracy": 0.1494095504283905,
|
|
"num_tokens": 4116792.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.220897674560547,
|
|
"epoch": 0.20778345594429157,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499896730275129,
|
|
"loss": 6.0706,
|
|
"mean_token_accuracy": 0.15271387100219727,
|
|
"num_tokens": 4127441.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.071835470199585,
|
|
"epoch": 0.20834503285224912,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00049989551041883,
|
|
"loss": 6.0561,
|
|
"mean_token_accuracy": 0.15183976292610168,
|
|
"num_tokens": 4138696.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.061728000640869,
|
|
"epoch": 0.20890660976020667,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998942834017707,
|
|
"loss": 5.915,
|
|
"mean_token_accuracy": 0.15786469280719756,
|
|
"num_tokens": 4151254.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.997844457626343,
|
|
"epoch": 0.2094681866681642,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998930492239901,
|
|
"loss": 5.8837,
|
|
"mean_token_accuracy": 0.1549679934978485,
|
|
"num_tokens": 4162046.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.995732355117798,
|
|
"epoch": 0.21002976357612174,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998918078855277,
|
|
"loss": 5.8325,
|
|
"mean_token_accuracy": 0.1628045290708542,
|
|
"num_tokens": 4172409.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.986175918579102,
|
|
"epoch": 0.2105913404840793,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998905593864227,
|
|
"loss": 5.9844,
|
|
"mean_token_accuracy": 0.16071528941392899,
|
|
"num_tokens": 4182949.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.048963737487793,
|
|
"epoch": 0.21115291739203684,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998893037267153,
|
|
"loss": 5.9605,
|
|
"mean_token_accuracy": 0.15584419518709183,
|
|
"num_tokens": 4194164.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.133493423461914,
|
|
"epoch": 0.2117144942999944,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998880409064452,
|
|
"loss": 5.9129,
|
|
"mean_token_accuracy": 0.16219342201948167,
|
|
"num_tokens": 4206056.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.956058120727539,
|
|
"epoch": 0.21227607120795192,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998867709256527,
|
|
"loss": 5.9854,
|
|
"mean_token_accuracy": 0.15834779739379884,
|
|
"num_tokens": 4216660.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.011321544647217,
|
|
"epoch": 0.21283764811590947,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499885493784378,
|
|
"loss": 5.8419,
|
|
"mean_token_accuracy": 0.16390256732702255,
|
|
"num_tokens": 4228495.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.061332416534424,
|
|
"epoch": 0.21339922502386702,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998842094826621,
|
|
"loss": 5.8681,
|
|
"mean_token_accuracy": 0.1624634876847267,
|
|
"num_tokens": 4238560.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.160039234161377,
|
|
"epoch": 0.21396080193182457,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998829180205458,
|
|
"loss": 6.0703,
|
|
"mean_token_accuracy": 0.15231714472174646,
|
|
"num_tokens": 4250553.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.0768242359161375,
|
|
"epoch": 0.21452237883978212,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998816193980701,
|
|
"loss": 5.9904,
|
|
"mean_token_accuracy": 0.15530536472797393,
|
|
"num_tokens": 4262050.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.142356586456299,
|
|
"epoch": 0.21508395574773964,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998803136152764,
|
|
"loss": 5.9473,
|
|
"mean_token_accuracy": 0.15309242606163026,
|
|
"num_tokens": 4273019.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.004923295974732,
|
|
"epoch": 0.2156455326556972,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998790006722063,
|
|
"loss": 5.8254,
|
|
"mean_token_accuracy": 0.16646857857704161,
|
|
"num_tokens": 4283585.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.993122625350952,
|
|
"epoch": 0.21620710956365474,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998776805689016,
|
|
"loss": 5.9043,
|
|
"mean_token_accuracy": 0.161615289747715,
|
|
"num_tokens": 4294905.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.161378240585327,
|
|
"epoch": 0.2167686864716123,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998763533054045,
|
|
"loss": 6.0087,
|
|
"mean_token_accuracy": 0.15805915147066116,
|
|
"num_tokens": 4305926.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.925935316085815,
|
|
"epoch": 0.21733026337956984,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998750188817568,
|
|
"loss": 5.9809,
|
|
"mean_token_accuracy": 0.1576686106622219,
|
|
"num_tokens": 4318297.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.998038911819458,
|
|
"epoch": 0.21789184028752737,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998736772980015,
|
|
"loss": 5.8028,
|
|
"mean_token_accuracy": 0.16835505217313768,
|
|
"num_tokens": 4328795.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.970638608932495,
|
|
"epoch": 0.21845341719548492,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499872328554181,
|
|
"loss": 5.8275,
|
|
"mean_token_accuracy": 0.16290033608675003,
|
|
"num_tokens": 4340279.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.099689674377442,
|
|
"epoch": 0.21901499410344247,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998709726503383,
|
|
"loss": 6.0003,
|
|
"mean_token_accuracy": 0.1518409989774227,
|
|
"num_tokens": 4352157.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.986471176147461,
|
|
"epoch": 0.21957657101140002,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998696095865168,
|
|
"loss": 5.824,
|
|
"mean_token_accuracy": 0.16872964352369307,
|
|
"num_tokens": 4361909.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.843346214294433,
|
|
"epoch": 0.22013814791935757,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998682393627595,
|
|
"loss": 5.7623,
|
|
"mean_token_accuracy": 0.16021531522274018,
|
|
"num_tokens": 4372177.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.961346864700317,
|
|
"epoch": 0.2206997248273151,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998668619791104,
|
|
"loss": 5.8063,
|
|
"mean_token_accuracy": 0.16359231173992156,
|
|
"num_tokens": 4382872.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.00990309715271,
|
|
"epoch": 0.22126130173527264,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998654774356131,
|
|
"loss": 5.9066,
|
|
"mean_token_accuracy": 0.15922408998012544,
|
|
"num_tokens": 4393623.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.948709440231323,
|
|
"epoch": 0.2218228786432302,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998640857323118,
|
|
"loss": 5.8402,
|
|
"mean_token_accuracy": 0.15961378663778306,
|
|
"num_tokens": 4404215.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.1061646938323975,
|
|
"epoch": 0.22238445555118774,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998626868692509,
|
|
"loss": 6.0948,
|
|
"mean_token_accuracy": 0.15816606134176253,
|
|
"num_tokens": 4415978.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.046572494506836,
|
|
"epoch": 0.2229460324591453,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998612808464748,
|
|
"loss": 5.8441,
|
|
"mean_token_accuracy": 0.16600802540779114,
|
|
"num_tokens": 4427060.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.935293436050415,
|
|
"epoch": 0.22350760936710282,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998598676640283,
|
|
"loss": 5.9204,
|
|
"mean_token_accuracy": 0.15637087672948838,
|
|
"num_tokens": 4438145.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.165454578399658,
|
|
"epoch": 0.22406918627506037,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998584473219563,
|
|
"loss": 5.9893,
|
|
"mean_token_accuracy": 0.1606801465153694,
|
|
"num_tokens": 4449324.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.938971281051636,
|
|
"epoch": 0.22463076318301792,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998570198203043,
|
|
"loss": 5.7297,
|
|
"mean_token_accuracy": 0.1644525095820427,
|
|
"num_tokens": 4459728.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.961595249176026,
|
|
"epoch": 0.22519234009097547,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998555851591175,
|
|
"loss": 5.9458,
|
|
"mean_token_accuracy": 0.16193436831235886,
|
|
"num_tokens": 4471164.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.059179592132568,
|
|
"epoch": 0.225753916998933,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998541433384416,
|
|
"loss": 6.0017,
|
|
"mean_token_accuracy": 0.1561392977833748,
|
|
"num_tokens": 4483349.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.103359651565552,
|
|
"epoch": 0.22631549390689054,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998526943583226,
|
|
"loss": 5.9563,
|
|
"mean_token_accuracy": 0.15778704583644867,
|
|
"num_tokens": 4495311.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.927799892425537,
|
|
"epoch": 0.2268770708148481,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998512382188066,
|
|
"loss": 5.8836,
|
|
"mean_token_accuracy": 0.1617691360414028,
|
|
"num_tokens": 4507017.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.996227025985718,
|
|
"epoch": 0.22743864772280564,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998497749199401,
|
|
"loss": 5.9212,
|
|
"mean_token_accuracy": 0.15882934331893922,
|
|
"num_tokens": 4517746.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.099315357208252,
|
|
"epoch": 0.2280002246307632,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998483044617694,
|
|
"loss": 6.0097,
|
|
"mean_token_accuracy": 0.15352682620286942,
|
|
"num_tokens": 4529149.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.046715021133423,
|
|
"epoch": 0.22856180153872072,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998468268443416,
|
|
"loss": 5.8928,
|
|
"mean_token_accuracy": 0.1632772609591484,
|
|
"num_tokens": 4540630.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.875202322006226,
|
|
"epoch": 0.22912337844667827,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998453420677034,
|
|
"loss": 5.8252,
|
|
"mean_token_accuracy": 0.16278187185525894,
|
|
"num_tokens": 4552877.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.0447197437286375,
|
|
"epoch": 0.22968495535463582,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998438501319025,
|
|
"loss": 5.9238,
|
|
"mean_token_accuracy": 0.16725802570581436,
|
|
"num_tokens": 4563634.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.03820834159851,
|
|
"epoch": 0.23024653226259337,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998423510369862,
|
|
"loss": 5.8429,
|
|
"mean_token_accuracy": 0.16436342447996138,
|
|
"num_tokens": 4574007.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.93084487915039,
|
|
"epoch": 0.23080810917055092,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998408447830022,
|
|
"loss": 5.8515,
|
|
"mean_token_accuracy": 0.16042328476905823,
|
|
"num_tokens": 4584146.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.019020128250122,
|
|
"epoch": 0.23136968607850844,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998393313699985,
|
|
"loss": 5.8658,
|
|
"mean_token_accuracy": 0.15834631770849228,
|
|
"num_tokens": 4594839.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.118397998809814,
|
|
"epoch": 0.231931262986466,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998378107980233,
|
|
"loss": 6.0378,
|
|
"mean_token_accuracy": 0.15390192568302155,
|
|
"num_tokens": 4608229.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.0200855255126955,
|
|
"epoch": 0.23249283989442354,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998362830671249,
|
|
"loss": 5.8386,
|
|
"mean_token_accuracy": 0.1594712480902672,
|
|
"num_tokens": 4619206.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.911860418319702,
|
|
"epoch": 0.2330544168023811,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998347481773522,
|
|
"loss": 5.8782,
|
|
"mean_token_accuracy": 0.16451769918203354,
|
|
"num_tokens": 4628966.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.036902618408203,
|
|
"epoch": 0.23361599371033864,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998332061287538,
|
|
"loss": 5.753,
|
|
"mean_token_accuracy": 0.16608522683382035,
|
|
"num_tokens": 4639935.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.02183985710144,
|
|
"epoch": 0.23417757061829617,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499831656921379,
|
|
"loss": 5.9959,
|
|
"mean_token_accuracy": 0.15738053619861603,
|
|
"num_tokens": 4651998.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.092220067977905,
|
|
"epoch": 0.23473914752625372,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499830100555277,
|
|
"loss": 5.9932,
|
|
"mean_token_accuracy": 0.15611726194620132,
|
|
"num_tokens": 4664002.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.96814341545105,
|
|
"epoch": 0.23530072443421127,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998285370304974,
|
|
"loss": 5.8598,
|
|
"mean_token_accuracy": 0.16325256526470183,
|
|
"num_tokens": 4675343.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.047848653793335,
|
|
"epoch": 0.23586230134216882,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049982696634709,
|
|
"loss": 5.8987,
|
|
"mean_token_accuracy": 0.16740916967391967,
|
|
"num_tokens": 4686410.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.984486770629883,
|
|
"epoch": 0.23642387825012637,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998253885051048,
|
|
"loss": 5.9357,
|
|
"mean_token_accuracy": 0.16218028217554092,
|
|
"num_tokens": 4697768.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.095366096496582,
|
|
"epoch": 0.2369854551580839,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499823803504592,
|
|
"loss": 5.9388,
|
|
"mean_token_accuracy": 0.1598934069275856,
|
|
"num_tokens": 4709933.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.017884826660156,
|
|
"epoch": 0.23754703206604144,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998222113456022,
|
|
"loss": 5.9774,
|
|
"mean_token_accuracy": 0.1559494897723198,
|
|
"num_tokens": 4721385.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.9762331485748295,
|
|
"epoch": 0.238108608973999,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998206120281858,
|
|
"loss": 5.7984,
|
|
"mean_token_accuracy": 0.1687019482254982,
|
|
"num_tokens": 4732562.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.9636999607086185,
|
|
"epoch": 0.23867018588195654,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499819005552394,
|
|
"loss": 5.8117,
|
|
"mean_token_accuracy": 0.16452171057462692,
|
|
"num_tokens": 4742794.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.919935417175293,
|
|
"epoch": 0.23923176278991407,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998173919182779,
|
|
"loss": 5.7881,
|
|
"mean_token_accuracy": 0.166632841527462,
|
|
"num_tokens": 4754903.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.9008917808532715,
|
|
"epoch": 0.23979333969787162,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499815771125889,
|
|
"loss": 5.8175,
|
|
"mean_token_accuracy": 0.16199010461568833,
|
|
"num_tokens": 4766165.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.972467041015625,
|
|
"epoch": 0.24035491660582917,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998141431752785,
|
|
"loss": 5.8284,
|
|
"mean_token_accuracy": 0.16583052426576614,
|
|
"num_tokens": 4776551.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.0888008117675785,
|
|
"epoch": 0.24091649351378672,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998125080664987,
|
|
"loss": 6.0294,
|
|
"mean_token_accuracy": 0.15712772458791732,
|
|
"num_tokens": 4788344.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.032654619216919,
|
|
"epoch": 0.24147807042174427,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998108657996012,
|
|
"loss": 5.8201,
|
|
"mean_token_accuracy": 0.16204651147127153,
|
|
"num_tokens": 4799314.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.93705735206604,
|
|
"epoch": 0.2420396473297018,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998092163746387,
|
|
"loss": 5.8618,
|
|
"mean_token_accuracy": 0.16488695591688157,
|
|
"num_tokens": 4809588.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.907848787307739,
|
|
"epoch": 0.24260122423765934,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998075597916636,
|
|
"loss": 5.6812,
|
|
"mean_token_accuracy": 0.17253921180963516,
|
|
"num_tokens": 4820076.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.989373302459716,
|
|
"epoch": 0.2431628011456169,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998058960507286,
|
|
"loss": 5.9562,
|
|
"mean_token_accuracy": 0.1578843265771866,
|
|
"num_tokens": 4831504.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.992100238800049,
|
|
"epoch": 0.24372437805357444,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998042251518866,
|
|
"loss": 5.8054,
|
|
"mean_token_accuracy": 0.16406459957361222,
|
|
"num_tokens": 4842826.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.86922173500061,
|
|
"epoch": 0.244285954961532,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998025470951908,
|
|
"loss": 5.8005,
|
|
"mean_token_accuracy": 0.16625914573669434,
|
|
"num_tokens": 4853279.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.003297185897827,
|
|
"epoch": 0.24484753186948952,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998008618806949,
|
|
"loss": 5.8589,
|
|
"mean_token_accuracy": 0.1688696026802063,
|
|
"num_tokens": 4863332.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.924489688873291,
|
|
"epoch": 0.24540910877744707,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997991695084523,
|
|
"loss": 5.9807,
|
|
"mean_token_accuracy": 0.15316371172666549,
|
|
"num_tokens": 4874217.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.1011065483093265,
|
|
"epoch": 0.24597068568540462,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997974699785169,
|
|
"loss": 5.8362,
|
|
"mean_token_accuracy": 0.16836950108408927,
|
|
"num_tokens": 4885322.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.828060865402222,
|
|
"epoch": 0.24653226259336217,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997957632909429,
|
|
"loss": 5.781,
|
|
"mean_token_accuracy": 0.16213512569665908,
|
|
"num_tokens": 4895546.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.1020842552185055,
|
|
"epoch": 0.24709383950131972,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997940494457846,
|
|
"loss": 5.9813,
|
|
"mean_token_accuracy": 0.157517471909523,
|
|
"num_tokens": 4906957.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.115909624099731,
|
|
"epoch": 0.24765541640927724,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997923284430967,
|
|
"loss": 5.9104,
|
|
"mean_token_accuracy": 0.1537712886929512,
|
|
"num_tokens": 4917965.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.8366883277893065,
|
|
"epoch": 0.2482169933172348,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997906002829338,
|
|
"loss": 5.7987,
|
|
"mean_token_accuracy": 0.16758462488651277,
|
|
"num_tokens": 4928585.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.961793851852417,
|
|
"epoch": 0.24877857022519234,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499788864965351,
|
|
"loss": 5.8096,
|
|
"mean_token_accuracy": 0.16297494918107985,
|
|
"num_tokens": 4939818.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.018909597396851,
|
|
"epoch": 0.2493401471331499,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997871224904036,
|
|
"loss": 5.8987,
|
|
"mean_token_accuracy": 0.1577194705605507,
|
|
"num_tokens": 4951752.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.85117998123169,
|
|
"epoch": 0.24990172404110744,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997853728581468,
|
|
"loss": 5.7255,
|
|
"mean_token_accuracy": 0.17753110378980635,
|
|
"num_tokens": 4961846.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.963651466369629,
|
|
"epoch": 0.250463300949065,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997836160686368,
|
|
"loss": 5.8962,
|
|
"mean_token_accuracy": 0.15754956007003784,
|
|
"num_tokens": 4973693.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.936974811553955,
|
|
"epoch": 0.25102487785702254,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997818521219291,
|
|
"loss": 5.7989,
|
|
"mean_token_accuracy": 0.16598349809646606,
|
|
"num_tokens": 4986156.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.9454022407531735,
|
|
"epoch": 0.25158645476498004,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997800810180803,
|
|
"loss": 5.8731,
|
|
"mean_token_accuracy": 0.16364911198616028,
|
|
"num_tokens": 4997615.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.981971311569214,
|
|
"epoch": 0.2521480316729376,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997783027571464,
|
|
"loss": 5.8097,
|
|
"mean_token_accuracy": 0.16514143496751785,
|
|
"num_tokens": 5007655.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.966670131683349,
|
|
"epoch": 0.25270960858089514,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997765173391841,
|
|
"loss": 5.8812,
|
|
"mean_token_accuracy": 0.16588087528944015,
|
|
"num_tokens": 5018933.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.058870506286621,
|
|
"epoch": 0.2532711854888527,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997747247642505,
|
|
"loss": 5.8748,
|
|
"mean_token_accuracy": 0.16249170750379563,
|
|
"num_tokens": 5030495.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.938293361663819,
|
|
"epoch": 0.25383276239681024,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997729250324023,
|
|
"loss": 5.916,
|
|
"mean_token_accuracy": 0.15933229476213456,
|
|
"num_tokens": 5041553.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.946228456497193,
|
|
"epoch": 0.2543943393047678,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997711181436971,
|
|
"loss": 5.8639,
|
|
"mean_token_accuracy": 0.16556437611579894,
|
|
"num_tokens": 5052312.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.082585287094116,
|
|
"epoch": 0.25495591621272534,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997693040981922,
|
|
"loss": 6.0487,
|
|
"mean_token_accuracy": 0.1565891683101654,
|
|
"num_tokens": 5063445.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.03095555305481,
|
|
"epoch": 0.2555174931206829,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997674828959456,
|
|
"loss": 5.8301,
|
|
"mean_token_accuracy": 0.16110838502645491,
|
|
"num_tokens": 5073052.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.920227956771851,
|
|
"epoch": 0.25607907002864044,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997656545370151,
|
|
"loss": 5.8694,
|
|
"mean_token_accuracy": 0.16425251513719558,
|
|
"num_tokens": 5084174.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.02871994972229,
|
|
"epoch": 0.256640646936598,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499763819021459,
|
|
"loss": 5.8353,
|
|
"mean_token_accuracy": 0.16484149694442748,
|
|
"num_tokens": 5094106.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.0660443782806395,
|
|
"epoch": 0.2572022238445555,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004997619763493357,
|
|
"loss": 5.9288,
|
|
"mean_token_accuracy": 0.1632024973630905,
|
|
"num_tokens": 5106963.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.8431133270263675,
|
|
"epoch": 0.25776380075251304,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499760126520704,
|
|
"loss": 5.7377,
|
|
"mean_token_accuracy": 0.16144067347049712,
|
|
"num_tokens": 5119476.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.031280374526977,
|
|
"epoch": 0.2583253776604706,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997582695356225,
|
|
"loss": 5.9879,
|
|
"mean_token_accuracy": 0.15699385106563568,
|
|
"num_tokens": 5132169.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.939564180374146,
|
|
"epoch": 0.25888695456842814,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997564053941507,
|
|
"loss": 5.82,
|
|
"mean_token_accuracy": 0.16523557752370835,
|
|
"num_tokens": 5143354.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.880933618545532,
|
|
"epoch": 0.2594485314763857,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997545340963478,
|
|
"loss": 5.8924,
|
|
"mean_token_accuracy": 0.15893735885620117,
|
|
"num_tokens": 5154624.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.041430854797364,
|
|
"epoch": 0.26001010838434324,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997526556422733,
|
|
"loss": 5.7748,
|
|
"mean_token_accuracy": 0.16341781467199326,
|
|
"num_tokens": 5165349.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.887167644500733,
|
|
"epoch": 0.2605716852923008,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997507700319872,
|
|
"loss": 5.8504,
|
|
"mean_token_accuracy": 0.16064828485250474,
|
|
"num_tokens": 5175874.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.964330816268921,
|
|
"epoch": 0.26113326220025834,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997488772655492,
|
|
"loss": 5.7554,
|
|
"mean_token_accuracy": 0.16929169446229936,
|
|
"num_tokens": 5186591.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.903693675994873,
|
|
"epoch": 0.2616948391082159,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997469773430199,
|
|
"loss": 5.8519,
|
|
"mean_token_accuracy": 0.17121090292930602,
|
|
"num_tokens": 5197307.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.88110842704773,
|
|
"epoch": 0.2622564160161734,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004997450702644596,
|
|
"loss": 5.818,
|
|
"mean_token_accuracy": 0.1627274125814438,
|
|
"num_tokens": 5209868.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.976365756988526,
|
|
"epoch": 0.26281799292413094,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997431560299292,
|
|
"loss": 5.8265,
|
|
"mean_token_accuracy": 0.16824889183044434,
|
|
"num_tokens": 5220365.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.904721117019653,
|
|
"epoch": 0.2633795698320885,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997412346394894,
|
|
"loss": 5.74,
|
|
"mean_token_accuracy": 0.16793981045484543,
|
|
"num_tokens": 5231575.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.969769144058228,
|
|
"epoch": 0.26394114674004604,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997393060932017,
|
|
"loss": 5.8382,
|
|
"mean_token_accuracy": 0.16210115253925322,
|
|
"num_tokens": 5241852.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.970647525787354,
|
|
"epoch": 0.2645027236480036,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997373703911273,
|
|
"loss": 5.8794,
|
|
"mean_token_accuracy": 0.16796267330646514,
|
|
"num_tokens": 5254536.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.984567260742187,
|
|
"epoch": 0.26506430055596114,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997354275333277,
|
|
"loss": 5.7922,
|
|
"mean_token_accuracy": 0.16661520600318908,
|
|
"num_tokens": 5264946.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.692500972747803,
|
|
"epoch": 0.2656258774639187,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499733477519865,
|
|
"loss": 5.6292,
|
|
"mean_token_accuracy": 0.16376495808362962,
|
|
"num_tokens": 5275527.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.928407621383667,
|
|
"epoch": 0.26618745437187624,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997315203508013,
|
|
"loss": 5.8023,
|
|
"mean_token_accuracy": 0.16296649128198623,
|
|
"num_tokens": 5285471.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.835812282562256,
|
|
"epoch": 0.2667490312798338,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997295560261988,
|
|
"loss": 5.7219,
|
|
"mean_token_accuracy": 0.16512494385242463,
|
|
"num_tokens": 5295743.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.956495523452759,
|
|
"epoch": 0.26731060818779134,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049972758454612,
|
|
"loss": 5.8692,
|
|
"mean_token_accuracy": 0.15754660218954086,
|
|
"num_tokens": 5307963.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.9242268085479735,
|
|
"epoch": 0.26787218509574884,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997256059106279,
|
|
"loss": 5.7534,
|
|
"mean_token_accuracy": 0.1652416855096817,
|
|
"num_tokens": 5318394.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.935852479934693,
|
|
"epoch": 0.2684337620037064,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004997236201197853,
|
|
"loss": 5.9947,
|
|
"mean_token_accuracy": 0.14979661107063294,
|
|
"num_tokens": 5331728.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.94870285987854,
|
|
"epoch": 0.26899533891166394,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997216271736554,
|
|
"loss": 5.869,
|
|
"mean_token_accuracy": 0.17228117436170579,
|
|
"num_tokens": 5342825.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.978704738616943,
|
|
"epoch": 0.2695569158196215,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997196270723018,
|
|
"loss": 5.7792,
|
|
"mean_token_accuracy": 0.1661553055047989,
|
|
"num_tokens": 5354232.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.882722234725952,
|
|
"epoch": 0.27011849272757904,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997176198157881,
|
|
"loss": 5.8705,
|
|
"mean_token_accuracy": 0.16065609604120254,
|
|
"num_tokens": 5364807.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.937169790267944,
|
|
"epoch": 0.2706800696355366,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997156054041781,
|
|
"loss": 5.8442,
|
|
"mean_token_accuracy": 0.1606588914990425,
|
|
"num_tokens": 5375593.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.968391370773316,
|
|
"epoch": 0.27124164654349414,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997135838375362,
|
|
"loss": 5.7928,
|
|
"mean_token_accuracy": 0.17065857201814652,
|
|
"num_tokens": 5386740.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.825274181365967,
|
|
"epoch": 0.2718032234514517,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997115551159267,
|
|
"loss": 5.7859,
|
|
"mean_token_accuracy": 0.16433975994586944,
|
|
"num_tokens": 5397732.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.979048871994019,
|
|
"epoch": 0.27236480035940924,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499709519239414,
|
|
"loss": 5.8433,
|
|
"mean_token_accuracy": 0.159425051510334,
|
|
"num_tokens": 5409392.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.79268445968628,
|
|
"epoch": 0.2729263772673668,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997074762080632,
|
|
"loss": 5.7906,
|
|
"mean_token_accuracy": 0.17156518399715423,
|
|
"num_tokens": 5420903.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.852681636810303,
|
|
"epoch": 0.2734879541753243,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499705426021939,
|
|
"loss": 5.7318,
|
|
"mean_token_accuracy": 0.16576131135225297,
|
|
"num_tokens": 5432631.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.858410882949829,
|
|
"epoch": 0.27404953108328184,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499703368681107,
|
|
"loss": 5.6874,
|
|
"mean_token_accuracy": 0.1763172999024391,
|
|
"num_tokens": 5443463.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.990561437606812,
|
|
"epoch": 0.2746111079912394,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997013041856326,
|
|
"loss": 6.0024,
|
|
"mean_token_accuracy": 0.15876681730151176,
|
|
"num_tokens": 5455903.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.941286277770996,
|
|
"epoch": 0.27517268489919694,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996992325355815,
|
|
"loss": 5.826,
|
|
"mean_token_accuracy": 0.1625517025589943,
|
|
"num_tokens": 5467201.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.9081957817077635,
|
|
"epoch": 0.2757342618071545,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996971537310198,
|
|
"loss": 5.7079,
|
|
"mean_token_accuracy": 0.16979653686285018,
|
|
"num_tokens": 5478109.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.908603048324585,
|
|
"epoch": 0.27629583871511204,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996950677720133,
|
|
"loss": 5.8226,
|
|
"mean_token_accuracy": 0.16229735761880876,
|
|
"num_tokens": 5489621.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.919325733184815,
|
|
"epoch": 0.2768574156230696,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499692974658629,
|
|
"loss": 5.7826,
|
|
"mean_token_accuracy": 0.16799012571573257,
|
|
"num_tokens": 5500606.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.937128257751465,
|
|
"epoch": 0.27741899253102714,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996908743909331,
|
|
"loss": 5.7359,
|
|
"mean_token_accuracy": 0.16903213709592818,
|
|
"num_tokens": 5510768.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.778143644332886,
|
|
"epoch": 0.2779805694389847,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996887669689926,
|
|
"loss": 5.7554,
|
|
"mean_token_accuracy": 0.16829170882701874,
|
|
"num_tokens": 5522210.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.009134101867676,
|
|
"epoch": 0.2785421463469422,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996866523928747,
|
|
"loss": 5.867,
|
|
"mean_token_accuracy": 0.16028780341148377,
|
|
"num_tokens": 5533055.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.925482892990113,
|
|
"epoch": 0.27910372325489974,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996845306626467,
|
|
"loss": 5.8813,
|
|
"mean_token_accuracy": 0.1584608882665634,
|
|
"num_tokens": 5544345.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.937867641448975,
|
|
"epoch": 0.2796653001628573,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996824017783759,
|
|
"loss": 5.7935,
|
|
"mean_token_accuracy": 0.16448234766721725,
|
|
"num_tokens": 5556734.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.975261259078979,
|
|
"epoch": 0.28022687707081484,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996802657401304,
|
|
"loss": 5.8289,
|
|
"mean_token_accuracy": 0.1649043843150139,
|
|
"num_tokens": 5566874.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.915608930587768,
|
|
"epoch": 0.2807884539787724,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996781225479781,
|
|
"loss": 5.8426,
|
|
"mean_token_accuracy": 0.16331143230199813,
|
|
"num_tokens": 5578812.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.944158029556275,
|
|
"epoch": 0.28135003088672994,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996759722019872,
|
|
"loss": 5.8711,
|
|
"mean_token_accuracy": 0.16549691557884216,
|
|
"num_tokens": 5590021.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.941056251525879,
|
|
"epoch": 0.2819116077946875,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996738147022262,
|
|
"loss": 5.8929,
|
|
"mean_token_accuracy": 0.1572035700082779,
|
|
"num_tokens": 5600921.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.888544178009033,
|
|
"epoch": 0.28247318470264504,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996716500487638,
|
|
"loss": 5.8032,
|
|
"mean_token_accuracy": 0.16694664508104323,
|
|
"num_tokens": 5610615.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.788763236999512,
|
|
"epoch": 0.2830347616106026,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499669478241669,
|
|
"loss": 5.7268,
|
|
"mean_token_accuracy": 0.16717411577701569,
|
|
"num_tokens": 5621596.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.033792781829834,
|
|
"epoch": 0.28359633851856014,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996672992810108,
|
|
"loss": 5.7846,
|
|
"mean_token_accuracy": 0.16378311067819595,
|
|
"num_tokens": 5633047.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.867732572555542,
|
|
"epoch": 0.28415791542651764,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996651131668587,
|
|
"loss": 5.7647,
|
|
"mean_token_accuracy": 0.1646569311618805,
|
|
"num_tokens": 5644970.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.851826286315918,
|
|
"epoch": 0.2847194923344752,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996629198992823,
|
|
"loss": 5.8849,
|
|
"mean_token_accuracy": 0.16250034421682358,
|
|
"num_tokens": 5656631.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.936293029785157,
|
|
"epoch": 0.28528106924243274,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996607194783513,
|
|
"loss": 5.8458,
|
|
"mean_token_accuracy": 0.16177234947681426,
|
|
"num_tokens": 5668808.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.834509754180909,
|
|
"epoch": 0.2858426461503903,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996585119041359,
|
|
"loss": 5.7581,
|
|
"mean_token_accuracy": 0.16683479249477387,
|
|
"num_tokens": 5679493.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.961978435516357,
|
|
"epoch": 0.28640422305834784,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996562971767063,
|
|
"loss": 5.7875,
|
|
"mean_token_accuracy": 0.17051588296890258,
|
|
"num_tokens": 5689879.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.955478048324585,
|
|
"epoch": 0.2869657999663054,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499654075296133,
|
|
"loss": 5.8868,
|
|
"mean_token_accuracy": 0.16586922556161882,
|
|
"num_tokens": 5699934.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.846363353729248,
|
|
"epoch": 0.28752737687426294,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499651846262487,
|
|
"loss": 5.7991,
|
|
"mean_token_accuracy": 0.17178635001182557,
|
|
"num_tokens": 5710171.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.9693992137908936,
|
|
"epoch": 0.2880889537822205,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996496100758389,
|
|
"loss": 5.788,
|
|
"mean_token_accuracy": 0.15814389437437057,
|
|
"num_tokens": 5721190.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.962607526779175,
|
|
"epoch": 0.28865053069017804,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996473667362604,
|
|
"loss": 5.9165,
|
|
"mean_token_accuracy": 0.15922336876392365,
|
|
"num_tokens": 5733706.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.861262464523316,
|
|
"epoch": 0.28921210759813554,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996451162438224,
|
|
"loss": 5.8646,
|
|
"mean_token_accuracy": 0.16674669682979584,
|
|
"num_tokens": 5745712.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.7940126895904545,
|
|
"epoch": 0.2897736845060931,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996428585985967,
|
|
"loss": 5.682,
|
|
"mean_token_accuracy": 0.17691746205091477,
|
|
"num_tokens": 5757915.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.956466007232666,
|
|
"epoch": 0.29033526141405064,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996405938006553,
|
|
"loss": 5.8215,
|
|
"mean_token_accuracy": 0.17083913683891297,
|
|
"num_tokens": 5768788.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.9059301853179935,
|
|
"epoch": 0.2908968383220082,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996383218500703,
|
|
"loss": 5.7558,
|
|
"mean_token_accuracy": 0.1652416318655014,
|
|
"num_tokens": 5779806.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.77002182006836,
|
|
"epoch": 0.29145841522996574,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499636042746914,
|
|
"loss": 5.7209,
|
|
"mean_token_accuracy": 0.15952013283967972,
|
|
"num_tokens": 5790177.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.923643255233765,
|
|
"epoch": 0.2920199921379233,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499633756491259,
|
|
"loss": 5.7569,
|
|
"mean_token_accuracy": 0.1707965239882469,
|
|
"num_tokens": 5800251.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.936167621612549,
|
|
"epoch": 0.29258156904588084,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004996314630831781,
|
|
"loss": 5.8339,
|
|
"mean_token_accuracy": 0.16565884947776793,
|
|
"num_tokens": 5812210.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.918135690689087,
|
|
"epoch": 0.2931431459538384,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996291625227443,
|
|
"loss": 5.823,
|
|
"mean_token_accuracy": 0.1682283952832222,
|
|
"num_tokens": 5823280.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.983985757827758,
|
|
"epoch": 0.29370472286179594,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996268548100307,
|
|
"loss": 5.8846,
|
|
"mean_token_accuracy": 0.15846949815750122,
|
|
"num_tokens": 5835076.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.774041032791137,
|
|
"epoch": 0.2942662997697535,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499624539945111,
|
|
"loss": 5.6842,
|
|
"mean_token_accuracy": 0.17633943408727645,
|
|
"num_tokens": 5845376.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.780922889709473,
|
|
"epoch": 0.294827876677711,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996222179280589,
|
|
"loss": 5.7233,
|
|
"mean_token_accuracy": 0.16174683272838591,
|
|
"num_tokens": 5857124.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.963794898986817,
|
|
"epoch": 0.29538945358566854,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996198887589481,
|
|
"loss": 5.8263,
|
|
"mean_token_accuracy": 0.15918904915452003,
|
|
"num_tokens": 5868681.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.872399187088012,
|
|
"epoch": 0.2959510304936261,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996175524378531,
|
|
"loss": 5.8141,
|
|
"mean_token_accuracy": 0.16962093859910965,
|
|
"num_tokens": 5880532.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.928860807418824,
|
|
"epoch": 0.29651260740158364,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499615208964848,
|
|
"loss": 5.7669,
|
|
"mean_token_accuracy": 0.1708823785185814,
|
|
"num_tokens": 5891582.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.85929856300354,
|
|
"epoch": 0.2970741843095412,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996128583400077,
|
|
"loss": 5.7778,
|
|
"mean_token_accuracy": 0.163731949031353,
|
|
"num_tokens": 5903543.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.830670642852783,
|
|
"epoch": 0.29763576121749874,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996105005634066,
|
|
"loss": 5.7276,
|
|
"mean_token_accuracy": 0.1748351737856865,
|
|
"num_tokens": 5913140.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.886608219146728,
|
|
"epoch": 0.2981973381254563,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004996081356351202,
|
|
"loss": 5.7024,
|
|
"mean_token_accuracy": 0.17049144208431244,
|
|
"num_tokens": 5924010.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.901228237152099,
|
|
"epoch": 0.29875891503341384,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996057635552237,
|
|
"loss": 5.9004,
|
|
"mean_token_accuracy": 0.16316385865211486,
|
|
"num_tokens": 5936246.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.900568342208862,
|
|
"epoch": 0.2993204919413714,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996033843237925,
|
|
"loss": 5.7884,
|
|
"mean_token_accuracy": 0.15582166761159896,
|
|
"num_tokens": 5947594.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.927651834487915,
|
|
"epoch": 0.29988206884932894,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996009979409025,
|
|
"loss": 5.7314,
|
|
"mean_token_accuracy": 0.15971839278936387,
|
|
"num_tokens": 5957660.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.685725259780884,
|
|
"epoch": 0.30044364575728644,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995986044066295,
|
|
"loss": 5.5661,
|
|
"mean_token_accuracy": 0.17532341331243514,
|
|
"num_tokens": 5968881.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.8464141368865965,
|
|
"epoch": 0.301005222665244,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00049959620372105,
|
|
"loss": 5.7354,
|
|
"mean_token_accuracy": 0.16859683096408845,
|
|
"num_tokens": 5980032.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.720075225830078,
|
|
"epoch": 0.30156679957320154,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004995937958842401,
|
|
"loss": 5.7348,
|
|
"mean_token_accuracy": 0.16227123737335206,
|
|
"num_tokens": 5991781.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.883849287033081,
|
|
"epoch": 0.3021283764811591,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995913808962767,
|
|
"loss": 5.7686,
|
|
"mean_token_accuracy": 0.16267271637916564,
|
|
"num_tokens": 6002303.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.965817070007324,
|
|
"epoch": 0.30268995338911664,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995889587572366,
|
|
"loss": 5.8528,
|
|
"mean_token_accuracy": 0.16787079870700836,
|
|
"num_tokens": 6011523.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.912099599838257,
|
|
"epoch": 0.3032515302970742,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499586529467197,
|
|
"loss": 5.662,
|
|
"mean_token_accuracy": 0.17042718827724457,
|
|
"num_tokens": 6022169.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.723714351654053,
|
|
"epoch": 0.30381310720503174,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995840930262351,
|
|
"loss": 5.7268,
|
|
"mean_token_accuracy": 0.16638493165373802,
|
|
"num_tokens": 6033393.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.8972358226776125,
|
|
"epoch": 0.3043746841129893,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995816494344287,
|
|
"loss": 5.7846,
|
|
"mean_token_accuracy": 0.1596575379371643,
|
|
"num_tokens": 6045365.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.826961803436279,
|
|
"epoch": 0.30493626102094684,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995791986918554,
|
|
"loss": 5.8057,
|
|
"mean_token_accuracy": 0.16703701317310332,
|
|
"num_tokens": 6057482.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.891117000579834,
|
|
"epoch": 0.30549783792890434,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995767407985933,
|
|
"loss": 5.7156,
|
|
"mean_token_accuracy": 0.17238480895757674,
|
|
"num_tokens": 6068194.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.850578546524048,
|
|
"epoch": 0.3060594148368619,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004995742757547207,
|
|
"loss": 5.7649,
|
|
"mean_token_accuracy": 0.17026786655187606,
|
|
"num_tokens": 6080540.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.857915544509888,
|
|
"epoch": 0.30662099174481944,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499571803560316,
|
|
"loss": 5.8099,
|
|
"mean_token_accuracy": 0.1647024117410183,
|
|
"num_tokens": 6092464.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.915971326828003,
|
|
"epoch": 0.307182568652777,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004995693242154581,
|
|
"loss": 5.7596,
|
|
"mean_token_accuracy": 0.16778793632984162,
|
|
"num_tokens": 6103242.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.825624752044678,
|
|
"epoch": 0.30774414556073454,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004995668377202258,
|
|
"loss": 5.7974,
|
|
"mean_token_accuracy": 0.16479281783103944,
|
|
"num_tokens": 6116383.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.792344808578491,
|
|
"epoch": 0.3083057224686921,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004995643440746982,
|
|
"loss": 5.6016,
|
|
"mean_token_accuracy": 0.17332126349210739,
|
|
"num_tokens": 6126883.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.887543678283691,
|
|
"epoch": 0.30886729937664964,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004995618432789548,
|
|
"loss": 5.7993,
|
|
"mean_token_accuracy": 0.16024126410484313,
|
|
"num_tokens": 6139613.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.885481071472168,
|
|
"epoch": 0.3094288762846072,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995593353330753,
|
|
"loss": 5.8573,
|
|
"mean_token_accuracy": 0.16386310905218124,
|
|
"num_tokens": 6151950.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.814095878601075,
|
|
"epoch": 0.30999045319256474,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995568202371393,
|
|
"loss": 5.6341,
|
|
"mean_token_accuracy": 0.17681725472211837,
|
|
"num_tokens": 6161563.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.80485954284668,
|
|
"epoch": 0.3105520301005223,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995542979912272,
|
|
"loss": 5.6624,
|
|
"mean_token_accuracy": 0.17834541499614714,
|
|
"num_tokens": 6170966.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.818015003204346,
|
|
"epoch": 0.3111136070084798,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995517685954192,
|
|
"loss": 5.7308,
|
|
"mean_token_accuracy": 0.16718895733356476,
|
|
"num_tokens": 6182563.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.846281957626343,
|
|
"epoch": 0.31167518391643734,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995492320497958,
|
|
"loss": 5.8416,
|
|
"mean_token_accuracy": 0.16075171381235123,
|
|
"num_tokens": 6194495.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.8640399932861325,
|
|
"epoch": 0.3122367608243949,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995466883544376,
|
|
"loss": 5.7408,
|
|
"mean_token_accuracy": 0.16369348615407944,
|
|
"num_tokens": 6206594.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.895187568664551,
|
|
"epoch": 0.31279833773235244,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995441375094258,
|
|
"loss": 5.7627,
|
|
"mean_token_accuracy": 0.16485580503940583,
|
|
"num_tokens": 6218371.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.882254314422608,
|
|
"epoch": 0.31335991464031,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995415795148417,
|
|
"loss": 5.6976,
|
|
"mean_token_accuracy": 0.17356550693511963,
|
|
"num_tokens": 6228723.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.886617183685303,
|
|
"epoch": 0.31392149154826754,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995390143707665,
|
|
"loss": 5.8831,
|
|
"mean_token_accuracy": 0.16673346012830734,
|
|
"num_tokens": 6240535.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.822242879867554,
|
|
"epoch": 0.3144830684562251,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995364420772821,
|
|
"loss": 5.5854,
|
|
"mean_token_accuracy": 0.17410123497247695,
|
|
"num_tokens": 6250643.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.7944286346435545,
|
|
"epoch": 0.31504464536418264,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995338626344702,
|
|
"loss": 5.7097,
|
|
"mean_token_accuracy": 0.1716044783592224,
|
|
"num_tokens": 6259569.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.858190250396729,
|
|
"epoch": 0.3156062222721402,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499531276042413,
|
|
"loss": 5.8734,
|
|
"mean_token_accuracy": 0.16926339864730836,
|
|
"num_tokens": 6271108.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.889335870742798,
|
|
"epoch": 0.31616779918009774,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995286823011929,
|
|
"loss": 5.7088,
|
|
"mean_token_accuracy": 0.15809194445610047,
|
|
"num_tokens": 6282352.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.8390350341796875,
|
|
"epoch": 0.31672937608805524,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995260814108926,
|
|
"loss": 5.8235,
|
|
"mean_token_accuracy": 0.16358305364847184,
|
|
"num_tokens": 6294946.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.754707479476929,
|
|
"epoch": 0.3172909529960128,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995234733715947,
|
|
"loss": 5.631,
|
|
"mean_token_accuracy": 0.1745324283838272,
|
|
"num_tokens": 6305552.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.797818899154663,
|
|
"epoch": 0.31785252990397034,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004995208581833824,
|
|
"loss": 5.6993,
|
|
"mean_token_accuracy": 0.1769035428762436,
|
|
"num_tokens": 6315815.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.864303636550903,
|
|
"epoch": 0.3184141068119279,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995182358463388,
|
|
"loss": 5.7426,
|
|
"mean_token_accuracy": 0.165255768597126,
|
|
"num_tokens": 6327384.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.861385011672974,
|
|
"epoch": 0.31897568371988544,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004995156063605475,
|
|
"loss": 5.7185,
|
|
"mean_token_accuracy": 0.1629460111260414,
|
|
"num_tokens": 6338083.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.876327419281006,
|
|
"epoch": 0.319537260627843,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004995129697260922,
|
|
"loss": 5.7197,
|
|
"mean_token_accuracy": 0.17031879872083663,
|
|
"num_tokens": 6349058.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.823698043823242,
|
|
"epoch": 0.32009883753580054,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995103259430569,
|
|
"loss": 5.7282,
|
|
"mean_token_accuracy": 0.17293349653482437,
|
|
"num_tokens": 6359655.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.917513751983643,
|
|
"epoch": 0.3206604144437581,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995076750115258,
|
|
"loss": 5.8714,
|
|
"mean_token_accuracy": 0.1634015515446663,
|
|
"num_tokens": 6372088.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.820725727081299,
|
|
"epoch": 0.32122199135171564,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995050169315832,
|
|
"loss": 5.757,
|
|
"mean_token_accuracy": 0.16435178220272065,
|
|
"num_tokens": 6382946.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.829253482818603,
|
|
"epoch": 0.32178356825967314,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004995023517033138,
|
|
"loss": 5.7626,
|
|
"mean_token_accuracy": 0.1649421587586403,
|
|
"num_tokens": 6392591.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.767510843276978,
|
|
"epoch": 0.3223451451676307,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994996793268024,
|
|
"loss": 5.6885,
|
|
"mean_token_accuracy": 0.17057053446769715,
|
|
"num_tokens": 6403159.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.859529638290406,
|
|
"epoch": 0.32290672207558824,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004994969998021342,
|
|
"loss": 5.7251,
|
|
"mean_token_accuracy": 0.16644418686628343,
|
|
"num_tokens": 6414232.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.8600890159606935,
|
|
"epoch": 0.3234682989835458,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994943131293944,
|
|
"loss": 5.6921,
|
|
"mean_token_accuracy": 0.18009964227676392,
|
|
"num_tokens": 6425762.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.778131580352783,
|
|
"epoch": 0.32402987589150334,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994916193086687,
|
|
"loss": 5.7359,
|
|
"mean_token_accuracy": 0.16423172056674956,
|
|
"num_tokens": 6439077.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.909442615509033,
|
|
"epoch": 0.3245914527994609,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994889183400428,
|
|
"loss": 5.8157,
|
|
"mean_token_accuracy": 0.16724281013011932,
|
|
"num_tokens": 6450425.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.829175615310669,
|
|
"epoch": 0.32515302970741844,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004994862102236025,
|
|
"loss": 5.7707,
|
|
"mean_token_accuracy": 0.1715887501835823,
|
|
"num_tokens": 6461347.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.865241003036499,
|
|
"epoch": 0.325714606615376,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994834949594342,
|
|
"loss": 5.759,
|
|
"mean_token_accuracy": 0.16879544407129288,
|
|
"num_tokens": 6472428.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.7962500095367435,
|
|
"epoch": 0.32627618352333354,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994807725476246,
|
|
"loss": 5.7168,
|
|
"mean_token_accuracy": 0.17446729838848113,
|
|
"num_tokens": 6483393.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.80073094367981,
|
|
"epoch": 0.3268377604312911,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994780429882599,
|
|
"loss": 5.7014,
|
|
"mean_token_accuracy": 0.17042361497879027,
|
|
"num_tokens": 6493520.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.751598072052002,
|
|
"epoch": 0.3273993373392486,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004994753062814274,
|
|
"loss": 5.6518,
|
|
"mean_token_accuracy": 0.17481115609407424,
|
|
"num_tokens": 6505282.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.936983394622803,
|
|
"epoch": 0.32796091424720614,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004994725624272139,
|
|
"loss": 5.816,
|
|
"mean_token_accuracy": 0.1736079603433609,
|
|
"num_tokens": 6516808.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.871405839920044,
|
|
"epoch": 0.3285224911551637,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004994698114257071,
|
|
"loss": 5.7754,
|
|
"mean_token_accuracy": 0.1640280917286873,
|
|
"num_tokens": 6529184.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.744284677505493,
|
|
"epoch": 0.32908406806312124,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994670532769944,
|
|
"loss": 5.6271,
|
|
"mean_token_accuracy": 0.17572139203548431,
|
|
"num_tokens": 6539909.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.8266712665557865,
|
|
"epoch": 0.3296456449710788,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994642879811637,
|
|
"loss": 5.6743,
|
|
"mean_token_accuracy": 0.1735612004995346,
|
|
"num_tokens": 6550870.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.756214761734009,
|
|
"epoch": 0.33020722187903634,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499461515538303,
|
|
"loss": 5.7291,
|
|
"mean_token_accuracy": 0.17583443224430084,
|
|
"num_tokens": 6561784.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.757110977172852,
|
|
"epoch": 0.3307687987869939,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004994587359485006,
|
|
"loss": 5.6696,
|
|
"mean_token_accuracy": 0.17046401351690293,
|
|
"num_tokens": 6573422.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.896243619918823,
|
|
"epoch": 0.33133037569495144,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499455949211845,
|
|
"loss": 5.7409,
|
|
"mean_token_accuracy": 0.17513602674007417,
|
|
"num_tokens": 6584565.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.869036149978638,
|
|
"epoch": 0.331891952602909,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994531553284248,
|
|
"loss": 5.6615,
|
|
"mean_token_accuracy": 0.16997261941432953,
|
|
"num_tokens": 6594238.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.723050689697265,
|
|
"epoch": 0.3324535295108665,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004994503542983293,
|
|
"loss": 5.741,
|
|
"mean_token_accuracy": 0.16911158263683318,
|
|
"num_tokens": 6606309.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.956376457214356,
|
|
"epoch": 0.33301510641882404,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994475461216472,
|
|
"loss": 5.8312,
|
|
"mean_token_accuracy": 0.1619592562317848,
|
|
"num_tokens": 6617916.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.807530403137207,
|
|
"epoch": 0.3335766833267816,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994447307984684,
|
|
"loss": 5.6867,
|
|
"mean_token_accuracy": 0.16937974691390992,
|
|
"num_tokens": 6627951.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.740665912628174,
|
|
"epoch": 0.33413826023473914,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004994419083288823,
|
|
"loss": 5.7516,
|
|
"mean_token_accuracy": 0.17015371173620225,
|
|
"num_tokens": 6639285.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.817653036117553,
|
|
"epoch": 0.3346998371426967,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994390787129787,
|
|
"loss": 5.6058,
|
|
"mean_token_accuracy": 0.1782895877957344,
|
|
"num_tokens": 6649973.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.73169355392456,
|
|
"epoch": 0.33526141405065424,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004994362419508478,
|
|
"loss": 5.6212,
|
|
"mean_token_accuracy": 0.17402680665254594,
|
|
"num_tokens": 6660625.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.835042095184326,
|
|
"epoch": 0.3358229909586118,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00049943339804258,
|
|
"loss": 5.7113,
|
|
"mean_token_accuracy": 0.16824356615543365,
|
|
"num_tokens": 6673191.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.834809255599976,
|
|
"epoch": 0.33638456786656934,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994305469882657,
|
|
"loss": 5.716,
|
|
"mean_token_accuracy": 0.17247826904058455,
|
|
"num_tokens": 6683993.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.763989877700806,
|
|
"epoch": 0.3369461447745269,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004994276887879957,
|
|
"loss": 5.7292,
|
|
"mean_token_accuracy": 0.1751634359359741,
|
|
"num_tokens": 6694881.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.3369461447745269,
|
|
"eval_entropy": 5.631992234315398,
|
|
"eval_loss": 5.732239246368408,
|
|
"eval_mean_token_accuracy": 0.17665448291421798,
|
|
"eval_num_tokens": 6694881.0,
|
|
"eval_runtime": 18.4364,
|
|
"eval_samples_per_second": 1682.164,
|
|
"eval_steps_per_second": 210.291,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.819136333465576,
|
|
"epoch": 0.33750772168248444,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994248234418611,
|
|
"loss": 5.733,
|
|
"mean_token_accuracy": 0.16972203850746154,
|
|
"num_tokens": 6706648.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.801159763336182,
|
|
"epoch": 0.33806929859044194,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499421950949953,
|
|
"loss": 5.7347,
|
|
"mean_token_accuracy": 0.17212952226400374,
|
|
"num_tokens": 6716858.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.724242496490478,
|
|
"epoch": 0.3386308754983995,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499419071312363,
|
|
"loss": 5.6889,
|
|
"mean_token_accuracy": 0.17499449700117112,
|
|
"num_tokens": 6726558.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.881882572174073,
|
|
"epoch": 0.33919245240635704,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994161845291828,
|
|
"loss": 5.6801,
|
|
"mean_token_accuracy": 0.16776044964790343,
|
|
"num_tokens": 6737819.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.794957828521729,
|
|
"epoch": 0.3397540293143146,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994132906005041,
|
|
"loss": 5.6322,
|
|
"mean_token_accuracy": 0.1724249988794327,
|
|
"num_tokens": 6748593.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.63336067199707,
|
|
"epoch": 0.34031560622227214,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004994103895264193,
|
|
"loss": 5.7422,
|
|
"mean_token_accuracy": 0.162245012819767,
|
|
"num_tokens": 6760631.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.919184780120849,
|
|
"epoch": 0.3408771831302297,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994074813070207,
|
|
"loss": 5.6398,
|
|
"mean_token_accuracy": 0.16651962250471114,
|
|
"num_tokens": 6772318.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.715067386627197,
|
|
"epoch": 0.34143876003818724,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004994045659424007,
|
|
"loss": 5.6772,
|
|
"mean_token_accuracy": 0.1750547170639038,
|
|
"num_tokens": 6782684.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.785168123245239,
|
|
"epoch": 0.3420003369461448,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004994016434326524,
|
|
"loss": 5.5655,
|
|
"mean_token_accuracy": 0.1777344137430191,
|
|
"num_tokens": 6793895.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.684515047073364,
|
|
"epoch": 0.34256191385410234,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004993987137778687,
|
|
"loss": 5.6293,
|
|
"mean_token_accuracy": 0.17251270562410354,
|
|
"num_tokens": 6804794.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.8218306541442875,
|
|
"epoch": 0.3431234907620599,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499395776978143,
|
|
"loss": 5.7589,
|
|
"mean_token_accuracy": 0.16612927317619325,
|
|
"num_tokens": 6815976.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.817735004425049,
|
|
"epoch": 0.3436850676700174,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004993928330335686,
|
|
"loss": 5.742,
|
|
"mean_token_accuracy": 0.16376831382513046,
|
|
"num_tokens": 6828027.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.815735101699829,
|
|
"epoch": 0.34424664457797494,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004993898819442395,
|
|
"loss": 5.7233,
|
|
"mean_token_accuracy": 0.1691370740532875,
|
|
"num_tokens": 6839195.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.656938266754151,
|
|
"epoch": 0.3448082214859325,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004993869237102494,
|
|
"loss": 5.5894,
|
|
"mean_token_accuracy": 0.17244611978530883,
|
|
"num_tokens": 6851731.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.8333851337432865,
|
|
"epoch": 0.34536979839389004,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993839583316927,
|
|
"loss": 5.6397,
|
|
"mean_token_accuracy": 0.17510228455066681,
|
|
"num_tokens": 6862916.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.888251066207886,
|
|
"epoch": 0.3459313753018476,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004993809858086638,
|
|
"loss": 5.8157,
|
|
"mean_token_accuracy": 0.162273408472538,
|
|
"num_tokens": 6876003.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.739641332626343,
|
|
"epoch": 0.34649295220980514,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993780061412571,
|
|
"loss": 5.7806,
|
|
"mean_token_accuracy": 0.1702667608857155,
|
|
"num_tokens": 6886040.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.829275894165039,
|
|
"epoch": 0.3470545291177627,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004993750193295678,
|
|
"loss": 5.6865,
|
|
"mean_token_accuracy": 0.1768171027302742,
|
|
"num_tokens": 6896758.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.833682680130005,
|
|
"epoch": 0.34761610602572024,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004993720253736909,
|
|
"loss": 5.7384,
|
|
"mean_token_accuracy": 0.17008273154497147,
|
|
"num_tokens": 6907287.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.768305683135987,
|
|
"epoch": 0.3481776829336778,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993690242737216,
|
|
"loss": 5.7566,
|
|
"mean_token_accuracy": 0.16723249703645707,
|
|
"num_tokens": 6918992.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.890691232681275,
|
|
"epoch": 0.3487392598416353,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004993660160297555,
|
|
"loss": 5.77,
|
|
"mean_token_accuracy": 0.1689866676926613,
|
|
"num_tokens": 6931493.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.7417604446411135,
|
|
"epoch": 0.34930083674959284,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004993630006418885,
|
|
"loss": 5.5921,
|
|
"mean_token_accuracy": 0.1775926724076271,
|
|
"num_tokens": 6941807.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.861759185791016,
|
|
"epoch": 0.3498624136575504,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004993599781102166,
|
|
"loss": 5.7927,
|
|
"mean_token_accuracy": 0.16744445115327836,
|
|
"num_tokens": 6953436.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.968575429916382,
|
|
"epoch": 0.35042399056550794,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993569484348359,
|
|
"loss": 5.9075,
|
|
"mean_token_accuracy": 0.16151681840419768,
|
|
"num_tokens": 6965247.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.7765837669372555,
|
|
"epoch": 0.3509855674734655,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004993539116158429,
|
|
"loss": 5.6958,
|
|
"mean_token_accuracy": 0.17401523888111115,
|
|
"num_tokens": 6976605.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.710376501083374,
|
|
"epoch": 0.35154714438142304,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993508676533346,
|
|
"loss": 5.6508,
|
|
"mean_token_accuracy": 0.18309797793626786,
|
|
"num_tokens": 6986205.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.774714517593384,
|
|
"epoch": 0.3521087212893806,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004993478165474074,
|
|
"loss": 5.6054,
|
|
"mean_token_accuracy": 0.178724704682827,
|
|
"num_tokens": 6997699.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.690198755264282,
|
|
"epoch": 0.35267029819733814,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004993447582981588,
|
|
"loss": 5.62,
|
|
"mean_token_accuracy": 0.1739739567041397,
|
|
"num_tokens": 7008968.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.8412824153900145,
|
|
"epoch": 0.3532318751052957,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499341692905686,
|
|
"loss": 5.6581,
|
|
"mean_token_accuracy": 0.1689726173877716,
|
|
"num_tokens": 7020633.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.73580117225647,
|
|
"epoch": 0.35379345201325324,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993386203700868,
|
|
"loss": 5.579,
|
|
"mean_token_accuracy": 0.18208679258823396,
|
|
"num_tokens": 7031187.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.816767406463623,
|
|
"epoch": 0.35435502892121074,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004993355406914589,
|
|
"loss": 5.7948,
|
|
"mean_token_accuracy": 0.16400412023067473,
|
|
"num_tokens": 7042662.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.848151445388794,
|
|
"epoch": 0.3549166058291683,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004993324538699003,
|
|
"loss": 5.7857,
|
|
"mean_token_accuracy": 0.173075395822525,
|
|
"num_tokens": 7054297.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.826444005966186,
|
|
"epoch": 0.35547818273712584,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004993293599055094,
|
|
"loss": 5.6413,
|
|
"mean_token_accuracy": 0.17617398798465728,
|
|
"num_tokens": 7064961.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.798005485534668,
|
|
"epoch": 0.3560397596450834,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004993262587983848,
|
|
"loss": 5.7994,
|
|
"mean_token_accuracy": 0.1694578006863594,
|
|
"num_tokens": 7076857.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.838046503067017,
|
|
"epoch": 0.35660133655304094,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499323150548625,
|
|
"loss": 5.6704,
|
|
"mean_token_accuracy": 0.17216843664646148,
|
|
"num_tokens": 7088926.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.656442022323608,
|
|
"epoch": 0.3571629134609985,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993200351563291,
|
|
"loss": 5.5703,
|
|
"mean_token_accuracy": 0.18148448467254638,
|
|
"num_tokens": 7099478.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.744642448425293,
|
|
"epoch": 0.35772449036895604,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004993169126215962,
|
|
"loss": 5.6312,
|
|
"mean_token_accuracy": 0.1722390189766884,
|
|
"num_tokens": 7111776.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.88515830039978,
|
|
"epoch": 0.3582860672769136,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993137829445259,
|
|
"loss": 5.7242,
|
|
"mean_token_accuracy": 0.16789288222789764,
|
|
"num_tokens": 7123084.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.764853668212891,
|
|
"epoch": 0.35884764418487114,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004993106461252177,
|
|
"loss": 5.704,
|
|
"mean_token_accuracy": 0.171440427005291,
|
|
"num_tokens": 7134973.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.692889022827148,
|
|
"epoch": 0.3594092210928287,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004993075021637716,
|
|
"loss": 5.7244,
|
|
"mean_token_accuracy": 0.16945530772209166,
|
|
"num_tokens": 7147227.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.874735164642334,
|
|
"epoch": 0.3599707980007862,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004993043510602875,
|
|
"loss": 5.7013,
|
|
"mean_token_accuracy": 0.17460730224847792,
|
|
"num_tokens": 7158201.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.709667730331421,
|
|
"epoch": 0.36053237490874374,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499301192814866,
|
|
"loss": 5.5983,
|
|
"mean_token_accuracy": 0.17740452587604522,
|
|
"num_tokens": 7168909.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.801937246322632,
|
|
"epoch": 0.3610939518167013,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004992980274276074,
|
|
"loss": 5.753,
|
|
"mean_token_accuracy": 0.16828656196594238,
|
|
"num_tokens": 7179877.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.793533849716186,
|
|
"epoch": 0.36165552872465884,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004992948548986128,
|
|
"loss": 5.6603,
|
|
"mean_token_accuracy": 0.1773525133728981,
|
|
"num_tokens": 7190823.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.752917909622193,
|
|
"epoch": 0.3622171056326164,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992916752279829,
|
|
"loss": 5.5894,
|
|
"mean_token_accuracy": 0.17470155656337738,
|
|
"num_tokens": 7201700.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.780609560012818,
|
|
"epoch": 0.36277868254057394,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499288488415819,
|
|
"loss": 5.6493,
|
|
"mean_token_accuracy": 0.17959498316049577,
|
|
"num_tokens": 7213618.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.866898870468139,
|
|
"epoch": 0.3633402594485315,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004992852944622229,
|
|
"loss": 5.8387,
|
|
"mean_token_accuracy": 0.16976505815982817,
|
|
"num_tokens": 7226207.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.7547344207763675,
|
|
"epoch": 0.36390183635648904,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004992820933672958,
|
|
"loss": 5.6698,
|
|
"mean_token_accuracy": 0.1762295573949814,
|
|
"num_tokens": 7237545.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.717173767089844,
|
|
"epoch": 0.3644634132644466,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004992788851311399,
|
|
"loss": 5.6514,
|
|
"mean_token_accuracy": 0.1721198230981827,
|
|
"num_tokens": 7247799.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.746833848953247,
|
|
"epoch": 0.3650249901724041,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004992756697538574,
|
|
"loss": 5.6435,
|
|
"mean_token_accuracy": 0.16833308786153794,
|
|
"num_tokens": 7260229.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.735746622085571,
|
|
"epoch": 0.36558656708036164,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992724472355505,
|
|
"loss": 5.7514,
|
|
"mean_token_accuracy": 0.1684183195233345,
|
|
"num_tokens": 7271457.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.780439186096191,
|
|
"epoch": 0.3661481439883192,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004992692175763219,
|
|
"loss": 5.65,
|
|
"mean_token_accuracy": 0.1729257583618164,
|
|
"num_tokens": 7282124.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.824368476867676,
|
|
"epoch": 0.36670972089627674,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992659807762745,
|
|
"loss": 5.7521,
|
|
"mean_token_accuracy": 0.16994550675153733,
|
|
"num_tokens": 7292981.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.935243320465088,
|
|
"epoch": 0.3672712978042343,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004992627368355112,
|
|
"loss": 5.9006,
|
|
"mean_token_accuracy": 0.16785538494586943,
|
|
"num_tokens": 7304591.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.849437046051025,
|
|
"epoch": 0.36783287471219184,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992594857541355,
|
|
"loss": 5.6396,
|
|
"mean_token_accuracy": 0.17560438215732574,
|
|
"num_tokens": 7315918.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.777096176147461,
|
|
"epoch": 0.3683944516201494,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004992562275322506,
|
|
"loss": 5.7355,
|
|
"mean_token_accuracy": 0.16889662742614747,
|
|
"num_tokens": 7327725.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.88145899772644,
|
|
"epoch": 0.36895602852810694,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992529621699606,
|
|
"loss": 5.7405,
|
|
"mean_token_accuracy": 0.16651637107133865,
|
|
"num_tokens": 7339787.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.858824682235718,
|
|
"epoch": 0.3695176054360645,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004992496896673692,
|
|
"loss": 5.7294,
|
|
"mean_token_accuracy": 0.17076862901449202,
|
|
"num_tokens": 7351284.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.658685493469238,
|
|
"epoch": 0.37007918234402204,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992464100245809,
|
|
"loss": 5.5524,
|
|
"mean_token_accuracy": 0.17875730544328688,
|
|
"num_tokens": 7362105.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.771422719955444,
|
|
"epoch": 0.37064075925197953,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004992431232416997,
|
|
"loss": 5.6694,
|
|
"mean_token_accuracy": 0.1705271676182747,
|
|
"num_tokens": 7375204.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.90152678489685,
|
|
"epoch": 0.3712023361599371,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004992398293188307,
|
|
"loss": 5.8067,
|
|
"mean_token_accuracy": 0.1683753490447998,
|
|
"num_tokens": 7385853.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.754110288619995,
|
|
"epoch": 0.37176391306789464,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004992365282560784,
|
|
"loss": 5.6737,
|
|
"mean_token_accuracy": 0.16615278273820877,
|
|
"num_tokens": 7397459.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.775053882598877,
|
|
"epoch": 0.3723254899758522,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992332200535483,
|
|
"loss": 5.6533,
|
|
"mean_token_accuracy": 0.16877304911613464,
|
|
"num_tokens": 7408996.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.84871244430542,
|
|
"epoch": 0.37288706688380974,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004992299047113452,
|
|
"loss": 5.7501,
|
|
"mean_token_accuracy": 0.16261120289564132,
|
|
"num_tokens": 7419938.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.813049745559693,
|
|
"epoch": 0.3734486437917673,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004992265822295752,
|
|
"loss": 5.7612,
|
|
"mean_token_accuracy": 0.16559012234210968,
|
|
"num_tokens": 7430181.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.810550117492676,
|
|
"epoch": 0.37401022069972484,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004992232526083438,
|
|
"loss": 5.7099,
|
|
"mean_token_accuracy": 0.16987437307834624,
|
|
"num_tokens": 7440774.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.818269824981689,
|
|
"epoch": 0.3745717976076824,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000499219915847757,
|
|
"loss": 5.6408,
|
|
"mean_token_accuracy": 0.17308392822742463,
|
|
"num_tokens": 7451744.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.647943449020386,
|
|
"epoch": 0.37513337451563994,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004992165719479211,
|
|
"loss": 5.6826,
|
|
"mean_token_accuracy": 0.17259350717067717,
|
|
"num_tokens": 7463731.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.836802339553833,
|
|
"epoch": 0.37569495142359743,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004992132209089427,
|
|
"loss": 5.6712,
|
|
"mean_token_accuracy": 0.1763611614704132,
|
|
"num_tokens": 7474392.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.715862989425659,
|
|
"epoch": 0.376256528331555,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004992098627309283,
|
|
"loss": 5.5792,
|
|
"mean_token_accuracy": 0.18714895993471145,
|
|
"num_tokens": 7484860.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.692795515060425,
|
|
"epoch": 0.37681810523951254,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499206497413985,
|
|
"loss": 5.6433,
|
|
"mean_token_accuracy": 0.17612822651863097,
|
|
"num_tokens": 7495877.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.870680618286133,
|
|
"epoch": 0.3773796821474701,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992031249582197,
|
|
"loss": 5.7041,
|
|
"mean_token_accuracy": 0.17734302431344987,
|
|
"num_tokens": 7506879.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.706663513183594,
|
|
"epoch": 0.37794125905542764,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004991997453637401,
|
|
"loss": 5.5412,
|
|
"mean_token_accuracy": 0.18161289244890214,
|
|
"num_tokens": 7517405.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.715374231338501,
|
|
"epoch": 0.3785028359633852,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004991963586306536,
|
|
"loss": 5.6328,
|
|
"mean_token_accuracy": 0.1720275640487671,
|
|
"num_tokens": 7528832.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.757056188583374,
|
|
"epoch": 0.37906441287134274,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004991929647590682,
|
|
"loss": 5.6105,
|
|
"mean_token_accuracy": 0.17205780744552612,
|
|
"num_tokens": 7541048.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.754649496078491,
|
|
"epoch": 0.3796259897793003,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004991895637490917,
|
|
"loss": 5.6185,
|
|
"mean_token_accuracy": 0.17652998715639115,
|
|
"num_tokens": 7551849.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.662470054626465,
|
|
"epoch": 0.38018756668725784,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991861556008326,
|
|
"loss": 5.6357,
|
|
"mean_token_accuracy": 0.17981449663639068,
|
|
"num_tokens": 7563148.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.894662761688233,
|
|
"epoch": 0.3807491435952154,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004991827403143992,
|
|
"loss": 5.8225,
|
|
"mean_token_accuracy": 0.1672139585018158,
|
|
"num_tokens": 7575119.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.8430053234100345,
|
|
"epoch": 0.3813107205031729,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004991793178899006,
|
|
"loss": 5.6704,
|
|
"mean_token_accuracy": 0.17408028542995452,
|
|
"num_tokens": 7585899.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.792122459411621,
|
|
"epoch": 0.38187229741113043,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004991758883274455,
|
|
"loss": 5.5733,
|
|
"mean_token_accuracy": 0.18275393694639205,
|
|
"num_tokens": 7598938.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.628747367858887,
|
|
"epoch": 0.382433874319088,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991724516271432,
|
|
"loss": 5.6521,
|
|
"mean_token_accuracy": 0.16920132786035538,
|
|
"num_tokens": 7610087.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.887259387969971,
|
|
"epoch": 0.38299545122704554,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991690077891032,
|
|
"loss": 5.7794,
|
|
"mean_token_accuracy": 0.16809322983026503,
|
|
"num_tokens": 7622186.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.874405384063721,
|
|
"epoch": 0.3835570281350031,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004991655568134348,
|
|
"loss": 5.7338,
|
|
"mean_token_accuracy": 0.17035729736089705,
|
|
"num_tokens": 7633501.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.654582500457764,
|
|
"epoch": 0.38411860504296064,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004991620987002483,
|
|
"loss": 5.6487,
|
|
"mean_token_accuracy": 0.1724038079380989,
|
|
"num_tokens": 7643656.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.780475711822509,
|
|
"epoch": 0.3846801819509182,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004991586334496536,
|
|
"loss": 5.6597,
|
|
"mean_token_accuracy": 0.17520257979631423,
|
|
"num_tokens": 7654565.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.750225830078125,
|
|
"epoch": 0.38524175885887574,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004991551610617611,
|
|
"loss": 5.5788,
|
|
"mean_token_accuracy": 0.1814594268798828,
|
|
"num_tokens": 7664725.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.658280611038208,
|
|
"epoch": 0.3858033357668333,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004991516815366812,
|
|
"loss": 5.6667,
|
|
"mean_token_accuracy": 0.17267031818628312,
|
|
"num_tokens": 7674772.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.855649948120117,
|
|
"epoch": 0.38636491267479084,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499148194874525,
|
|
"loss": 5.7189,
|
|
"mean_token_accuracy": 0.16851244121789932,
|
|
"num_tokens": 7686488.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.850823068618775,
|
|
"epoch": 0.38692648958274833,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004991447010754032,
|
|
"loss": 5.7083,
|
|
"mean_token_accuracy": 0.1727656215429306,
|
|
"num_tokens": 7698842.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.685489082336426,
|
|
"epoch": 0.3874880664907059,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004991412001394273,
|
|
"loss": 5.4988,
|
|
"mean_token_accuracy": 0.17627423107624055,
|
|
"num_tokens": 7709255.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.605527257919311,
|
|
"epoch": 0.38804964339866344,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004991376920667086,
|
|
"loss": 5.5555,
|
|
"mean_token_accuracy": 0.17667909264564513,
|
|
"num_tokens": 7720182.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.701817989349365,
|
|
"epoch": 0.388611220306621,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004991341768573589,
|
|
"loss": 5.5803,
|
|
"mean_token_accuracy": 0.18403764963150024,
|
|
"num_tokens": 7730944.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.778051900863647,
|
|
"epoch": 0.38917279721457854,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00049913065451149,
|
|
"loss": 5.6454,
|
|
"mean_token_accuracy": 0.1756534218788147,
|
|
"num_tokens": 7741686.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.7675353527069095,
|
|
"epoch": 0.3897343741225361,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004991271250292141,
|
|
"loss": 5.6537,
|
|
"mean_token_accuracy": 0.17629104107618332,
|
|
"num_tokens": 7752245.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.637860631942749,
|
|
"epoch": 0.39029595103049364,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004991235884106437,
|
|
"loss": 5.6335,
|
|
"mean_token_accuracy": 0.16780858039855956,
|
|
"num_tokens": 7762622.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.866631984710693,
|
|
"epoch": 0.3908575279384512,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004991200446558913,
|
|
"loss": 5.7482,
|
|
"mean_token_accuracy": 0.17427458316087724,
|
|
"num_tokens": 7773550.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.693408346176147,
|
|
"epoch": 0.39141910484640874,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004991164937650698,
|
|
"loss": 5.6254,
|
|
"mean_token_accuracy": 0.17077690064907075,
|
|
"num_tokens": 7784988.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.7872772216796875,
|
|
"epoch": 0.39198068175436623,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004991129357382922,
|
|
"loss": 5.7126,
|
|
"mean_token_accuracy": 0.17314721494913102,
|
|
"num_tokens": 7797706.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.722473287582398,
|
|
"epoch": 0.3925422586623238,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004991093705756718,
|
|
"loss": 5.5935,
|
|
"mean_token_accuracy": 0.17936303317546845,
|
|
"num_tokens": 7808960.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.681925201416016,
|
|
"epoch": 0.39310383557028133,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004991057982773221,
|
|
"loss": 5.5715,
|
|
"mean_token_accuracy": 0.18486556261777878,
|
|
"num_tokens": 7819271.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.7344615936279295,
|
|
"epoch": 0.3936654124782389,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004991022188433569,
|
|
"loss": 5.6962,
|
|
"mean_token_accuracy": 0.17472131848335265,
|
|
"num_tokens": 7832257.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.852534914016724,
|
|
"epoch": 0.39422698938619644,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00049909863227389,
|
|
"loss": 5.7017,
|
|
"mean_token_accuracy": 0.16729053854942322,
|
|
"num_tokens": 7842684.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.770964336395264,
|
|
"epoch": 0.394788566294154,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004990950385690358,
|
|
"loss": 5.719,
|
|
"mean_token_accuracy": 0.16776077896356584,
|
|
"num_tokens": 7855031.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.674540424346924,
|
|
"epoch": 0.39535014320211154,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004990914377289088,
|
|
"loss": 5.5148,
|
|
"mean_token_accuracy": 0.1746792569756508,
|
|
"num_tokens": 7865291.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.6400972366333,
|
|
"epoch": 0.3959117201100691,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004990878297536233,
|
|
"loss": 5.4908,
|
|
"mean_token_accuracy": 0.17839647978544235,
|
|
"num_tokens": 7876401.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.634608030319214,
|
|
"epoch": 0.39647329701802664,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004990842146432946,
|
|
"loss": 5.536,
|
|
"mean_token_accuracy": 0.17374856024980545,
|
|
"num_tokens": 7887787.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.707843494415283,
|
|
"epoch": 0.3970348739259842,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004990805923980375,
|
|
"loss": 5.523,
|
|
"mean_token_accuracy": 0.1763603776693344,
|
|
"num_tokens": 7898550.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.68929762840271,
|
|
"epoch": 0.3975964508339417,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004990769630179673,
|
|
"loss": 5.6747,
|
|
"mean_token_accuracy": 0.17355783879756928,
|
|
"num_tokens": 7909254.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.852826881408691,
|
|
"epoch": 0.39815802774189923,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990733265032,
|
|
"loss": 5.7042,
|
|
"mean_token_accuracy": 0.17926168888807298,
|
|
"num_tokens": 7920164.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.705505084991455,
|
|
"epoch": 0.3987196046498568,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990696828538508,
|
|
"loss": 5.6434,
|
|
"mean_token_accuracy": 0.17162723541259767,
|
|
"num_tokens": 7931390.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.765172052383423,
|
|
"epoch": 0.39928118155781434,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499066032070036,
|
|
"loss": 5.6634,
|
|
"mean_token_accuracy": 0.1701713427901268,
|
|
"num_tokens": 7943765.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.695808792114258,
|
|
"epoch": 0.3998427584657719,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004990623741518719,
|
|
"loss": 5.5016,
|
|
"mean_token_accuracy": 0.1803964599967003,
|
|
"num_tokens": 7954621.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.671160173416138,
|
|
"epoch": 0.40040433537372944,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499058709099475,
|
|
"loss": 5.7128,
|
|
"mean_token_accuracy": 0.16859437972307206,
|
|
"num_tokens": 7966063.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.835380983352661,
|
|
"epoch": 0.400965912281687,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990550369129618,
|
|
"loss": 5.6232,
|
|
"mean_token_accuracy": 0.17717592418193817,
|
|
"num_tokens": 7977391.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.743214464187622,
|
|
"epoch": 0.40152748918964454,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004990513575924494,
|
|
"loss": 5.7367,
|
|
"mean_token_accuracy": 0.16896894723176956,
|
|
"num_tokens": 7988786.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.742875957489014,
|
|
"epoch": 0.4020890660976021,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004990476711380548,
|
|
"loss": 5.5241,
|
|
"mean_token_accuracy": 0.17627668231725693,
|
|
"num_tokens": 8000848.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.750096702575684,
|
|
"epoch": 0.40265064300555964,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004990439775498954,
|
|
"loss": 5.6817,
|
|
"mean_token_accuracy": 0.17042557001113892,
|
|
"num_tokens": 8012621.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.833896017074585,
|
|
"epoch": 0.40321221991351713,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499040276828089,
|
|
"loss": 5.7354,
|
|
"mean_token_accuracy": 0.16869859397411346,
|
|
"num_tokens": 8023599.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.644566774368286,
|
|
"epoch": 0.4037737968214747,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004990365689727533,
|
|
"loss": 5.5444,
|
|
"mean_token_accuracy": 0.17929765433073044,
|
|
"num_tokens": 8037151.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.742999458312989,
|
|
"epoch": 0.40433537372943223,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004990328539840062,
|
|
"loss": 5.7393,
|
|
"mean_token_accuracy": 0.17098934650421144,
|
|
"num_tokens": 8048606.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.707454442977905,
|
|
"epoch": 0.4048969506373898,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004990291318619663,
|
|
"loss": 5.531,
|
|
"mean_token_accuracy": 0.18790849000215532,
|
|
"num_tokens": 8058430.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.626982164382935,
|
|
"epoch": 0.40545852754534734,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004990254026067518,
|
|
"loss": 5.5427,
|
|
"mean_token_accuracy": 0.17823073863983155,
|
|
"num_tokens": 8069554.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.806381511688232,
|
|
"epoch": 0.4060201044533049,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004990216662184817,
|
|
"loss": 5.7041,
|
|
"mean_token_accuracy": 0.1629281982779503,
|
|
"num_tokens": 8082131.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.690978956222534,
|
|
"epoch": 0.40658168136126244,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004990179226972749,
|
|
"loss": 5.5306,
|
|
"mean_token_accuracy": 0.1793044000864029,
|
|
"num_tokens": 8093454.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.816726446151733,
|
|
"epoch": 0.40714325826922,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004990141720432504,
|
|
"loss": 5.7961,
|
|
"mean_token_accuracy": 0.1596296101808548,
|
|
"num_tokens": 8105502.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.728281879425049,
|
|
"epoch": 0.40770483517717754,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004990104142565279,
|
|
"loss": 5.6486,
|
|
"mean_token_accuracy": 0.17166142165660858,
|
|
"num_tokens": 8116524.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.749354457855224,
|
|
"epoch": 0.40826641208513503,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499006649337227,
|
|
"loss": 5.6378,
|
|
"mean_token_accuracy": 0.18110090345144272,
|
|
"num_tokens": 8126949.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.751841020584107,
|
|
"epoch": 0.4088279889930926,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004990028772854674,
|
|
"loss": 5.5948,
|
|
"mean_token_accuracy": 0.18108304888010024,
|
|
"num_tokens": 8137346.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.655619096755982,
|
|
"epoch": 0.40938956590105013,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004989990981013693,
|
|
"loss": 5.6204,
|
|
"mean_token_accuracy": 0.17147953510284425,
|
|
"num_tokens": 8148499.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.795197439193726,
|
|
"epoch": 0.4099511428090077,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000498995311785053,
|
|
"loss": 5.6606,
|
|
"mean_token_accuracy": 0.17419218868017197,
|
|
"num_tokens": 8159645.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.71441879272461,
|
|
"epoch": 0.41051271971696524,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004989915183366392,
|
|
"loss": 5.5503,
|
|
"mean_token_accuracy": 0.176376548409462,
|
|
"num_tokens": 8171033.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.646851682662964,
|
|
"epoch": 0.4110742966249228,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989877177562485,
|
|
"loss": 5.6198,
|
|
"mean_token_accuracy": 0.17579082101583482,
|
|
"num_tokens": 8181582.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.713270759582519,
|
|
"epoch": 0.41163587353288034,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000498983910044002,
|
|
"loss": 5.5233,
|
|
"mean_token_accuracy": 0.17835837006568908,
|
|
"num_tokens": 8192432.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.781804943084717,
|
|
"epoch": 0.4121974504408379,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989800952000209,
|
|
"loss": 5.7125,
|
|
"mean_token_accuracy": 0.17426385283470153,
|
|
"num_tokens": 8203995.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.669413900375366,
|
|
"epoch": 0.41275902734879544,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004989762732244268,
|
|
"loss": 5.5416,
|
|
"mean_token_accuracy": 0.1784492939710617,
|
|
"num_tokens": 8214323.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.635898303985596,
|
|
"epoch": 0.413320604256753,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989724441173413,
|
|
"loss": 5.6093,
|
|
"mean_token_accuracy": 0.1708337113261223,
|
|
"num_tokens": 8226285.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.830092430114746,
|
|
"epoch": 0.4138821811647105,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004989686078788862,
|
|
"loss": 5.7605,
|
|
"mean_token_accuracy": 0.16820843517780304,
|
|
"num_tokens": 8237961.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.674856519699096,
|
|
"epoch": 0.41444375807266803,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004989647645091839,
|
|
"loss": 5.519,
|
|
"mean_token_accuracy": 0.18347225934267045,
|
|
"num_tokens": 8248463.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.76221284866333,
|
|
"epoch": 0.4150053349806256,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004989609140083565,
|
|
"loss": 5.6666,
|
|
"mean_token_accuracy": 0.17800566107034682,
|
|
"num_tokens": 8260342.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.7744965076446535,
|
|
"epoch": 0.41556691188858313,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004989570563765269,
|
|
"loss": 5.7668,
|
|
"mean_token_accuracy": 0.17411787509918214,
|
|
"num_tokens": 8272055.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.876493167877197,
|
|
"epoch": 0.4161284887965407,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989531916138176,
|
|
"loss": 5.701,
|
|
"mean_token_accuracy": 0.17120005339384078,
|
|
"num_tokens": 8282129.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.768954277038574,
|
|
"epoch": 0.41669006570449824,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004989493197203519,
|
|
"loss": 5.7052,
|
|
"mean_token_accuracy": 0.1731296017765999,
|
|
"num_tokens": 8294663.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.672701168060303,
|
|
"epoch": 0.4172516426124558,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000498945440696253,
|
|
"loss": 5.5249,
|
|
"mean_token_accuracy": 0.17951664328575134,
|
|
"num_tokens": 8305882.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.714199781417847,
|
|
"epoch": 0.41781321952041334,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004989415545416444,
|
|
"loss": 5.6191,
|
|
"mean_token_accuracy": 0.1792944297194481,
|
|
"num_tokens": 8316604.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.792916488647461,
|
|
"epoch": 0.4183747964283709,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004989376612566498,
|
|
"loss": 5.7111,
|
|
"mean_token_accuracy": 0.1719786509871483,
|
|
"num_tokens": 8328126.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.734830093383789,
|
|
"epoch": 0.4189363733363284,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004989337608413933,
|
|
"loss": 5.6239,
|
|
"mean_token_accuracy": 0.1773782342672348,
|
|
"num_tokens": 8339050.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.642179203033447,
|
|
"epoch": 0.41949795024428593,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004989298532959989,
|
|
"loss": 5.4623,
|
|
"mean_token_accuracy": 0.1804968997836113,
|
|
"num_tokens": 8350216.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.7204163551330565,
|
|
"epoch": 0.4200595271522435,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004989259386205912,
|
|
"loss": 5.6339,
|
|
"mean_token_accuracy": 0.17768179327249528,
|
|
"num_tokens": 8362311.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.783650588989258,
|
|
"epoch": 0.42062110406020103,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989220168152948,
|
|
"loss": 5.7899,
|
|
"mean_token_accuracy": 0.17361119985580445,
|
|
"num_tokens": 8373751.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.797900867462158,
|
|
"epoch": 0.4211826809681586,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004989180878802346,
|
|
"loss": 5.6225,
|
|
"mean_token_accuracy": 0.17424166947603226,
|
|
"num_tokens": 8384932.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.630241584777832,
|
|
"epoch": 0.42174425787611614,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989141518155354,
|
|
"loss": 5.5664,
|
|
"mean_token_accuracy": 0.17962265759706497,
|
|
"num_tokens": 8394973.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.756151723861694,
|
|
"epoch": 0.4223058347840737,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004989102086213229,
|
|
"loss": 5.6639,
|
|
"mean_token_accuracy": 0.17477635145187378,
|
|
"num_tokens": 8406590.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.695920419692993,
|
|
"epoch": 0.42286741169203124,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004989062582977225,
|
|
"loss": 5.592,
|
|
"mean_token_accuracy": 0.17508405297994614,
|
|
"num_tokens": 8417127.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.719182825088501,
|
|
"epoch": 0.4234289885999888,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004989023008448599,
|
|
"loss": 5.6987,
|
|
"mean_token_accuracy": 0.1726223737001419,
|
|
"num_tokens": 8429442.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.696038007736206,
|
|
"epoch": 0.42399056550794634,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004988983362628614,
|
|
"loss": 5.595,
|
|
"mean_token_accuracy": 0.17900979667901992,
|
|
"num_tokens": 8439375.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.667362976074219,
|
|
"epoch": 0.42455214241590383,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004988943645518528,
|
|
"loss": 5.5991,
|
|
"mean_token_accuracy": 0.18217457532882692,
|
|
"num_tokens": 8449817.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.666533088684082,
|
|
"epoch": 0.4251137193238614,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004988903857119611,
|
|
"loss": 5.5059,
|
|
"mean_token_accuracy": 0.18276909589767457,
|
|
"num_tokens": 8460096.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.695093154907227,
|
|
"epoch": 0.42567529623181893,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004988863997433125,
|
|
"loss": 5.6116,
|
|
"mean_token_accuracy": 0.17873996049165725,
|
|
"num_tokens": 8470241.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.745785713195801,
|
|
"epoch": 0.4262368731397765,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004988824066460341,
|
|
"loss": 5.6353,
|
|
"mean_token_accuracy": 0.16566867083311082,
|
|
"num_tokens": 8481438.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.791307163238526,
|
|
"epoch": 0.42679845004773403,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000498878406420253,
|
|
"loss": 5.6993,
|
|
"mean_token_accuracy": 0.16865878105163573,
|
|
"num_tokens": 8492588.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.663080310821533,
|
|
"epoch": 0.4273600269556916,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004988743990660967,
|
|
"loss": 5.6246,
|
|
"mean_token_accuracy": 0.17759007811546326,
|
|
"num_tokens": 8502298.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.645330810546875,
|
|
"epoch": 0.42792160386364914,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004988703845836927,
|
|
"loss": 5.46,
|
|
"mean_token_accuracy": 0.1789509564638138,
|
|
"num_tokens": 8513507.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.767054462432862,
|
|
"epoch": 0.4284831807716067,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004988663629731687,
|
|
"loss": 5.5565,
|
|
"mean_token_accuracy": 0.18155122995376588,
|
|
"num_tokens": 8523888.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.657794332504272,
|
|
"epoch": 0.42904475767956424,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000498862334234653,
|
|
"loss": 5.5043,
|
|
"mean_token_accuracy": 0.1860446438193321,
|
|
"num_tokens": 8534032.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.664388275146484,
|
|
"epoch": 0.4296063345875218,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004988582983682737,
|
|
"loss": 5.6528,
|
|
"mean_token_accuracy": 0.17626046091318132,
|
|
"num_tokens": 8545544.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.736386108398437,
|
|
"epoch": 0.4301679114954793,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004988542553741594,
|
|
"loss": 5.6058,
|
|
"mean_token_accuracy": 0.1761350154876709,
|
|
"num_tokens": 8555428.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.627249908447266,
|
|
"epoch": 0.43072948840343683,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004988502052524388,
|
|
"loss": 5.4982,
|
|
"mean_token_accuracy": 0.18298625946044922,
|
|
"num_tokens": 8566456.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.6816253662109375,
|
|
"epoch": 0.4312910653113944,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004988461480032408,
|
|
"loss": 5.5049,
|
|
"mean_token_accuracy": 0.18162183314561844,
|
|
"num_tokens": 8578125.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.71356987953186,
|
|
"epoch": 0.43185264221935193,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004988420836266946,
|
|
"loss": 5.5837,
|
|
"mean_token_accuracy": 0.17177168726921083,
|
|
"num_tokens": 8589530.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.738637924194336,
|
|
"epoch": 0.4324142191273095,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004988380121229298,
|
|
"loss": 5.695,
|
|
"mean_token_accuracy": 0.17725915759801864,
|
|
"num_tokens": 8601655.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.653723478317261,
|
|
"epoch": 0.43297579603526704,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004988339334920757,
|
|
"loss": 5.6109,
|
|
"mean_token_accuracy": 0.17556392550468444,
|
|
"num_tokens": 8613355.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.665377569198609,
|
|
"epoch": 0.4335373729432246,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004988298477342625,
|
|
"loss": 5.5393,
|
|
"mean_token_accuracy": 0.18229811638593674,
|
|
"num_tokens": 8624154.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.6893205642700195,
|
|
"epoch": 0.43409894985118214,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00049882575484962,
|
|
"loss": 5.6251,
|
|
"mean_token_accuracy": 0.17756401896476745,
|
|
"num_tokens": 8633888.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.708053398132324,
|
|
"epoch": 0.4346605267591397,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004988216548382787,
|
|
"loss": 5.5992,
|
|
"mean_token_accuracy": 0.17779675424098967,
|
|
"num_tokens": 8644965.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.706338500976562,
|
|
"epoch": 0.4352221036670972,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004988175477003691,
|
|
"loss": 5.545,
|
|
"mean_token_accuracy": 0.183621321618557,
|
|
"num_tokens": 8655483.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.690682077407837,
|
|
"epoch": 0.43578368057505473,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000498813433436022,
|
|
"loss": 5.5178,
|
|
"mean_token_accuracy": 0.17505193054676055,
|
|
"num_tokens": 8666443.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.733745527267456,
|
|
"epoch": 0.4363452574830123,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988093120453684,
|
|
"loss": 5.5847,
|
|
"mean_token_accuracy": 0.18064320236444473,
|
|
"num_tokens": 8677198.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.660390377044678,
|
|
"epoch": 0.43690683439096983,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004988051835285394,
|
|
"loss": 5.6425,
|
|
"mean_token_accuracy": 0.17053310573101044,
|
|
"num_tokens": 8688303.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.738673543930053,
|
|
"epoch": 0.4374684112989274,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004988010478856667,
|
|
"loss": 5.6068,
|
|
"mean_token_accuracy": 0.17490874230861664,
|
|
"num_tokens": 8700326.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.606908464431763,
|
|
"epoch": 0.43802998820688493,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004987969051168816,
|
|
"loss": 5.5531,
|
|
"mean_token_accuracy": 0.18172637969255448,
|
|
"num_tokens": 8711101.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.669354200363159,
|
|
"epoch": 0.4385915651148425,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004987927552223165,
|
|
"loss": 5.6969,
|
|
"mean_token_accuracy": 0.1714338928461075,
|
|
"num_tokens": 8721751.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.812888717651367,
|
|
"epoch": 0.43915314202280004,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004987885982021032,
|
|
"loss": 5.7783,
|
|
"mean_token_accuracy": 0.16904164403676986,
|
|
"num_tokens": 8733550.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.734032821655274,
|
|
"epoch": 0.4397147189307576,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004987844340563741,
|
|
"loss": 5.5672,
|
|
"mean_token_accuracy": 0.18006644397974014,
|
|
"num_tokens": 8744218.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.663970279693603,
|
|
"epoch": 0.44027629583871514,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004987802627852619,
|
|
"loss": 5.6093,
|
|
"mean_token_accuracy": 0.1743227168917656,
|
|
"num_tokens": 8756531.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.830068778991699,
|
|
"epoch": 0.44083787274667263,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004987760843888992,
|
|
"loss": 5.6509,
|
|
"mean_token_accuracy": 0.17603119611740112,
|
|
"num_tokens": 8768114.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.6779029846191404,
|
|
"epoch": 0.4413994496546302,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004987718988674193,
|
|
"loss": 5.6435,
|
|
"mean_token_accuracy": 0.17040744572877883,
|
|
"num_tokens": 8780010.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.763619709014892,
|
|
"epoch": 0.44196102656258773,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004987677062209552,
|
|
"loss": 5.6019,
|
|
"mean_token_accuracy": 0.1691674992442131,
|
|
"num_tokens": 8792183.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.758844232559204,
|
|
"epoch": 0.4425226034705453,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004987635064496407,
|
|
"loss": 5.7029,
|
|
"mean_token_accuracy": 0.16982857137918472,
|
|
"num_tokens": 8804513.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.672817754745483,
|
|
"epoch": 0.44308418037850283,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004987592995536093,
|
|
"loss": 5.5779,
|
|
"mean_token_accuracy": 0.1853375628590584,
|
|
"num_tokens": 8814918.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.673820924758911,
|
|
"epoch": 0.4436457572864604,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004987550855329951,
|
|
"loss": 5.5445,
|
|
"mean_token_accuracy": 0.17637069821357726,
|
|
"num_tokens": 8826176.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.61413893699646,
|
|
"epoch": 0.44420733419441794,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004987508643879322,
|
|
"loss": 5.5677,
|
|
"mean_token_accuracy": 0.17783082276582718,
|
|
"num_tokens": 8837242.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.780583095550537,
|
|
"epoch": 0.4447689111023755,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004987466361185549,
|
|
"loss": 5.5419,
|
|
"mean_token_accuracy": 0.1803451105952263,
|
|
"num_tokens": 8848972.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.590166616439819,
|
|
"epoch": 0.44533048801033304,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004987424007249979,
|
|
"loss": 5.5183,
|
|
"mean_token_accuracy": 0.17309907227754592,
|
|
"num_tokens": 8861108.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.674707412719727,
|
|
"epoch": 0.4458920649182906,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004987381582073962,
|
|
"loss": 5.629,
|
|
"mean_token_accuracy": 0.17385578751564026,
|
|
"num_tokens": 8872161.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.906851768493652,
|
|
"epoch": 0.4464536418262481,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004987339085658848,
|
|
"loss": 5.6923,
|
|
"mean_token_accuracy": 0.17808567732572556,
|
|
"num_tokens": 8882497.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.525469541549683,
|
|
"epoch": 0.44701521873420563,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004987296518005988,
|
|
"loss": 5.4302,
|
|
"mean_token_accuracy": 0.18390298187732695,
|
|
"num_tokens": 8893155.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.612870502471924,
|
|
"epoch": 0.4475767956421632,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000498725387911674,
|
|
"loss": 5.5021,
|
|
"mean_token_accuracy": 0.18402701914310454,
|
|
"num_tokens": 8904478.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.669520568847656,
|
|
"epoch": 0.44813837255012073,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004987211168992461,
|
|
"loss": 5.6115,
|
|
"mean_token_accuracy": 0.17307900935411452,
|
|
"num_tokens": 8915470.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.748878002166748,
|
|
"epoch": 0.4486999494580783,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000498716838763451,
|
|
"loss": 5.5531,
|
|
"mean_token_accuracy": 0.17950351685285568,
|
|
"num_tokens": 8925644.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.708513021469116,
|
|
"epoch": 0.44926152636603583,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000498712553504425,
|
|
"loss": 5.5843,
|
|
"mean_token_accuracy": 0.17659425139427185,
|
|
"num_tokens": 8937000.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.657143020629883,
|
|
"epoch": 0.4498231032739934,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004987082611223046,
|
|
"loss": 5.5782,
|
|
"mean_token_accuracy": 0.1724244773387909,
|
|
"num_tokens": 8948258.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.712979650497436,
|
|
"epoch": 0.45038468018195094,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004987039616172265,
|
|
"loss": 5.5817,
|
|
"mean_token_accuracy": 0.1748627707362175,
|
|
"num_tokens": 8960107.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.744423294067383,
|
|
"epoch": 0.4509462570899085,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004986996549893273,
|
|
"loss": 5.5799,
|
|
"mean_token_accuracy": 0.1767027959227562,
|
|
"num_tokens": 8969612.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.763703680038452,
|
|
"epoch": 0.451507833997866,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004986953412387445,
|
|
"loss": 5.6786,
|
|
"mean_token_accuracy": 0.17461298555135726,
|
|
"num_tokens": 8980970.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.721253871917725,
|
|
"epoch": 0.45206941090582353,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004986910203656151,
|
|
"loss": 5.6045,
|
|
"mean_token_accuracy": 0.1786344677209854,
|
|
"num_tokens": 8992218.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.594237995147705,
|
|
"epoch": 0.4526309878137811,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004986866923700769,
|
|
"loss": 5.5428,
|
|
"mean_token_accuracy": 0.17788070887327195,
|
|
"num_tokens": 9003737.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.679529619216919,
|
|
"epoch": 0.45319256472173863,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004986823572522677,
|
|
"loss": 5.6029,
|
|
"mean_token_accuracy": 0.17558735609054565,
|
|
"num_tokens": 9015427.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.717615461349487,
|
|
"epoch": 0.4537541416296962,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004986780150123254,
|
|
"loss": 5.6126,
|
|
"mean_token_accuracy": 0.1770196735858917,
|
|
"num_tokens": 9025003.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.649677562713623,
|
|
"epoch": 0.45431571853765373,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004986736656503885,
|
|
"loss": 5.5617,
|
|
"mean_token_accuracy": 0.17711025327444077,
|
|
"num_tokens": 9036074.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.8062300205230715,
|
|
"epoch": 0.4548772954456113,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004986693091665952,
|
|
"loss": 5.5675,
|
|
"mean_token_accuracy": 0.17667278349399568,
|
|
"num_tokens": 9046878.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.71130142211914,
|
|
"epoch": 0.45543887235356884,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004986649455610845,
|
|
"loss": 5.622,
|
|
"mean_token_accuracy": 0.17998187839984894,
|
|
"num_tokens": 9058366.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.726722717285156,
|
|
"epoch": 0.4560004492615264,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000498660574833995,
|
|
"loss": 5.6611,
|
|
"mean_token_accuracy": 0.17204404175281524,
|
|
"num_tokens": 9069542.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.74843020439148,
|
|
"epoch": 0.45656202616948394,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004986561969854661,
|
|
"loss": 5.8364,
|
|
"mean_token_accuracy": 0.16937779784202575,
|
|
"num_tokens": 9081219.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.757581186294556,
|
|
"epoch": 0.45712360307744143,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004986518120156373,
|
|
"loss": 5.5295,
|
|
"mean_token_accuracy": 0.18289404660463332,
|
|
"num_tokens": 9092101.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.670637702941894,
|
|
"epoch": 0.457685179985399,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000498647419924648,
|
|
"loss": 5.5692,
|
|
"mean_token_accuracy": 0.17209210842847825,
|
|
"num_tokens": 9101900.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.769422960281372,
|
|
"epoch": 0.45824675689335653,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000498643020712638,
|
|
"loss": 5.7047,
|
|
"mean_token_accuracy": 0.17082441747188568,
|
|
"num_tokens": 9114369.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.673053789138794,
|
|
"epoch": 0.4588083338013141,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004986386143797475,
|
|
"loss": 5.5125,
|
|
"mean_token_accuracy": 0.17445550709962845,
|
|
"num_tokens": 9126548.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.714936351776123,
|
|
"epoch": 0.45936991070927163,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004986342009261169,
|
|
"loss": 5.7072,
|
|
"mean_token_accuracy": 0.17885012328624725,
|
|
"num_tokens": 9138070.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.760405254364014,
|
|
"epoch": 0.4599314876172292,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004986297803518865,
|
|
"loss": 5.6077,
|
|
"mean_token_accuracy": 0.1735104128718376,
|
|
"num_tokens": 9149489.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.67493782043457,
|
|
"epoch": 0.46049306452518673,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004986253526571971,
|
|
"loss": 5.5924,
|
|
"mean_token_accuracy": 0.18236540853977204,
|
|
"num_tokens": 9160363.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.7304445743560795,
|
|
"epoch": 0.4610546414331443,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004986209178421899,
|
|
"loss": 5.6528,
|
|
"mean_token_accuracy": 0.1718761533498764,
|
|
"num_tokens": 9171619.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.67438383102417,
|
|
"epoch": 0.46161621834110184,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000498616475907006,
|
|
"loss": 5.5035,
|
|
"mean_token_accuracy": 0.17841653674840927,
|
|
"num_tokens": 9182828.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.775537061691284,
|
|
"epoch": 0.46217779524905933,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004986120268517865,
|
|
"loss": 5.6635,
|
|
"mean_token_accuracy": 0.18059315979480745,
|
|
"num_tokens": 9195249.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.564350366592407,
|
|
"epoch": 0.4627393721570169,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004986075706766736,
|
|
"loss": 5.4649,
|
|
"mean_token_accuracy": 0.1827670380473137,
|
|
"num_tokens": 9205770.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.616291856765747,
|
|
"epoch": 0.46330094906497443,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004986031073818088,
|
|
"loss": 5.4841,
|
|
"mean_token_accuracy": 0.18152681291103362,
|
|
"num_tokens": 9216367.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.703184652328491,
|
|
"epoch": 0.463862525972932,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004985986369673343,
|
|
"loss": 5.5842,
|
|
"mean_token_accuracy": 0.17080659717321395,
|
|
"num_tokens": 9228524.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.67804183959961,
|
|
"epoch": 0.46442410288088953,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004985941594333926,
|
|
"loss": 5.5459,
|
|
"mean_token_accuracy": 0.18683858066797257,
|
|
"num_tokens": 9238907.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.7259095191955565,
|
|
"epoch": 0.4649856797888471,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000498589674780126,
|
|
"loss": 5.6864,
|
|
"mean_token_accuracy": 0.17780255675315856,
|
|
"num_tokens": 9250491.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.699339294433594,
|
|
"epoch": 0.46554725669680463,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004985851830076775,
|
|
"loss": 5.4742,
|
|
"mean_token_accuracy": 0.18620740622282028,
|
|
"num_tokens": 9260984.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.7042759418487545,
|
|
"epoch": 0.4661088336047622,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004985806841161901,
|
|
"loss": 5.6436,
|
|
"mean_token_accuracy": 0.1757622852921486,
|
|
"num_tokens": 9272416.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.714568996429444,
|
|
"epoch": 0.46667041051271974,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000498576178105807,
|
|
"loss": 5.6256,
|
|
"mean_token_accuracy": 0.17754258066415787,
|
|
"num_tokens": 9284513.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.716816473007202,
|
|
"epoch": 0.4672319874206773,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004985716649766717,
|
|
"loss": 5.5227,
|
|
"mean_token_accuracy": 0.1860297590494156,
|
|
"num_tokens": 9293422.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.625087022781372,
|
|
"epoch": 0.4677935643286348,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004985671447289277,
|
|
"loss": 5.51,
|
|
"mean_token_accuracy": 0.1776867017149925,
|
|
"num_tokens": 9304735.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.643379878997803,
|
|
"epoch": 0.46835514123659233,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985626173627194,
|
|
"loss": 5.6197,
|
|
"mean_token_accuracy": 0.17623546570539475,
|
|
"num_tokens": 9315659.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.682793521881104,
|
|
"epoch": 0.4689167181445499,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004985580828781904,
|
|
"loss": 5.6363,
|
|
"mean_token_accuracy": 0.17618870884180068,
|
|
"num_tokens": 9327106.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.805673456192016,
|
|
"epoch": 0.46947829505250743,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004985535412754855,
|
|
"loss": 5.6816,
|
|
"mean_token_accuracy": 0.17468448281288146,
|
|
"num_tokens": 9338762.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.689402008056641,
|
|
"epoch": 0.470039871960465,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000498548992554749,
|
|
"loss": 5.5366,
|
|
"mean_token_accuracy": 0.17719955295324324,
|
|
"num_tokens": 9349495.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.751715517044067,
|
|
"epoch": 0.47060144886842253,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004985444367161259,
|
|
"loss": 5.6351,
|
|
"mean_token_accuracy": 0.1837965279817581,
|
|
"num_tokens": 9360830.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.611725521087647,
|
|
"epoch": 0.4711630257763801,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004985398737597614,
|
|
"loss": 5.5128,
|
|
"mean_token_accuracy": 0.17987315803766252,
|
|
"num_tokens": 9371668.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.692264032363892,
|
|
"epoch": 0.47172460268433763,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004985353036858004,
|
|
"loss": 5.6528,
|
|
"mean_token_accuracy": 0.17369603365659714,
|
|
"num_tokens": 9383437.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.6641716957092285,
|
|
"epoch": 0.4722861795922952,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004985307264943887,
|
|
"loss": 5.4732,
|
|
"mean_token_accuracy": 0.18241805881261824,
|
|
"num_tokens": 9394597.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.5171393871307375,
|
|
"epoch": 0.47284775650025274,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004985261421856721,
|
|
"loss": 5.4037,
|
|
"mean_token_accuracy": 0.18648850917816162,
|
|
"num_tokens": 9404322.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.739780330657959,
|
|
"epoch": 0.47340933340821023,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004985215507597963,
|
|
"loss": 5.7738,
|
|
"mean_token_accuracy": 0.16741739362478256,
|
|
"num_tokens": 9416740.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.774796772003174,
|
|
"epoch": 0.4739709103161678,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004985169522169076,
|
|
"loss": 5.5869,
|
|
"mean_token_accuracy": 0.1814936414361,
|
|
"num_tokens": 9428617.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.589036846160889,
|
|
"epoch": 0.47453248722412533,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004985123465571526,
|
|
"loss": 5.5365,
|
|
"mean_token_accuracy": 0.18152604401111602,
|
|
"num_tokens": 9439686.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.66499891281128,
|
|
"epoch": 0.4750940641320829,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004985077337806777,
|
|
"loss": 5.5205,
|
|
"mean_token_accuracy": 0.18545324802398683,
|
|
"num_tokens": 9450378.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.71506986618042,
|
|
"epoch": 0.47565564104004043,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004985031138876299,
|
|
"loss": 5.5493,
|
|
"mean_token_accuracy": 0.17825888246297836,
|
|
"num_tokens": 9461659.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.6576087474823,
|
|
"epoch": 0.476217217947998,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004984984868781563,
|
|
"loss": 5.5898,
|
|
"mean_token_accuracy": 0.18185754865407944,
|
|
"num_tokens": 9472528.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.703695344924927,
|
|
"epoch": 0.47677879485595553,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004984938527524041,
|
|
"loss": 5.5287,
|
|
"mean_token_accuracy": 0.1899208128452301,
|
|
"num_tokens": 9483388.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.507798099517823,
|
|
"epoch": 0.4773403717639131,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000498489211510521,
|
|
"loss": 5.3892,
|
|
"mean_token_accuracy": 0.1911943331360817,
|
|
"num_tokens": 9495178.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.614229679107666,
|
|
"epoch": 0.47790194867187064,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004984845631526547,
|
|
"loss": 5.6046,
|
|
"mean_token_accuracy": 0.1775161936879158,
|
|
"num_tokens": 9506226.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.740632104873657,
|
|
"epoch": 0.47846352557982813,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004984799076789534,
|
|
"loss": 5.5104,
|
|
"mean_token_accuracy": 0.17976359128952027,
|
|
"num_tokens": 9517671.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.634478282928467,
|
|
"epoch": 0.4790251024877857,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004984752450895649,
|
|
"loss": 5.5976,
|
|
"mean_token_accuracy": 0.18178414106369017,
|
|
"num_tokens": 9527637.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.764854478836059,
|
|
"epoch": 0.47958667939574323,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000498470575384638,
|
|
"loss": 5.6761,
|
|
"mean_token_accuracy": 0.17296643704175949,
|
|
"num_tokens": 9539686.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.710594987869262,
|
|
"epoch": 0.4801482563037008,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004984658985643214,
|
|
"loss": 5.6446,
|
|
"mean_token_accuracy": 0.18062152415513993,
|
|
"num_tokens": 9550775.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.712454986572266,
|
|
"epoch": 0.48070983321165833,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004984612146287638,
|
|
"loss": 5.5456,
|
|
"mean_token_accuracy": 0.17569558173418046,
|
|
"num_tokens": 9561760.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.592285585403443,
|
|
"epoch": 0.4812714101196159,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004984565235781147,
|
|
"loss": 5.5841,
|
|
"mean_token_accuracy": 0.17345283627510072,
|
|
"num_tokens": 9573899.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.622520446777344,
|
|
"epoch": 0.48183298702757343,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000498451825412523,
|
|
"loss": 5.5414,
|
|
"mean_token_accuracy": 0.17724068611860275,
|
|
"num_tokens": 9584336.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.816002225875854,
|
|
"epoch": 0.482394563935531,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004984471201321386,
|
|
"loss": 5.733,
|
|
"mean_token_accuracy": 0.17272676825523375,
|
|
"num_tokens": 9596614.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.745497703552246,
|
|
"epoch": 0.48295614084348854,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004984424077371112,
|
|
"loss": 5.5683,
|
|
"mean_token_accuracy": 0.1837946966290474,
|
|
"num_tokens": 9606796.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.686303329467774,
|
|
"epoch": 0.4835177177514461,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004984376882275909,
|
|
"loss": 5.5547,
|
|
"mean_token_accuracy": 0.1825352668762207,
|
|
"num_tokens": 9617705.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.594384860992432,
|
|
"epoch": 0.4840792946594036,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004984329616037279,
|
|
"loss": 5.5749,
|
|
"mean_token_accuracy": 0.18000427335500718,
|
|
"num_tokens": 9628098.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.730225658416748,
|
|
"epoch": 0.48464087156736113,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004984282278656727,
|
|
"loss": 5.5117,
|
|
"mean_token_accuracy": 0.18523356467485427,
|
|
"num_tokens": 9637697.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.626879787445068,
|
|
"epoch": 0.4852024484753187,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984234870135762,
|
|
"loss": 5.4198,
|
|
"mean_token_accuracy": 0.18843667954206467,
|
|
"num_tokens": 9648221.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.726041078567505,
|
|
"epoch": 0.48576402538327623,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004984187390475891,
|
|
"loss": 5.6037,
|
|
"mean_token_accuracy": 0.17221028804779054,
|
|
"num_tokens": 9660182.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.653705310821533,
|
|
"epoch": 0.4863256022912338,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004984139839678628,
|
|
"loss": 5.6154,
|
|
"mean_token_accuracy": 0.1761000081896782,
|
|
"num_tokens": 9672121.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.697546911239624,
|
|
"epoch": 0.48688717919919133,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004984092217745486,
|
|
"loss": 5.5036,
|
|
"mean_token_accuracy": 0.18291919976472854,
|
|
"num_tokens": 9682651.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.700353384017944,
|
|
"epoch": 0.4874487561071489,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004984044524677981,
|
|
"loss": 5.6686,
|
|
"mean_token_accuracy": 0.17320136576890946,
|
|
"num_tokens": 9693989.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.607551622390747,
|
|
"epoch": 0.48801033301510643,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004983996760477632,
|
|
"loss": 5.5109,
|
|
"mean_token_accuracy": 0.18393711745738983,
|
|
"num_tokens": 9703802.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.662387704849243,
|
|
"epoch": 0.488571909923064,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000498394892514596,
|
|
"loss": 5.461,
|
|
"mean_token_accuracy": 0.18972480595111846,
|
|
"num_tokens": 9714287.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.616183423995972,
|
|
"epoch": 0.48913348683102154,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004983901018684486,
|
|
"loss": 5.4953,
|
|
"mean_token_accuracy": 0.18152210414409636,
|
|
"num_tokens": 9724819.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.637750244140625,
|
|
"epoch": 0.48969506373897903,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004983853041094739,
|
|
"loss": 5.6436,
|
|
"mean_token_accuracy": 0.1711961507797241,
|
|
"num_tokens": 9736326.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.772123241424561,
|
|
"epoch": 0.4902566406469366,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004983804992378243,
|
|
"loss": 5.665,
|
|
"mean_token_accuracy": 0.17694464474916458,
|
|
"num_tokens": 9747883.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.6365245342254635,
|
|
"epoch": 0.49081821755489413,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004983756872536532,
|
|
"loss": 5.5193,
|
|
"mean_token_accuracy": 0.18201339542865752,
|
|
"num_tokens": 9758191.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.715147972106934,
|
|
"epoch": 0.4913797944628517,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004983708681571134,
|
|
"loss": 5.617,
|
|
"mean_token_accuracy": 0.17647611498832702,
|
|
"num_tokens": 9768852.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.734269666671753,
|
|
"epoch": 0.49194137137080923,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004983660419483586,
|
|
"loss": 5.5551,
|
|
"mean_token_accuracy": 0.17609058320522308,
|
|
"num_tokens": 9779033.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.6143005847930905,
|
|
"epoch": 0.4925029482787668,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004983612086275424,
|
|
"loss": 5.4827,
|
|
"mean_token_accuracy": 0.18476453572511672,
|
|
"num_tokens": 9790777.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.769971466064453,
|
|
"epoch": 0.49306452518672433,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004983563681948187,
|
|
"loss": 5.7418,
|
|
"mean_token_accuracy": 0.16620710790157317,
|
|
"num_tokens": 9802305.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.711023330688477,
|
|
"epoch": 0.4936261020946819,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004983515206503416,
|
|
"loss": 5.5426,
|
|
"mean_token_accuracy": 0.17464770376682281,
|
|
"num_tokens": 9813590.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.67334361076355,
|
|
"epoch": 0.49418767900263944,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004983466659942655,
|
|
"loss": 5.6284,
|
|
"mean_token_accuracy": 0.17277866154909133,
|
|
"num_tokens": 9824080.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.697000885009766,
|
|
"epoch": 0.49474925591059693,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004983418042267449,
|
|
"loss": 5.5046,
|
|
"mean_token_accuracy": 0.176873978972435,
|
|
"num_tokens": 9835441.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.627409172058106,
|
|
"epoch": 0.4953108328185545,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004983369353479345,
|
|
"loss": 5.4943,
|
|
"mean_token_accuracy": 0.1827621951699257,
|
|
"num_tokens": 9846750.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.710919618606567,
|
|
"epoch": 0.49587240972651203,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004983320593579895,
|
|
"loss": 5.651,
|
|
"mean_token_accuracy": 0.17651382833719254,
|
|
"num_tokens": 9857987.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.680669784545898,
|
|
"epoch": 0.4964339866344696,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004983271762570653,
|
|
"loss": 5.6017,
|
|
"mean_token_accuracy": 0.17698585242033005,
|
|
"num_tokens": 9869736.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.753222894668579,
|
|
"epoch": 0.49699556354242713,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000498322286045317,
|
|
"loss": 5.5771,
|
|
"mean_token_accuracy": 0.17493117451667786,
|
|
"num_tokens": 9881610.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.647378921508789,
|
|
"epoch": 0.4975571404503847,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004983173887229006,
|
|
"loss": 5.5623,
|
|
"mean_token_accuracy": 0.1751056432723999,
|
|
"num_tokens": 9893203.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.6928294658660885,
|
|
"epoch": 0.49811871735834223,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004983124842899719,
|
|
"loss": 5.4897,
|
|
"mean_token_accuracy": 0.17579762488603592,
|
|
"num_tokens": 9904392.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.519991159439087,
|
|
"epoch": 0.4986802942662998,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004983075727466871,
|
|
"loss": 5.4734,
|
|
"mean_token_accuracy": 0.18386689871549605,
|
|
"num_tokens": 9916184.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.664324522018433,
|
|
"epoch": 0.49924187117425733,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004983026540932026,
|
|
"loss": 5.5901,
|
|
"mean_token_accuracy": 0.18246736973524094,
|
|
"num_tokens": 9927516.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.741987419128418,
|
|
"epoch": 0.4998034480822149,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004982977283296749,
|
|
"loss": 5.6074,
|
|
"mean_token_accuracy": 0.17554258108139037,
|
|
"num_tokens": 9939182.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.743662643432617,
|
|
"epoch": 0.5003650249901724,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000498292795456261,
|
|
"loss": 5.6361,
|
|
"mean_token_accuracy": 0.174177448451519,
|
|
"num_tokens": 9950382.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.707113122940063,
|
|
"epoch": 0.50092660189813,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004982878554731178,
|
|
"loss": 5.6283,
|
|
"mean_token_accuracy": 0.18307442367076873,
|
|
"num_tokens": 9961053.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.644644641876221,
|
|
"epoch": 0.5014881788060875,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004982829083804028,
|
|
"loss": 5.5112,
|
|
"mean_token_accuracy": 0.18234430849552155,
|
|
"num_tokens": 9971313.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.635139608383179,
|
|
"epoch": 0.5020497557140451,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004982779541782733,
|
|
"loss": 5.5398,
|
|
"mean_token_accuracy": 0.1916440635919571,
|
|
"num_tokens": 9981257.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.640893363952637,
|
|
"epoch": 0.5026113326220026,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004982729928668872,
|
|
"loss": 5.4739,
|
|
"mean_token_accuracy": 0.17892623990774154,
|
|
"num_tokens": 9991860.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.623174571990967,
|
|
"epoch": 0.5031729095299601,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004982680244464024,
|
|
"loss": 5.5624,
|
|
"mean_token_accuracy": 0.1814965933561325,
|
|
"num_tokens": 10002320.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.754784631729126,
|
|
"epoch": 0.5037344864379176,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004982630489169771,
|
|
"loss": 5.6358,
|
|
"mean_token_accuracy": 0.17755780518054962,
|
|
"num_tokens": 10013187.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.57007794380188,
|
|
"epoch": 0.5042960633458752,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004982580662787697,
|
|
"loss": 5.3944,
|
|
"mean_token_accuracy": 0.1904952883720398,
|
|
"num_tokens": 10024268.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.692174434661865,
|
|
"epoch": 0.5048576402538327,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004982530765319389,
|
|
"loss": 5.6562,
|
|
"mean_token_accuracy": 0.17762195765972139,
|
|
"num_tokens": 10034738.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.782405185699463,
|
|
"epoch": 0.5054192171617903,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004982480796766436,
|
|
"loss": 5.6058,
|
|
"mean_token_accuracy": 0.17828063815832138,
|
|
"num_tokens": 10045666.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.604255056381225,
|
|
"epoch": 0.5059807940697478,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004982430757130429,
|
|
"loss": 5.4812,
|
|
"mean_token_accuracy": 0.1805545598268509,
|
|
"num_tokens": 10057084.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.627578830718994,
|
|
"epoch": 0.5065423709777054,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004982380646412959,
|
|
"loss": 5.4564,
|
|
"mean_token_accuracy": 0.1791461542248726,
|
|
"num_tokens": 10066754.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.571236085891724,
|
|
"epoch": 0.5071039478856629,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004982330464615625,
|
|
"loss": 5.4565,
|
|
"mean_token_accuracy": 0.18998907655477523,
|
|
"num_tokens": 10078139.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.666440105438232,
|
|
"epoch": 0.5076655247936205,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004982280211740023,
|
|
"loss": 5.5324,
|
|
"mean_token_accuracy": 0.1763441488146782,
|
|
"num_tokens": 10089652.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.504432582855225,
|
|
"epoch": 0.508227101701578,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004982229887787753,
|
|
"loss": 5.3525,
|
|
"mean_token_accuracy": 0.19223741292953492,
|
|
"num_tokens": 10100642.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.644719839096069,
|
|
"epoch": 0.5087886786095356,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004982179492760418,
|
|
"loss": 5.5838,
|
|
"mean_token_accuracy": 0.17960658222436904,
|
|
"num_tokens": 10112036.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.624582052230835,
|
|
"epoch": 0.5093502555174931,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004982129026659621,
|
|
"loss": 5.455,
|
|
"mean_token_accuracy": 0.1824001595377922,
|
|
"num_tokens": 10121653.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.631822824478149,
|
|
"epoch": 0.5099118324254507,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004982078489486972,
|
|
"loss": 5.5637,
|
|
"mean_token_accuracy": 0.17775342911481856,
|
|
"num_tokens": 10132271.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.5466217517852785,
|
|
"epoch": 0.5104734093334082,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004982027881244076,
|
|
"loss": 5.4496,
|
|
"mean_token_accuracy": 0.18065108060836793,
|
|
"num_tokens": 10143411.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.7046802043914795,
|
|
"epoch": 0.5110349862413658,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004981977201932549,
|
|
"loss": 5.555,
|
|
"mean_token_accuracy": 0.18349169492721557,
|
|
"num_tokens": 10154338.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.668397617340088,
|
|
"epoch": 0.5115965631493233,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004981926451554001,
|
|
"loss": 5.5849,
|
|
"mean_token_accuracy": 0.18315830826759338,
|
|
"num_tokens": 10164810.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.639742231369018,
|
|
"epoch": 0.5121581400572809,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004981875630110048,
|
|
"loss": 5.5051,
|
|
"mean_token_accuracy": 0.18220127522945403,
|
|
"num_tokens": 10176323.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.642209482192993,
|
|
"epoch": 0.5127197169652384,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004981824737602311,
|
|
"loss": 5.5208,
|
|
"mean_token_accuracy": 0.18486607670783997,
|
|
"num_tokens": 10187110.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.612886762619018,
|
|
"epoch": 0.513281293873196,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004981773774032409,
|
|
"loss": 5.5083,
|
|
"mean_token_accuracy": 0.17804306149482726,
|
|
"num_tokens": 10199099.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.686509990692139,
|
|
"epoch": 0.5138428707811534,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004981722739401962,
|
|
"loss": 5.486,
|
|
"mean_token_accuracy": 0.18251441270112992,
|
|
"num_tokens": 10209726.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.702648544311524,
|
|
"epoch": 0.514404447689111,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00049816716337126,
|
|
"loss": 5.5922,
|
|
"mean_token_accuracy": 0.17905279695987703,
|
|
"num_tokens": 10220858.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.518071508407592,
|
|
"epoch": 0.5149660245970685,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004981620456965946,
|
|
"loss": 5.413,
|
|
"mean_token_accuracy": 0.18944605588912963,
|
|
"num_tokens": 10232250.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.725042724609375,
|
|
"epoch": 0.5155276015050261,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004981569209163633,
|
|
"loss": 5.609,
|
|
"mean_token_accuracy": 0.17123129218816757,
|
|
"num_tokens": 10244584.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.716646003723144,
|
|
"epoch": 0.5160891784129836,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004981517890307288,
|
|
"loss": 5.481,
|
|
"mean_token_accuracy": 0.1807915136218071,
|
|
"num_tokens": 10255926.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.665557146072388,
|
|
"epoch": 0.5166507553209412,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498146650039855,
|
|
"loss": 5.5723,
|
|
"mean_token_accuracy": 0.18312949687242508,
|
|
"num_tokens": 10266691.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.692429542541504,
|
|
"epoch": 0.5172123322288987,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004981415039439054,
|
|
"loss": 5.6224,
|
|
"mean_token_accuracy": 0.18030687123537065,
|
|
"num_tokens": 10277744.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.600763511657715,
|
|
"epoch": 0.5177739091368563,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004981363507430436,
|
|
"loss": 5.4703,
|
|
"mean_token_accuracy": 0.18670175075531006,
|
|
"num_tokens": 10288792.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.703523778915406,
|
|
"epoch": 0.5183354860448138,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004981311904374339,
|
|
"loss": 5.5218,
|
|
"mean_token_accuracy": 0.18117523938417435,
|
|
"num_tokens": 10299569.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.632540655136109,
|
|
"epoch": 0.5188970629527714,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004981260230272405,
|
|
"loss": 5.4972,
|
|
"mean_token_accuracy": 0.18545956462621688,
|
|
"num_tokens": 10309742.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.680473136901855,
|
|
"epoch": 0.5194586398607289,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004981208485126281,
|
|
"loss": 5.5506,
|
|
"mean_token_accuracy": 0.17689417153596879,
|
|
"num_tokens": 10320603.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.607299709320069,
|
|
"epoch": 0.5200202167686865,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004981156668937613,
|
|
"loss": 5.5088,
|
|
"mean_token_accuracy": 0.18380599915981294,
|
|
"num_tokens": 10331498.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.677219200134277,
|
|
"epoch": 0.520581793676644,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004981104781708051,
|
|
"loss": 5.5408,
|
|
"mean_token_accuracy": 0.18248181641101838,
|
|
"num_tokens": 10342002.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.6430576801300045,
|
|
"epoch": 0.5211433705846016,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004981052823439247,
|
|
"loss": 5.4927,
|
|
"mean_token_accuracy": 0.18074288517236708,
|
|
"num_tokens": 10351797.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.580838346481324,
|
|
"epoch": 0.5217049474925591,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004981000794132858,
|
|
"loss": 5.4331,
|
|
"mean_token_accuracy": 0.1847847133874893,
|
|
"num_tokens": 10362538.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.600670051574707,
|
|
"epoch": 0.5222665244005167,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004980948693790536,
|
|
"loss": 5.4477,
|
|
"mean_token_accuracy": 0.18671983033418654,
|
|
"num_tokens": 10373365.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.558433389663696,
|
|
"epoch": 0.5228281013084742,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004980896522413943,
|
|
"loss": 5.454,
|
|
"mean_token_accuracy": 0.18048152774572374,
|
|
"num_tokens": 10385087.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.618748950958252,
|
|
"epoch": 0.5233896782164318,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004980844280004739,
|
|
"loss": 5.5731,
|
|
"mean_token_accuracy": 0.17731207013130187,
|
|
"num_tokens": 10396014.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.579803514480591,
|
|
"epoch": 0.5239512551243893,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004980791966564589,
|
|
"loss": 5.4968,
|
|
"mean_token_accuracy": 0.18150824904441834,
|
|
"num_tokens": 10407844.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.580438184738159,
|
|
"epoch": 0.5245128320323468,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004980739582095158,
|
|
"loss": 5.5668,
|
|
"mean_token_accuracy": 0.17426397800445556,
|
|
"num_tokens": 10419892.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.690279579162597,
|
|
"epoch": 0.5250744089403043,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004980687126598111,
|
|
"loss": 5.527,
|
|
"mean_token_accuracy": 0.1738398015499115,
|
|
"num_tokens": 10430686.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.643109941482544,
|
|
"epoch": 0.5256359858482619,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004980634600075123,
|
|
"loss": 5.5599,
|
|
"mean_token_accuracy": 0.17802226841449736,
|
|
"num_tokens": 10443785.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.587534379959107,
|
|
"epoch": 0.5261975627562194,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004980582002527863,
|
|
"loss": 5.4399,
|
|
"mean_token_accuracy": 0.1904889687895775,
|
|
"num_tokens": 10454889.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.597082805633545,
|
|
"epoch": 0.526759139664177,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004980529333958008,
|
|
"loss": 5.6024,
|
|
"mean_token_accuracy": 0.1754663571715355,
|
|
"num_tokens": 10466525.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.722401237487793,
|
|
"epoch": 0.5273207165721345,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004980476594367233,
|
|
"loss": 5.5465,
|
|
"mean_token_accuracy": 0.18529189825057985,
|
|
"num_tokens": 10476329.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.748387002944947,
|
|
"epoch": 0.5278822934800921,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004980423783757219,
|
|
"loss": 5.6097,
|
|
"mean_token_accuracy": 0.17898427844047546,
|
|
"num_tokens": 10487178.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.644168710708618,
|
|
"epoch": 0.5284438703880496,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004980370902129646,
|
|
"loss": 5.5554,
|
|
"mean_token_accuracy": 0.1712798923254013,
|
|
"num_tokens": 10499293.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.768489265441895,
|
|
"epoch": 0.5290054472960072,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00049803179494862,
|
|
"loss": 5.7316,
|
|
"mean_token_accuracy": 0.16541629433631896,
|
|
"num_tokens": 10511762.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.667138910293579,
|
|
"epoch": 0.5295670242039647,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004980264925828563,
|
|
"loss": 5.4547,
|
|
"mean_token_accuracy": 0.19035084992647172,
|
|
"num_tokens": 10521725.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.569765329360962,
|
|
"epoch": 0.5301286011119223,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004980211831158427,
|
|
"loss": 5.4007,
|
|
"mean_token_accuracy": 0.18478177189826966,
|
|
"num_tokens": 10531764.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.67407488822937,
|
|
"epoch": 0.5306901780198798,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004980158665477481,
|
|
"loss": 5.4897,
|
|
"mean_token_accuracy": 0.18613315969705582,
|
|
"num_tokens": 10542127.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.706964445114136,
|
|
"epoch": 0.5312517549278374,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004980105428787419,
|
|
"loss": 5.5833,
|
|
"mean_token_accuracy": 0.1766618549823761,
|
|
"num_tokens": 10552580.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.628377914428711,
|
|
"epoch": 0.5318133318357949,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004980052121089934,
|
|
"loss": 5.5111,
|
|
"mean_token_accuracy": 0.1801474079489708,
|
|
"num_tokens": 10562961.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.730417633056641,
|
|
"epoch": 0.5323749087437525,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004979998742386725,
|
|
"loss": 5.5057,
|
|
"mean_token_accuracy": 0.18176156133413315,
|
|
"num_tokens": 10573210.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.521605539321899,
|
|
"epoch": 0.53293648565171,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004979945292679492,
|
|
"loss": 5.4754,
|
|
"mean_token_accuracy": 0.17918767482042314,
|
|
"num_tokens": 10583878.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.64623875617981,
|
|
"epoch": 0.5334980625596676,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004979891771969935,
|
|
"loss": 5.5537,
|
|
"mean_token_accuracy": 0.17740156054496764,
|
|
"num_tokens": 10593420.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.704613780975341,
|
|
"epoch": 0.5340596394676251,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000497983818025976,
|
|
"loss": 5.5753,
|
|
"mean_token_accuracy": 0.1787201002240181,
|
|
"num_tokens": 10604213.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.696094036102295,
|
|
"epoch": 0.5346212163755827,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004979784517550671,
|
|
"loss": 5.5457,
|
|
"mean_token_accuracy": 0.1722053959965706,
|
|
"num_tokens": 10615502.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.6494340896606445,
|
|
"epoch": 0.5351827932835401,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004979730783844379,
|
|
"loss": 5.6009,
|
|
"mean_token_accuracy": 0.17084263116121293,
|
|
"num_tokens": 10627589.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.5736168384552,
|
|
"epoch": 0.5357443701914977,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004979676979142595,
|
|
"loss": 5.4282,
|
|
"mean_token_accuracy": 0.18405757546424867,
|
|
"num_tokens": 10638365.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.637544584274292,
|
|
"epoch": 0.5363059470994552,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000497962310344703,
|
|
"loss": 5.5334,
|
|
"mean_token_accuracy": 0.18157838881015778,
|
|
"num_tokens": 10650664.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.681172561645508,
|
|
"epoch": 0.5368675240074128,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00049795691567594,
|
|
"loss": 5.5893,
|
|
"mean_token_accuracy": 0.18533241599798203,
|
|
"num_tokens": 10662418.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.627472829818726,
|
|
"epoch": 0.5374291009153703,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004979515139081426,
|
|
"loss": 5.4668,
|
|
"mean_token_accuracy": 0.184379480779171,
|
|
"num_tokens": 10672793.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.5839722633361815,
|
|
"epoch": 0.5379906778233279,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004979461050414822,
|
|
"loss": 5.5119,
|
|
"mean_token_accuracy": 0.1882890358567238,
|
|
"num_tokens": 10684082.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.492992544174195,
|
|
"epoch": 0.5385522547312854,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004979406890761315,
|
|
"loss": 5.4543,
|
|
"mean_token_accuracy": 0.1841624855995178,
|
|
"num_tokens": 10694490.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.63221583366394,
|
|
"epoch": 0.539113831639243,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004979352660122629,
|
|
"loss": 5.4588,
|
|
"mean_token_accuracy": 0.18302005976438523,
|
|
"num_tokens": 10704731.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.611063766479492,
|
|
"epoch": 0.5396754085472005,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004979298358500488,
|
|
"loss": 5.4887,
|
|
"mean_token_accuracy": 0.18789714425802231,
|
|
"num_tokens": 10715735.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.545275735855102,
|
|
"epoch": 0.5402369854551581,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004979243985896624,
|
|
"loss": 5.4553,
|
|
"mean_token_accuracy": 0.1809619754552841,
|
|
"num_tokens": 10726951.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.602046537399292,
|
|
"epoch": 0.5407985623631156,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004979189542312765,
|
|
"loss": 5.5138,
|
|
"mean_token_accuracy": 0.17767608910799026,
|
|
"num_tokens": 10737609.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.606081628799439,
|
|
"epoch": 0.5413601392710732,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004979135027750649,
|
|
"loss": 5.4109,
|
|
"mean_token_accuracy": 0.19260681569576263,
|
|
"num_tokens": 10748957.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.6902268409729,
|
|
"epoch": 0.5419217161790307,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004979080442212007,
|
|
"loss": 5.5907,
|
|
"mean_token_accuracy": 0.17853567153215408,
|
|
"num_tokens": 10759398.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.654111862182617,
|
|
"epoch": 0.5424832930869883,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004979025785698581,
|
|
"loss": 5.5672,
|
|
"mean_token_accuracy": 0.17787721753120422,
|
|
"num_tokens": 10770436.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.577683019638061,
|
|
"epoch": 0.5430448699949458,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004978971058212108,
|
|
"loss": 5.3983,
|
|
"mean_token_accuracy": 0.19398372024297714,
|
|
"num_tokens": 10781160.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.692035388946533,
|
|
"epoch": 0.5436064469029034,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004978916259754331,
|
|
"loss": 5.5257,
|
|
"mean_token_accuracy": 0.18834299147129058,
|
|
"num_tokens": 10793170.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.574293184280395,
|
|
"epoch": 0.5441680238108609,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004978861390326998,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.18172243386507034,
|
|
"num_tokens": 10803515.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.624358606338501,
|
|
"epoch": 0.5447296007188185,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004978806449931854,
|
|
"loss": 5.5051,
|
|
"mean_token_accuracy": 0.18323239982128142,
|
|
"num_tokens": 10814508.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.687337398529053,
|
|
"epoch": 0.545291177626776,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004978751438570647,
|
|
"loss": 5.6114,
|
|
"mean_token_accuracy": 0.17625804543495177,
|
|
"num_tokens": 10825924.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.649694776535034,
|
|
"epoch": 0.5458527545347336,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004978696356245129,
|
|
"loss": 5.5908,
|
|
"mean_token_accuracy": 0.17919801622629167,
|
|
"num_tokens": 10837854.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.60722770690918,
|
|
"epoch": 0.546414331442691,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004978641202957057,
|
|
"loss": 5.4684,
|
|
"mean_token_accuracy": 0.18659446835517884,
|
|
"num_tokens": 10848279.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.557261037826538,
|
|
"epoch": 0.5469759083506486,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004978585978708183,
|
|
"loss": 5.4864,
|
|
"mean_token_accuracy": 0.17544039487838745,
|
|
"num_tokens": 10859615.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.695983839035034,
|
|
"epoch": 0.5475374852586061,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004978530683500267,
|
|
"loss": 5.4622,
|
|
"mean_token_accuracy": 0.18064787834882737,
|
|
"num_tokens": 10871388.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.5865131378173825,
|
|
"epoch": 0.5480990621665637,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004978475317335071,
|
|
"loss": 5.5138,
|
|
"mean_token_accuracy": 0.18382047712802888,
|
|
"num_tokens": 10882411.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.63999924659729,
|
|
"epoch": 0.5486606390745212,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004978419880214356,
|
|
"loss": 5.6316,
|
|
"mean_token_accuracy": 0.18017077893018724,
|
|
"num_tokens": 10894116.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.560580778121948,
|
|
"epoch": 0.5492222159824788,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004978364372139887,
|
|
"loss": 5.41,
|
|
"mean_token_accuracy": 0.18437618613243104,
|
|
"num_tokens": 10904514.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.554110431671143,
|
|
"epoch": 0.5497837928904363,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004978308793113434,
|
|
"loss": 5.4572,
|
|
"mean_token_accuracy": 0.18201902955770494,
|
|
"num_tokens": 10915602.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.588807582855225,
|
|
"epoch": 0.5503453697983939,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004978253143136762,
|
|
"loss": 5.4407,
|
|
"mean_token_accuracy": 0.19006901681423188,
|
|
"num_tokens": 10926172.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.675413513183594,
|
|
"epoch": 0.5509069467063514,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004978197422211647,
|
|
"loss": 5.5649,
|
|
"mean_token_accuracy": 0.17791180312633514,
|
|
"num_tokens": 10938435.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.5930407524108885,
|
|
"epoch": 0.551468523614309,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004978141630339863,
|
|
"loss": 5.433,
|
|
"mean_token_accuracy": 0.18169896602630614,
|
|
"num_tokens": 10949118.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.564508962631225,
|
|
"epoch": 0.5520301005222665,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004978085767523184,
|
|
"loss": 5.4879,
|
|
"mean_token_accuracy": 0.1805576741695404,
|
|
"num_tokens": 10960120.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.629130506515503,
|
|
"epoch": 0.5525916774302241,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000497802983376339,
|
|
"loss": 5.4775,
|
|
"mean_token_accuracy": 0.18393729776144027,
|
|
"num_tokens": 10971210.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.595309782028198,
|
|
"epoch": 0.5531532543381816,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004977973829062263,
|
|
"loss": 5.4569,
|
|
"mean_token_accuracy": 0.19195475429296494,
|
|
"num_tokens": 10983446.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.653829622268677,
|
|
"epoch": 0.5537148312461392,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004977917753421585,
|
|
"loss": 5.589,
|
|
"mean_token_accuracy": 0.17618100047111512,
|
|
"num_tokens": 10994776.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.699292516708374,
|
|
"epoch": 0.5542764081540967,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000497786160684314,
|
|
"loss": 5.4901,
|
|
"mean_token_accuracy": 0.17770370990037918,
|
|
"num_tokens": 11005280.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.538117599487305,
|
|
"epoch": 0.5548379850620543,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004977805389328719,
|
|
"loss": 5.4795,
|
|
"mean_token_accuracy": 0.17729776054620744,
|
|
"num_tokens": 11017509.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.609230899810791,
|
|
"epoch": 0.5553995619700118,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000497774910088011,
|
|
"loss": 5.5081,
|
|
"mean_token_accuracy": 0.18174312859773636,
|
|
"num_tokens": 11029087.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.669476509094238,
|
|
"epoch": 0.5559611388779694,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004977692741499106,
|
|
"loss": 5.5614,
|
|
"mean_token_accuracy": 0.17520818561315538,
|
|
"num_tokens": 11041144.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.765043258666992,
|
|
"epoch": 0.5565227157859269,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00049776363111875,
|
|
"loss": 5.6188,
|
|
"mean_token_accuracy": 0.17266984283924103,
|
|
"num_tokens": 11054050.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.576721334457398,
|
|
"epoch": 0.5570842926938844,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004977579809947091,
|
|
"loss": 5.4415,
|
|
"mean_token_accuracy": 0.1856127619743347,
|
|
"num_tokens": 11064257.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.647933101654052,
|
|
"epoch": 0.5576458696018419,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004977523237779676,
|
|
"loss": 5.5591,
|
|
"mean_token_accuracy": 0.18124807327985765,
|
|
"num_tokens": 11075568.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.651572418212891,
|
|
"epoch": 0.5582074465097995,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004977466594687057,
|
|
"loss": 5.5026,
|
|
"mean_token_accuracy": 0.18101075142621995,
|
|
"num_tokens": 11087078.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.726760768890381,
|
|
"epoch": 0.558769023417757,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004977409880671039,
|
|
"loss": 5.6542,
|
|
"mean_token_accuracy": 0.1728218376636505,
|
|
"num_tokens": 11100655.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.670252847671509,
|
|
"epoch": 0.5593306003257146,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004977353095733427,
|
|
"loss": 5.5503,
|
|
"mean_token_accuracy": 0.17902832329273224,
|
|
"num_tokens": 11110675.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.616565752029419,
|
|
"epoch": 0.5598921772336721,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004977296239876026,
|
|
"loss": 5.5456,
|
|
"mean_token_accuracy": 0.18028604239225388,
|
|
"num_tokens": 11122337.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.699768733978272,
|
|
"epoch": 0.5604537541416297,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000497723931310065,
|
|
"loss": 5.4543,
|
|
"mean_token_accuracy": 0.18633654564619065,
|
|
"num_tokens": 11132672.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.606082248687744,
|
|
"epoch": 0.5610153310495872,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004977182315409111,
|
|
"loss": 5.4983,
|
|
"mean_token_accuracy": 0.18540901094675064,
|
|
"num_tokens": 11143740.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.561510276794434,
|
|
"epoch": 0.5615769079575448,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004977125246803224,
|
|
"loss": 5.4353,
|
|
"mean_token_accuracy": 0.18260809630155564,
|
|
"num_tokens": 11153722.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.659125947952271,
|
|
"epoch": 0.5621384848655023,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004977068107284803,
|
|
"loss": 5.568,
|
|
"mean_token_accuracy": 0.18011747300624847,
|
|
"num_tokens": 11165042.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.6353111743927,
|
|
"epoch": 0.5627000617734599,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004977010896855672,
|
|
"loss": 5.4419,
|
|
"mean_token_accuracy": 0.18952011615037917,
|
|
"num_tokens": 11176834.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.623426389694214,
|
|
"epoch": 0.5632616386814174,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004976953615517649,
|
|
"loss": 5.5016,
|
|
"mean_token_accuracy": 0.18498848527669906,
|
|
"num_tokens": 11188442.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.576831293106079,
|
|
"epoch": 0.563823215589375,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000497689626327256,
|
|
"loss": 5.4149,
|
|
"mean_token_accuracy": 0.19040623009204866,
|
|
"num_tokens": 11197855.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.597378063201904,
|
|
"epoch": 0.5643847924973325,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000497683884012223,
|
|
"loss": 5.5236,
|
|
"mean_token_accuracy": 0.17814671993255615,
|
|
"num_tokens": 11209300.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.604292917251587,
|
|
"epoch": 0.5649463694052901,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004976781346068487,
|
|
"loss": 5.5237,
|
|
"mean_token_accuracy": 0.17906069606542588,
|
|
"num_tokens": 11222175.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.669887399673462,
|
|
"epoch": 0.5655079463132476,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004976723781113163,
|
|
"loss": 5.5376,
|
|
"mean_token_accuracy": 0.17941499203443528,
|
|
"num_tokens": 11233277.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.647896575927734,
|
|
"epoch": 0.5660695232212052,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004976666145258089,
|
|
"loss": 5.5599,
|
|
"mean_token_accuracy": 0.18245493173599242,
|
|
"num_tokens": 11245241.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.6755060195922855,
|
|
"epoch": 0.5666311001291627,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004976608438505103,
|
|
"loss": 5.5661,
|
|
"mean_token_accuracy": 0.18422424793243408,
|
|
"num_tokens": 11257359.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.614133977890015,
|
|
"epoch": 0.5671926770371203,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004976550660856041,
|
|
"loss": 5.5163,
|
|
"mean_token_accuracy": 0.1842909574508667,
|
|
"num_tokens": 11270651.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.607726955413819,
|
|
"epoch": 0.5677542539450777,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000497649281231274,
|
|
"loss": 5.4707,
|
|
"mean_token_accuracy": 0.1895418033003807,
|
|
"num_tokens": 11280164.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.599555587768554,
|
|
"epoch": 0.5683158308530353,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004976434892877046,
|
|
"loss": 5.4141,
|
|
"mean_token_accuracy": 0.18119289427995683,
|
|
"num_tokens": 11290156.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.612470483779907,
|
|
"epoch": 0.5688774077609928,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004976376902550802,
|
|
"loss": 5.4759,
|
|
"mean_token_accuracy": 0.18851063549518585,
|
|
"num_tokens": 11301929.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.5531538963317875,
|
|
"epoch": 0.5694389846689504,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004976318841335854,
|
|
"loss": 5.3883,
|
|
"mean_token_accuracy": 0.19327545613050462,
|
|
"num_tokens": 11312805.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.456476163864136,
|
|
"epoch": 0.5700005615769079,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004976260709234049,
|
|
"loss": 5.2884,
|
|
"mean_token_accuracy": 0.18960177898406982,
|
|
"num_tokens": 11322316.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.5868700504302975,
|
|
"epoch": 0.5705621384848655,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000497620250624724,
|
|
"loss": 5.4795,
|
|
"mean_token_accuracy": 0.18839925825595855,
|
|
"num_tokens": 11332994.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.628772020339966,
|
|
"epoch": 0.571123715392823,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000497614423237728,
|
|
"loss": 5.4692,
|
|
"mean_token_accuracy": 0.17971829026937486,
|
|
"num_tokens": 11344355.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.582499217987061,
|
|
"epoch": 0.5716852923007806,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004976085887626026,
|
|
"loss": 5.5217,
|
|
"mean_token_accuracy": 0.17927353084087372,
|
|
"num_tokens": 11356275.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.596384048461914,
|
|
"epoch": 0.5722468692087381,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004976027471995331,
|
|
"loss": 5.4939,
|
|
"mean_token_accuracy": 0.18226930350065232,
|
|
"num_tokens": 11368624.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.697848796844482,
|
|
"epoch": 0.5728084461166957,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000497596898548706,
|
|
"loss": 5.6062,
|
|
"mean_token_accuracy": 0.17915936410427094,
|
|
"num_tokens": 11380520.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.58489089012146,
|
|
"epoch": 0.5733700230246532,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004975910428103072,
|
|
"loss": 5.5021,
|
|
"mean_token_accuracy": 0.18580701500177382,
|
|
"num_tokens": 11392293.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.6542316436767575,
|
|
"epoch": 0.5739315999326108,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004975851799845233,
|
|
"loss": 5.5717,
|
|
"mean_token_accuracy": 0.17740507423877716,
|
|
"num_tokens": 11403866.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.558068656921387,
|
|
"epoch": 0.5744931768405683,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000497579310071541,
|
|
"loss": 5.4008,
|
|
"mean_token_accuracy": 0.18831710666418075,
|
|
"num_tokens": 11415334.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.580965232849121,
|
|
"epoch": 0.5750547537485259,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004975734330715471,
|
|
"loss": 5.5464,
|
|
"mean_token_accuracy": 0.18406864255666733,
|
|
"num_tokens": 11426840.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.704878950119019,
|
|
"epoch": 0.5756163306564834,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004975675489847287,
|
|
"loss": 5.6915,
|
|
"mean_token_accuracy": 0.17358105182647704,
|
|
"num_tokens": 11438497.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.608832836151123,
|
|
"epoch": 0.576177907564441,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004975616578112734,
|
|
"loss": 5.4116,
|
|
"mean_token_accuracy": 0.1894557297229767,
|
|
"num_tokens": 11448705.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.725475406646728,
|
|
"epoch": 0.5767394844723985,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004975557595513684,
|
|
"loss": 5.6549,
|
|
"mean_token_accuracy": 0.17674582004547118,
|
|
"num_tokens": 11460610.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.615379667282104,
|
|
"epoch": 0.5773010613803561,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004975498542052018,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.18672376573085786,
|
|
"num_tokens": 11471170.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.5798238754272464,
|
|
"epoch": 0.5778626382883136,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004975439417729615,
|
|
"loss": 5.4144,
|
|
"mean_token_accuracy": 0.1908004879951477,
|
|
"num_tokens": 11482090.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.552998208999634,
|
|
"epoch": 0.5784242151962711,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004975380222548358,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.18054262697696685,
|
|
"num_tokens": 11493650.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.626877212524414,
|
|
"epoch": 0.5789857921042286,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004975320956510131,
|
|
"loss": 5.5028,
|
|
"mean_token_accuracy": 0.1770804211497307,
|
|
"num_tokens": 11505903.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.694047975540161,
|
|
"epoch": 0.5795473690121862,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004975261619616822,
|
|
"loss": 5.5351,
|
|
"mean_token_accuracy": 0.18056992888450624,
|
|
"num_tokens": 11517194.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.645776748657227,
|
|
"epoch": 0.5801089459201437,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004975202211870321,
|
|
"loss": 5.5483,
|
|
"mean_token_accuracy": 0.187668114900589,
|
|
"num_tokens": 11528683.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.619265031814575,
|
|
"epoch": 0.5806705228281013,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004975142733272518,
|
|
"loss": 5.5718,
|
|
"mean_token_accuracy": 0.18432468473911284,
|
|
"num_tokens": 11541940.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.582946252822876,
|
|
"epoch": 0.5812320997360588,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004975083183825306,
|
|
"loss": 5.4477,
|
|
"mean_token_accuracy": 0.18226873576641084,
|
|
"num_tokens": 11553045.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.567510271072388,
|
|
"epoch": 0.5817936766440164,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004975023563530584,
|
|
"loss": 5.4232,
|
|
"mean_token_accuracy": 0.19102198332548143,
|
|
"num_tokens": 11564401.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.590689706802368,
|
|
"epoch": 0.5823552535519739,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004974963872390249,
|
|
"loss": 5.4638,
|
|
"mean_token_accuracy": 0.1833739846944809,
|
|
"num_tokens": 11576424.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.660714054107666,
|
|
"epoch": 0.5829168304599315,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.00049749041104062,
|
|
"loss": 5.4818,
|
|
"mean_token_accuracy": 0.18013193905353547,
|
|
"num_tokens": 11587853.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.668058681488037,
|
|
"epoch": 0.583478407367889,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004974844277580343,
|
|
"loss": 5.4713,
|
|
"mean_token_accuracy": 0.18619268983602524,
|
|
"num_tokens": 11597938.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.704557037353515,
|
|
"epoch": 0.5840399842758466,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004974784373914579,
|
|
"loss": 5.6392,
|
|
"mean_token_accuracy": 0.18226669430732728,
|
|
"num_tokens": 11610077.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.579728794097901,
|
|
"epoch": 0.5846015611838041,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004974724399410818,
|
|
"loss": 5.5021,
|
|
"mean_token_accuracy": 0.18503529876470565,
|
|
"num_tokens": 11622079.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.523500871658325,
|
|
"epoch": 0.5851631380917617,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004974664354070971,
|
|
"loss": 5.417,
|
|
"mean_token_accuracy": 0.19386857897043228,
|
|
"num_tokens": 11633047.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.549732303619384,
|
|
"epoch": 0.5857247149997192,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004974604237896947,
|
|
"loss": 5.3688,
|
|
"mean_token_accuracy": 0.18848908692598343,
|
|
"num_tokens": 11643858.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.541607427597046,
|
|
"epoch": 0.5862862919076768,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004974544050890662,
|
|
"loss": 5.4053,
|
|
"mean_token_accuracy": 0.1883080154657364,
|
|
"num_tokens": 11654550.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.5493570327758786,
|
|
"epoch": 0.5868478688156343,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000497448379305403,
|
|
"loss": 5.4274,
|
|
"mean_token_accuracy": 0.18527335971593856,
|
|
"num_tokens": 11665787.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.655500841140747,
|
|
"epoch": 0.5874094457235919,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004974423464388973,
|
|
"loss": 5.5622,
|
|
"mean_token_accuracy": 0.17959532588720323,
|
|
"num_tokens": 11677717.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.619990444183349,
|
|
"epoch": 0.5879710226315494,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000497436306489741,
|
|
"loss": 5.4358,
|
|
"mean_token_accuracy": 0.18572364002466202,
|
|
"num_tokens": 11687714.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.550149869918823,
|
|
"epoch": 0.588532599539507,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004974302594581264,
|
|
"loss": 5.3355,
|
|
"mean_token_accuracy": 0.19635276347398758,
|
|
"num_tokens": 11698777.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.568590974807739,
|
|
"epoch": 0.5890941764474645,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004974242053442461,
|
|
"loss": 5.4262,
|
|
"mean_token_accuracy": 0.1932222217321396,
|
|
"num_tokens": 11710922.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.575196647644043,
|
|
"epoch": 0.589655753355422,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004974181441482927,
|
|
"loss": 5.4741,
|
|
"mean_token_accuracy": 0.18178150206804275,
|
|
"num_tokens": 11721450.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.520800971984864,
|
|
"epoch": 0.5902173302633795,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004974120758704595,
|
|
"loss": 5.3861,
|
|
"mean_token_accuracy": 0.18722872734069823,
|
|
"num_tokens": 11732458.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.522866821289062,
|
|
"epoch": 0.5907789071713371,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004974060005109394,
|
|
"loss": 5.35,
|
|
"mean_token_accuracy": 0.19123259037733079,
|
|
"num_tokens": 11742649.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.577361011505127,
|
|
"epoch": 0.5913404840792946,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000497399918069926,
|
|
"loss": 5.3894,
|
|
"mean_token_accuracy": 0.19077312350273132,
|
|
"num_tokens": 11753811.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.621190118789673,
|
|
"epoch": 0.5919020609872522,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004973938285476131,
|
|
"loss": 5.4925,
|
|
"mean_token_accuracy": 0.178723706305027,
|
|
"num_tokens": 11763965.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.614044523239135,
|
|
"epoch": 0.5924636378952097,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004973877319441943,
|
|
"loss": 5.4999,
|
|
"mean_token_accuracy": 0.18876443058252335,
|
|
"num_tokens": 11774323.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.628261756896973,
|
|
"epoch": 0.5930252148031673,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004973816282598639,
|
|
"loss": 5.4729,
|
|
"mean_token_accuracy": 0.18141622245311737,
|
|
"num_tokens": 11786157.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.611000013351441,
|
|
"epoch": 0.5935867917111248,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004973755174948162,
|
|
"loss": 5.45,
|
|
"mean_token_accuracy": 0.19105252325534822,
|
|
"num_tokens": 11797344.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.448312091827392,
|
|
"epoch": 0.5941483686190824,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004973693996492458,
|
|
"loss": 5.3984,
|
|
"mean_token_accuracy": 0.18638614416122437,
|
|
"num_tokens": 11808149.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.552359485626221,
|
|
"epoch": 0.5947099455270399,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004973632747233475,
|
|
"loss": 5.414,
|
|
"mean_token_accuracy": 0.1930566906929016,
|
|
"num_tokens": 11820203.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.617059373855591,
|
|
"epoch": 0.5952715224349975,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004973571427173163,
|
|
"loss": 5.4928,
|
|
"mean_token_accuracy": 0.18311173915863038,
|
|
"num_tokens": 11830172.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.611087846755981,
|
|
"epoch": 0.595833099342955,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004973510036313473,
|
|
"loss": 5.4504,
|
|
"mean_token_accuracy": 0.1895171508193016,
|
|
"num_tokens": 11840203.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.59495210647583,
|
|
"epoch": 0.5963946762509126,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004973448574656362,
|
|
"loss": 5.4147,
|
|
"mean_token_accuracy": 0.18466875255107879,
|
|
"num_tokens": 11851002.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.571983194351196,
|
|
"epoch": 0.5969562531588701,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004973387042203786,
|
|
"loss": 5.4066,
|
|
"mean_token_accuracy": 0.1829525947570801,
|
|
"num_tokens": 11861559.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.55874285697937,
|
|
"epoch": 0.5975178300668277,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004973325438957704,
|
|
"loss": 5.491,
|
|
"mean_token_accuracy": 0.18227005898952484,
|
|
"num_tokens": 11872535.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.640175628662109,
|
|
"epoch": 0.5980794069747852,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004973263764920079,
|
|
"loss": 5.4932,
|
|
"mean_token_accuracy": 0.18847439289093018,
|
|
"num_tokens": 11884308.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.6690717220306395,
|
|
"epoch": 0.5986409838827428,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004973202020092871,
|
|
"loss": 5.5659,
|
|
"mean_token_accuracy": 0.18065213561058044,
|
|
"num_tokens": 11896136.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.595011615753174,
|
|
"epoch": 0.5992025607907003,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000497314020447805,
|
|
"loss": 5.4011,
|
|
"mean_token_accuracy": 0.1973426029086113,
|
|
"num_tokens": 11906497.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.6279065132141115,
|
|
"epoch": 0.5997641376986579,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004973078318077583,
|
|
"loss": 5.5099,
|
|
"mean_token_accuracy": 0.1770203560590744,
|
|
"num_tokens": 11917872.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.663007164001465,
|
|
"epoch": 0.6003257146066153,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000497301636089344,
|
|
"loss": 5.5404,
|
|
"mean_token_accuracy": 0.18449182361364364,
|
|
"num_tokens": 11929727.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.631331539154052,
|
|
"epoch": 0.6008872915145729,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004972954332927592,
|
|
"loss": 5.3267,
|
|
"mean_token_accuracy": 0.18630826622247695,
|
|
"num_tokens": 11939996.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.533454132080078,
|
|
"epoch": 0.6014488684225304,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004972892234182018,
|
|
"loss": 5.4119,
|
|
"mean_token_accuracy": 0.19154259711503982,
|
|
"num_tokens": 11950683.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.5050122261047365,
|
|
"epoch": 0.602010445330488,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004972830064658692,
|
|
"loss": 5.4089,
|
|
"mean_token_accuracy": 0.18465373665094376,
|
|
"num_tokens": 11962447.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.640342664718628,
|
|
"epoch": 0.6025720222384455,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004972767824359596,
|
|
"loss": 5.4919,
|
|
"mean_token_accuracy": 0.182956001162529,
|
|
"num_tokens": 11972740.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.555352592468262,
|
|
"epoch": 0.6031335991464031,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004972705513286709,
|
|
"loss": 5.3702,
|
|
"mean_token_accuracy": 0.1916798397898674,
|
|
"num_tokens": 11983292.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.674102401733398,
|
|
"epoch": 0.6036951760543606,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004972643131442017,
|
|
"loss": 5.5922,
|
|
"mean_token_accuracy": 0.18003977239131927,
|
|
"num_tokens": 11996384.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.696470832824707,
|
|
"epoch": 0.6042567529623182,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004972580678827506,
|
|
"loss": 5.5061,
|
|
"mean_token_accuracy": 0.19199381321668624,
|
|
"num_tokens": 12006938.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.482018661499024,
|
|
"epoch": 0.6048183298702757,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004972518155445163,
|
|
"loss": 5.3386,
|
|
"mean_token_accuracy": 0.18582624047994614,
|
|
"num_tokens": 12018729.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.7195052146911625,
|
|
"epoch": 0.6053799067782333,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004972455561296982,
|
|
"loss": 5.7041,
|
|
"mean_token_accuracy": 0.17384667247533797,
|
|
"num_tokens": 12029625.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.56141209602356,
|
|
"epoch": 0.6059414836861908,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004972392896384952,
|
|
"loss": 5.3895,
|
|
"mean_token_accuracy": 0.18369418978691102,
|
|
"num_tokens": 12040243.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.7068993091583256,
|
|
"epoch": 0.6065030605941484,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004972330160711071,
|
|
"loss": 5.671,
|
|
"mean_token_accuracy": 0.175175179541111,
|
|
"num_tokens": 12051961.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.6262939453125,
|
|
"epoch": 0.6070646375021059,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004972267354277336,
|
|
"loss": 5.5378,
|
|
"mean_token_accuracy": 0.1859945684671402,
|
|
"num_tokens": 12063969.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.647840547561645,
|
|
"epoch": 0.6076262144100635,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004972204477085746,
|
|
"loss": 5.4178,
|
|
"mean_token_accuracy": 0.18723357021808623,
|
|
"num_tokens": 12075682.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.672305297851563,
|
|
"epoch": 0.608187791318021,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004972141529138303,
|
|
"loss": 5.5541,
|
|
"mean_token_accuracy": 0.18671936988830568,
|
|
"num_tokens": 12086595.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.586926698684692,
|
|
"epoch": 0.6087493682259786,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004972078510437013,
|
|
"loss": 5.4268,
|
|
"mean_token_accuracy": 0.18619488626718522,
|
|
"num_tokens": 12099421.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.633434104919433,
|
|
"epoch": 0.6093109451339361,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004972015420983882,
|
|
"loss": 5.5427,
|
|
"mean_token_accuracy": 0.1840139091014862,
|
|
"num_tokens": 12109680.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.543154954910278,
|
|
"epoch": 0.6098725220418937,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004971952260780915,
|
|
"loss": 5.4224,
|
|
"mean_token_accuracy": 0.19202370345592498,
|
|
"num_tokens": 12121196.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.569849824905395,
|
|
"epoch": 0.6104340989498512,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000497188902983013,
|
|
"loss": 5.3755,
|
|
"mean_token_accuracy": 0.17969895005226136,
|
|
"num_tokens": 12132262.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.629948139190674,
|
|
"epoch": 0.6109956758578087,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004971825728133535,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.18493406623601913,
|
|
"num_tokens": 12143747.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.7156328678131105,
|
|
"epoch": 0.6115572527657662,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004971762355693146,
|
|
"loss": 5.6394,
|
|
"mean_token_accuracy": 0.1741531029343605,
|
|
"num_tokens": 12155887.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.5822920322418215,
|
|
"epoch": 0.6121188296737238,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004971698912510983,
|
|
"loss": 5.4178,
|
|
"mean_token_accuracy": 0.18080265671014786,
|
|
"num_tokens": 12166718.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.620777988433838,
|
|
"epoch": 0.6126804065816813,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004971635398589066,
|
|
"loss": 5.5632,
|
|
"mean_token_accuracy": 0.1833667978644371,
|
|
"num_tokens": 12178540.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.719579219818115,
|
|
"epoch": 0.6132419834896389,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004971571813929415,
|
|
"loss": 5.6076,
|
|
"mean_token_accuracy": 0.1786387026309967,
|
|
"num_tokens": 12189820.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.616104698181152,
|
|
"epoch": 0.6138035603975964,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004971508158534056,
|
|
"loss": 5.4899,
|
|
"mean_token_accuracy": 0.18555515855550767,
|
|
"num_tokens": 12201679.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.6018133640289305,
|
|
"epoch": 0.614365137305554,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004971444432405015,
|
|
"loss": 5.5228,
|
|
"mean_token_accuracy": 0.1803461119532585,
|
|
"num_tokens": 12213793.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.688950681686402,
|
|
"epoch": 0.6149267142135115,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004971380635544323,
|
|
"loss": 5.6075,
|
|
"mean_token_accuracy": 0.1852038875222206,
|
|
"num_tokens": 12224519.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.766947793960571,
|
|
"epoch": 0.6154882911214691,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004971316767954009,
|
|
"loss": 5.5854,
|
|
"mean_token_accuracy": 0.1751009479165077,
|
|
"num_tokens": 12236401.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.640927457809449,
|
|
"epoch": 0.6160498680294266,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004971252829636108,
|
|
"loss": 5.607,
|
|
"mean_token_accuracy": 0.17650003284215926,
|
|
"num_tokens": 12247670.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.5905811309814455,
|
|
"epoch": 0.6166114449373842,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004971188820592656,
|
|
"loss": 5.4792,
|
|
"mean_token_accuracy": 0.18335412591695785,
|
|
"num_tokens": 12258877.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.609956502914429,
|
|
"epoch": 0.6171730218453417,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000497112474082569,
|
|
"loss": 5.4556,
|
|
"mean_token_accuracy": 0.18799896836280822,
|
|
"num_tokens": 12268507.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.591432285308838,
|
|
"epoch": 0.6177345987532993,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000497106059033725,
|
|
"loss": 5.4415,
|
|
"mean_token_accuracy": 0.18227818310260774,
|
|
"num_tokens": 12280420.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.568288421630859,
|
|
"epoch": 0.6182961756612568,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004970996369129381,
|
|
"loss": 5.4455,
|
|
"mean_token_accuracy": 0.1805670827627182,
|
|
"num_tokens": 12290876.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.564266633987427,
|
|
"epoch": 0.6188577525692144,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004970932077204125,
|
|
"loss": 5.346,
|
|
"mean_token_accuracy": 0.1907796800136566,
|
|
"num_tokens": 12301831.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.4954017162322994,
|
|
"epoch": 0.6194193294771719,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000497086771456353,
|
|
"loss": 5.3746,
|
|
"mean_token_accuracy": 0.18919067233800888,
|
|
"num_tokens": 12312678.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.676490306854248,
|
|
"epoch": 0.6199809063851295,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004970803281209646,
|
|
"loss": 5.5504,
|
|
"mean_token_accuracy": 0.17842403501272203,
|
|
"num_tokens": 12322905.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.610180139541626,
|
|
"epoch": 0.620542483293087,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004970738777144524,
|
|
"loss": 5.4105,
|
|
"mean_token_accuracy": 0.18521541357040405,
|
|
"num_tokens": 12333091.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.595136499404907,
|
|
"epoch": 0.6211040602010446,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004970674202370218,
|
|
"loss": 5.4231,
|
|
"mean_token_accuracy": 0.18607301265001297,
|
|
"num_tokens": 12346310.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.510883331298828,
|
|
"epoch": 0.621665637109002,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004970609556888785,
|
|
"loss": 5.3426,
|
|
"mean_token_accuracy": 0.18486004024744035,
|
|
"num_tokens": 12357138.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.643247938156128,
|
|
"epoch": 0.6222272140169596,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004970544840702282,
|
|
"loss": 5.434,
|
|
"mean_token_accuracy": 0.19092607945203782,
|
|
"num_tokens": 12367382.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.54682765007019,
|
|
"epoch": 0.6227887909249171,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004970480053812771,
|
|
"loss": 5.4278,
|
|
"mean_token_accuracy": 0.17990480065345765,
|
|
"num_tokens": 12380357.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.649844694137573,
|
|
"epoch": 0.6233503678328747,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004970415196222312,
|
|
"loss": 5.6104,
|
|
"mean_token_accuracy": 0.17453047633171082,
|
|
"num_tokens": 12392187.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.642471170425415,
|
|
"epoch": 0.6239119447408322,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004970350267932973,
|
|
"loss": 5.4626,
|
|
"mean_token_accuracy": 0.1919781044125557,
|
|
"num_tokens": 12402924.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.690981531143189,
|
|
"epoch": 0.6244735216487898,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000497028526894682,
|
|
"loss": 5.6001,
|
|
"mean_token_accuracy": 0.18040583431720733,
|
|
"num_tokens": 12413554.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.594972753524781,
|
|
"epoch": 0.6250350985567473,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004970220199265923,
|
|
"loss": 5.4719,
|
|
"mean_token_accuracy": 0.18820811361074447,
|
|
"num_tokens": 12424525.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.5729231357574465,
|
|
"epoch": 0.6255966754647049,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004970155058892354,
|
|
"loss": 5.4757,
|
|
"mean_token_accuracy": 0.18470598757266998,
|
|
"num_tokens": 12436405.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.630585432052612,
|
|
"epoch": 0.6261582523726624,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004970089847828187,
|
|
"loss": 5.5239,
|
|
"mean_token_accuracy": 0.1797418400645256,
|
|
"num_tokens": 12446909.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.632023048400879,
|
|
"epoch": 0.62671982928062,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004970024566075497,
|
|
"loss": 5.5103,
|
|
"mean_token_accuracy": 0.1853021651506424,
|
|
"num_tokens": 12458739.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.576176357269287,
|
|
"epoch": 0.6272814061885775,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004969959213636365,
|
|
"loss": 5.4511,
|
|
"mean_token_accuracy": 0.18338645100593567,
|
|
"num_tokens": 12469529.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.673983478546143,
|
|
"epoch": 0.6278429830965351,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004969893790512871,
|
|
"loss": 5.4896,
|
|
"mean_token_accuracy": 0.17851488143205643,
|
|
"num_tokens": 12480067.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.605591201782227,
|
|
"epoch": 0.6284045600044926,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004969828296707097,
|
|
"loss": 5.3631,
|
|
"mean_token_accuracy": 0.19283511638641357,
|
|
"num_tokens": 12491043.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.49311146736145,
|
|
"epoch": 0.6289661369124502,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004969762732221129,
|
|
"loss": 5.2978,
|
|
"mean_token_accuracy": 0.19157171100378037,
|
|
"num_tokens": 12501852.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.592472171783447,
|
|
"epoch": 0.6295277138204077,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004969697097057054,
|
|
"loss": 5.6187,
|
|
"mean_token_accuracy": 0.17990778535604476,
|
|
"num_tokens": 12512696.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.623296737670898,
|
|
"epoch": 0.6300892907283653,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004969631391216964,
|
|
"loss": 5.456,
|
|
"mean_token_accuracy": 0.18712275922298433,
|
|
"num_tokens": 12523643.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.598635911941528,
|
|
"epoch": 0.6306508676363228,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004969565614702948,
|
|
"loss": 5.4289,
|
|
"mean_token_accuracy": 0.18764980584383012,
|
|
"num_tokens": 12534827.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.46979455947876,
|
|
"epoch": 0.6312124445442804,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004969499767517104,
|
|
"loss": 5.3034,
|
|
"mean_token_accuracy": 0.1917729213833809,
|
|
"num_tokens": 12545977.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.4649755477905275,
|
|
"epoch": 0.6317740214522379,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004969433849661525,
|
|
"loss": 5.3726,
|
|
"mean_token_accuracy": 0.18026579469442366,
|
|
"num_tokens": 12555890.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.544844627380371,
|
|
"epoch": 0.6323355983601955,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004969367861138313,
|
|
"loss": 5.4302,
|
|
"mean_token_accuracy": 0.193123060464859,
|
|
"num_tokens": 12566412.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.634961366653442,
|
|
"epoch": 0.6328971752681529,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004969301801949565,
|
|
"loss": 5.4747,
|
|
"mean_token_accuracy": 0.18541150838136672,
|
|
"num_tokens": 12577175.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.53953857421875,
|
|
"epoch": 0.6334587521761105,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000496923567209739,
|
|
"loss": 5.3978,
|
|
"mean_token_accuracy": 0.18610223531723022,
|
|
"num_tokens": 12588760.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.5577116966247555,
|
|
"epoch": 0.634020329084068,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004969169471583889,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.18638110607862474,
|
|
"num_tokens": 12599899.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.646306705474854,
|
|
"epoch": 0.6345819059920256,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004969103200411171,
|
|
"loss": 5.4182,
|
|
"mean_token_accuracy": 0.19530787616968154,
|
|
"num_tokens": 12610836.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.538104391098022,
|
|
"epoch": 0.6351434828999831,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004969036858581346,
|
|
"loss": 5.3832,
|
|
"mean_token_accuracy": 0.19196907579898834,
|
|
"num_tokens": 12621855.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.597290754318237,
|
|
"epoch": 0.6357050598079407,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004968970446096527,
|
|
"loss": 5.464,
|
|
"mean_token_accuracy": 0.18715441077947617,
|
|
"num_tokens": 12632964.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.509879541397095,
|
|
"epoch": 0.6362666367158982,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000496890396295883,
|
|
"loss": 5.3246,
|
|
"mean_token_accuracy": 0.19128041863441467,
|
|
"num_tokens": 12643717.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.588350248336792,
|
|
"epoch": 0.6368282136238558,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004968837409170368,
|
|
"loss": 5.4352,
|
|
"mean_token_accuracy": 0.1833639457821846,
|
|
"num_tokens": 12654491.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.574241399765015,
|
|
"epoch": 0.6373897905318133,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004968770784733263,
|
|
"loss": 5.4882,
|
|
"mean_token_accuracy": 0.18664699345827102,
|
|
"num_tokens": 12666128.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.667492341995239,
|
|
"epoch": 0.6379513674397709,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004968704089649636,
|
|
"loss": 5.5725,
|
|
"mean_token_accuracy": 0.1784846618771553,
|
|
"num_tokens": 12677957.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.590038394927978,
|
|
"epoch": 0.6385129443477284,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004968637323921611,
|
|
"loss": 5.4011,
|
|
"mean_token_accuracy": 0.18758929818868636,
|
|
"num_tokens": 12687964.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.492672872543335,
|
|
"epoch": 0.639074521255686,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004968570487551312,
|
|
"loss": 5.4048,
|
|
"mean_token_accuracy": 0.18345636129379272,
|
|
"num_tokens": 12698805.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.616511344909668,
|
|
"epoch": 0.6396360981636435,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004968503580540869,
|
|
"loss": 5.4221,
|
|
"mean_token_accuracy": 0.18310350477695464,
|
|
"num_tokens": 12709942.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.685959434509277,
|
|
"epoch": 0.6401976750716011,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004968436602892411,
|
|
"loss": 5.4875,
|
|
"mean_token_accuracy": 0.18588088899850846,
|
|
"num_tokens": 12721856.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.478527450561524,
|
|
"epoch": 0.6407592519795586,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004968369554608071,
|
|
"loss": 5.3205,
|
|
"mean_token_accuracy": 0.18528069853782653,
|
|
"num_tokens": 12732619.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.545958375930786,
|
|
"epoch": 0.6413208288875162,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004968302435689985,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.18862492889165877,
|
|
"num_tokens": 12743478.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.532248306274414,
|
|
"epoch": 0.6418824057954737,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004968235246140288,
|
|
"loss": 5.3664,
|
|
"mean_token_accuracy": 0.18406943678855897,
|
|
"num_tokens": 12754761.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.665899085998535,
|
|
"epoch": 0.6424439827034313,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004968167985961121,
|
|
"loss": 5.4834,
|
|
"mean_token_accuracy": 0.18930073082447052,
|
|
"num_tokens": 12765803.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.574135589599609,
|
|
"epoch": 0.6430055596113888,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004968100655154625,
|
|
"loss": 5.5096,
|
|
"mean_token_accuracy": 0.18169724941253662,
|
|
"num_tokens": 12777882.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.643469667434692,
|
|
"epoch": 0.6435671365193463,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004968033253722943,
|
|
"loss": 5.5135,
|
|
"mean_token_accuracy": 0.18031821995973588,
|
|
"num_tokens": 12788268.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.600995302200317,
|
|
"epoch": 0.6441287134273038,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004967965781668223,
|
|
"loss": 5.503,
|
|
"mean_token_accuracy": 0.18759284317493438,
|
|
"num_tokens": 12800506.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.60623836517334,
|
|
"epoch": 0.6446902903352614,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004967898238992613,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.18512337803840637,
|
|
"num_tokens": 12813040.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.637520360946655,
|
|
"epoch": 0.6452518672432189,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004967830625698262,
|
|
"loss": 5.5197,
|
|
"mean_token_accuracy": 0.18802948147058487,
|
|
"num_tokens": 12825534.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.576848983764648,
|
|
"epoch": 0.6458134441511765,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004967762941787323,
|
|
"loss": 5.3975,
|
|
"mean_token_accuracy": 0.1857204630970955,
|
|
"num_tokens": 12835882.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.585302686691284,
|
|
"epoch": 0.646375021059134,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004967695187261952,
|
|
"loss": 5.6039,
|
|
"mean_token_accuracy": 0.17597048431634904,
|
|
"num_tokens": 12847663.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.744038200378418,
|
|
"epoch": 0.6469365979670916,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004967627362124306,
|
|
"loss": 5.7125,
|
|
"mean_token_accuracy": 0.17757612019777297,
|
|
"num_tokens": 12860789.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.647675704956055,
|
|
"epoch": 0.6474981748750491,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004967559466376546,
|
|
"loss": 5.4558,
|
|
"mean_token_accuracy": 0.18649709075689316,
|
|
"num_tokens": 12872509.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.555054569244385,
|
|
"epoch": 0.6480597517830067,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004967491500020831,
|
|
"loss": 5.4534,
|
|
"mean_token_accuracy": 0.18682979196310043,
|
|
"num_tokens": 12884321.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.431756973266602,
|
|
"epoch": 0.6486213286909642,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004967423463059328,
|
|
"loss": 5.3309,
|
|
"mean_token_accuracy": 0.19240241646766662,
|
|
"num_tokens": 12894559.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.564483499526977,
|
|
"epoch": 0.6491829055989218,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004967355355494201,
|
|
"loss": 5.4319,
|
|
"mean_token_accuracy": 0.18994510620832444,
|
|
"num_tokens": 12904934.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.70449275970459,
|
|
"epoch": 0.6497444825068793,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000496728717732762,
|
|
"loss": 5.555,
|
|
"mean_token_accuracy": 0.1803714379668236,
|
|
"num_tokens": 12916551.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.609445714950562,
|
|
"epoch": 0.6503060594148369,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004967218928561755,
|
|
"loss": 5.454,
|
|
"mean_token_accuracy": 0.18270530104637145,
|
|
"num_tokens": 12928097.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.558883285522461,
|
|
"epoch": 0.6508676363227944,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004967150609198779,
|
|
"loss": 5.3349,
|
|
"mean_token_accuracy": 0.19458029717206954,
|
|
"num_tokens": 12939161.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.479016637802124,
|
|
"epoch": 0.651429213230752,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004967082219240869,
|
|
"loss": 5.3878,
|
|
"mean_token_accuracy": 0.18893582224845887,
|
|
"num_tokens": 12950862.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.587749862670899,
|
|
"epoch": 0.6519907901387095,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004967013758690199,
|
|
"loss": 5.4337,
|
|
"mean_token_accuracy": 0.18156342059373856,
|
|
"num_tokens": 12962333.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.59279727935791,
|
|
"epoch": 0.6525523670466671,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004966945227548953,
|
|
"loss": 5.3942,
|
|
"mean_token_accuracy": 0.18726360201835632,
|
|
"num_tokens": 12973136.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.587766170501709,
|
|
"epoch": 0.6531139439546246,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004966876625819309,
|
|
"loss": 5.4462,
|
|
"mean_token_accuracy": 0.18316376209259033,
|
|
"num_tokens": 12983602.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.575126361846924,
|
|
"epoch": 0.6536755208625822,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004966807953503456,
|
|
"loss": 5.3571,
|
|
"mean_token_accuracy": 0.19102459400892258,
|
|
"num_tokens": 12994129.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.565567350387573,
|
|
"epoch": 0.6542370977705396,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004966739210603578,
|
|
"loss": 5.4066,
|
|
"mean_token_accuracy": 0.18423057496547698,
|
|
"num_tokens": 13005071.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.66208438873291,
|
|
"epoch": 0.6547986746784972,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004966670397121862,
|
|
"loss": 5.5974,
|
|
"mean_token_accuracy": 0.18425355702638627,
|
|
"num_tokens": 13016202.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.645590591430664,
|
|
"epoch": 0.6553602515864547,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004966601513060502,
|
|
"loss": 5.5697,
|
|
"mean_token_accuracy": 0.1739979788661003,
|
|
"num_tokens": 13028468.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.606764221191407,
|
|
"epoch": 0.6559218284944123,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000496653255842169,
|
|
"loss": 5.4487,
|
|
"mean_token_accuracy": 0.18786526769399642,
|
|
"num_tokens": 13039667.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.617080545425415,
|
|
"epoch": 0.6564834054023698,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004966463533207621,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.17802227288484573,
|
|
"num_tokens": 13051583.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.606671905517578,
|
|
"epoch": 0.6570449823103274,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004966394437420493,
|
|
"loss": 5.4708,
|
|
"mean_token_accuracy": 0.17936455011367797,
|
|
"num_tokens": 13062401.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.533967208862305,
|
|
"epoch": 0.6576065592182849,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004966325271062508,
|
|
"loss": 5.3433,
|
|
"mean_token_accuracy": 0.1948936700820923,
|
|
"num_tokens": 13074219.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.618377780914306,
|
|
"epoch": 0.6581681361262425,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004966256034135866,
|
|
"loss": 5.5585,
|
|
"mean_token_accuracy": 0.18522871136665345,
|
|
"num_tokens": 13086073.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.6113865852355955,
|
|
"epoch": 0.6587297130342,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004966186726642772,
|
|
"loss": 5.4566,
|
|
"mean_token_accuracy": 0.18118618726730346,
|
|
"num_tokens": 13096340.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.520273065567016,
|
|
"epoch": 0.6592912899421576,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004966117348585434,
|
|
"loss": 5.433,
|
|
"mean_token_accuracy": 0.18932820707559586,
|
|
"num_tokens": 13107273.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.5223218441009525,
|
|
"epoch": 0.6598528668501151,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004966047899966059,
|
|
"loss": 5.4083,
|
|
"mean_token_accuracy": 0.17953830510377883,
|
|
"num_tokens": 13117388.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.585290336608887,
|
|
"epoch": 0.6604144437580727,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000496597838078686,
|
|
"loss": 5.5291,
|
|
"mean_token_accuracy": 0.18056883960962294,
|
|
"num_tokens": 13128720.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.605383491516113,
|
|
"epoch": 0.6609760206660302,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000496590879105005,
|
|
"loss": 5.4437,
|
|
"mean_token_accuracy": 0.18524353951215744,
|
|
"num_tokens": 13139405.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.6540992736816404,
|
|
"epoch": 0.6615375975739878,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004965839130757845,
|
|
"loss": 5.5396,
|
|
"mean_token_accuracy": 0.18290454149246216,
|
|
"num_tokens": 13151408.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.585953855514527,
|
|
"epoch": 0.6620991744819453,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004965769399912462,
|
|
"loss": 5.4388,
|
|
"mean_token_accuracy": 0.18750968277454377,
|
|
"num_tokens": 13162592.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.613091945648193,
|
|
"epoch": 0.6626607513899029,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004965699598516122,
|
|
"loss": 5.4654,
|
|
"mean_token_accuracy": 0.18831417411565782,
|
|
"num_tokens": 13173040.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.580550241470337,
|
|
"epoch": 0.6632223282978604,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004965629726571047,
|
|
"loss": 5.5408,
|
|
"mean_token_accuracy": 0.18459512442350387,
|
|
"num_tokens": 13185475.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.546143627166748,
|
|
"epoch": 0.663783905205818,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004965559784079463,
|
|
"loss": 5.4001,
|
|
"mean_token_accuracy": 0.19337214678525924,
|
|
"num_tokens": 13196481.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.508285856246948,
|
|
"epoch": 0.6643454821137755,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004965489771043596,
|
|
"loss": 5.2867,
|
|
"mean_token_accuracy": 0.1948182225227356,
|
|
"num_tokens": 13207947.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.468513250350952,
|
|
"epoch": 0.664907059021733,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004965419687465676,
|
|
"loss": 5.338,
|
|
"mean_token_accuracy": 0.19859456717967988,
|
|
"num_tokens": 13219392.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.487781715393067,
|
|
"epoch": 0.6654686359296905,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004965349533347934,
|
|
"loss": 5.3837,
|
|
"mean_token_accuracy": 0.19404632598161697,
|
|
"num_tokens": 13231556.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.560096693038941,
|
|
"epoch": 0.6660302128376481,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004965279308692602,
|
|
"loss": 5.3223,
|
|
"mean_token_accuracy": 0.18837640136480333,
|
|
"num_tokens": 13241287.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.512104034423828,
|
|
"epoch": 0.6665917897456056,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004965209013501919,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.18145681619644166,
|
|
"num_tokens": 13254120.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.558088684082032,
|
|
"epoch": 0.6671533666535632,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004965138647778122,
|
|
"loss": 5.4523,
|
|
"mean_token_accuracy": 0.1826157882809639,
|
|
"num_tokens": 13265745.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.666581439971924,
|
|
"epoch": 0.6677149435615207,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000496506821152345,
|
|
"loss": 5.512,
|
|
"mean_token_accuracy": 0.18324743062257767,
|
|
"num_tokens": 13277791.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.560856914520263,
|
|
"epoch": 0.6682765204694783,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004964997704740147,
|
|
"loss": 5.3751,
|
|
"mean_token_accuracy": 0.18288409113883972,
|
|
"num_tokens": 13288078.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.54308385848999,
|
|
"epoch": 0.6688380973774358,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000496492712743046,
|
|
"loss": 5.4164,
|
|
"mean_token_accuracy": 0.18916729539632798,
|
|
"num_tokens": 13300547.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.574636030197143,
|
|
"epoch": 0.6693996742853934,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004964856479596632,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.1844284325838089,
|
|
"num_tokens": 13310339.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.649972581863404,
|
|
"epoch": 0.6699612511933509,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004964785761240915,
|
|
"loss": 5.4652,
|
|
"mean_token_accuracy": 0.18339674770832062,
|
|
"num_tokens": 13321294.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.5962268829345705,
|
|
"epoch": 0.6705228281013085,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004964714972365562,
|
|
"loss": 5.4876,
|
|
"mean_token_accuracy": 0.18522342145442963,
|
|
"num_tokens": 13332608.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.588433122634887,
|
|
"epoch": 0.671084405009266,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004964644112972824,
|
|
"loss": 5.4135,
|
|
"mean_token_accuracy": 0.1959644690155983,
|
|
"num_tokens": 13344169.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.4729576587677,
|
|
"epoch": 0.6716459819172236,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004964573183064959,
|
|
"loss": 5.3822,
|
|
"mean_token_accuracy": 0.18695180267095565,
|
|
"num_tokens": 13355713.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.600048303604126,
|
|
"epoch": 0.6722075588251811,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004964502182644225,
|
|
"loss": 5.4743,
|
|
"mean_token_accuracy": 0.1833113133907318,
|
|
"num_tokens": 13366644.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.611146450042725,
|
|
"epoch": 0.6727691357331387,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004964431111712883,
|
|
"loss": 5.447,
|
|
"mean_token_accuracy": 0.18404945284128188,
|
|
"num_tokens": 13378125.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.538123226165771,
|
|
"epoch": 0.6733307126410962,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004964359970273195,
|
|
"loss": 5.4918,
|
|
"mean_token_accuracy": 0.18231723010540007,
|
|
"num_tokens": 13389681.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.638032388687134,
|
|
"epoch": 0.6738922895490538,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004964288758327426,
|
|
"loss": 5.4689,
|
|
"mean_token_accuracy": 0.18596884310245515,
|
|
"num_tokens": 13399814.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.6738922895490538,
|
|
"eval_entropy": 5.401589800347856,
|
|
"eval_loss": 5.4581098556518555,
|
|
"eval_mean_token_accuracy": 0.192657116930264,
|
|
"eval_num_tokens": 13399814.0,
|
|
"eval_runtime": 18.2338,
|
|
"eval_samples_per_second": 1700.857,
|
|
"eval_steps_per_second": 212.628,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.646923589706421,
|
|
"epoch": 0.6744538664570113,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004964217475877846,
|
|
"loss": 5.4957,
|
|
"mean_token_accuracy": 0.18415769040584565,
|
|
"num_tokens": 13410614.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.57463698387146,
|
|
"epoch": 0.6750154433649689,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000496414612292672,
|
|
"loss": 5.5008,
|
|
"mean_token_accuracy": 0.1825885832309723,
|
|
"num_tokens": 13421392.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.6496422290802,
|
|
"epoch": 0.6755770202729264,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004964074699476325,
|
|
"loss": 5.5291,
|
|
"mean_token_accuracy": 0.18065254390239716,
|
|
"num_tokens": 13432004.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.580326557159424,
|
|
"epoch": 0.6761385971808839,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004964003205528933,
|
|
"loss": 5.3787,
|
|
"mean_token_accuracy": 0.1912464365363121,
|
|
"num_tokens": 13442450.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.587422704696655,
|
|
"epoch": 0.6767001740888414,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004963931641086819,
|
|
"loss": 5.4337,
|
|
"mean_token_accuracy": 0.18147221207618713,
|
|
"num_tokens": 13453848.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.537183475494385,
|
|
"epoch": 0.677261750996799,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004963860006152262,
|
|
"loss": 5.4354,
|
|
"mean_token_accuracy": 0.18918716460466384,
|
|
"num_tokens": 13465119.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.525205278396607,
|
|
"epoch": 0.6778233279047565,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004963788300727546,
|
|
"loss": 5.4136,
|
|
"mean_token_accuracy": 0.1885279580950737,
|
|
"num_tokens": 13475937.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.559143924713135,
|
|
"epoch": 0.6783849048127141,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004963716524814951,
|
|
"loss": 5.399,
|
|
"mean_token_accuracy": 0.18962415903806687,
|
|
"num_tokens": 13487430.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.604590988159179,
|
|
"epoch": 0.6789464817206716,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004963644678416763,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.19052744209766387,
|
|
"num_tokens": 13499631.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.587384033203125,
|
|
"epoch": 0.6795080586286292,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000496357276153527,
|
|
"loss": 5.4668,
|
|
"mean_token_accuracy": 0.18758317530155183,
|
|
"num_tokens": 13511753.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.585440444946289,
|
|
"epoch": 0.6800696355365867,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004963500774172763,
|
|
"loss": 5.522,
|
|
"mean_token_accuracy": 0.17988150864839553,
|
|
"num_tokens": 13524228.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.66345181465149,
|
|
"epoch": 0.6806312124445443,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000496342871633153,
|
|
"loss": 5.5442,
|
|
"mean_token_accuracy": 0.1844257578253746,
|
|
"num_tokens": 13535700.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.607192277908325,
|
|
"epoch": 0.6811927893525018,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004963356588013871,
|
|
"loss": 5.5257,
|
|
"mean_token_accuracy": 0.17659420073032378,
|
|
"num_tokens": 13547337.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.487743520736695,
|
|
"epoch": 0.6817543662604594,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004963284389222078,
|
|
"loss": 5.3796,
|
|
"mean_token_accuracy": 0.18587132096290587,
|
|
"num_tokens": 13558350.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.577818298339844,
|
|
"epoch": 0.6823159431684169,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004963212119958453,
|
|
"loss": 5.4212,
|
|
"mean_token_accuracy": 0.1904219791293144,
|
|
"num_tokens": 13569230.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.64628233909607,
|
|
"epoch": 0.6828775200763745,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004963139780225295,
|
|
"loss": 5.5055,
|
|
"mean_token_accuracy": 0.18413326591253282,
|
|
"num_tokens": 13580502.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.611775588989258,
|
|
"epoch": 0.683439096984332,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004963067370024909,
|
|
"loss": 5.4251,
|
|
"mean_token_accuracy": 0.19118367433547973,
|
|
"num_tokens": 13591524.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.589556741714477,
|
|
"epoch": 0.6840006738922896,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004962994889359598,
|
|
"loss": 5.4441,
|
|
"mean_token_accuracy": 0.1964499443769455,
|
|
"num_tokens": 13602432.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.5022101402282715,
|
|
"epoch": 0.6845622508002471,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004962922338231673,
|
|
"loss": 5.373,
|
|
"mean_token_accuracy": 0.19672563821077346,
|
|
"num_tokens": 13613052.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.5472776889801025,
|
|
"epoch": 0.6851238277082047,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004962849716643441,
|
|
"loss": 5.3863,
|
|
"mean_token_accuracy": 0.19051288664340973,
|
|
"num_tokens": 13623961.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.524657487869263,
|
|
"epoch": 0.6856854046161622,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004962777024597216,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.1882488965988159,
|
|
"num_tokens": 13635285.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.666265821456909,
|
|
"epoch": 0.6862469815241198,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004962704262095314,
|
|
"loss": 5.5333,
|
|
"mean_token_accuracy": 0.17889947146177293,
|
|
"num_tokens": 13647720.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.523880243301392,
|
|
"epoch": 0.6868085584320772,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004962631429140048,
|
|
"loss": 5.3972,
|
|
"mean_token_accuracy": 0.18586231619119645,
|
|
"num_tokens": 13659726.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.662991333007812,
|
|
"epoch": 0.6873701353400348,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000496255852573374,
|
|
"loss": 5.5763,
|
|
"mean_token_accuracy": 0.1790321499109268,
|
|
"num_tokens": 13670332.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.703384304046631,
|
|
"epoch": 0.6879317122479923,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004962485551878711,
|
|
"loss": 5.5346,
|
|
"mean_token_accuracy": 0.17642847299575806,
|
|
"num_tokens": 13682419.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.4620270252227785,
|
|
"epoch": 0.6884932891559499,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004962412507577283,
|
|
"loss": 5.2815,
|
|
"mean_token_accuracy": 0.19445524513721466,
|
|
"num_tokens": 13692698.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.50990047454834,
|
|
"epoch": 0.6890548660639074,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004962339392831783,
|
|
"loss": 5.4666,
|
|
"mean_token_accuracy": 0.18721719086170197,
|
|
"num_tokens": 13704791.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.604409885406494,
|
|
"epoch": 0.689616442971865,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000496226620764454,
|
|
"loss": 5.3977,
|
|
"mean_token_accuracy": 0.19106096178293228,
|
|
"num_tokens": 13715860.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.5842962741851805,
|
|
"epoch": 0.6901780198798225,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000496219295201788,
|
|
"loss": 5.372,
|
|
"mean_token_accuracy": 0.19463435113430022,
|
|
"num_tokens": 13727029.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.5058893203735355,
|
|
"epoch": 0.6907395967877801,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004962119625954141,
|
|
"loss": 5.3707,
|
|
"mean_token_accuracy": 0.19573699980974196,
|
|
"num_tokens": 13737168.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.589278888702393,
|
|
"epoch": 0.6913011736957376,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004962046229455653,
|
|
"loss": 5.5219,
|
|
"mean_token_accuracy": 0.17839339077472688,
|
|
"num_tokens": 13749828.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.516400766372681,
|
|
"epoch": 0.6918627506036952,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004961972762524757,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.18713945597410203,
|
|
"num_tokens": 13761617.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.611632585525513,
|
|
"epoch": 0.6924243275116527,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000496189922516379,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.19397446513175964,
|
|
"num_tokens": 13772721.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.482655096054077,
|
|
"epoch": 0.6929859044196103,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004961825617375093,
|
|
"loss": 5.3812,
|
|
"mean_token_accuracy": 0.1874512568116188,
|
|
"num_tokens": 13783215.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.491256427764893,
|
|
"epoch": 0.6935474813275678,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004961751939161011,
|
|
"loss": 5.3287,
|
|
"mean_token_accuracy": 0.19310313314199448,
|
|
"num_tokens": 13793496.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.462819814682007,
|
|
"epoch": 0.6941090582355254,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000496167819052389,
|
|
"loss": 5.25,
|
|
"mean_token_accuracy": 0.18821246027946473,
|
|
"num_tokens": 13802818.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.680048990249634,
|
|
"epoch": 0.6946706351434829,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004961604371466077,
|
|
"loss": 5.5542,
|
|
"mean_token_accuracy": 0.1835671290755272,
|
|
"num_tokens": 13814449.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.573808002471924,
|
|
"epoch": 0.6952322120514405,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004961530481989923,
|
|
"loss": 5.4917,
|
|
"mean_token_accuracy": 0.1829431265592575,
|
|
"num_tokens": 13825369.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.480724239349366,
|
|
"epoch": 0.695793788959398,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004961456522097782,
|
|
"loss": 5.3489,
|
|
"mean_token_accuracy": 0.18638586699962617,
|
|
"num_tokens": 13837992.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.568413543701172,
|
|
"epoch": 0.6963553658673556,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004961382491792006,
|
|
"loss": 5.4477,
|
|
"mean_token_accuracy": 0.1812524452805519,
|
|
"num_tokens": 13849771.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.595166349411011,
|
|
"epoch": 0.6969169427753131,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004961308391074953,
|
|
"loss": 5.42,
|
|
"mean_token_accuracy": 0.18859976828098296,
|
|
"num_tokens": 13861997.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.659422731399536,
|
|
"epoch": 0.6974785196832706,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004961234219948986,
|
|
"loss": 5.5096,
|
|
"mean_token_accuracy": 0.1829330876469612,
|
|
"num_tokens": 13872972.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.4354277610778805,
|
|
"epoch": 0.6980400965912281,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004961159978416461,
|
|
"loss": 5.2824,
|
|
"mean_token_accuracy": 0.19414234906435013,
|
|
"num_tokens": 13883139.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.582811975479126,
|
|
"epoch": 0.6986016734991857,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004961085666479746,
|
|
"loss": 5.4405,
|
|
"mean_token_accuracy": 0.18963438123464585,
|
|
"num_tokens": 13894326.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.603238773345947,
|
|
"epoch": 0.6991632504071432,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004961011284141206,
|
|
"loss": 5.4808,
|
|
"mean_token_accuracy": 0.18860790580511094,
|
|
"num_tokens": 13905525.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.5148704051971436,
|
|
"epoch": 0.6997248273151008,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004960936831403209,
|
|
"loss": 5.4041,
|
|
"mean_token_accuracy": 0.187268990278244,
|
|
"num_tokens": 13915973.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.51510763168335,
|
|
"epoch": 0.7002864042230583,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004960862308268126,
|
|
"loss": 5.2199,
|
|
"mean_token_accuracy": 0.19681506752967834,
|
|
"num_tokens": 13926380.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.55254430770874,
|
|
"epoch": 0.7008479811310159,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004960787714738329,
|
|
"loss": 5.4171,
|
|
"mean_token_accuracy": 0.18290770351886748,
|
|
"num_tokens": 13938523.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.5069276809692385,
|
|
"epoch": 0.7014095580389734,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004960713050816194,
|
|
"loss": 5.3924,
|
|
"mean_token_accuracy": 0.19256162494421006,
|
|
"num_tokens": 13949343.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.591718006134033,
|
|
"epoch": 0.701971134946931,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004960638316504098,
|
|
"loss": 5.5111,
|
|
"mean_token_accuracy": 0.18868376314640045,
|
|
"num_tokens": 13960056.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.67092456817627,
|
|
"epoch": 0.7025327118548885,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004960563511804421,
|
|
"loss": 5.4685,
|
|
"mean_token_accuracy": 0.18847769796848296,
|
|
"num_tokens": 13971932.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.629927158355713,
|
|
"epoch": 0.7030942887628461,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004960488636719545,
|
|
"loss": 5.479,
|
|
"mean_token_accuracy": 0.18567973971366883,
|
|
"num_tokens": 13981992.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.566175651550293,
|
|
"epoch": 0.7036558656708036,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004960413691251852,
|
|
"loss": 5.4326,
|
|
"mean_token_accuracy": 0.1920413225889206,
|
|
"num_tokens": 13992215.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.530323839187622,
|
|
"epoch": 0.7042174425787612,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004960338675403731,
|
|
"loss": 5.3218,
|
|
"mean_token_accuracy": 0.19865480661392212,
|
|
"num_tokens": 14002689.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.531408071517944,
|
|
"epoch": 0.7047790194867187,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004960263589177568,
|
|
"loss": 5.4472,
|
|
"mean_token_accuracy": 0.18879526406526564,
|
|
"num_tokens": 14014951.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.584560108184815,
|
|
"epoch": 0.7053405963946763,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004960188432575757,
|
|
"loss": 5.3944,
|
|
"mean_token_accuracy": 0.1890434667468071,
|
|
"num_tokens": 14025502.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.607841062545776,
|
|
"epoch": 0.7059021733026338,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004960113205600688,
|
|
"loss": 5.4389,
|
|
"mean_token_accuracy": 0.19130444824695586,
|
|
"num_tokens": 14036576.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.621018886566162,
|
|
"epoch": 0.7064637502105914,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004960037908254757,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.1888699486851692,
|
|
"num_tokens": 14046493.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.609211587905884,
|
|
"epoch": 0.7070253271185489,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004959962540540361,
|
|
"loss": 5.5076,
|
|
"mean_token_accuracy": 0.18652400821447374,
|
|
"num_tokens": 14057297.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.505354499816894,
|
|
"epoch": 0.7075869040265065,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004959887102459903,
|
|
"loss": 5.29,
|
|
"mean_token_accuracy": 0.19129664450883865,
|
|
"num_tokens": 14068947.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.536684226989746,
|
|
"epoch": 0.7081484809344639,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004959811594015781,
|
|
"loss": 5.3957,
|
|
"mean_token_accuracy": 0.18915995955467224,
|
|
"num_tokens": 14078979.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.5250598907470705,
|
|
"epoch": 0.7087100578424215,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004959736015210401,
|
|
"loss": 5.3218,
|
|
"mean_token_accuracy": 0.19602209478616714,
|
|
"num_tokens": 14089785.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.566288661956787,
|
|
"epoch": 0.709271634750379,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004959660366046169,
|
|
"loss": 5.4172,
|
|
"mean_token_accuracy": 0.18718542009592057,
|
|
"num_tokens": 14099921.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.455599546432495,
|
|
"epoch": 0.7098332116583366,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004959584646525494,
|
|
"loss": 5.3229,
|
|
"mean_token_accuracy": 0.18730655461549758,
|
|
"num_tokens": 14110965.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.619172811508179,
|
|
"epoch": 0.7103947885662941,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004959508856650788,
|
|
"loss": 5.476,
|
|
"mean_token_accuracy": 0.18679166734218597,
|
|
"num_tokens": 14122409.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.585164785385132,
|
|
"epoch": 0.7109563654742517,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004959432996424463,
|
|
"loss": 5.4064,
|
|
"mean_token_accuracy": 0.19553910940885544,
|
|
"num_tokens": 14134017.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.550099849700928,
|
|
"epoch": 0.7115179423822092,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004959357065848932,
|
|
"loss": 5.5294,
|
|
"mean_token_accuracy": 0.1850521206855774,
|
|
"num_tokens": 14144843.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.584148693084717,
|
|
"epoch": 0.7120795192901668,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004959281064926618,
|
|
"loss": 5.3801,
|
|
"mean_token_accuracy": 0.18981605917215347,
|
|
"num_tokens": 14155944.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.5727903842926025,
|
|
"epoch": 0.7126410961981243,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004959204993659936,
|
|
"loss": 5.4403,
|
|
"mean_token_accuracy": 0.1895127698779106,
|
|
"num_tokens": 14167064.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.584324741363526,
|
|
"epoch": 0.7132026731060819,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004959128852051311,
|
|
"loss": 5.432,
|
|
"mean_token_accuracy": 0.18523438423871993,
|
|
"num_tokens": 14178583.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.50538740158081,
|
|
"epoch": 0.7137642500140394,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004959052640103167,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.19202942103147508,
|
|
"num_tokens": 14188752.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.520774888992309,
|
|
"epoch": 0.714325826921997,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000495897635781793,
|
|
"loss": 5.3325,
|
|
"mean_token_accuracy": 0.1939898669719696,
|
|
"num_tokens": 14199962.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.529936647415161,
|
|
"epoch": 0.7148874038299545,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004958900005198029,
|
|
"loss": 5.3526,
|
|
"mean_token_accuracy": 0.19180352091789246,
|
|
"num_tokens": 14209877.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.508715867996216,
|
|
"epoch": 0.7154489807379121,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004958823582245894,
|
|
"loss": 5.4061,
|
|
"mean_token_accuracy": 0.19456677287817,
|
|
"num_tokens": 14220672.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.635096693038941,
|
|
"epoch": 0.7160105576458696,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004958747088963961,
|
|
"loss": 5.3994,
|
|
"mean_token_accuracy": 0.19460146725177765,
|
|
"num_tokens": 14232348.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.544111728668213,
|
|
"epoch": 0.7165721345538272,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004958670525354663,
|
|
"loss": 5.4144,
|
|
"mean_token_accuracy": 0.18092965185642243,
|
|
"num_tokens": 14243985.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.451342964172364,
|
|
"epoch": 0.7171337114617847,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000495859389142044,
|
|
"loss": 5.29,
|
|
"mean_token_accuracy": 0.19636288434267044,
|
|
"num_tokens": 14253548.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.595607852935791,
|
|
"epoch": 0.7176952883697423,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000495851718716373,
|
|
"loss": 5.4383,
|
|
"mean_token_accuracy": 0.18815089911222457,
|
|
"num_tokens": 14264757.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.4588829517364506,
|
|
"epoch": 0.7182568652776998,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004958440412586977,
|
|
"loss": 5.3494,
|
|
"mean_token_accuracy": 0.1987864926457405,
|
|
"num_tokens": 14275946.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.505002546310425,
|
|
"epoch": 0.7188184421856574,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004958363567692624,
|
|
"loss": 5.4124,
|
|
"mean_token_accuracy": 0.18201731890439987,
|
|
"num_tokens": 14287006.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.654749965667724,
|
|
"epoch": 0.7193800190936148,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004958286652483118,
|
|
"loss": 5.4488,
|
|
"mean_token_accuracy": 0.1832731172442436,
|
|
"num_tokens": 14299328.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.603736782073975,
|
|
"epoch": 0.7199415960015724,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004958209666960909,
|
|
"loss": 5.4416,
|
|
"mean_token_accuracy": 0.1916926309466362,
|
|
"num_tokens": 14310048.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.469794273376465,
|
|
"epoch": 0.7205031729095299,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004958132611128448,
|
|
"loss": 5.3665,
|
|
"mean_token_accuracy": 0.19476278126239777,
|
|
"num_tokens": 14321107.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.511231136322022,
|
|
"epoch": 0.7210647498174875,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004958055484988188,
|
|
"loss": 5.2868,
|
|
"mean_token_accuracy": 0.1940134882926941,
|
|
"num_tokens": 14332561.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.6382426738739015,
|
|
"epoch": 0.721626326725445,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004957978288542585,
|
|
"loss": 5.4774,
|
|
"mean_token_accuracy": 0.1871576800942421,
|
|
"num_tokens": 14343238.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.563603067398072,
|
|
"epoch": 0.7221879036334026,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004957901021794098,
|
|
"loss": 5.3769,
|
|
"mean_token_accuracy": 0.19246648401021957,
|
|
"num_tokens": 14356067.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.504949760437012,
|
|
"epoch": 0.7227494805413601,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004957823684745184,
|
|
"loss": 5.4069,
|
|
"mean_token_accuracy": 0.19316048324108123,
|
|
"num_tokens": 14367302.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.519736480712891,
|
|
"epoch": 0.7233110574493177,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004957746277398309,
|
|
"loss": 5.3349,
|
|
"mean_token_accuracy": 0.19798117876052856,
|
|
"num_tokens": 14377535.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.597304964065552,
|
|
"epoch": 0.7238726343572752,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004957668799755937,
|
|
"loss": 5.4703,
|
|
"mean_token_accuracy": 0.18569201678037645,
|
|
"num_tokens": 14389493.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.513818645477295,
|
|
"epoch": 0.7244342112652328,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004957591251820532,
|
|
"loss": 5.38,
|
|
"mean_token_accuracy": 0.19683949947357177,
|
|
"num_tokens": 14401564.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.583502721786499,
|
|
"epoch": 0.7249957881731903,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004957513633594567,
|
|
"loss": 5.4452,
|
|
"mean_token_accuracy": 0.1950697973370552,
|
|
"num_tokens": 14412123.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.582270765304566,
|
|
"epoch": 0.7255573650811479,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004957435945080512,
|
|
"loss": 5.4358,
|
|
"mean_token_accuracy": 0.19213946908712387,
|
|
"num_tokens": 14423614.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.5610638618469235,
|
|
"epoch": 0.7261189419891054,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004957358186280839,
|
|
"loss": 5.4092,
|
|
"mean_token_accuracy": 0.18669372648000718,
|
|
"num_tokens": 14434830.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.5573282718658445,
|
|
"epoch": 0.726680518897063,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004957280357198026,
|
|
"loss": 5.443,
|
|
"mean_token_accuracy": 0.18869293481111526,
|
|
"num_tokens": 14445015.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.619374179840088,
|
|
"epoch": 0.7272420958050205,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004957202457834551,
|
|
"loss": 5.545,
|
|
"mean_token_accuracy": 0.17871332168579102,
|
|
"num_tokens": 14455809.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.612972593307495,
|
|
"epoch": 0.7278036727129781,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004957124488192893,
|
|
"loss": 5.3051,
|
|
"mean_token_accuracy": 0.20037926733493805,
|
|
"num_tokens": 14466565.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.583424758911133,
|
|
"epoch": 0.7283652496209356,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004957046448275535,
|
|
"loss": 5.4051,
|
|
"mean_token_accuracy": 0.19647229909896852,
|
|
"num_tokens": 14477383.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.5140275955200195,
|
|
"epoch": 0.7289268265288932,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004956968338084961,
|
|
"loss": 5.3961,
|
|
"mean_token_accuracy": 0.19006068855524064,
|
|
"num_tokens": 14489968.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.6003580570220945,
|
|
"epoch": 0.7294884034368507,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004956890157623661,
|
|
"loss": 5.4535,
|
|
"mean_token_accuracy": 0.1879394993185997,
|
|
"num_tokens": 14500808.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.547910356521607,
|
|
"epoch": 0.7300499803448082,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004956811906894122,
|
|
"loss": 5.4572,
|
|
"mean_token_accuracy": 0.1888415828347206,
|
|
"num_tokens": 14511444.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.5708457946777346,
|
|
"epoch": 0.7306115572527657,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004956733585898836,
|
|
"loss": 5.3589,
|
|
"mean_token_accuracy": 0.19092436581850053,
|
|
"num_tokens": 14522562.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.524218368530273,
|
|
"epoch": 0.7311731341607233,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004956655194640297,
|
|
"loss": 5.4033,
|
|
"mean_token_accuracy": 0.18657224774360656,
|
|
"num_tokens": 14533497.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.559765386581421,
|
|
"epoch": 0.7317347110686808,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004956576733121,
|
|
"loss": 5.4253,
|
|
"mean_token_accuracy": 0.18306263387203217,
|
|
"num_tokens": 14545637.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.603921270370483,
|
|
"epoch": 0.7322962879766384,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004956498201343444,
|
|
"loss": 5.4155,
|
|
"mean_token_accuracy": 0.18643435686826706,
|
|
"num_tokens": 14556826.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.49514331817627,
|
|
"epoch": 0.7328578648845959,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000495641959931013,
|
|
"loss": 5.3596,
|
|
"mean_token_accuracy": 0.18760323375463486,
|
|
"num_tokens": 14567315.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.547469234466552,
|
|
"epoch": 0.7334194417925535,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004956340927023561,
|
|
"loss": 5.4247,
|
|
"mean_token_accuracy": 0.18974489718675613,
|
|
"num_tokens": 14577685.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.572555875778198,
|
|
"epoch": 0.733981018700511,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000495626218448624,
|
|
"loss": 5.3799,
|
|
"mean_token_accuracy": 0.19248069375753402,
|
|
"num_tokens": 14588885.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.600017261505127,
|
|
"epoch": 0.7345425956084686,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004956183371700676,
|
|
"loss": 5.4081,
|
|
"mean_token_accuracy": 0.1935748502612114,
|
|
"num_tokens": 14599774.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.628725242614746,
|
|
"epoch": 0.7351041725164261,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004956104488669377,
|
|
"loss": 5.4471,
|
|
"mean_token_accuracy": 0.18519861549139022,
|
|
"num_tokens": 14612101.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.661167860031128,
|
|
"epoch": 0.7356657494243837,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004956025535394856,
|
|
"loss": 5.519,
|
|
"mean_token_accuracy": 0.1750835120677948,
|
|
"num_tokens": 14622151.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.5682800769805905,
|
|
"epoch": 0.7362273263323412,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004955946511879626,
|
|
"loss": 5.4037,
|
|
"mean_token_accuracy": 0.18312456905841829,
|
|
"num_tokens": 14634631.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.542213344573975,
|
|
"epoch": 0.7367889032402988,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004955867418126205,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.1886059269309044,
|
|
"num_tokens": 14645429.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.521846008300781,
|
|
"epoch": 0.7373504801482563,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004955788254137108,
|
|
"loss": 5.3583,
|
|
"mean_token_accuracy": 0.19451422840356827,
|
|
"num_tokens": 14657309.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.505011129379272,
|
|
"epoch": 0.7379120570562139,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004955709019914857,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.1937410607933998,
|
|
"num_tokens": 14668578.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.569357442855835,
|
|
"epoch": 0.7384736339641714,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004955629715461977,
|
|
"loss": 5.5221,
|
|
"mean_token_accuracy": 0.18763448297977448,
|
|
"num_tokens": 14679120.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.629948091506958,
|
|
"epoch": 0.739035210872129,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004955550340780991,
|
|
"loss": 5.4717,
|
|
"mean_token_accuracy": 0.18317111879587172,
|
|
"num_tokens": 14690849.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.589046144485474,
|
|
"epoch": 0.7395967877800865,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004955470895874427,
|
|
"loss": 5.4297,
|
|
"mean_token_accuracy": 0.18859443962574005,
|
|
"num_tokens": 14702431.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.465069723129273,
|
|
"epoch": 0.7401583646880441,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004955391380744813,
|
|
"loss": 5.3306,
|
|
"mean_token_accuracy": 0.1946323871612549,
|
|
"num_tokens": 14714271.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.518150568008423,
|
|
"epoch": 0.7407199415960015,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004955311795394684,
|
|
"loss": 5.4504,
|
|
"mean_token_accuracy": 0.19020374566316606,
|
|
"num_tokens": 14724796.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.5341894149780275,
|
|
"epoch": 0.7412815185039591,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000495523213982657,
|
|
"loss": 5.3861,
|
|
"mean_token_accuracy": 0.18682342320680617,
|
|
"num_tokens": 14735331.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.659159135818482,
|
|
"epoch": 0.7418430954119166,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004955152414043011,
|
|
"loss": 5.4613,
|
|
"mean_token_accuracy": 0.18522186428308487,
|
|
"num_tokens": 14748595.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.600618886947632,
|
|
"epoch": 0.7424046723198742,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004955072618046543,
|
|
"loss": 5.3706,
|
|
"mean_token_accuracy": 0.18925037682056428,
|
|
"num_tokens": 14759501.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.455843830108643,
|
|
"epoch": 0.7429662492278317,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004954992751839708,
|
|
"loss": 5.4301,
|
|
"mean_token_accuracy": 0.19183726012706756,
|
|
"num_tokens": 14769752.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.5726597785949705,
|
|
"epoch": 0.7435278261357893,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004954912815425048,
|
|
"loss": 5.3623,
|
|
"mean_token_accuracy": 0.19258251041173935,
|
|
"num_tokens": 14781166.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.4954887390136715,
|
|
"epoch": 0.7440894030437468,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000495483280880511,
|
|
"loss": 5.2698,
|
|
"mean_token_accuracy": 0.19690830111503602,
|
|
"num_tokens": 14790536.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.588681983947754,
|
|
"epoch": 0.7446509799517044,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000495475273198244,
|
|
"loss": 5.4871,
|
|
"mean_token_accuracy": 0.18325650095939636,
|
|
"num_tokens": 14801673.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.573399448394776,
|
|
"epoch": 0.7452125568596619,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004954672584959588,
|
|
"loss": 5.3765,
|
|
"mean_token_accuracy": 0.18690255433320999,
|
|
"num_tokens": 14812345.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.62178111076355,
|
|
"epoch": 0.7457741337676195,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004954592367739104,
|
|
"loss": 5.5528,
|
|
"mean_token_accuracy": 0.18060370683670043,
|
|
"num_tokens": 14823620.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.566000509262085,
|
|
"epoch": 0.746335710675577,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004954512080323546,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.19653813689947128,
|
|
"num_tokens": 14833487.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.434810543060303,
|
|
"epoch": 0.7468972875835346,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004954431722715468,
|
|
"loss": 5.2261,
|
|
"mean_token_accuracy": 0.19704335033893586,
|
|
"num_tokens": 14844421.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.472637557983399,
|
|
"epoch": 0.7474588644914921,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004954351294917428,
|
|
"loss": 5.4071,
|
|
"mean_token_accuracy": 0.19750991612672805,
|
|
"num_tokens": 14855525.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.626046895980835,
|
|
"epoch": 0.7480204413994497,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004954270796931989,
|
|
"loss": 5.4507,
|
|
"mean_token_accuracy": 0.1893661677837372,
|
|
"num_tokens": 14866717.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.528974771499634,
|
|
"epoch": 0.7485820183074072,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004954190228761712,
|
|
"loss": 5.3667,
|
|
"mean_token_accuracy": 0.1851828545331955,
|
|
"num_tokens": 14877372.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.5370550632476805,
|
|
"epoch": 0.7491435952153648,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004954109590409164,
|
|
"loss": 5.4143,
|
|
"mean_token_accuracy": 0.18978495597839357,
|
|
"num_tokens": 14888618.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.5310461044311525,
|
|
"epoch": 0.7497051721233223,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004954028881876911,
|
|
"loss": 5.4265,
|
|
"mean_token_accuracy": 0.18488093167543412,
|
|
"num_tokens": 14900421.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.569034290313721,
|
|
"epoch": 0.7502667490312799,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004953948103167524,
|
|
"loss": 5.395,
|
|
"mean_token_accuracy": 0.1861965164542198,
|
|
"num_tokens": 14910634.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.6285967350006105,
|
|
"epoch": 0.7508283259392374,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004953867254283575,
|
|
"loss": 5.4555,
|
|
"mean_token_accuracy": 0.18458913266658783,
|
|
"num_tokens": 14921408.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.571818542480469,
|
|
"epoch": 0.7513899028471949,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004953786335227636,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.19003868997097015,
|
|
"num_tokens": 14933435.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.537566995620727,
|
|
"epoch": 0.7519514797551524,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004953705346002287,
|
|
"loss": 5.4524,
|
|
"mean_token_accuracy": 0.18646232038736343,
|
|
"num_tokens": 14946488.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.551724195480347,
|
|
"epoch": 0.75251305666311,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004953624286610106,
|
|
"loss": 5.3194,
|
|
"mean_token_accuracy": 0.19105692356824874,
|
|
"num_tokens": 14958053.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.557274389266968,
|
|
"epoch": 0.7530746335710675,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004953543157053672,
|
|
"loss": 5.3849,
|
|
"mean_token_accuracy": 0.18780029714107513,
|
|
"num_tokens": 14968922.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.550119066238404,
|
|
"epoch": 0.7536362104790251,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004953461957335569,
|
|
"loss": 5.4083,
|
|
"mean_token_accuracy": 0.1934783563017845,
|
|
"num_tokens": 14979541.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.5849934101104735,
|
|
"epoch": 0.7541977873869826,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004953380687458382,
|
|
"loss": 5.4127,
|
|
"mean_token_accuracy": 0.18646025508642197,
|
|
"num_tokens": 14990009.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.512436628341675,
|
|
"epoch": 0.7547593642949402,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004953299347424701,
|
|
"loss": 5.4081,
|
|
"mean_token_accuracy": 0.1883482962846756,
|
|
"num_tokens": 15001712.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.5713903427124025,
|
|
"epoch": 0.7553209412028977,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004953217937237114,
|
|
"loss": 5.367,
|
|
"mean_token_accuracy": 0.19454659521579742,
|
|
"num_tokens": 15012574.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.48911452293396,
|
|
"epoch": 0.7558825181108553,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004953136456898212,
|
|
"loss": 5.3695,
|
|
"mean_token_accuracy": 0.1913204848766327,
|
|
"num_tokens": 15023034.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.623052501678467,
|
|
"epoch": 0.7564440950188128,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004953054906410593,
|
|
"loss": 5.4206,
|
|
"mean_token_accuracy": 0.18837956637144088,
|
|
"num_tokens": 15033925.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.5848432064056395,
|
|
"epoch": 0.7570056719267704,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004952973285776848,
|
|
"loss": 5.4134,
|
|
"mean_token_accuracy": 0.19637832492589952,
|
|
"num_tokens": 15044947.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.5618785381317135,
|
|
"epoch": 0.7575672488347279,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004952891594999582,
|
|
"loss": 5.3211,
|
|
"mean_token_accuracy": 0.1985709175467491,
|
|
"num_tokens": 15054784.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.5245020389556885,
|
|
"epoch": 0.7581288257426855,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004952809834081392,
|
|
"loss": 5.4005,
|
|
"mean_token_accuracy": 0.18477832973003389,
|
|
"num_tokens": 15066272.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.5647424221038815,
|
|
"epoch": 0.758690402650643,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004952728003024883,
|
|
"loss": 5.4776,
|
|
"mean_token_accuracy": 0.18543320745229722,
|
|
"num_tokens": 15079504.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.603858995437622,
|
|
"epoch": 0.7592519795586006,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004952646101832659,
|
|
"loss": 5.4143,
|
|
"mean_token_accuracy": 0.1918395146727562,
|
|
"num_tokens": 15089623.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.50961480140686,
|
|
"epoch": 0.7598135564665581,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004952564130507331,
|
|
"loss": 5.3154,
|
|
"mean_token_accuracy": 0.1919368550181389,
|
|
"num_tokens": 15100816.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.524628400802612,
|
|
"epoch": 0.7603751333745157,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004952482089051506,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.19635622650384904,
|
|
"num_tokens": 15111697.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.548503875732422,
|
|
"epoch": 0.7609367102824732,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004952399977467796,
|
|
"loss": 5.4877,
|
|
"mean_token_accuracy": 0.18239143043756484,
|
|
"num_tokens": 15122869.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.499809646606446,
|
|
"epoch": 0.7614982871904308,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004952317795758817,
|
|
"loss": 5.2861,
|
|
"mean_token_accuracy": 0.1911429449915886,
|
|
"num_tokens": 15134709.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.527266597747802,
|
|
"epoch": 0.7620598640983883,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004952235543927185,
|
|
"loss": 5.2965,
|
|
"mean_token_accuracy": 0.1974724605679512,
|
|
"num_tokens": 15145319.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.520294809341431,
|
|
"epoch": 0.7626214410063458,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000495215322197552,
|
|
"loss": 5.352,
|
|
"mean_token_accuracy": 0.18900242298841477,
|
|
"num_tokens": 15156463.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.620303964614868,
|
|
"epoch": 0.7631830179143033,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004952070829906442,
|
|
"loss": 5.4938,
|
|
"mean_token_accuracy": 0.17575843557715415,
|
|
"num_tokens": 15167618.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.608112096786499,
|
|
"epoch": 0.7637445948222609,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004951988367722574,
|
|
"loss": 5.4301,
|
|
"mean_token_accuracy": 0.1902905896306038,
|
|
"num_tokens": 15179312.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.493063926696777,
|
|
"epoch": 0.7643061717302184,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004951905835426544,
|
|
"loss": 5.3797,
|
|
"mean_token_accuracy": 0.1939145416021347,
|
|
"num_tokens": 15191370.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.606846714019776,
|
|
"epoch": 0.764867748638176,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004951823233020976,
|
|
"loss": 5.3275,
|
|
"mean_token_accuracy": 0.19638228565454482,
|
|
"num_tokens": 15201060.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.475592184066772,
|
|
"epoch": 0.7654293255461335,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004951740560508504,
|
|
"loss": 5.2656,
|
|
"mean_token_accuracy": 0.19386058747768403,
|
|
"num_tokens": 15212186.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.489868545532227,
|
|
"epoch": 0.7659909024540911,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004951657817891758,
|
|
"loss": 5.2892,
|
|
"mean_token_accuracy": 0.19804201722145082,
|
|
"num_tokens": 15223301.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.52301549911499,
|
|
"epoch": 0.7665524793620486,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004951575005173373,
|
|
"loss": 5.4391,
|
|
"mean_token_accuracy": 0.18734809756278992,
|
|
"num_tokens": 15234475.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.575947284698486,
|
|
"epoch": 0.7671140562700062,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004951492122355986,
|
|
"loss": 5.4062,
|
|
"mean_token_accuracy": 0.1875208780169487,
|
|
"num_tokens": 15245877.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.627669906616211,
|
|
"epoch": 0.7676756331779637,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004951409169442236,
|
|
"loss": 5.4073,
|
|
"mean_token_accuracy": 0.190565824508667,
|
|
"num_tokens": 15257375.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.575936651229858,
|
|
"epoch": 0.7682372100859213,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004951326146434765,
|
|
"loss": 5.4183,
|
|
"mean_token_accuracy": 0.1895638108253479,
|
|
"num_tokens": 15268079.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.491517400741577,
|
|
"epoch": 0.7687987869938788,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004951243053336214,
|
|
"loss": 5.4063,
|
|
"mean_token_accuracy": 0.18927390575408937,
|
|
"num_tokens": 15278678.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.618205642700195,
|
|
"epoch": 0.7693603639018364,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004951159890149232,
|
|
"loss": 5.5076,
|
|
"mean_token_accuracy": 0.1865157887339592,
|
|
"num_tokens": 15290080.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.583620357513428,
|
|
"epoch": 0.7699219408097939,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004951076656876466,
|
|
"loss": 5.432,
|
|
"mean_token_accuracy": 0.18702781349420547,
|
|
"num_tokens": 15300602.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.594201231002808,
|
|
"epoch": 0.7704835177177515,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004950993353520564,
|
|
"loss": 5.4349,
|
|
"mean_token_accuracy": 0.19131208211183548,
|
|
"num_tokens": 15312823.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.634102821350098,
|
|
"epoch": 0.771045094625709,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000495090998008418,
|
|
"loss": 5.4441,
|
|
"mean_token_accuracy": 0.18723303079605103,
|
|
"num_tokens": 15323870.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.4997388362884525,
|
|
"epoch": 0.7716066715336666,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000495082653656997,
|
|
"loss": 5.3302,
|
|
"mean_token_accuracy": 0.1965235248208046,
|
|
"num_tokens": 15334887.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.572580862045288,
|
|
"epoch": 0.7721682484416241,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004950743022980587,
|
|
"loss": 5.4373,
|
|
"mean_token_accuracy": 0.18693511039018632,
|
|
"num_tokens": 15345871.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.509525918960572,
|
|
"epoch": 0.7727298253495817,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004950659439318696,
|
|
"loss": 5.2795,
|
|
"mean_token_accuracy": 0.1993497222661972,
|
|
"num_tokens": 15356530.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.530187654495239,
|
|
"epoch": 0.7732914022575391,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004950575785586952,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.19166866093873977,
|
|
"num_tokens": 15368756.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.612720966339111,
|
|
"epoch": 0.7738529791654967,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004950492061788023,
|
|
"loss": 5.4484,
|
|
"mean_token_accuracy": 0.1904335215687752,
|
|
"num_tokens": 15379450.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.519256973266602,
|
|
"epoch": 0.7744145560734542,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004950408267924573,
|
|
"loss": 5.3537,
|
|
"mean_token_accuracy": 0.1858827590942383,
|
|
"num_tokens": 15389501.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.385013151168823,
|
|
"epoch": 0.7749761329814118,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004950324403999271,
|
|
"loss": 5.3646,
|
|
"mean_token_accuracy": 0.19009243696928024,
|
|
"num_tokens": 15400608.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.608634376525879,
|
|
"epoch": 0.7755377098893693,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004950240470014785,
|
|
"loss": 5.4393,
|
|
"mean_token_accuracy": 0.1848304584622383,
|
|
"num_tokens": 15411709.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.53405122756958,
|
|
"epoch": 0.7760992867973269,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004950156465973791,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.19948293417692184,
|
|
"num_tokens": 15422292.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.550871086120606,
|
|
"epoch": 0.7766608637052844,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000495007239187896,
|
|
"loss": 5.4532,
|
|
"mean_token_accuracy": 0.18661819994449616,
|
|
"num_tokens": 15434439.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.514196968078613,
|
|
"epoch": 0.777222440613242,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004949988247732972,
|
|
"loss": 5.3966,
|
|
"mean_token_accuracy": 0.19032733142375946,
|
|
"num_tokens": 15445480.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.508719158172608,
|
|
"epoch": 0.7777840175211995,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004949904033538504,
|
|
"loss": 5.3857,
|
|
"mean_token_accuracy": 0.19126745760440828,
|
|
"num_tokens": 15456960.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.510855197906494,
|
|
"epoch": 0.7783455944291571,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000494981974929824,
|
|
"loss": 5.3858,
|
|
"mean_token_accuracy": 0.18876940459012986,
|
|
"num_tokens": 15468169.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.550881004333496,
|
|
"epoch": 0.7789071713371146,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000494973539501486,
|
|
"loss": 5.3383,
|
|
"mean_token_accuracy": 0.1927856683731079,
|
|
"num_tokens": 15478740.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.555187034606933,
|
|
"epoch": 0.7794687482450722,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004949650970691052,
|
|
"loss": 5.4513,
|
|
"mean_token_accuracy": 0.18629500418901443,
|
|
"num_tokens": 15489705.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.4992107391357425,
|
|
"epoch": 0.7800303251530297,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004949566476329505,
|
|
"loss": 5.2956,
|
|
"mean_token_accuracy": 0.18771727234125138,
|
|
"num_tokens": 15500549.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.647176933288574,
|
|
"epoch": 0.7805919020609873,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004949481911932908,
|
|
"loss": 5.4289,
|
|
"mean_token_accuracy": 0.18746083974838257,
|
|
"num_tokens": 15511124.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.5008502960205075,
|
|
"epoch": 0.7811534789689448,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004949397277503954,
|
|
"loss": 5.3351,
|
|
"mean_token_accuracy": 0.1971758633852005,
|
|
"num_tokens": 15521810.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.530869197845459,
|
|
"epoch": 0.7817150558769024,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004949312573045338,
|
|
"loss": 5.3992,
|
|
"mean_token_accuracy": 0.1918172210454941,
|
|
"num_tokens": 15533108.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.530841445922851,
|
|
"epoch": 0.7822766327848599,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004949227798559757,
|
|
"loss": 5.4111,
|
|
"mean_token_accuracy": 0.1919243112206459,
|
|
"num_tokens": 15544841.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.560785245895386,
|
|
"epoch": 0.7828382096928175,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004949142954049909,
|
|
"loss": 5.4083,
|
|
"mean_token_accuracy": 0.18217880874872208,
|
|
"num_tokens": 15556297.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.5459887981414795,
|
|
"epoch": 0.783399786600775,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004949058039518496,
|
|
"loss": 5.2868,
|
|
"mean_token_accuracy": 0.19351261705160142,
|
|
"num_tokens": 15566607.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.55396466255188,
|
|
"epoch": 0.7839613635087325,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004948973054968222,
|
|
"loss": 5.4688,
|
|
"mean_token_accuracy": 0.18487369418144226,
|
|
"num_tokens": 15577435.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.538680505752564,
|
|
"epoch": 0.78452294041669,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004948888000401794,
|
|
"loss": 5.3663,
|
|
"mean_token_accuracy": 0.1931474909186363,
|
|
"num_tokens": 15587844.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.637773132324218,
|
|
"epoch": 0.7850845173246476,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004948802875821918,
|
|
"loss": 5.4324,
|
|
"mean_token_accuracy": 0.18827223032712936,
|
|
"num_tokens": 15599586.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.513357830047608,
|
|
"epoch": 0.7856460942326051,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004948717681231308,
|
|
"loss": 5.318,
|
|
"mean_token_accuracy": 0.18972791731357574,
|
|
"num_tokens": 15610838.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.547962617874146,
|
|
"epoch": 0.7862076711405627,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004948632416632672,
|
|
"loss": 5.4026,
|
|
"mean_token_accuracy": 0.19327963143587112,
|
|
"num_tokens": 15622652.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.64856448173523,
|
|
"epoch": 0.7867692480485202,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004948547082028728,
|
|
"loss": 5.4897,
|
|
"mean_token_accuracy": 0.18318869769573212,
|
|
"num_tokens": 15634280.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.4800700664520265,
|
|
"epoch": 0.7873308249564778,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004948461677422193,
|
|
"loss": 5.2215,
|
|
"mean_token_accuracy": 0.199824021756649,
|
|
"num_tokens": 15644088.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.486963939666748,
|
|
"epoch": 0.7878924018644353,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004948376202815785,
|
|
"loss": 5.4564,
|
|
"mean_token_accuracy": 0.1799951523542404,
|
|
"num_tokens": 15654968.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.549936771392822,
|
|
"epoch": 0.7884539787723929,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004948290658212225,
|
|
"loss": 5.3667,
|
|
"mean_token_accuracy": 0.19336676746606826,
|
|
"num_tokens": 15666758.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.424612140655517,
|
|
"epoch": 0.7890155556803504,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004948205043614239,
|
|
"loss": 5.213,
|
|
"mean_token_accuracy": 0.19932689517736435,
|
|
"num_tokens": 15677295.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.5242737293243405,
|
|
"epoch": 0.789577132588308,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004948119359024551,
|
|
"loss": 5.4261,
|
|
"mean_token_accuracy": 0.19343287497758865,
|
|
"num_tokens": 15689508.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.58857364654541,
|
|
"epoch": 0.7901387094962655,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004948033604445891,
|
|
"loss": 5.3808,
|
|
"mean_token_accuracy": 0.19007019251585006,
|
|
"num_tokens": 15701289.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.494377374649048,
|
|
"epoch": 0.7907002864042231,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004947947779880988,
|
|
"loss": 5.336,
|
|
"mean_token_accuracy": 0.19051492512226104,
|
|
"num_tokens": 15711579.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.527608489990234,
|
|
"epoch": 0.7912618633121806,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004947861885332576,
|
|
"loss": 5.4217,
|
|
"mean_token_accuracy": 0.19214471131563188,
|
|
"num_tokens": 15722629.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.557682180404663,
|
|
"epoch": 0.7918234402201382,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004947775920803388,
|
|
"loss": 5.3596,
|
|
"mean_token_accuracy": 0.18356509059667586,
|
|
"num_tokens": 15735818.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.512237167358398,
|
|
"epoch": 0.7923850171280957,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004947689886296162,
|
|
"loss": 5.4147,
|
|
"mean_token_accuracy": 0.1895158275961876,
|
|
"num_tokens": 15746914.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.513495969772339,
|
|
"epoch": 0.7929465940360533,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000494760378181364,
|
|
"loss": 5.3162,
|
|
"mean_token_accuracy": 0.18762257397174836,
|
|
"num_tokens": 15757597.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.458051300048828,
|
|
"epoch": 0.7935081709440108,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004947517607358559,
|
|
"loss": 5.2458,
|
|
"mean_token_accuracy": 0.19967395961284637,
|
|
"num_tokens": 15768860.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.538003635406494,
|
|
"epoch": 0.7940697478519684,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004947431362933666,
|
|
"loss": 5.3602,
|
|
"mean_token_accuracy": 0.19036328196525573,
|
|
"num_tokens": 15779476.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.519798755645752,
|
|
"epoch": 0.7946313247599258,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004947345048541706,
|
|
"loss": 5.4229,
|
|
"mean_token_accuracy": 0.185899318754673,
|
|
"num_tokens": 15792142.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.565739440917969,
|
|
"epoch": 0.7951929016678834,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004947258664185427,
|
|
"loss": 5.3904,
|
|
"mean_token_accuracy": 0.1878409206867218,
|
|
"num_tokens": 15802307.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.5143050193786625,
|
|
"epoch": 0.7957544785758409,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004947172209867581,
|
|
"loss": 5.3508,
|
|
"mean_token_accuracy": 0.18899307996034623,
|
|
"num_tokens": 15812986.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.46642804145813,
|
|
"epoch": 0.7963160554837985,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004947085685590919,
|
|
"loss": 5.3079,
|
|
"mean_token_accuracy": 0.19560994058847428,
|
|
"num_tokens": 15823938.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.463511753082275,
|
|
"epoch": 0.796877632391756,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004946999091358196,
|
|
"loss": 5.294,
|
|
"mean_token_accuracy": 0.19440711587667464,
|
|
"num_tokens": 15835813.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.563611745834351,
|
|
"epoch": 0.7974392092997136,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000494691242717217,
|
|
"loss": 5.3676,
|
|
"mean_token_accuracy": 0.19473447799682617,
|
|
"num_tokens": 15846203.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.548427248001099,
|
|
"epoch": 0.7980007862076711,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004946825693035601,
|
|
"loss": 5.3116,
|
|
"mean_token_accuracy": 0.1960406556725502,
|
|
"num_tokens": 15856919.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.528464078903198,
|
|
"epoch": 0.7985623631156287,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000494673888895125,
|
|
"loss": 5.4381,
|
|
"mean_token_accuracy": 0.18583116829395294,
|
|
"num_tokens": 15867149.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.451193571090698,
|
|
"epoch": 0.7991239400235862,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004946652014921881,
|
|
"loss": 5.3199,
|
|
"mean_token_accuracy": 0.1911962777376175,
|
|
"num_tokens": 15877229.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.534007453918457,
|
|
"epoch": 0.7996855169315438,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004946565070950259,
|
|
"loss": 5.3105,
|
|
"mean_token_accuracy": 0.1942991554737091,
|
|
"num_tokens": 15888799.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.453420400619507,
|
|
"epoch": 0.8002470938395013,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004946478057039153,
|
|
"loss": 5.2998,
|
|
"mean_token_accuracy": 0.20614445805549622,
|
|
"num_tokens": 15900144.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.5438392639160154,
|
|
"epoch": 0.8008086707474589,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004946390973191335,
|
|
"loss": 5.4826,
|
|
"mean_token_accuracy": 0.18744038939476013,
|
|
"num_tokens": 15912030.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.532735061645508,
|
|
"epoch": 0.8013702476554164,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004946303819409575,
|
|
"loss": 5.3432,
|
|
"mean_token_accuracy": 0.19349053651094436,
|
|
"num_tokens": 15923606.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.513996839523315,
|
|
"epoch": 0.801931824563374,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004946216595696652,
|
|
"loss": 5.3457,
|
|
"mean_token_accuracy": 0.19366424530744553,
|
|
"num_tokens": 15935077.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.463584470748901,
|
|
"epoch": 0.8024934014713315,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004946129302055338,
|
|
"loss": 5.2792,
|
|
"mean_token_accuracy": 0.19784001410007476,
|
|
"num_tokens": 15945331.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.484343242645264,
|
|
"epoch": 0.8030549783792891,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004946041938488417,
|
|
"loss": 5.3751,
|
|
"mean_token_accuracy": 0.1876963496208191,
|
|
"num_tokens": 15957031.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.553222417831421,
|
|
"epoch": 0.8036165552872466,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004945954504998668,
|
|
"loss": 5.3959,
|
|
"mean_token_accuracy": 0.19386137425899505,
|
|
"num_tokens": 15967545.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.667354869842529,
|
|
"epoch": 0.8041781321952042,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004945867001588877,
|
|
"loss": 5.4384,
|
|
"mean_token_accuracy": 0.18039540499448775,
|
|
"num_tokens": 15978700.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.5349548816680905,
|
|
"epoch": 0.8047397091031617,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004945779428261827,
|
|
"loss": 5.3387,
|
|
"mean_token_accuracy": 0.1968977376818657,
|
|
"num_tokens": 15989712.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.606640815734863,
|
|
"epoch": 0.8053012860111193,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.000494569178502031,
|
|
"loss": 5.551,
|
|
"mean_token_accuracy": 0.18528392165899277,
|
|
"num_tokens": 16002380.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.566968727111816,
|
|
"epoch": 0.8058628629190767,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004945604071867114,
|
|
"loss": 5.3175,
|
|
"mean_token_accuracy": 0.1930129960179329,
|
|
"num_tokens": 16013749.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.561373567581176,
|
|
"epoch": 0.8064244398270343,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004945516288805035,
|
|
"loss": 5.5018,
|
|
"mean_token_accuracy": 0.1882968232035637,
|
|
"num_tokens": 16025131.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.568534517288208,
|
|
"epoch": 0.8069860167349918,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004945428435836864,
|
|
"loss": 5.3688,
|
|
"mean_token_accuracy": 0.1933572143316269,
|
|
"num_tokens": 16037269.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.671428966522217,
|
|
"epoch": 0.8075475936429494,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004945340512965401,
|
|
"loss": 5.5666,
|
|
"mean_token_accuracy": 0.17810628414154053,
|
|
"num_tokens": 16050992.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.507680368423462,
|
|
"epoch": 0.8081091705509069,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004945252520193443,
|
|
"loss": 5.3812,
|
|
"mean_token_accuracy": 0.18824538588523865,
|
|
"num_tokens": 16062309.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.600071954727173,
|
|
"epoch": 0.8086707474588645,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004945164457523795,
|
|
"loss": 5.4184,
|
|
"mean_token_accuracy": 0.18918824046850205,
|
|
"num_tokens": 16073079.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.570611572265625,
|
|
"epoch": 0.809232324366822,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004945076324959258,
|
|
"loss": 5.3146,
|
|
"mean_token_accuracy": 0.1991833671927452,
|
|
"num_tokens": 16082885.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.431540012359619,
|
|
"epoch": 0.8097939012747796,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004944988122502641,
|
|
"loss": 5.2685,
|
|
"mean_token_accuracy": 0.20003439486026764,
|
|
"num_tokens": 16094173.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.469393920898438,
|
|
"epoch": 0.8103554781827371,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000494489985015675,
|
|
"loss": 5.3326,
|
|
"mean_token_accuracy": 0.19339679181575775,
|
|
"num_tokens": 16106351.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.4503538608551025,
|
|
"epoch": 0.8109170550906947,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004944811507924396,
|
|
"loss": 5.3145,
|
|
"mean_token_accuracy": 0.1912689507007599,
|
|
"num_tokens": 16116892.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.6118786334991455,
|
|
"epoch": 0.8114786319986522,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004944723095808393,
|
|
"loss": 5.4661,
|
|
"mean_token_accuracy": 0.18370114117860795,
|
|
"num_tokens": 16128316.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.521116590499878,
|
|
"epoch": 0.8120402089066098,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004944634613811555,
|
|
"loss": 5.2968,
|
|
"mean_token_accuracy": 0.19552281200885774,
|
|
"num_tokens": 16139245.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.5180247783660885,
|
|
"epoch": 0.8126017858145673,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00049445460619367,
|
|
"loss": 5.3374,
|
|
"mean_token_accuracy": 0.1948014661669731,
|
|
"num_tokens": 16150893.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.5881579399108885,
|
|
"epoch": 0.8131633627225249,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004944457440186648,
|
|
"loss": 5.4639,
|
|
"mean_token_accuracy": 0.17190439850091935,
|
|
"num_tokens": 16163430.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.57142825126648,
|
|
"epoch": 0.8137249396304824,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004944368748564219,
|
|
"loss": 5.3525,
|
|
"mean_token_accuracy": 0.1935686409473419,
|
|
"num_tokens": 16173954.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.552434825897217,
|
|
"epoch": 0.81428651653844,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004944279987072238,
|
|
"loss": 5.4205,
|
|
"mean_token_accuracy": 0.185828697681427,
|
|
"num_tokens": 16185491.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.450665426254273,
|
|
"epoch": 0.8148480934463975,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004944191155713531,
|
|
"loss": 5.267,
|
|
"mean_token_accuracy": 0.20237178206443787,
|
|
"num_tokens": 16195301.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.556926202774048,
|
|
"epoch": 0.8154096703543551,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004944102254490928,
|
|
"loss": 5.3913,
|
|
"mean_token_accuracy": 0.1841839298605919,
|
|
"num_tokens": 16206620.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.5046991348266605,
|
|
"epoch": 0.8159712472623126,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004944013283407257,
|
|
"loss": 5.4839,
|
|
"mean_token_accuracy": 0.1835168182849884,
|
|
"num_tokens": 16218693.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.570673894882202,
|
|
"epoch": 0.8165328241702701,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004943924242465352,
|
|
"loss": 5.3636,
|
|
"mean_token_accuracy": 0.192826946079731,
|
|
"num_tokens": 16229124.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.52437915802002,
|
|
"epoch": 0.8170944010782276,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004943835131668049,
|
|
"loss": 5.3274,
|
|
"mean_token_accuracy": 0.19266424775123597,
|
|
"num_tokens": 16239999.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.519512367248535,
|
|
"epoch": 0.8176559779861852,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004943745951018184,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.19051078855991363,
|
|
"num_tokens": 16251027.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.564484930038452,
|
|
"epoch": 0.8182175548941427,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004943656700518597,
|
|
"loss": 5.3595,
|
|
"mean_token_accuracy": 0.19417764544486998,
|
|
"num_tokens": 16262924.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.636598253250122,
|
|
"epoch": 0.8187791318021003,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004943567380172129,
|
|
"loss": 5.4695,
|
|
"mean_token_accuracy": 0.1896255284547806,
|
|
"num_tokens": 16274481.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.530969762802124,
|
|
"epoch": 0.8193407087100578,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004943477989981627,
|
|
"loss": 5.4005,
|
|
"mean_token_accuracy": 0.19529114067554473,
|
|
"num_tokens": 16285214.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.5609289646148685,
|
|
"epoch": 0.8199022856180154,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004943388529949933,
|
|
"loss": 5.4643,
|
|
"mean_token_accuracy": 0.18784563839435578,
|
|
"num_tokens": 16296077.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.588407897949219,
|
|
"epoch": 0.8204638625259729,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004943299000079899,
|
|
"loss": 5.3795,
|
|
"mean_token_accuracy": 0.19368068128824234,
|
|
"num_tokens": 16307514.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.652513551712036,
|
|
"epoch": 0.8210254394339305,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004943209400374373,
|
|
"loss": 5.3754,
|
|
"mean_token_accuracy": 0.19173796027898787,
|
|
"num_tokens": 16318734.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.497101211547852,
|
|
"epoch": 0.821587016341888,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000494311973083621,
|
|
"loss": 5.4136,
|
|
"mean_token_accuracy": 0.18982843905687333,
|
|
"num_tokens": 16329057.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.501382112503052,
|
|
"epoch": 0.8221485932498456,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004943029991468264,
|
|
"loss": 5.3257,
|
|
"mean_token_accuracy": 0.19335218369960785,
|
|
"num_tokens": 16339646.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.582084655761719,
|
|
"epoch": 0.8227101701578031,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004942940182273393,
|
|
"loss": 5.4173,
|
|
"mean_token_accuracy": 0.18968148976564408,
|
|
"num_tokens": 16349783.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.5929333686828615,
|
|
"epoch": 0.8232717470657607,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004942850303254455,
|
|
"loss": 5.331,
|
|
"mean_token_accuracy": 0.1926446095108986,
|
|
"num_tokens": 16361078.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.478531408309936,
|
|
"epoch": 0.8238333239737182,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004942760354414313,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.19307311475276948,
|
|
"num_tokens": 16371308.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.527521324157715,
|
|
"epoch": 0.8243949008816758,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004942670335755831,
|
|
"loss": 5.3868,
|
|
"mean_token_accuracy": 0.19338780492544175,
|
|
"num_tokens": 16382682.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.605612945556641,
|
|
"epoch": 0.8249564777896333,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004942580247281876,
|
|
"loss": 5.4086,
|
|
"mean_token_accuracy": 0.19141978174448013,
|
|
"num_tokens": 16393715.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.468640565872192,
|
|
"epoch": 0.8255180546975909,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004942490088995315,
|
|
"loss": 5.3949,
|
|
"mean_token_accuracy": 0.19251279532909393,
|
|
"num_tokens": 16406332.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.5208453178405765,
|
|
"epoch": 0.8260796316055484,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004942399860899018,
|
|
"loss": 5.3301,
|
|
"mean_token_accuracy": 0.18916616588830948,
|
|
"num_tokens": 16417702.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.563840389251709,
|
|
"epoch": 0.826641208513506,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004942309562995862,
|
|
"loss": 5.3709,
|
|
"mean_token_accuracy": 0.19190021306276323,
|
|
"num_tokens": 16428497.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.543086099624634,
|
|
"epoch": 0.8272027854214634,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004942219195288716,
|
|
"loss": 5.3661,
|
|
"mean_token_accuracy": 0.1900161996483803,
|
|
"num_tokens": 16440637.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.521610069274902,
|
|
"epoch": 0.827764362329421,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004942128757780463,
|
|
"loss": 5.3881,
|
|
"mean_token_accuracy": 0.18313750624656677,
|
|
"num_tokens": 16453213.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.528475093841553,
|
|
"epoch": 0.8283259392373785,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004942038250473979,
|
|
"loss": 5.3975,
|
|
"mean_token_accuracy": 0.19446578472852707,
|
|
"num_tokens": 16464345.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.535910940170288,
|
|
"epoch": 0.8288875161453361,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004941947673372147,
|
|
"loss": 5.2892,
|
|
"mean_token_accuracy": 0.19729151874780654,
|
|
"num_tokens": 16475399.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.48125319480896,
|
|
"epoch": 0.8294490930532936,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004941857026477851,
|
|
"loss": 5.2577,
|
|
"mean_token_accuracy": 0.1967956691980362,
|
|
"num_tokens": 16485439.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.482007074356079,
|
|
"epoch": 0.8300106699612512,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004941766309793978,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.1964390233159065,
|
|
"num_tokens": 16496765.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.475945377349854,
|
|
"epoch": 0.8305722468692087,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004941675523323414,
|
|
"loss": 5.3035,
|
|
"mean_token_accuracy": 0.1950630024075508,
|
|
"num_tokens": 16509199.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.546600580215454,
|
|
"epoch": 0.8311338237771663,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004941584667069052,
|
|
"loss": 5.4583,
|
|
"mean_token_accuracy": 0.1897977501153946,
|
|
"num_tokens": 16520073.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.472220230102539,
|
|
"epoch": 0.8316954006851238,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004941493741033784,
|
|
"loss": 5.331,
|
|
"mean_token_accuracy": 0.19148144870996475,
|
|
"num_tokens": 16530919.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.536686372756958,
|
|
"epoch": 0.8322569775930814,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004941402745220507,
|
|
"loss": 5.3571,
|
|
"mean_token_accuracy": 0.19261872321367263,
|
|
"num_tokens": 16542591.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.57855257987976,
|
|
"epoch": 0.8328185545010389,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004941311679632115,
|
|
"loss": 5.3693,
|
|
"mean_token_accuracy": 0.19039538949728013,
|
|
"num_tokens": 16554984.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.433529186248779,
|
|
"epoch": 0.8333801314089965,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000494122054427151,
|
|
"loss": 5.2631,
|
|
"mean_token_accuracy": 0.19918903708457947,
|
|
"num_tokens": 16566598.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.60313572883606,
|
|
"epoch": 0.833941708316954,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004941129339141592,
|
|
"loss": 5.4063,
|
|
"mean_token_accuracy": 0.18586488366127013,
|
|
"num_tokens": 16577868.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.516066837310791,
|
|
"epoch": 0.8345032852249116,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004941038064245267,
|
|
"loss": 5.3602,
|
|
"mean_token_accuracy": 0.19123763740062713,
|
|
"num_tokens": 16587891.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.518604183197022,
|
|
"epoch": 0.8350648621328691,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000494094671958544,
|
|
"loss": 5.3008,
|
|
"mean_token_accuracy": 0.2017410770058632,
|
|
"num_tokens": 16599924.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.476879024505616,
|
|
"epoch": 0.8356264390408267,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004940855305165019,
|
|
"loss": 5.2494,
|
|
"mean_token_accuracy": 0.19790668934583663,
|
|
"num_tokens": 16609958.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.483253622055054,
|
|
"epoch": 0.8361880159487842,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004940763820986916,
|
|
"loss": 5.3777,
|
|
"mean_token_accuracy": 0.18868407756090164,
|
|
"num_tokens": 16621159.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.592933893203735,
|
|
"epoch": 0.8367495928567418,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004940672267054044,
|
|
"loss": 5.468,
|
|
"mean_token_accuracy": 0.19059434980154039,
|
|
"num_tokens": 16632263.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.529058313369751,
|
|
"epoch": 0.8373111697646993,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004940580643369316,
|
|
"loss": 5.3614,
|
|
"mean_token_accuracy": 0.18601302355527877,
|
|
"num_tokens": 16644117.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.427464723587036,
|
|
"epoch": 0.8378727466726568,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004940488949935651,
|
|
"loss": 5.2831,
|
|
"mean_token_accuracy": 0.19728361517190934,
|
|
"num_tokens": 16654529.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.473336267471313,
|
|
"epoch": 0.8384343235806143,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004940397186755968,
|
|
"loss": 5.3,
|
|
"mean_token_accuracy": 0.2006448820233345,
|
|
"num_tokens": 16666191.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.529743385314942,
|
|
"epoch": 0.8389959004885719,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004940305353833191,
|
|
"loss": 5.2796,
|
|
"mean_token_accuracy": 0.19333176612854003,
|
|
"num_tokens": 16677252.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.492028474807739,
|
|
"epoch": 0.8395574773965294,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000494021345117024,
|
|
"loss": 5.3378,
|
|
"mean_token_accuracy": 0.19180602729320526,
|
|
"num_tokens": 16689487.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.461004590988159,
|
|
"epoch": 0.840119054304487,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004940121478770044,
|
|
"loss": 5.2332,
|
|
"mean_token_accuracy": 0.19861174374818802,
|
|
"num_tokens": 16699955.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.393486642837525,
|
|
"epoch": 0.8406806312124445,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004940029436635531,
|
|
"loss": 5.2896,
|
|
"mean_token_accuracy": 0.18961472660303116,
|
|
"num_tokens": 16711071.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.430171346664428,
|
|
"epoch": 0.8412422081204021,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004939937324769631,
|
|
"loss": 5.2964,
|
|
"mean_token_accuracy": 0.194288931787014,
|
|
"num_tokens": 16722115.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.485861444473267,
|
|
"epoch": 0.8418037850283596,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004939845143175276,
|
|
"loss": 5.3248,
|
|
"mean_token_accuracy": 0.18838993161916734,
|
|
"num_tokens": 16733146.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.486392593383789,
|
|
"epoch": 0.8423653619363172,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004939752891855404,
|
|
"loss": 5.319,
|
|
"mean_token_accuracy": 0.19011340141296387,
|
|
"num_tokens": 16745543.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.540941953659058,
|
|
"epoch": 0.8429269388442747,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004939660570812951,
|
|
"loss": 5.3722,
|
|
"mean_token_accuracy": 0.1917041152715683,
|
|
"num_tokens": 16755782.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.617510795593262,
|
|
"epoch": 0.8434885157522323,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004939568180050855,
|
|
"loss": 5.4143,
|
|
"mean_token_accuracy": 0.18830805867910386,
|
|
"num_tokens": 16767509.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.4642973899841305,
|
|
"epoch": 0.8440500926601898,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004939475719572059,
|
|
"loss": 5.281,
|
|
"mean_token_accuracy": 0.19337462335824968,
|
|
"num_tokens": 16779257.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.441992902755738,
|
|
"epoch": 0.8446116695681474,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004939383189379507,
|
|
"loss": 5.3159,
|
|
"mean_token_accuracy": 0.1949651435017586,
|
|
"num_tokens": 16790769.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.51636118888855,
|
|
"epoch": 0.8451732464761049,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004939290589476145,
|
|
"loss": 5.31,
|
|
"mean_token_accuracy": 0.19314562678337097,
|
|
"num_tokens": 16800054.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.59525785446167,
|
|
"epoch": 0.8457348233840625,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004939197919864922,
|
|
"loss": 5.4189,
|
|
"mean_token_accuracy": 0.1875070497393608,
|
|
"num_tokens": 16811485.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.621941375732422,
|
|
"epoch": 0.84629640029202,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004939105180548788,
|
|
"loss": 5.4679,
|
|
"mean_token_accuracy": 0.19378382563591004,
|
|
"num_tokens": 16822683.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.537042951583862,
|
|
"epoch": 0.8468579771999776,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004939012371530696,
|
|
"loss": 5.3388,
|
|
"mean_token_accuracy": 0.19330107271671296,
|
|
"num_tokens": 16834200.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.543708467483521,
|
|
"epoch": 0.8474195541079351,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004938919492813601,
|
|
"loss": 5.3785,
|
|
"mean_token_accuracy": 0.18811353892087937,
|
|
"num_tokens": 16846399.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.649693870544434,
|
|
"epoch": 0.8479811310158927,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004938826544400461,
|
|
"loss": 5.5236,
|
|
"mean_token_accuracy": 0.1862836241722107,
|
|
"num_tokens": 16858322.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.560483121871949,
|
|
"epoch": 0.8485427079238502,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004938733526294234,
|
|
"loss": 5.3538,
|
|
"mean_token_accuracy": 0.19695565700531006,
|
|
"num_tokens": 16869537.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.6301332950592045,
|
|
"epoch": 0.8491042848318077,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004938640438497883,
|
|
"loss": 5.3907,
|
|
"mean_token_accuracy": 0.19266645312309266,
|
|
"num_tokens": 16881566.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.458097124099732,
|
|
"epoch": 0.8496658617397652,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004938547281014372,
|
|
"loss": 5.3145,
|
|
"mean_token_accuracy": 0.19759692400693893,
|
|
"num_tokens": 16892959.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.530508184432984,
|
|
"epoch": 0.8502274386477228,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004938454053846666,
|
|
"loss": 5.3778,
|
|
"mean_token_accuracy": 0.18589012324810028,
|
|
"num_tokens": 16904809.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.57429575920105,
|
|
"epoch": 0.8507890155556803,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004938360756997735,
|
|
"loss": 5.3971,
|
|
"mean_token_accuracy": 0.1847073659300804,
|
|
"num_tokens": 16916969.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.461697816848755,
|
|
"epoch": 0.8513505924636379,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004938267390470547,
|
|
"loss": 5.2724,
|
|
"mean_token_accuracy": 0.19852736294269563,
|
|
"num_tokens": 16928253.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.4836688995361325,
|
|
"epoch": 0.8519121693715954,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004938173954268079,
|
|
"loss": 5.3268,
|
|
"mean_token_accuracy": 0.19043341279029846,
|
|
"num_tokens": 16939875.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.629465341567993,
|
|
"epoch": 0.852473746279553,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004938080448393302,
|
|
"loss": 5.4481,
|
|
"mean_token_accuracy": 0.1888473078608513,
|
|
"num_tokens": 16950173.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.478756999969482,
|
|
"epoch": 0.8530353231875105,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004937986872849195,
|
|
"loss": 5.3698,
|
|
"mean_token_accuracy": 0.19270646274089814,
|
|
"num_tokens": 16960933.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.494446277618408,
|
|
"epoch": 0.8535969000954681,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004937893227638738,
|
|
"loss": 5.268,
|
|
"mean_token_accuracy": 0.19606069177389146,
|
|
"num_tokens": 16972284.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.510715007781982,
|
|
"epoch": 0.8541584770034256,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004937799512764912,
|
|
"loss": 5.2819,
|
|
"mean_token_accuracy": 0.19838723242282869,
|
|
"num_tokens": 16983541.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.545347261428833,
|
|
"epoch": 0.8547200539113832,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00049377057282307,
|
|
"loss": 5.4283,
|
|
"mean_token_accuracy": 0.18634025305509566,
|
|
"num_tokens": 16993773.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.615330791473388,
|
|
"epoch": 0.8552816308193407,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000493761187403909,
|
|
"loss": 5.4084,
|
|
"mean_token_accuracy": 0.19078975915908813,
|
|
"num_tokens": 17005287.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.548895788192749,
|
|
"epoch": 0.8558432077272983,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000493751795019307,
|
|
"loss": 5.3438,
|
|
"mean_token_accuracy": 0.18888139426708223,
|
|
"num_tokens": 17015664.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.490134954452515,
|
|
"epoch": 0.8564047846352558,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004937423956695629,
|
|
"loss": 5.2514,
|
|
"mean_token_accuracy": 0.19612780809402466,
|
|
"num_tokens": 17026876.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.466113615036011,
|
|
"epoch": 0.8569663615432134,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004937329893549762,
|
|
"loss": 5.3004,
|
|
"mean_token_accuracy": 0.2042296215891838,
|
|
"num_tokens": 17037321.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.507684326171875,
|
|
"epoch": 0.8575279384511709,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004937235760758462,
|
|
"loss": 5.3795,
|
|
"mean_token_accuracy": 0.19242687225341798,
|
|
"num_tokens": 17047506.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.560714054107666,
|
|
"epoch": 0.8580895153591285,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004937141558324726,
|
|
"loss": 5.4205,
|
|
"mean_token_accuracy": 0.19133085161447524,
|
|
"num_tokens": 17059710.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.57714581489563,
|
|
"epoch": 0.858651092267086,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004937047286251556,
|
|
"loss": 5.4412,
|
|
"mean_token_accuracy": 0.1824363186955452,
|
|
"num_tokens": 17070956.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.607796049118042,
|
|
"epoch": 0.8592126691750436,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004936952944541952,
|
|
"loss": 5.4052,
|
|
"mean_token_accuracy": 0.19116396307945252,
|
|
"num_tokens": 17081404.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.643889713287353,
|
|
"epoch": 0.859774246083001,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004936858533198917,
|
|
"loss": 5.4151,
|
|
"mean_token_accuracy": 0.19118166118860244,
|
|
"num_tokens": 17092692.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.4890522956848145,
|
|
"epoch": 0.8603358229909586,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000493676405222546,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.1976029172539711,
|
|
"num_tokens": 17103730.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.532904243469238,
|
|
"epoch": 0.8608973998989161,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004936669501624586,
|
|
"loss": 5.3381,
|
|
"mean_token_accuracy": 0.19136169403791428,
|
|
"num_tokens": 17115086.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.5359259128570555,
|
|
"epoch": 0.8614589768068737,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004936574881399308,
|
|
"loss": 5.3333,
|
|
"mean_token_accuracy": 0.19453381299972533,
|
|
"num_tokens": 17125928.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.523212480545044,
|
|
"epoch": 0.8620205537148312,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004936480191552637,
|
|
"loss": 5.3739,
|
|
"mean_token_accuracy": 0.18908844143152237,
|
|
"num_tokens": 17137328.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.524524784088134,
|
|
"epoch": 0.8625821306227888,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004936385432087589,
|
|
"loss": 5.3495,
|
|
"mean_token_accuracy": 0.19175111055374144,
|
|
"num_tokens": 17148274.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.544976091384887,
|
|
"epoch": 0.8631437075307463,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004936290603007181,
|
|
"loss": 5.3815,
|
|
"mean_token_accuracy": 0.18837463706731797,
|
|
"num_tokens": 17158834.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.5258111476898195,
|
|
"epoch": 0.8637052844387039,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004936195704314432,
|
|
"loss": 5.2427,
|
|
"mean_token_accuracy": 0.1950663670897484,
|
|
"num_tokens": 17169276.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.503770923614502,
|
|
"epoch": 0.8642668613466614,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004936100736012363,
|
|
"loss": 5.2914,
|
|
"mean_token_accuracy": 0.19853373765945434,
|
|
"num_tokens": 17180642.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.494513034820557,
|
|
"epoch": 0.864828438254619,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004936005698104,
|
|
"loss": 5.3445,
|
|
"mean_token_accuracy": 0.197983980178833,
|
|
"num_tokens": 17192477.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.569464302062988,
|
|
"epoch": 0.8653900151625765,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004935910590592367,
|
|
"loss": 5.4847,
|
|
"mean_token_accuracy": 0.18918235301971437,
|
|
"num_tokens": 17202653.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.447111320495606,
|
|
"epoch": 0.8659515920705341,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004935815413480494,
|
|
"loss": 5.2162,
|
|
"mean_token_accuracy": 0.2023095965385437,
|
|
"num_tokens": 17212607.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.541468286514283,
|
|
"epoch": 0.8665131689784916,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000493572016677141,
|
|
"loss": 5.3531,
|
|
"mean_token_accuracy": 0.19717216789722442,
|
|
"num_tokens": 17223701.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.535778760910034,
|
|
"epoch": 0.8670747458864492,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004935624850468148,
|
|
"loss": 5.2691,
|
|
"mean_token_accuracy": 0.19667365849018098,
|
|
"num_tokens": 17234878.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.508067464828491,
|
|
"epoch": 0.8676363227944067,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004935529464573742,
|
|
"loss": 5.346,
|
|
"mean_token_accuracy": 0.19576495438814162,
|
|
"num_tokens": 17245813.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.515953826904297,
|
|
"epoch": 0.8681978997023643,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004935434009091232,
|
|
"loss": 5.4193,
|
|
"mean_token_accuracy": 0.19034817367792128,
|
|
"num_tokens": 17257378.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.48284945487976,
|
|
"epoch": 0.8687594766103218,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004935338484023655,
|
|
"loss": 5.3412,
|
|
"mean_token_accuracy": 0.19484313279390336,
|
|
"num_tokens": 17269108.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.550235271453857,
|
|
"epoch": 0.8693210535182794,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004935242889374052,
|
|
"loss": 5.3306,
|
|
"mean_token_accuracy": 0.18691225796937944,
|
|
"num_tokens": 17280643.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.593494558334351,
|
|
"epoch": 0.8698826304262369,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004935147225145469,
|
|
"loss": 5.3916,
|
|
"mean_token_accuracy": 0.19205151349306107,
|
|
"num_tokens": 17291236.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.604566144943237,
|
|
"epoch": 0.8704442073341944,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004935051491340951,
|
|
"loss": 5.463,
|
|
"mean_token_accuracy": 0.18148287236690522,
|
|
"num_tokens": 17303547.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.613951539993286,
|
|
"epoch": 0.8710057842421519,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004934955687963546,
|
|
"loss": 5.4302,
|
|
"mean_token_accuracy": 0.18613469749689102,
|
|
"num_tokens": 17314803.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.53216519355774,
|
|
"epoch": 0.8715673611501095,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004934859815016304,
|
|
"loss": 5.298,
|
|
"mean_token_accuracy": 0.19373864829540252,
|
|
"num_tokens": 17326009.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.569486904144287,
|
|
"epoch": 0.872128938058067,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004934763872502278,
|
|
"loss": 5.2991,
|
|
"mean_token_accuracy": 0.20181606709957123,
|
|
"num_tokens": 17337078.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.547098207473755,
|
|
"epoch": 0.8726905149660246,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004934667860424523,
|
|
"loss": 5.4276,
|
|
"mean_token_accuracy": 0.18845681548118592,
|
|
"num_tokens": 17349266.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.401117372512817,
|
|
"epoch": 0.8732520918739821,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004934571778786096,
|
|
"loss": 5.2293,
|
|
"mean_token_accuracy": 0.1980017215013504,
|
|
"num_tokens": 17360327.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.618751907348633,
|
|
"epoch": 0.8738136687819397,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004934475627590057,
|
|
"loss": 5.4021,
|
|
"mean_token_accuracy": 0.18749536275863649,
|
|
"num_tokens": 17372727.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.631286334991455,
|
|
"epoch": 0.8743752456898972,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004934379406839466,
|
|
"loss": 5.4525,
|
|
"mean_token_accuracy": 0.183826045691967,
|
|
"num_tokens": 17384160.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.523481798171997,
|
|
"epoch": 0.8749368225978548,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004934283116537387,
|
|
"loss": 5.3731,
|
|
"mean_token_accuracy": 0.18825365453958512,
|
|
"num_tokens": 17396009.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.521708822250366,
|
|
"epoch": 0.8754983995058123,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004934186756686888,
|
|
"loss": 5.3739,
|
|
"mean_token_accuracy": 0.1929594859480858,
|
|
"num_tokens": 17406903.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.470612192153931,
|
|
"epoch": 0.8760599764137699,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004934090327291034,
|
|
"loss": 5.2255,
|
|
"mean_token_accuracy": 0.1995358482003212,
|
|
"num_tokens": 17417694.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.503048610687256,
|
|
"epoch": 0.8766215533217274,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004933993828352898,
|
|
"loss": 5.4652,
|
|
"mean_token_accuracy": 0.19427064955234527,
|
|
"num_tokens": 17428731.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.5018659114837645,
|
|
"epoch": 0.877183130229685,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004933897259875551,
|
|
"loss": 5.2014,
|
|
"mean_token_accuracy": 0.19879435896873474,
|
|
"num_tokens": 17439242.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.567990493774414,
|
|
"epoch": 0.8777447071376425,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004933800621862069,
|
|
"loss": 5.3333,
|
|
"mean_token_accuracy": 0.19243992865085602,
|
|
"num_tokens": 17449980.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.596957969665527,
|
|
"epoch": 0.8783062840456001,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004933703914315527,
|
|
"loss": 5.425,
|
|
"mean_token_accuracy": 0.18374176025390626,
|
|
"num_tokens": 17464140.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.615205717086792,
|
|
"epoch": 0.8788678609535576,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004933607137239006,
|
|
"loss": 5.4335,
|
|
"mean_token_accuracy": 0.18940581679344176,
|
|
"num_tokens": 17476246.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.596604347229004,
|
|
"epoch": 0.8794294378615152,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004933510290635587,
|
|
"loss": 5.4443,
|
|
"mean_token_accuracy": 0.18022418767213821,
|
|
"num_tokens": 17488169.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.505037450790406,
|
|
"epoch": 0.8799910147694727,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004933413374508353,
|
|
"loss": 5.2575,
|
|
"mean_token_accuracy": 0.19681808799505235,
|
|
"num_tokens": 17498465.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.558221769332886,
|
|
"epoch": 0.8805525916774303,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004933316388860391,
|
|
"loss": 5.254,
|
|
"mean_token_accuracy": 0.2049960345029831,
|
|
"num_tokens": 17509217.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.472606801986695,
|
|
"epoch": 0.8811141685853877,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004933219333694787,
|
|
"loss": 5.3036,
|
|
"mean_token_accuracy": 0.19729041755199433,
|
|
"num_tokens": 17519851.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.502962446212768,
|
|
"epoch": 0.8816757454933453,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004933122209014634,
|
|
"loss": 5.3673,
|
|
"mean_token_accuracy": 0.19381319284439086,
|
|
"num_tokens": 17532144.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.499823713302613,
|
|
"epoch": 0.8822373224013028,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004933025014823022,
|
|
"loss": 5.2621,
|
|
"mean_token_accuracy": 0.20211952477693557,
|
|
"num_tokens": 17542929.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.6443767070770265,
|
|
"epoch": 0.8827988993092604,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004932927751123048,
|
|
"loss": 5.4472,
|
|
"mean_token_accuracy": 0.18478454500436783,
|
|
"num_tokens": 17554931.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.512378692626953,
|
|
"epoch": 0.8833604762172179,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004932830417917808,
|
|
"loss": 5.2632,
|
|
"mean_token_accuracy": 0.19460886418819429,
|
|
"num_tokens": 17566026.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.502492427825928,
|
|
"epoch": 0.8839220531251755,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00049327330152104,
|
|
"loss": 5.3605,
|
|
"mean_token_accuracy": 0.19323073625564574,
|
|
"num_tokens": 17578396.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.5544038772583,
|
|
"epoch": 0.884483630033133,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004932635543003927,
|
|
"loss": 5.3439,
|
|
"mean_token_accuracy": 0.19812433272600175,
|
|
"num_tokens": 17590559.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.51351408958435,
|
|
"epoch": 0.8850452069410906,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004932538001301491,
|
|
"loss": 5.3202,
|
|
"mean_token_accuracy": 0.19301193207502365,
|
|
"num_tokens": 17600833.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.487991523742676,
|
|
"epoch": 0.8856067838490481,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004932440390106199,
|
|
"loss": 5.3149,
|
|
"mean_token_accuracy": 0.19400409758090972,
|
|
"num_tokens": 17612166.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.564039659500122,
|
|
"epoch": 0.8861683607570057,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004932342709421159,
|
|
"loss": 5.4208,
|
|
"mean_token_accuracy": 0.18780704736709594,
|
|
"num_tokens": 17623070.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.62103009223938,
|
|
"epoch": 0.8867299376649632,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000493224495924948,
|
|
"loss": 5.4862,
|
|
"mean_token_accuracy": 0.18929917961359025,
|
|
"num_tokens": 17633319.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.550469541549683,
|
|
"epoch": 0.8872915145729208,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004932147139594276,
|
|
"loss": 5.2996,
|
|
"mean_token_accuracy": 0.19384047985076905,
|
|
"num_tokens": 17643818.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.468474674224853,
|
|
"epoch": 0.8878530914808783,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004932049250458659,
|
|
"loss": 5.2935,
|
|
"mean_token_accuracy": 0.19358717501163483,
|
|
"num_tokens": 17655665.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.454145526885986,
|
|
"epoch": 0.8884146683888359,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004931951291845749,
|
|
"loss": 5.2182,
|
|
"mean_token_accuracy": 0.20388979613780975,
|
|
"num_tokens": 17666200.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.485030221939087,
|
|
"epoch": 0.8889762452967934,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004931853263758663,
|
|
"loss": 5.4095,
|
|
"mean_token_accuracy": 0.1872565269470215,
|
|
"num_tokens": 17677299.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.572393131256104,
|
|
"epoch": 0.889537822204751,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004931755166200523,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.20393956452608109,
|
|
"num_tokens": 17687870.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.52224178314209,
|
|
"epoch": 0.8900993991127085,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004931656999174452,
|
|
"loss": 5.2995,
|
|
"mean_token_accuracy": 0.19359648674726487,
|
|
"num_tokens": 17698853.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.513133859634399,
|
|
"epoch": 0.8906609760206661,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004931558762683577,
|
|
"loss": 5.3475,
|
|
"mean_token_accuracy": 0.19691725075244904,
|
|
"num_tokens": 17709897.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.555172634124756,
|
|
"epoch": 0.8912225529286236,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004931460456731024,
|
|
"loss": 5.352,
|
|
"mean_token_accuracy": 0.19076764583587646,
|
|
"num_tokens": 17720974.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.640217590332031,
|
|
"epoch": 0.8917841298365812,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004931362081319925,
|
|
"loss": 5.5075,
|
|
"mean_token_accuracy": 0.18322578966617584,
|
|
"num_tokens": 17734449.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.438530492782593,
|
|
"epoch": 0.8923457067445386,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004931263636453409,
|
|
"loss": 5.2417,
|
|
"mean_token_accuracy": 0.19710720777511598,
|
|
"num_tokens": 17744735.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.491062259674072,
|
|
"epoch": 0.8929072836524962,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004931165122134616,
|
|
"loss": 5.2637,
|
|
"mean_token_accuracy": 0.19604025185108184,
|
|
"num_tokens": 17755641.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.5673990726470945,
|
|
"epoch": 0.8934688605604537,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004931066538366677,
|
|
"loss": 5.3708,
|
|
"mean_token_accuracy": 0.187679785490036,
|
|
"num_tokens": 17767621.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.640732288360596,
|
|
"epoch": 0.8940304374684113,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004930967885152734,
|
|
"loss": 5.4709,
|
|
"mean_token_accuracy": 0.18887109756469728,
|
|
"num_tokens": 17779507.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.499023199081421,
|
|
"epoch": 0.8945920143763688,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004930869162495929,
|
|
"loss": 5.3152,
|
|
"mean_token_accuracy": 0.18959518522024155,
|
|
"num_tokens": 17790371.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.525818395614624,
|
|
"epoch": 0.8951535912843264,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004930770370399403,
|
|
"loss": 5.3162,
|
|
"mean_token_accuracy": 0.19837681353092193,
|
|
"num_tokens": 17800903.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.58081464767456,
|
|
"epoch": 0.8957151681922839,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004930671508866303,
|
|
"loss": 5.5155,
|
|
"mean_token_accuracy": 0.17849943935871124,
|
|
"num_tokens": 17812053.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.508196544647217,
|
|
"epoch": 0.8962767451002415,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004930572577899776,
|
|
"loss": 5.2358,
|
|
"mean_token_accuracy": 0.19567595422267914,
|
|
"num_tokens": 17822113.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.510505151748657,
|
|
"epoch": 0.896838322008199,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004930473577502972,
|
|
"loss": 5.2858,
|
|
"mean_token_accuracy": 0.19738962948322297,
|
|
"num_tokens": 17832741.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.3847143173217775,
|
|
"epoch": 0.8973998989161566,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004930374507679044,
|
|
"loss": 5.2142,
|
|
"mean_token_accuracy": 0.1925610765814781,
|
|
"num_tokens": 17842968.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.636124515533448,
|
|
"epoch": 0.8979614758241141,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004930275368431146,
|
|
"loss": 5.4743,
|
|
"mean_token_accuracy": 0.18087823539972306,
|
|
"num_tokens": 17854295.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.648864507675171,
|
|
"epoch": 0.8985230527320717,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004930176159762435,
|
|
"loss": 5.396,
|
|
"mean_token_accuracy": 0.19515135735273362,
|
|
"num_tokens": 17865597.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.421992588043213,
|
|
"epoch": 0.8990846296400292,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004930076881676069,
|
|
"loss": 5.1851,
|
|
"mean_token_accuracy": 0.1959100067615509,
|
|
"num_tokens": 17877405.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.612342739105225,
|
|
"epoch": 0.8996462065479868,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004929977534175211,
|
|
"loss": 5.3702,
|
|
"mean_token_accuracy": 0.19155756682157515,
|
|
"num_tokens": 17889273.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.464116716384888,
|
|
"epoch": 0.9002077834559443,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004929878117263021,
|
|
"loss": 5.2856,
|
|
"mean_token_accuracy": 0.19995818585157393,
|
|
"num_tokens": 17899761.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.476109457015991,
|
|
"epoch": 0.9007693603639019,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004929778630942668,
|
|
"loss": 5.2957,
|
|
"mean_token_accuracy": 0.1960954025387764,
|
|
"num_tokens": 17910607.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.558165597915649,
|
|
"epoch": 0.9013309372718594,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004929679075217317,
|
|
"loss": 5.3559,
|
|
"mean_token_accuracy": 0.19106128215789794,
|
|
"num_tokens": 17922538.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.52228741645813,
|
|
"epoch": 0.901892514179817,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004929579450090139,
|
|
"loss": 5.3825,
|
|
"mean_token_accuracy": 0.1919267013669014,
|
|
"num_tokens": 17933313.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.626115608215332,
|
|
"epoch": 0.9024540910877745,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004929479755564305,
|
|
"loss": 5.4825,
|
|
"mean_token_accuracy": 0.18904066383838652,
|
|
"num_tokens": 17944893.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.547903442382813,
|
|
"epoch": 0.903015667995732,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004929379991642991,
|
|
"loss": 5.3435,
|
|
"mean_token_accuracy": 0.19203057736158372,
|
|
"num_tokens": 17955019.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.620864963531494,
|
|
"epoch": 0.9035772449036895,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004929280158329373,
|
|
"loss": 5.3799,
|
|
"mean_token_accuracy": 0.18826183080673217,
|
|
"num_tokens": 17965793.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.515917253494263,
|
|
"epoch": 0.9041388218116471,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000492918025562663,
|
|
"loss": 5.2072,
|
|
"mean_token_accuracy": 0.19581181704998016,
|
|
"num_tokens": 17975709.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.554681015014649,
|
|
"epoch": 0.9047003987196046,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004929080283537942,
|
|
"loss": 5.4439,
|
|
"mean_token_accuracy": 0.18521264046430588,
|
|
"num_tokens": 17985405.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.572683048248291,
|
|
"epoch": 0.9052619756275622,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004928980242066492,
|
|
"loss": 5.4617,
|
|
"mean_token_accuracy": 0.1860238254070282,
|
|
"num_tokens": 17997105.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.557096385955811,
|
|
"epoch": 0.9058235525355197,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004928880131215467,
|
|
"loss": 5.3486,
|
|
"mean_token_accuracy": 0.19937967360019684,
|
|
"num_tokens": 18007914.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.490323162078857,
|
|
"epoch": 0.9063851294434773,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004928779950988053,
|
|
"loss": 5.3503,
|
|
"mean_token_accuracy": 0.19325897693634034,
|
|
"num_tokens": 18018328.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.569067096710205,
|
|
"epoch": 0.9069467063514348,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000492867970138744,
|
|
"loss": 5.312,
|
|
"mean_token_accuracy": 0.19093905091285707,
|
|
"num_tokens": 18028568.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.548278379440307,
|
|
"epoch": 0.9075082832593924,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004928579382416821,
|
|
"loss": 5.3293,
|
|
"mean_token_accuracy": 0.1936284586787224,
|
|
"num_tokens": 18038655.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.490902996063232,
|
|
"epoch": 0.9080698601673499,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000492847899407939,
|
|
"loss": 5.2668,
|
|
"mean_token_accuracy": 0.19545679688453674,
|
|
"num_tokens": 18049716.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.447275638580322,
|
|
"epoch": 0.9086314370753075,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004928378536378341,
|
|
"loss": 5.2484,
|
|
"mean_token_accuracy": 0.19852099865674971,
|
|
"num_tokens": 18062530.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.503797626495361,
|
|
"epoch": 0.909193013983265,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004928278009316877,
|
|
"loss": 5.3548,
|
|
"mean_token_accuracy": 0.19214667081832887,
|
|
"num_tokens": 18073076.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.587497901916504,
|
|
"epoch": 0.9097545908912226,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004928177412898195,
|
|
"loss": 5.3025,
|
|
"mean_token_accuracy": 0.19379561096429826,
|
|
"num_tokens": 18083759.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.458155870437622,
|
|
"epoch": 0.9103161677991801,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004928076747125499,
|
|
"loss": 5.2375,
|
|
"mean_token_accuracy": 0.1974729210138321,
|
|
"num_tokens": 18095980.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.5262823581695555,
|
|
"epoch": 0.9108777447071377,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004927976012001995,
|
|
"loss": 5.3323,
|
|
"mean_token_accuracy": 0.19940765500068663,
|
|
"num_tokens": 18106672.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.514932918548584,
|
|
"epoch": 0.9114393216150952,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004927875207530889,
|
|
"loss": 5.353,
|
|
"mean_token_accuracy": 0.19236091673374175,
|
|
"num_tokens": 18117481.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.4810340881347654,
|
|
"epoch": 0.9120008985230528,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004927774333715394,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.19350982159376146,
|
|
"num_tokens": 18127602.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.562128257751465,
|
|
"epoch": 0.9125624754310103,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004927673390558718,
|
|
"loss": 5.3671,
|
|
"mean_token_accuracy": 0.19208624809980393,
|
|
"num_tokens": 18140109.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.476376247406006,
|
|
"epoch": 0.9131240523389679,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004927572378064077,
|
|
"loss": 5.2397,
|
|
"mean_token_accuracy": 0.20164853185415268,
|
|
"num_tokens": 18150271.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.486606884002685,
|
|
"epoch": 0.9136856292469253,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004927471296234687,
|
|
"loss": 5.3604,
|
|
"mean_token_accuracy": 0.1954893186688423,
|
|
"num_tokens": 18160746.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.599887132644653,
|
|
"epoch": 0.9142472061548829,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004927370145073767,
|
|
"loss": 5.3643,
|
|
"mean_token_accuracy": 0.19265573769807814,
|
|
"num_tokens": 18172271.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.508764982223511,
|
|
"epoch": 0.9148087830628404,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004927268924584536,
|
|
"loss": 5.2831,
|
|
"mean_token_accuracy": 0.19398891925811768,
|
|
"num_tokens": 18183116.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.459906101226807,
|
|
"epoch": 0.915370359970798,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004927167634770219,
|
|
"loss": 5.2578,
|
|
"mean_token_accuracy": 0.20310339629650115,
|
|
"num_tokens": 18195147.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.526568651199341,
|
|
"epoch": 0.9159319368787555,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000492706627563404,
|
|
"loss": 5.3078,
|
|
"mean_token_accuracy": 0.19455216079950333,
|
|
"num_tokens": 18206217.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.495534801483155,
|
|
"epoch": 0.9164935137867131,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004926964847179225,
|
|
"loss": 5.3289,
|
|
"mean_token_accuracy": 0.19275714606046676,
|
|
"num_tokens": 18217434.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.534586429595947,
|
|
"epoch": 0.9170550906946706,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004926863349409006,
|
|
"loss": 5.3309,
|
|
"mean_token_accuracy": 0.19082320630550384,
|
|
"num_tokens": 18229277.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.451659727096557,
|
|
"epoch": 0.9176166676026282,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004926761782326613,
|
|
"loss": 5.1895,
|
|
"mean_token_accuracy": 0.2019288346171379,
|
|
"num_tokens": 18240320.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.464824676513672,
|
|
"epoch": 0.9181782445105857,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004926660145935282,
|
|
"loss": 5.2307,
|
|
"mean_token_accuracy": 0.19750059694051741,
|
|
"num_tokens": 18250380.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.529764413833618,
|
|
"epoch": 0.9187398214185433,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004926558440238247,
|
|
"loss": 5.4003,
|
|
"mean_token_accuracy": 0.1937176465988159,
|
|
"num_tokens": 18261703.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.512107563018799,
|
|
"epoch": 0.9193013983265008,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004926456665238746,
|
|
"loss": 5.3174,
|
|
"mean_token_accuracy": 0.1919119492173195,
|
|
"num_tokens": 18272472.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.627255821228028,
|
|
"epoch": 0.9198629752344584,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004926354820940023,
|
|
"loss": 5.4242,
|
|
"mean_token_accuracy": 0.18777076303958892,
|
|
"num_tokens": 18282168.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.64281005859375,
|
|
"epoch": 0.9204245521424159,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004926252907345317,
|
|
"loss": 5.4103,
|
|
"mean_token_accuracy": 0.1880524516105652,
|
|
"num_tokens": 18293750.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.509887409210205,
|
|
"epoch": 0.9209861290503735,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004926150924457874,
|
|
"loss": 5.3149,
|
|
"mean_token_accuracy": 0.1946457579731941,
|
|
"num_tokens": 18304568.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.473498296737671,
|
|
"epoch": 0.921547705958331,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004926048872280943,
|
|
"loss": 5.2652,
|
|
"mean_token_accuracy": 0.19549497812986374,
|
|
"num_tokens": 18315129.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.43020396232605,
|
|
"epoch": 0.9221092828662886,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000492594675081777,
|
|
"loss": 5.2227,
|
|
"mean_token_accuracy": 0.1941726803779602,
|
|
"num_tokens": 18324628.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.391623592376709,
|
|
"epoch": 0.9226708597742461,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000492584456007161,
|
|
"loss": 5.2183,
|
|
"mean_token_accuracy": 0.20514661818742752,
|
|
"num_tokens": 18334899.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.519819974899292,
|
|
"epoch": 0.9232324366822037,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004925742300045716,
|
|
"loss": 5.2346,
|
|
"mean_token_accuracy": 0.20070850551128389,
|
|
"num_tokens": 18345719.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.5702324390411375,
|
|
"epoch": 0.9237940135901612,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004925639970743341,
|
|
"loss": 5.3399,
|
|
"mean_token_accuracy": 0.19450607001781464,
|
|
"num_tokens": 18355814.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.55308952331543,
|
|
"epoch": 0.9243555904981187,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004925537572167746,
|
|
"loss": 5.4063,
|
|
"mean_token_accuracy": 0.18684204518795014,
|
|
"num_tokens": 18366746.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.463734531402588,
|
|
"epoch": 0.9249171674060762,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004925435104322192,
|
|
"loss": 5.2273,
|
|
"mean_token_accuracy": 0.2022406905889511,
|
|
"num_tokens": 18375846.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.446729707717895,
|
|
"epoch": 0.9254787443140338,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000492533256720994,
|
|
"loss": 5.3524,
|
|
"mean_token_accuracy": 0.19247244745492936,
|
|
"num_tokens": 18386850.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.469273376464844,
|
|
"epoch": 0.9260403212219913,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004925229960834256,
|
|
"loss": 5.2508,
|
|
"mean_token_accuracy": 0.1982171654701233,
|
|
"num_tokens": 18396347.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.466515398025512,
|
|
"epoch": 0.9266018981299489,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004925127285198407,
|
|
"loss": 5.2853,
|
|
"mean_token_accuracy": 0.19833889603614807,
|
|
"num_tokens": 18406583.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.59253306388855,
|
|
"epoch": 0.9271634750379064,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000492502454030566,
|
|
"loss": 5.412,
|
|
"mean_token_accuracy": 0.18874627351760864,
|
|
"num_tokens": 18418586.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.5294488906860355,
|
|
"epoch": 0.927725051945864,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004924921726159288,
|
|
"loss": 5.2392,
|
|
"mean_token_accuracy": 0.19591175466775895,
|
|
"num_tokens": 18429752.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.529174566268921,
|
|
"epoch": 0.9282866288538215,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004924818842762565,
|
|
"loss": 5.3355,
|
|
"mean_token_accuracy": 0.18996217846870422,
|
|
"num_tokens": 18440663.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.4571661949157715,
|
|
"epoch": 0.9288482057617791,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004924715890118768,
|
|
"loss": 5.2721,
|
|
"mean_token_accuracy": 0.20011357814073563,
|
|
"num_tokens": 18451497.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.499194192886352,
|
|
"epoch": 0.9294097826697366,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004924612868231173,
|
|
"loss": 5.2748,
|
|
"mean_token_accuracy": 0.18895938694477082,
|
|
"num_tokens": 18462794.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.5031129837036135,
|
|
"epoch": 0.9299713595776942,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004924509777103059,
|
|
"loss": 5.2639,
|
|
"mean_token_accuracy": 0.19696242958307267,
|
|
"num_tokens": 18472973.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.546626949310303,
|
|
"epoch": 0.9305329364856517,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004924406616737712,
|
|
"loss": 5.4316,
|
|
"mean_token_accuracy": 0.1955415740609169,
|
|
"num_tokens": 18484451.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.5921026229858395,
|
|
"epoch": 0.9310945133936093,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004924303387138415,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.2020363301038742,
|
|
"num_tokens": 18496412.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.539563989639282,
|
|
"epoch": 0.9316560903015668,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004924200088308455,
|
|
"loss": 5.3189,
|
|
"mean_token_accuracy": 0.196001236140728,
|
|
"num_tokens": 18508547.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.460558557510376,
|
|
"epoch": 0.9322176672095244,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000492409672025112,
|
|
"loss": 5.3446,
|
|
"mean_token_accuracy": 0.19378729164600372,
|
|
"num_tokens": 18518954.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.474789333343506,
|
|
"epoch": 0.9327792441174819,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004923993282969703,
|
|
"loss": 5.2074,
|
|
"mean_token_accuracy": 0.20229743272066117,
|
|
"num_tokens": 18530444.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.518152236938477,
|
|
"epoch": 0.9333408210254395,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004923889776467495,
|
|
"loss": 5.2782,
|
|
"mean_token_accuracy": 0.19407936334609985,
|
|
"num_tokens": 18541612.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.528368091583252,
|
|
"epoch": 0.933902397933397,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004923786200747795,
|
|
"loss": 5.4168,
|
|
"mean_token_accuracy": 0.18776628524065017,
|
|
"num_tokens": 18553316.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.479777479171753,
|
|
"epoch": 0.9344639748413546,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00049236825558139,
|
|
"loss": 5.3017,
|
|
"mean_token_accuracy": 0.1947462663054466,
|
|
"num_tokens": 18564468.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.465587186813354,
|
|
"epoch": 0.9350255517493121,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004923578841669108,
|
|
"loss": 5.2305,
|
|
"mean_token_accuracy": 0.20041596591472627,
|
|
"num_tokens": 18575536.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.48757004737854,
|
|
"epoch": 0.9355871286572696,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004923475058316723,
|
|
"loss": 5.3602,
|
|
"mean_token_accuracy": 0.18073692172765732,
|
|
"num_tokens": 18586906.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.583889770507812,
|
|
"epoch": 0.9361487055652271,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004923371205760049,
|
|
"loss": 5.3313,
|
|
"mean_token_accuracy": 0.19059130996465684,
|
|
"num_tokens": 18599064.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.495828866958618,
|
|
"epoch": 0.9367102824731847,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004923267284002394,
|
|
"loss": 5.3661,
|
|
"mean_token_accuracy": 0.18868516385555267,
|
|
"num_tokens": 18610057.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.404728841781616,
|
|
"epoch": 0.9372718593811422,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004923163293047065,
|
|
"loss": 5.1775,
|
|
"mean_token_accuracy": 0.2008477121591568,
|
|
"num_tokens": 18620008.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.441278791427612,
|
|
"epoch": 0.9378334362890998,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004923059232897374,
|
|
"loss": 5.1993,
|
|
"mean_token_accuracy": 0.19684551060199737,
|
|
"num_tokens": 18630599.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.506535768508911,
|
|
"epoch": 0.9383950131970573,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004922955103556633,
|
|
"loss": 5.39,
|
|
"mean_token_accuracy": 0.19271948784589768,
|
|
"num_tokens": 18643898.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.556987667083741,
|
|
"epoch": 0.9389565901050149,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000492285090502816,
|
|
"loss": 5.3672,
|
|
"mean_token_accuracy": 0.18643654584884645,
|
|
"num_tokens": 18654760.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.556431579589844,
|
|
"epoch": 0.9395181670129724,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004922746637315272,
|
|
"loss": 5.3275,
|
|
"mean_token_accuracy": 0.19593957364559172,
|
|
"num_tokens": 18666036.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.543078088760376,
|
|
"epoch": 0.94007974392093,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004922642300421288,
|
|
"loss": 5.3809,
|
|
"mean_token_accuracy": 0.19456374645233154,
|
|
"num_tokens": 18677806.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.600285768508911,
|
|
"epoch": 0.9406413208288875,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000492253789434953,
|
|
"loss": 5.4998,
|
|
"mean_token_accuracy": 0.18756832480430602,
|
|
"num_tokens": 18688971.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.489480304718017,
|
|
"epoch": 0.9412028977368451,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004922433419103323,
|
|
"loss": 5.3643,
|
|
"mean_token_accuracy": 0.19015772342681886,
|
|
"num_tokens": 18700153.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.630396795272827,
|
|
"epoch": 0.9417644746448026,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004922328874685993,
|
|
"loss": 5.4173,
|
|
"mean_token_accuracy": 0.19243549704551696,
|
|
"num_tokens": 18711935.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.44732403755188,
|
|
"epoch": 0.9423260515527602,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004922224261100869,
|
|
"loss": 5.2239,
|
|
"mean_token_accuracy": 0.1980170026421547,
|
|
"num_tokens": 18722694.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.544261121749878,
|
|
"epoch": 0.9428876284607177,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004922119578351283,
|
|
"loss": 5.3842,
|
|
"mean_token_accuracy": 0.19403104931116105,
|
|
"num_tokens": 18733443.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.579034423828125,
|
|
"epoch": 0.9434492053686753,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004922014826440566,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.19047629088163376,
|
|
"num_tokens": 18743965.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.508858251571655,
|
|
"epoch": 0.9440107822766328,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004921910005372056,
|
|
"loss": 5.3837,
|
|
"mean_token_accuracy": 0.19500262141227723,
|
|
"num_tokens": 18755712.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.510873889923095,
|
|
"epoch": 0.9445723591845904,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004921805115149088,
|
|
"loss": 5.2907,
|
|
"mean_token_accuracy": 0.19899307936429977,
|
|
"num_tokens": 18766756.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.527020215988159,
|
|
"epoch": 0.9451339360925479,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004921700155775002,
|
|
"loss": 5.3986,
|
|
"mean_token_accuracy": 0.1874764159321785,
|
|
"num_tokens": 18776932.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.586201143264771,
|
|
"epoch": 0.9456955130005055,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004921595127253142,
|
|
"loss": 5.32,
|
|
"mean_token_accuracy": 0.1923366293311119,
|
|
"num_tokens": 18787197.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.472904920578003,
|
|
"epoch": 0.9462570899084629,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004921490029586852,
|
|
"loss": 5.2833,
|
|
"mean_token_accuracy": 0.19781346023082733,
|
|
"num_tokens": 18797861.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.489264488220215,
|
|
"epoch": 0.9468186668164205,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004921384862779475,
|
|
"loss": 5.2721,
|
|
"mean_token_accuracy": 0.19531847834587096,
|
|
"num_tokens": 18809111.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.502651834487915,
|
|
"epoch": 0.947380243724378,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004921279626834363,
|
|
"loss": 5.292,
|
|
"mean_token_accuracy": 0.20616334527730942,
|
|
"num_tokens": 18820236.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.4803853034973145,
|
|
"epoch": 0.9479418206323356,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004921174321754865,
|
|
"loss": 5.291,
|
|
"mean_token_accuracy": 0.1944515287876129,
|
|
"num_tokens": 18831942.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.515991640090943,
|
|
"epoch": 0.9485033975402931,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004921068947544335,
|
|
"loss": 5.3232,
|
|
"mean_token_accuracy": 0.19548382312059404,
|
|
"num_tokens": 18843271.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.54376802444458,
|
|
"epoch": 0.9490649744482507,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004920963504206128,
|
|
"loss": 5.3731,
|
|
"mean_token_accuracy": 0.19469914436340333,
|
|
"num_tokens": 18856285.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.5682103633880615,
|
|
"epoch": 0.9496265513562082,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00049208579917436,
|
|
"loss": 5.3826,
|
|
"mean_token_accuracy": 0.19510563164949418,
|
|
"num_tokens": 18867203.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.530523061752319,
|
|
"epoch": 0.9501881282641658,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004920752410160113,
|
|
"loss": 5.421,
|
|
"mean_token_accuracy": 0.1850555270910263,
|
|
"num_tokens": 18878598.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.586306476593018,
|
|
"epoch": 0.9507497051721233,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004920646759459026,
|
|
"loss": 5.3313,
|
|
"mean_token_accuracy": 0.1959939107298851,
|
|
"num_tokens": 18890233.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.59341025352478,
|
|
"epoch": 0.9513112820800809,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004920541039643705,
|
|
"loss": 5.4251,
|
|
"mean_token_accuracy": 0.18987570852041244,
|
|
"num_tokens": 18900362.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.574532175064087,
|
|
"epoch": 0.9518728589880384,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004920435250717515,
|
|
"loss": 5.3468,
|
|
"mean_token_accuracy": 0.19702188074588775,
|
|
"num_tokens": 18911924.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.514659261703491,
|
|
"epoch": 0.952434435895996,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004920329392683826,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.18938423544168473,
|
|
"num_tokens": 18923931.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.496541690826416,
|
|
"epoch": 0.9529960128039535,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004920223465546006,
|
|
"loss": 5.2642,
|
|
"mean_token_accuracy": 0.19337952136993408,
|
|
"num_tokens": 18935859.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.534044551849365,
|
|
"epoch": 0.9535575897119111,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004920117469307429,
|
|
"loss": 5.3994,
|
|
"mean_token_accuracy": 0.18973634093999864,
|
|
"num_tokens": 18946939.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.581312084197998,
|
|
"epoch": 0.9541191666198686,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004920011403971471,
|
|
"loss": 5.3517,
|
|
"mean_token_accuracy": 0.19256744980812074,
|
|
"num_tokens": 18958067.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.56809253692627,
|
|
"epoch": 0.9546807435278262,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004919905269541508,
|
|
"loss": 5.2723,
|
|
"mean_token_accuracy": 0.20111051946878433,
|
|
"num_tokens": 18967920.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.532199048995972,
|
|
"epoch": 0.9552423204357837,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000491979906602092,
|
|
"loss": 5.2783,
|
|
"mean_token_accuracy": 0.2051227569580078,
|
|
"num_tokens": 18978244.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.5091753005981445,
|
|
"epoch": 0.9558038973437413,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004919692793413089,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.19475196450948715,
|
|
"num_tokens": 18988464.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.440777397155761,
|
|
"epoch": 0.9563654742516988,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004919586451721396,
|
|
"loss": 5.2181,
|
|
"mean_token_accuracy": 0.19491596817970275,
|
|
"num_tokens": 18998318.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.45198802947998,
|
|
"epoch": 0.9569270511596563,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004919480040949229,
|
|
"loss": 5.2174,
|
|
"mean_token_accuracy": 0.19848695695400237,
|
|
"num_tokens": 19009802.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.58954553604126,
|
|
"epoch": 0.9574886280676138,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004919373561099977,
|
|
"loss": 5.4242,
|
|
"mean_token_accuracy": 0.1954422414302826,
|
|
"num_tokens": 19020174.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.538468980789185,
|
|
"epoch": 0.9580502049755714,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000491926701217703,
|
|
"loss": 5.3552,
|
|
"mean_token_accuracy": 0.18940722346305847,
|
|
"num_tokens": 19031505.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.492196702957154,
|
|
"epoch": 0.9586117818835289,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004919160394183779,
|
|
"loss": 5.242,
|
|
"mean_token_accuracy": 0.20092486590147018,
|
|
"num_tokens": 19042052.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.636459827423096,
|
|
"epoch": 0.9591733587914865,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000491905370712362,
|
|
"loss": 5.4543,
|
|
"mean_token_accuracy": 0.1879579856991768,
|
|
"num_tokens": 19052050.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.5843945980072025,
|
|
"epoch": 0.959734935699444,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004918946950999949,
|
|
"loss": 5.3641,
|
|
"mean_token_accuracy": 0.1980499505996704,
|
|
"num_tokens": 19062053.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.445322275161743,
|
|
"epoch": 0.9602965126074016,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004918840125816167,
|
|
"loss": 5.3066,
|
|
"mean_token_accuracy": 0.19347066879272462,
|
|
"num_tokens": 19073095.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.566421699523926,
|
|
"epoch": 0.9608580895153591,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004918733231575673,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.1968414694070816,
|
|
"num_tokens": 19084521.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.569588613510132,
|
|
"epoch": 0.9614196664233167,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004918626268281874,
|
|
"loss": 5.358,
|
|
"mean_token_accuracy": 0.19272718727588653,
|
|
"num_tokens": 19096372.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.594934177398682,
|
|
"epoch": 0.9619812433312742,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004918519235938171,
|
|
"loss": 5.4749,
|
|
"mean_token_accuracy": 0.18462338149547577,
|
|
"num_tokens": 19108535.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.618961954116822,
|
|
"epoch": 0.9625428202392318,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004918412134547976,
|
|
"loss": 5.3066,
|
|
"mean_token_accuracy": 0.20059431940317154,
|
|
"num_tokens": 19119480.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.506146192550659,
|
|
"epoch": 0.9631043971471893,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004918304964114696,
|
|
"loss": 5.3054,
|
|
"mean_token_accuracy": 0.1992769494652748,
|
|
"num_tokens": 19131168.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.556567049026489,
|
|
"epoch": 0.9636659740551469,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004918197724641747,
|
|
"loss": 5.4679,
|
|
"mean_token_accuracy": 0.18865093141794204,
|
|
"num_tokens": 19142454.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.569630146026611,
|
|
"epoch": 0.9642275509631044,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.000491809041613254,
|
|
"loss": 5.3101,
|
|
"mean_token_accuracy": 0.1951150804758072,
|
|
"num_tokens": 19154682.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.5051126956939695,
|
|
"epoch": 0.964789127871062,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004917983038590495,
|
|
"loss": 5.2585,
|
|
"mean_token_accuracy": 0.19430696368217468,
|
|
"num_tokens": 19165190.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.533736228942871,
|
|
"epoch": 0.9653507047790195,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004917875592019028,
|
|
"loss": 5.386,
|
|
"mean_token_accuracy": 0.19778713434934617,
|
|
"num_tokens": 19176075.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.5400341033935545,
|
|
"epoch": 0.9659122816869771,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004917768076421561,
|
|
"loss": 5.3942,
|
|
"mean_token_accuracy": 0.18972357511520385,
|
|
"num_tokens": 19188450.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.449521780014038,
|
|
"epoch": 0.9664738585949346,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004917660491801518,
|
|
"loss": 5.2448,
|
|
"mean_token_accuracy": 0.20544234812259674,
|
|
"num_tokens": 19201254.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.483716821670532,
|
|
"epoch": 0.9670354355028922,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004917552838162324,
|
|
"loss": 5.339,
|
|
"mean_token_accuracy": 0.19322220981121063,
|
|
"num_tokens": 19214062.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.514604806900024,
|
|
"epoch": 0.9675970124108496,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004917445115507408,
|
|
"loss": 5.2301,
|
|
"mean_token_accuracy": 0.19938719719648362,
|
|
"num_tokens": 19224844.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.517232751846313,
|
|
"epoch": 0.9681585893188072,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004917337323840198,
|
|
"loss": 5.3884,
|
|
"mean_token_accuracy": 0.19019622951745987,
|
|
"num_tokens": 19237347.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.568839979171753,
|
|
"epoch": 0.9687201662267647,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004917229463164128,
|
|
"loss": 5.2929,
|
|
"mean_token_accuracy": 0.19349850863218307,
|
|
"num_tokens": 19248743.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.5409348487854,
|
|
"epoch": 0.9692817431347223,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004917121533482631,
|
|
"loss": 5.2811,
|
|
"mean_token_accuracy": 0.19889605045318604,
|
|
"num_tokens": 19259904.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.476102256774903,
|
|
"epoch": 0.9698433200426798,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004917013534799144,
|
|
"loss": 5.2135,
|
|
"mean_token_accuracy": 0.1982925906777382,
|
|
"num_tokens": 19271388.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.472508955001831,
|
|
"epoch": 0.9704048969506374,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004916905467117104,
|
|
"loss": 5.3459,
|
|
"mean_token_accuracy": 0.19611824601888656,
|
|
"num_tokens": 19282790.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.476872730255127,
|
|
"epoch": 0.9709664738585949,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004916797330439955,
|
|
"loss": 5.2542,
|
|
"mean_token_accuracy": 0.20165022611618041,
|
|
"num_tokens": 19293389.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.516427230834961,
|
|
"epoch": 0.9715280507665525,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004916689124771138,
|
|
"loss": 5.3204,
|
|
"mean_token_accuracy": 0.19275973290205,
|
|
"num_tokens": 19304593.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.521431970596313,
|
|
"epoch": 0.97208962767451,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004916580850114099,
|
|
"loss": 5.2453,
|
|
"mean_token_accuracy": 0.19730097353458403,
|
|
"num_tokens": 19317388.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.5133246898651125,
|
|
"epoch": 0.9726512045824676,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004916472506472286,
|
|
"loss": 5.3082,
|
|
"mean_token_accuracy": 0.19863904714584352,
|
|
"num_tokens": 19329228.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.557421541213989,
|
|
"epoch": 0.9732127814904251,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004916364093849147,
|
|
"loss": 5.2904,
|
|
"mean_token_accuracy": 0.19996307790279388,
|
|
"num_tokens": 19339421.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.405920171737671,
|
|
"epoch": 0.9737743583983827,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004916255612248136,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.19828363209962846,
|
|
"num_tokens": 19349618.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.4068992137908936,
|
|
"epoch": 0.9743359353063402,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004916147061672706,
|
|
"loss": 5.274,
|
|
"mean_token_accuracy": 0.19820062071084976,
|
|
"num_tokens": 19361324.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.5136371612548825,
|
|
"epoch": 0.9748975122142978,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004916038442126314,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.19429763406515121,
|
|
"num_tokens": 19373631.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.512303686141967,
|
|
"epoch": 0.9754590891222553,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004915929753612416,
|
|
"loss": 5.2596,
|
|
"mean_token_accuracy": 0.1894065722823143,
|
|
"num_tokens": 19384682.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.577161693572998,
|
|
"epoch": 0.9760206660302129,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004915820996134477,
|
|
"loss": 5.3596,
|
|
"mean_token_accuracy": 0.19214255213737488,
|
|
"num_tokens": 19396344.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.491068601608276,
|
|
"epoch": 0.9765822429381704,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004915712169695956,
|
|
"loss": 5.2228,
|
|
"mean_token_accuracy": 0.19514360427856445,
|
|
"num_tokens": 19406921.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.4801679134368895,
|
|
"epoch": 0.977143819846128,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000491560327430032,
|
|
"loss": 5.3266,
|
|
"mean_token_accuracy": 0.19372628778219222,
|
|
"num_tokens": 19416851.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.533003902435302,
|
|
"epoch": 0.9777053967540855,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004915494309951035,
|
|
"loss": 5.3108,
|
|
"mean_token_accuracy": 0.19475093483924866,
|
|
"num_tokens": 19428180.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.630847930908203,
|
|
"epoch": 0.9782669736620431,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004915385276651573,
|
|
"loss": 5.3742,
|
|
"mean_token_accuracy": 0.19478792548179627,
|
|
"num_tokens": 19439575.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.536477088928223,
|
|
"epoch": 0.9788285505700005,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004915276174405403,
|
|
"loss": 5.3302,
|
|
"mean_token_accuracy": 0.19357409924268723,
|
|
"num_tokens": 19452074.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.425706577301026,
|
|
"epoch": 0.9793901274779581,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004915167003215999,
|
|
"loss": 5.2486,
|
|
"mean_token_accuracy": 0.20036822855472564,
|
|
"num_tokens": 19463085.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.623198986053467,
|
|
"epoch": 0.9799517043859156,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004915057763086838,
|
|
"loss": 5.4146,
|
|
"mean_token_accuracy": 0.1868090495467186,
|
|
"num_tokens": 19472726.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.487967443466187,
|
|
"epoch": 0.9805132812938732,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00049149484540214,
|
|
"loss": 5.2552,
|
|
"mean_token_accuracy": 0.1935631588101387,
|
|
"num_tokens": 19482275.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.505958414077758,
|
|
"epoch": 0.9810748582018307,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004914839076023161,
|
|
"loss": 5.3595,
|
|
"mean_token_accuracy": 0.19699829518795015,
|
|
"num_tokens": 19492782.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.446452713012695,
|
|
"epoch": 0.9816364351097883,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004914729629095609,
|
|
"loss": 5.2307,
|
|
"mean_token_accuracy": 0.1958414539694786,
|
|
"num_tokens": 19505709.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.541211843490601,
|
|
"epoch": 0.9821980120177458,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004914620113242224,
|
|
"loss": 5.3263,
|
|
"mean_token_accuracy": 0.1925818592309952,
|
|
"num_tokens": 19516269.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.496512413024902,
|
|
"epoch": 0.9827595889257034,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004914510528466495,
|
|
"loss": 5.2824,
|
|
"mean_token_accuracy": 0.19538244009017944,
|
|
"num_tokens": 19526786.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.492437362670898,
|
|
"epoch": 0.9833211658336609,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004914400874771913,
|
|
"loss": 5.3183,
|
|
"mean_token_accuracy": 0.18935514986515045,
|
|
"num_tokens": 19537865.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.424366855621338,
|
|
"epoch": 0.9838827427416185,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004914291152161967,
|
|
"loss": 5.2566,
|
|
"mean_token_accuracy": 0.2032148703932762,
|
|
"num_tokens": 19548320.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.526584100723267,
|
|
"epoch": 0.984444319649576,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000491418136064015,
|
|
"loss": 5.2705,
|
|
"mean_token_accuracy": 0.19547163248062133,
|
|
"num_tokens": 19558856.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.554690217971801,
|
|
"epoch": 0.9850058965575336,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000491407150020996,
|
|
"loss": 5.3689,
|
|
"mean_token_accuracy": 0.20002047270536422,
|
|
"num_tokens": 19570792.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.530953502655029,
|
|
"epoch": 0.9855674734654911,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004913961570874895,
|
|
"loss": 5.2727,
|
|
"mean_token_accuracy": 0.2007561966776848,
|
|
"num_tokens": 19581982.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.435000228881836,
|
|
"epoch": 0.9861290503734487,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004913851572638453,
|
|
"loss": 5.241,
|
|
"mean_token_accuracy": 0.19601088762283325,
|
|
"num_tokens": 19592882.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.551732063293457,
|
|
"epoch": 0.9866906272814062,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004913741505504138,
|
|
"loss": 5.4594,
|
|
"mean_token_accuracy": 0.19115378260612487,
|
|
"num_tokens": 19605967.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.597033596038818,
|
|
"epoch": 0.9872522041893638,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004913631369475454,
|
|
"loss": 5.2916,
|
|
"mean_token_accuracy": 0.19472094923257827,
|
|
"num_tokens": 19616494.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.554978656768799,
|
|
"epoch": 0.9878137810973213,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004913521164555909,
|
|
"loss": 5.3866,
|
|
"mean_token_accuracy": 0.19440087527036667,
|
|
"num_tokens": 19627013.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.5084312915802,
|
|
"epoch": 0.9883753580052789,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.000491341089074901,
|
|
"loss": 5.2808,
|
|
"mean_token_accuracy": 0.19979849457740784,
|
|
"num_tokens": 19639099.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.423909091949463,
|
|
"epoch": 0.9889369349132364,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000491330054805827,
|
|
"loss": 5.2667,
|
|
"mean_token_accuracy": 0.20079948902130126,
|
|
"num_tokens": 19650650.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.513259363174439,
|
|
"epoch": 0.9894985118211939,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004913190136487201,
|
|
"loss": 5.3168,
|
|
"mean_token_accuracy": 0.19340629875659943,
|
|
"num_tokens": 19662869.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.486497497558593,
|
|
"epoch": 0.9900600887291514,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004913079656039318,
|
|
"loss": 5.3063,
|
|
"mean_token_accuracy": 0.1968105748295784,
|
|
"num_tokens": 19673232.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.498173379898072,
|
|
"epoch": 0.990621665637109,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004912969106718142,
|
|
"loss": 5.324,
|
|
"mean_token_accuracy": 0.19287081211805343,
|
|
"num_tokens": 19685069.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.54580078125,
|
|
"epoch": 0.9911832425450665,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000491285848852719,
|
|
"loss": 5.4141,
|
|
"mean_token_accuracy": 0.18451459109783172,
|
|
"num_tokens": 19697018.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.523934412002563,
|
|
"epoch": 0.9917448194530241,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004912747801469984,
|
|
"loss": 5.2722,
|
|
"mean_token_accuracy": 0.2014525279402733,
|
|
"num_tokens": 19707922.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.423628091812134,
|
|
"epoch": 0.9923063963609816,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000491263704555005,
|
|
"loss": 5.2151,
|
|
"mean_token_accuracy": 0.19532766938209534,
|
|
"num_tokens": 19718693.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.465753889083862,
|
|
"epoch": 0.9928679732689392,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004912526220770913,
|
|
"loss": 5.2905,
|
|
"mean_token_accuracy": 0.1943553179502487,
|
|
"num_tokens": 19730846.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.500577354431153,
|
|
"epoch": 0.9934295501768967,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004912415327136103,
|
|
"loss": 5.3017,
|
|
"mean_token_accuracy": 0.20023206174373626,
|
|
"num_tokens": 19742099.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.545119380950927,
|
|
"epoch": 0.9939911270848543,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000491230436464915,
|
|
"loss": 5.3017,
|
|
"mean_token_accuracy": 0.1975068509578705,
|
|
"num_tokens": 19753216.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.490866613388062,
|
|
"epoch": 0.9945527039928118,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004912193333313589,
|
|
"loss": 5.2465,
|
|
"mean_token_accuracy": 0.19712071716785431,
|
|
"num_tokens": 19765316.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.4881330013275145,
|
|
"epoch": 0.9951142809007694,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004912082233132951,
|
|
"loss": 5.2666,
|
|
"mean_token_accuracy": 0.19463828206062317,
|
|
"num_tokens": 19776208.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.560824251174926,
|
|
"epoch": 0.9956758578087269,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004911971064110778,
|
|
"loss": 5.301,
|
|
"mean_token_accuracy": 0.19955289661884307,
|
|
"num_tokens": 19788065.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.509456396102905,
|
|
"epoch": 0.9962374347166845,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004911859826250607,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.19480395019054414,
|
|
"num_tokens": 19799388.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.5303130626678465,
|
|
"epoch": 0.996799011624642,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004911748519555981,
|
|
"loss": 5.3259,
|
|
"mean_token_accuracy": 0.1891831636428833,
|
|
"num_tokens": 19809933.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.620634746551514,
|
|
"epoch": 0.9973605885325996,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004911637144030444,
|
|
"loss": 5.4136,
|
|
"mean_token_accuracy": 0.18932687044143676,
|
|
"num_tokens": 19821566.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.571918249130249,
|
|
"epoch": 0.9979221654405571,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004911525699677541,
|
|
"loss": 5.3724,
|
|
"mean_token_accuracy": 0.19498956203460693,
|
|
"num_tokens": 19833727.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.572908639907837,
|
|
"epoch": 0.9984837423485147,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004911414186500822,
|
|
"loss": 5.392,
|
|
"mean_token_accuracy": 0.1903043270111084,
|
|
"num_tokens": 19845176.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.5138904571533205,
|
|
"epoch": 0.9990453192564722,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004911302604503837,
|
|
"loss": 5.2911,
|
|
"mean_token_accuracy": 0.18927495181560516,
|
|
"num_tokens": 19857528.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.549451923370361,
|
|
"epoch": 0.9996068961644298,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004911190953690139,
|
|
"loss": 5.2114,
|
|
"mean_token_accuracy": 0.19732483476400375,
|
|
"num_tokens": 19868232.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.4804858101738825,
|
|
"epoch": 1.0001123153815914,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004911079234063284,
|
|
"loss": 5.1536,
|
|
"mean_token_accuracy": 0.20015125473340353,
|
|
"num_tokens": 19877881.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.396058654785156,
|
|
"epoch": 1.000673892289549,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004910967445626826,
|
|
"loss": 5.2504,
|
|
"mean_token_accuracy": 0.20254514813423158,
|
|
"num_tokens": 19888398.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.541640901565552,
|
|
"epoch": 1.0012354691975065,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004910855588384327,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.20296085327863694,
|
|
"num_tokens": 19899661.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.555482578277588,
|
|
"epoch": 1.0017970461054642,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004910743662339348,
|
|
"loss": 5.2615,
|
|
"mean_token_accuracy": 0.20101720690727234,
|
|
"num_tokens": 19911073.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.463236618041992,
|
|
"epoch": 1.0023586230134216,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004910631667495452,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.20411583483219148,
|
|
"num_tokens": 19922567.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.560108327865601,
|
|
"epoch": 1.0029201999213793,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004910519603856207,
|
|
"loss": 5.296,
|
|
"mean_token_accuracy": 0.19743030667304992,
|
|
"num_tokens": 19934547.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.4949757099151615,
|
|
"epoch": 1.0034817768293367,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004910407471425179,
|
|
"loss": 5.2888,
|
|
"mean_token_accuracy": 0.19609466642141343,
|
|
"num_tokens": 19947659.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.531194591522217,
|
|
"epoch": 1.0040433537372944,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000491029527020594,
|
|
"loss": 5.2054,
|
|
"mean_token_accuracy": 0.19615259468555452,
|
|
"num_tokens": 19958150.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.472798204421997,
|
|
"epoch": 1.0046049306452518,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004910183000202061,
|
|
"loss": 5.1853,
|
|
"mean_token_accuracy": 0.20172982066869735,
|
|
"num_tokens": 19968173.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.453453397750854,
|
|
"epoch": 1.0051665075532095,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004910070661417119,
|
|
"loss": 5.2407,
|
|
"mean_token_accuracy": 0.19461157023906708,
|
|
"num_tokens": 19978543.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.512823152542114,
|
|
"epoch": 1.005728084461167,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004909958253854687,
|
|
"loss": 5.2117,
|
|
"mean_token_accuracy": 0.19809273034334182,
|
|
"num_tokens": 19989586.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.5184050559997555,
|
|
"epoch": 1.0062896613691246,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004909845777518347,
|
|
"loss": 5.2273,
|
|
"mean_token_accuracy": 0.19661420583724976,
|
|
"num_tokens": 20000524.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.567474222183227,
|
|
"epoch": 1.006851238277082,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004909733232411681,
|
|
"loss": 5.3365,
|
|
"mean_token_accuracy": 0.1945196881890297,
|
|
"num_tokens": 20012935.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.499795770645141,
|
|
"epoch": 1.0074128151850397,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004909620618538271,
|
|
"loss": 5.2742,
|
|
"mean_token_accuracy": 0.19491551965475082,
|
|
"num_tokens": 20024435.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.528020858764648,
|
|
"epoch": 1.007974392092997,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004909507935901702,
|
|
"loss": 5.2646,
|
|
"mean_token_accuracy": 0.1961827978491783,
|
|
"num_tokens": 20036017.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.547647142410279,
|
|
"epoch": 1.0085359690009548,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004909395184505564,
|
|
"loss": 5.2806,
|
|
"mean_token_accuracy": 0.19958003759384155,
|
|
"num_tokens": 20047216.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.481222105026245,
|
|
"epoch": 1.0090975459089122,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004909282364353445,
|
|
"loss": 5.1365,
|
|
"mean_token_accuracy": 0.20559441447257995,
|
|
"num_tokens": 20057439.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.515385723114013,
|
|
"epoch": 1.0096591228168699,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004909169475448938,
|
|
"loss": 5.2931,
|
|
"mean_token_accuracy": 0.19677991718053817,
|
|
"num_tokens": 20069602.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.465009069442749,
|
|
"epoch": 1.0102206997248273,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004909056517795638,
|
|
"loss": 5.2476,
|
|
"mean_token_accuracy": 0.2002618208527565,
|
|
"num_tokens": 20081366.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.524226188659668,
|
|
"epoch": 1.010782276632785,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004908943491397141,
|
|
"loss": 5.2482,
|
|
"mean_token_accuracy": 0.20423384308815,
|
|
"num_tokens": 20091384.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 1.010782276632785,
|
|
"eval_entropy": 5.3189411881599105,
|
|
"eval_loss": 5.32230806350708,
|
|
"eval_mean_token_accuracy": 0.20194207033181363,
|
|
"eval_num_tokens": 20091384.0,
|
|
"eval_runtime": 18.4866,
|
|
"eval_samples_per_second": 1677.59,
|
|
"eval_steps_per_second": 209.719,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.583727216720581,
|
|
"epoch": 1.0113438535407424,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004908830396257045,
|
|
"loss": 5.2568,
|
|
"mean_token_accuracy": 0.19337106347084046,
|
|
"num_tokens": 20102953.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.4839965343475345,
|
|
"epoch": 1.0119054304486998,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004908717232378953,
|
|
"loss": 5.2081,
|
|
"mean_token_accuracy": 0.20201504230499268,
|
|
"num_tokens": 20113672.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.496430397033691,
|
|
"epoch": 1.0124670073566575,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004908603999766467,
|
|
"loss": 5.2308,
|
|
"mean_token_accuracy": 0.19618422091007232,
|
|
"num_tokens": 20125143.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.522008228302002,
|
|
"epoch": 1.013028584264615,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004908490698423191,
|
|
"loss": 5.2353,
|
|
"mean_token_accuracy": 0.19966784119606018,
|
|
"num_tokens": 20135489.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.463982200622558,
|
|
"epoch": 1.0135901611725726,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004908377328352736,
|
|
"loss": 5.2354,
|
|
"mean_token_accuracy": 0.20298486202955246,
|
|
"num_tokens": 20146768.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.323273515701294,
|
|
"epoch": 1.01415173808053,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004908263889558709,
|
|
"loss": 5.0436,
|
|
"mean_token_accuracy": 0.20798300206661224,
|
|
"num_tokens": 20156894.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.513165903091431,
|
|
"epoch": 1.0147133149884877,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004908150382044722,
|
|
"loss": 5.2579,
|
|
"mean_token_accuracy": 0.20556545108556748,
|
|
"num_tokens": 20168174.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.5859458446502686,
|
|
"epoch": 1.0152748918964452,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000490803680581439,
|
|
"loss": 5.3437,
|
|
"mean_token_accuracy": 0.18951404690742493,
|
|
"num_tokens": 20179962.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.51582899093628,
|
|
"epoch": 1.0158364688044028,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000490792316087133,
|
|
"loss": 5.2449,
|
|
"mean_token_accuracy": 0.198522213101387,
|
|
"num_tokens": 20189842.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.469941806793213,
|
|
"epoch": 1.0163980457123603,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004907809447219158,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.20657957941293717,
|
|
"num_tokens": 20200471.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.495346593856811,
|
|
"epoch": 1.016959622620318,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004907695664861498,
|
|
"loss": 5.2226,
|
|
"mean_token_accuracy": 0.1934772327542305,
|
|
"num_tokens": 20212145.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.508553457260132,
|
|
"epoch": 1.0175211995282754,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004907581813801971,
|
|
"loss": 5.1937,
|
|
"mean_token_accuracy": 0.20555748790502548,
|
|
"num_tokens": 20222454.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.605180501937866,
|
|
"epoch": 1.018082776436233,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004907467894044202,
|
|
"loss": 5.341,
|
|
"mean_token_accuracy": 0.19292936325073243,
|
|
"num_tokens": 20233402.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.429851055145264,
|
|
"epoch": 1.0186443533441905,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004907353905591817,
|
|
"loss": 5.1479,
|
|
"mean_token_accuracy": 0.20717176645994187,
|
|
"num_tokens": 20244102.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.569330358505249,
|
|
"epoch": 1.0192059302521481,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000490723984844845,
|
|
"loss": 5.3466,
|
|
"mean_token_accuracy": 0.195126311480999,
|
|
"num_tokens": 20255003.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.512718629837036,
|
|
"epoch": 1.0197675071601056,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004907125722617727,
|
|
"loss": 5.184,
|
|
"mean_token_accuracy": 0.19991266429424287,
|
|
"num_tokens": 20265211.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.477661800384522,
|
|
"epoch": 1.0203290840680632,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004907011528103285,
|
|
"loss": 5.1613,
|
|
"mean_token_accuracy": 0.20236938893795015,
|
|
"num_tokens": 20276552.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.538715934753418,
|
|
"epoch": 1.0208906609760207,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004906897264908759,
|
|
"loss": 5.2848,
|
|
"mean_token_accuracy": 0.19699635207653046,
|
|
"num_tokens": 20286805.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.54463152885437,
|
|
"epoch": 1.0214522378839783,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004906782933037789,
|
|
"loss": 5.2308,
|
|
"mean_token_accuracy": 0.20046712905168534,
|
|
"num_tokens": 20298536.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.477355098724365,
|
|
"epoch": 1.0220138147919358,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004906668532494012,
|
|
"loss": 5.2267,
|
|
"mean_token_accuracy": 0.1972913846373558,
|
|
"num_tokens": 20309842.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.463448143005371,
|
|
"epoch": 1.0225753916998932,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004906554063281074,
|
|
"loss": 5.1551,
|
|
"mean_token_accuracy": 0.20000912994146347,
|
|
"num_tokens": 20320413.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.4874673843383786,
|
|
"epoch": 1.0231369686078509,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004906439525402618,
|
|
"loss": 5.21,
|
|
"mean_token_accuracy": 0.19910569936037065,
|
|
"num_tokens": 20331812.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.464101123809814,
|
|
"epoch": 1.0236985455158083,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004906324918862291,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.20653669387102128,
|
|
"num_tokens": 20342148.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.5220417976379395,
|
|
"epoch": 1.024260122423766,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004906210243663742,
|
|
"loss": 5.2656,
|
|
"mean_token_accuracy": 0.1975223734974861,
|
|
"num_tokens": 20353843.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.507647180557251,
|
|
"epoch": 1.0248216993317234,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004906095499810622,
|
|
"loss": 5.2507,
|
|
"mean_token_accuracy": 0.1995355397462845,
|
|
"num_tokens": 20364846.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.5044286251068115,
|
|
"epoch": 1.025383276239681,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004905980687306586,
|
|
"loss": 5.1992,
|
|
"mean_token_accuracy": 0.20238448083400726,
|
|
"num_tokens": 20376874.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.488220834732056,
|
|
"epoch": 1.0259448531476385,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004905865806155288,
|
|
"loss": 5.1963,
|
|
"mean_token_accuracy": 0.20079576671123506,
|
|
"num_tokens": 20388189.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.5182538509368895,
|
|
"epoch": 1.0265064300555962,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004905750856360387,
|
|
"loss": 5.2382,
|
|
"mean_token_accuracy": 0.2024891421198845,
|
|
"num_tokens": 20399155.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.4669781684875485,
|
|
"epoch": 1.0270680069635536,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004905635837925543,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.20529061406850815,
|
|
"num_tokens": 20410569.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.404199934005737,
|
|
"epoch": 1.0276295838715113,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004905520750854418,
|
|
"loss": 5.1762,
|
|
"mean_token_accuracy": 0.20634560585021972,
|
|
"num_tokens": 20420438.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.500921154022217,
|
|
"epoch": 1.0281911607794687,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004905405595150674,
|
|
"loss": 5.2257,
|
|
"mean_token_accuracy": 0.20004838705062866,
|
|
"num_tokens": 20431874.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.472363758087158,
|
|
"epoch": 1.0287527376874264,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004905290370817982,
|
|
"loss": 5.2302,
|
|
"mean_token_accuracy": 0.19746422320604323,
|
|
"num_tokens": 20442792.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.5148707866668705,
|
|
"epoch": 1.0293143145953838,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000490517507786001,
|
|
"loss": 5.2288,
|
|
"mean_token_accuracy": 0.19690819084644318,
|
|
"num_tokens": 20454410.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.598886346817016,
|
|
"epoch": 1.0298758915033415,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004905059716280425,
|
|
"loss": 5.3649,
|
|
"mean_token_accuracy": 0.1899912029504776,
|
|
"num_tokens": 20467072.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.537892818450928,
|
|
"epoch": 1.030437468411299,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004904944286082904,
|
|
"loss": 5.283,
|
|
"mean_token_accuracy": 0.20207869708538057,
|
|
"num_tokens": 20477697.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.48917145729065,
|
|
"epoch": 1.0309990453192566,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004904828787271121,
|
|
"loss": 5.1154,
|
|
"mean_token_accuracy": 0.20494226962327958,
|
|
"num_tokens": 20489024.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.473089170455933,
|
|
"epoch": 1.031560622227214,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004904713219848753,
|
|
"loss": 5.2037,
|
|
"mean_token_accuracy": 0.1965711459517479,
|
|
"num_tokens": 20499928.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.461671495437622,
|
|
"epoch": 1.0321221991351717,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004904597583819481,
|
|
"loss": 5.2574,
|
|
"mean_token_accuracy": 0.19312940090894698,
|
|
"num_tokens": 20511085.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.492776775360108,
|
|
"epoch": 1.032683776043129,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004904481879186987,
|
|
"loss": 5.1024,
|
|
"mean_token_accuracy": 0.20232841968536378,
|
|
"num_tokens": 20522164.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.521366453170776,
|
|
"epoch": 1.0332453529510865,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004904366105954954,
|
|
"loss": 5.2945,
|
|
"mean_token_accuracy": 0.20026582926511766,
|
|
"num_tokens": 20534187.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.576307392120361,
|
|
"epoch": 1.0338069298590442,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004904250264127067,
|
|
"loss": 5.2574,
|
|
"mean_token_accuracy": 0.202733638882637,
|
|
"num_tokens": 20545819.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.588125324249267,
|
|
"epoch": 1.0343685067670016,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004904134353707018,
|
|
"loss": 5.2712,
|
|
"mean_token_accuracy": 0.19890021830797194,
|
|
"num_tokens": 20556803.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.535311460494995,
|
|
"epoch": 1.0349300836749593,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004904018374698496,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.198699426651001,
|
|
"num_tokens": 20567366.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.507753562927246,
|
|
"epoch": 1.0354916605829168,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004903902327105191,
|
|
"loss": 5.2962,
|
|
"mean_token_accuracy": 0.1953882098197937,
|
|
"num_tokens": 20579182.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.466451406478882,
|
|
"epoch": 1.0360532374908744,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004903786210930803,
|
|
"loss": 5.1512,
|
|
"mean_token_accuracy": 0.20047435015439988,
|
|
"num_tokens": 20590346.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.525947904586792,
|
|
"epoch": 1.0366148143988319,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004903670026179025,
|
|
"loss": 5.2595,
|
|
"mean_token_accuracy": 0.2004369929432869,
|
|
"num_tokens": 20601279.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.495059537887573,
|
|
"epoch": 1.0371763913067895,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000490355377285356,
|
|
"loss": 5.1696,
|
|
"mean_token_accuracy": 0.19908430725336074,
|
|
"num_tokens": 20612163.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.486514663696289,
|
|
"epoch": 1.037737968214747,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004903437450958106,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.20307854413986207,
|
|
"num_tokens": 20622587.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.505575513839721,
|
|
"epoch": 1.0382995451227046,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004903321060496369,
|
|
"loss": 5.3125,
|
|
"mean_token_accuracy": 0.18896912038326263,
|
|
"num_tokens": 20633341.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.44008207321167,
|
|
"epoch": 1.038861122030662,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004903204601472054,
|
|
"loss": 5.1862,
|
|
"mean_token_accuracy": 0.20291981101036072,
|
|
"num_tokens": 20644582.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.502528667449951,
|
|
"epoch": 1.0394226989386197,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004903088073888869,
|
|
"loss": 5.1559,
|
|
"mean_token_accuracy": 0.2060237005352974,
|
|
"num_tokens": 20654936.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.479387903213501,
|
|
"epoch": 1.0399842758465772,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004902971477750526,
|
|
"loss": 5.18,
|
|
"mean_token_accuracy": 0.19857182800769807,
|
|
"num_tokens": 20666348.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.576429319381714,
|
|
"epoch": 1.0405458527545348,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004902854813060736,
|
|
"loss": 5.3527,
|
|
"mean_token_accuracy": 0.19512815177440643,
|
|
"num_tokens": 20677482.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.556309175491333,
|
|
"epoch": 1.0411074296624923,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004902738079823213,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.20312489569187164,
|
|
"num_tokens": 20688369.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.447544813156128,
|
|
"epoch": 1.04166900657045,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004902621278041674,
|
|
"loss": 5.2744,
|
|
"mean_token_accuracy": 0.19016608595848083,
|
|
"num_tokens": 20698933.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.490622854232788,
|
|
"epoch": 1.0422305834784074,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004902504407719839,
|
|
"loss": 5.1313,
|
|
"mean_token_accuracy": 0.20354401618242263,
|
|
"num_tokens": 20710192.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.493754100799561,
|
|
"epoch": 1.042792160386365,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004902387468861429,
|
|
"loss": 5.211,
|
|
"mean_token_accuracy": 0.198832930624485,
|
|
"num_tokens": 20721408.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.438203191757202,
|
|
"epoch": 1.0433537372943225,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004902270461470169,
|
|
"loss": 5.1104,
|
|
"mean_token_accuracy": 0.2063740983605385,
|
|
"num_tokens": 20732155.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.441533136367798,
|
|
"epoch": 1.04391531420228,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000490215338554978,
|
|
"loss": 5.1046,
|
|
"mean_token_accuracy": 0.20939861536026,
|
|
"num_tokens": 20741819.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.513307857513428,
|
|
"epoch": 1.0444768911102376,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004902036241103994,
|
|
"loss": 5.2478,
|
|
"mean_token_accuracy": 0.19722046107053756,
|
|
"num_tokens": 20754931.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.499553060531616,
|
|
"epoch": 1.045038468018195,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004901919028136539,
|
|
"loss": 5.3198,
|
|
"mean_token_accuracy": 0.18906616121530534,
|
|
"num_tokens": 20766533.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.471915340423584,
|
|
"epoch": 1.0456000449261527,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004901801746651147,
|
|
"loss": 5.1732,
|
|
"mean_token_accuracy": 0.20560022741556166,
|
|
"num_tokens": 20777055.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.426851415634156,
|
|
"epoch": 1.04616162183411,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004901684396651554,
|
|
"loss": 5.1155,
|
|
"mean_token_accuracy": 0.20422170162200928,
|
|
"num_tokens": 20786871.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.541410255432129,
|
|
"epoch": 1.0467231987420678,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004901566978141494,
|
|
"loss": 5.2817,
|
|
"mean_token_accuracy": 0.1956240639090538,
|
|
"num_tokens": 20798546.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.525883913040161,
|
|
"epoch": 1.0472847756500252,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004901449491124708,
|
|
"loss": 5.2088,
|
|
"mean_token_accuracy": 0.19941770881414414,
|
|
"num_tokens": 20809657.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.440621995925904,
|
|
"epoch": 1.0478463525579829,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004901331935604936,
|
|
"loss": 5.2298,
|
|
"mean_token_accuracy": 0.194198140501976,
|
|
"num_tokens": 20819662.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.3771546363830565,
|
|
"epoch": 1.0484079294659403,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000490121431158592,
|
|
"loss": 5.0884,
|
|
"mean_token_accuracy": 0.21119288653135299,
|
|
"num_tokens": 20830554.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.50520920753479,
|
|
"epoch": 1.048969506373898,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004901096619071407,
|
|
"loss": 5.2674,
|
|
"mean_token_accuracy": 0.1961747795343399,
|
|
"num_tokens": 20842003.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.487845182418823,
|
|
"epoch": 1.0495310832818554,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004900978858065142,
|
|
"loss": 5.2625,
|
|
"mean_token_accuracy": 0.20116258412599564,
|
|
"num_tokens": 20853453.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.585537052154541,
|
|
"epoch": 1.050092660189813,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004900861028570877,
|
|
"loss": 5.3101,
|
|
"mean_token_accuracy": 0.19838019460439682,
|
|
"num_tokens": 20867296.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.447028160095215,
|
|
"epoch": 1.0506542370977705,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004900743130592362,
|
|
"loss": 5.1996,
|
|
"mean_token_accuracy": 0.20565367192029954,
|
|
"num_tokens": 20878951.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.543765926361084,
|
|
"epoch": 1.0512158140057282,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004900625164133351,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.1965576171875,
|
|
"num_tokens": 20891103.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.5436663150787355,
|
|
"epoch": 1.0517773909136856,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004900507129197601,
|
|
"loss": 5.3617,
|
|
"mean_token_accuracy": 0.19579455703496934,
|
|
"num_tokens": 20903570.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.555352687835693,
|
|
"epoch": 1.0523389678216433,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004900389025788871,
|
|
"loss": 5.3124,
|
|
"mean_token_accuracy": 0.19468713104724883,
|
|
"num_tokens": 20914156.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.464226150512696,
|
|
"epoch": 1.0529005447296007,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000490027085391092,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.20149350464344024,
|
|
"num_tokens": 20925192.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.481942415237427,
|
|
"epoch": 1.0534621216375584,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000490015261356751,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.21118777990341187,
|
|
"num_tokens": 20935281.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.567909908294678,
|
|
"epoch": 1.0540236985455158,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004900034304762408,
|
|
"loss": 5.309,
|
|
"mean_token_accuracy": 0.19850397258996963,
|
|
"num_tokens": 20947397.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.432170438766479,
|
|
"epoch": 1.0545852754534732,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000489991592749938,
|
|
"loss": 5.1667,
|
|
"mean_token_accuracy": 0.2089316129684448,
|
|
"num_tokens": 20958473.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.603392505645752,
|
|
"epoch": 1.055146852361431,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004899797481782193,
|
|
"loss": 5.2826,
|
|
"mean_token_accuracy": 0.19170767068862915,
|
|
"num_tokens": 20970112.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.4718832015991214,
|
|
"epoch": 1.0557084292693883,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004899678967614623,
|
|
"loss": 5.191,
|
|
"mean_token_accuracy": 0.20091700702905654,
|
|
"num_tokens": 20980762.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.404077100753784,
|
|
"epoch": 1.056270006177346,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004899560385000439,
|
|
"loss": 5.0995,
|
|
"mean_token_accuracy": 0.20930145382881166,
|
|
"num_tokens": 20991663.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.462149143218994,
|
|
"epoch": 1.0568315830853034,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000489944173394342,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.2062255322933197,
|
|
"num_tokens": 21002121.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.473354530334473,
|
|
"epoch": 1.0573931599932611,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004899323014447342,
|
|
"loss": 5.1957,
|
|
"mean_token_accuracy": 0.19004318863153458,
|
|
"num_tokens": 21013791.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.440091562271118,
|
|
"epoch": 1.0579547369012186,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004899204226515985,
|
|
"loss": 5.1143,
|
|
"mean_token_accuracy": 0.20271998196840285,
|
|
"num_tokens": 21022977.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.492621946334839,
|
|
"epoch": 1.0585163138091762,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004899085370153133,
|
|
"loss": 5.3023,
|
|
"mean_token_accuracy": 0.19832295030355454,
|
|
"num_tokens": 21036372.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.609709692001343,
|
|
"epoch": 1.0590778907171337,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004898966445362569,
|
|
"loss": 5.3715,
|
|
"mean_token_accuracy": 0.18739080280065537,
|
|
"num_tokens": 21047984.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.559036779403686,
|
|
"epoch": 1.0596394676250913,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004898847452148079,
|
|
"loss": 5.2385,
|
|
"mean_token_accuracy": 0.19740052074193953,
|
|
"num_tokens": 21060127.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.469058179855347,
|
|
"epoch": 1.0602010445330488,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004898728390513454,
|
|
"loss": 5.2021,
|
|
"mean_token_accuracy": 0.19429519325494765,
|
|
"num_tokens": 21070659.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.467495346069336,
|
|
"epoch": 1.0607626214410064,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004898609260462483,
|
|
"loss": 5.1467,
|
|
"mean_token_accuracy": 0.20710503607988356,
|
|
"num_tokens": 21081667.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.452310180664062,
|
|
"epoch": 1.0613241983489639,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004898490061998961,
|
|
"loss": 5.1669,
|
|
"mean_token_accuracy": 0.2016437292098999,
|
|
"num_tokens": 21094275.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.497532081604004,
|
|
"epoch": 1.0618857752569215,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004898370795126681,
|
|
"loss": 5.2257,
|
|
"mean_token_accuracy": 0.20021361410617827,
|
|
"num_tokens": 21106360.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.5165211200714115,
|
|
"epoch": 1.062447352164879,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004898251459849441,
|
|
"loss": 5.194,
|
|
"mean_token_accuracy": 0.2019632026553154,
|
|
"num_tokens": 21117647.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.380741357803345,
|
|
"epoch": 1.0630089290728366,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004898132056171041,
|
|
"loss": 5.0442,
|
|
"mean_token_accuracy": 0.21173667162656784,
|
|
"num_tokens": 21129599.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.475966739654541,
|
|
"epoch": 1.063570505980794,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004898012584095285,
|
|
"loss": 5.1514,
|
|
"mean_token_accuracy": 0.2001177340745926,
|
|
"num_tokens": 21140573.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.49524245262146,
|
|
"epoch": 1.0641320828887517,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004897893043625975,
|
|
"loss": 5.2613,
|
|
"mean_token_accuracy": 0.20271366387605666,
|
|
"num_tokens": 21151899.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.561719799041748,
|
|
"epoch": 1.0646936597967092,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004897773434766917,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.189687779545784,
|
|
"num_tokens": 21162748.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.508446550369262,
|
|
"epoch": 1.0652552367046666,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000489765375752192,
|
|
"loss": 5.2299,
|
|
"mean_token_accuracy": 0.2017131581902504,
|
|
"num_tokens": 21172962.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.532747745513916,
|
|
"epoch": 1.0658168136126243,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004897534011894793,
|
|
"loss": 5.2009,
|
|
"mean_token_accuracy": 0.20353374034166336,
|
|
"num_tokens": 21183805.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.423833847045898,
|
|
"epoch": 1.0663783905205817,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004897414197889352,
|
|
"loss": 5.1253,
|
|
"mean_token_accuracy": 0.20723408013582229,
|
|
"num_tokens": 21195129.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.404111719131469,
|
|
"epoch": 1.0669399674285394,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000489729431550941,
|
|
"loss": 5.2491,
|
|
"mean_token_accuracy": 0.1957872211933136,
|
|
"num_tokens": 21206300.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.516879224777222,
|
|
"epoch": 1.0675015443364968,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004897174364758783,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.19922613501548767,
|
|
"num_tokens": 21217137.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.482291221618652,
|
|
"epoch": 1.0680631212444545,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004897054345641291,
|
|
"loss": 5.1546,
|
|
"mean_token_accuracy": 0.2049860805273056,
|
|
"num_tokens": 21228399.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.500407743453979,
|
|
"epoch": 1.068624698152412,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004896934258160757,
|
|
"loss": 5.2742,
|
|
"mean_token_accuracy": 0.19596217423677445,
|
|
"num_tokens": 21239396.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.498952722549438,
|
|
"epoch": 1.0691862750603696,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004896814102321004,
|
|
"loss": 5.1819,
|
|
"mean_token_accuracy": 0.20035670697689056,
|
|
"num_tokens": 21249966.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.473047208786011,
|
|
"epoch": 1.069747851968327,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004896693878125857,
|
|
"loss": 5.1818,
|
|
"mean_token_accuracy": 0.20321815758943557,
|
|
"num_tokens": 21260157.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.507161808013916,
|
|
"epoch": 1.0703094288762847,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004896573585579144,
|
|
"loss": 5.2423,
|
|
"mean_token_accuracy": 0.20358157753944398,
|
|
"num_tokens": 21270738.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.459889268875122,
|
|
"epoch": 1.070871005784242,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004896453224684695,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.2016464203596115,
|
|
"num_tokens": 21282469.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.420162153244019,
|
|
"epoch": 1.0714325826921998,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004896332795446345,
|
|
"loss": 5.1494,
|
|
"mean_token_accuracy": 0.19594088941812515,
|
|
"num_tokens": 21293474.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.5055560111999515,
|
|
"epoch": 1.0719941596001572,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004896212297867924,
|
|
"loss": 5.2751,
|
|
"mean_token_accuracy": 0.19317637383937836,
|
|
"num_tokens": 21304904.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.5614612102508545,
|
|
"epoch": 1.0725557365081149,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004896091731953271,
|
|
"loss": 5.2233,
|
|
"mean_token_accuracy": 0.19620270878076554,
|
|
"num_tokens": 21315407.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.440782308578491,
|
|
"epoch": 1.0731173134160723,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004895971097706227,
|
|
"loss": 5.1531,
|
|
"mean_token_accuracy": 0.20602274537086487,
|
|
"num_tokens": 21326496.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.476405477523803,
|
|
"epoch": 1.07367889032403,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004895850395130629,
|
|
"loss": 5.2445,
|
|
"mean_token_accuracy": 0.19865497350692748,
|
|
"num_tokens": 21339449.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.495727062225342,
|
|
"epoch": 1.0742404672319874,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004895729624230323,
|
|
"loss": 5.2984,
|
|
"mean_token_accuracy": 0.19452223628759385,
|
|
"num_tokens": 21350431.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.462311553955078,
|
|
"epoch": 1.074802044139945,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004895608785009153,
|
|
"loss": 5.185,
|
|
"mean_token_accuracy": 0.20112013518810273,
|
|
"num_tokens": 21361168.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.50471568107605,
|
|
"epoch": 1.0753636210479025,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004895487877470969,
|
|
"loss": 5.1944,
|
|
"mean_token_accuracy": 0.20499631464481355,
|
|
"num_tokens": 21372635.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.435432958602905,
|
|
"epoch": 1.07592519795586,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004895366901619617,
|
|
"loss": 5.1865,
|
|
"mean_token_accuracy": 0.19774627536535264,
|
|
"num_tokens": 21384051.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.450306129455567,
|
|
"epoch": 1.0764867748638176,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004895245857458951,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.19065044969320297,
|
|
"num_tokens": 21397496.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.439748001098633,
|
|
"epoch": 1.077048351771775,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004895124744992825,
|
|
"loss": 5.2761,
|
|
"mean_token_accuracy": 0.1959267020225525,
|
|
"num_tokens": 21409349.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.500283527374267,
|
|
"epoch": 1.0776099286797327,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004895003564225095,
|
|
"loss": 5.2343,
|
|
"mean_token_accuracy": 0.2013654440641403,
|
|
"num_tokens": 21421843.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.4338454246521,
|
|
"epoch": 1.0781715055876901,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004894882315159621,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.203974212706089,
|
|
"num_tokens": 21433230.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.507578992843628,
|
|
"epoch": 1.0787330824956478,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000489476099780026,
|
|
"loss": 5.226,
|
|
"mean_token_accuracy": 0.19867302775382994,
|
|
"num_tokens": 21444295.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.505974197387696,
|
|
"epoch": 1.0792946594036052,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004894639612150879,
|
|
"loss": 5.1701,
|
|
"mean_token_accuracy": 0.1997839853167534,
|
|
"num_tokens": 21455721.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.469446182250977,
|
|
"epoch": 1.079856236311563,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004894518158215339,
|
|
"loss": 5.2085,
|
|
"mean_token_accuracy": 0.20309991687536239,
|
|
"num_tokens": 21466514.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.479997968673706,
|
|
"epoch": 1.0804178132195204,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000489439663599751,
|
|
"loss": 5.2424,
|
|
"mean_token_accuracy": 0.19875058829784392,
|
|
"num_tokens": 21478782.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.5083568572998045,
|
|
"epoch": 1.080979390127478,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000489427504550126,
|
|
"loss": 5.207,
|
|
"mean_token_accuracy": 0.20856829285621642,
|
|
"num_tokens": 21490428.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.390064907073975,
|
|
"epoch": 1.0815409670354355,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004894153386730462,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.2056634843349457,
|
|
"num_tokens": 21501530.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.457349157333374,
|
|
"epoch": 1.0821025439433931,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004894031659688988,
|
|
"loss": 5.1511,
|
|
"mean_token_accuracy": 0.20669750720262528,
|
|
"num_tokens": 21512122.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.423903083801269,
|
|
"epoch": 1.0826641208513506,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004893909864380714,
|
|
"loss": 5.1004,
|
|
"mean_token_accuracy": 0.20614136904478073,
|
|
"num_tokens": 21521896.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.446603393554687,
|
|
"epoch": 1.0832256977593082,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000489378800080952,
|
|
"loss": 5.2613,
|
|
"mean_token_accuracy": 0.1994054138660431,
|
|
"num_tokens": 21533584.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.423087167739868,
|
|
"epoch": 1.0837872746672657,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004893666068979283,
|
|
"loss": 5.2331,
|
|
"mean_token_accuracy": 0.20098746865987777,
|
|
"num_tokens": 21545432.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.487134695053101,
|
|
"epoch": 1.0843488515752233,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004893544068893887,
|
|
"loss": 5.2212,
|
|
"mean_token_accuracy": 0.19565849304199218,
|
|
"num_tokens": 21556547.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.498757028579712,
|
|
"epoch": 1.0849104284831808,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004893422000557217,
|
|
"loss": 5.2763,
|
|
"mean_token_accuracy": 0.19918344020843506,
|
|
"num_tokens": 21567354.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.472388076782226,
|
|
"epoch": 1.0854720053911384,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004893299863973159,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.20034267902374267,
|
|
"num_tokens": 21578694.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.425048875808716,
|
|
"epoch": 1.0860335822990959,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004893177659145601,
|
|
"loss": 5.112,
|
|
"mean_token_accuracy": 0.21066864877939223,
|
|
"num_tokens": 21589365.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.487691116333008,
|
|
"epoch": 1.0865951592070533,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004893055386078438,
|
|
"loss": 5.1736,
|
|
"mean_token_accuracy": 0.19831692576408386,
|
|
"num_tokens": 21600766.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.518604183197022,
|
|
"epoch": 1.087156736115011,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004892933044775558,
|
|
"loss": 5.3533,
|
|
"mean_token_accuracy": 0.1903294190764427,
|
|
"num_tokens": 21613969.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.443315315246582,
|
|
"epoch": 1.0877183130229684,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004892810635240859,
|
|
"loss": 5.1925,
|
|
"mean_token_accuracy": 0.20269359052181243,
|
|
"num_tokens": 21626302.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.517415285110474,
|
|
"epoch": 1.088279889930926,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004892688157478238,
|
|
"loss": 5.2388,
|
|
"mean_token_accuracy": 0.19961371272802353,
|
|
"num_tokens": 21637058.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.529087495803833,
|
|
"epoch": 1.0888414668388835,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004892565611491597,
|
|
"loss": 5.2549,
|
|
"mean_token_accuracy": 0.1948593810200691,
|
|
"num_tokens": 21648729.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.3914531707763675,
|
|
"epoch": 1.0894030437468412,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004892442997284834,
|
|
"loss": 5.0555,
|
|
"mean_token_accuracy": 0.21181618720293044,
|
|
"num_tokens": 21659961.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.424667549133301,
|
|
"epoch": 1.0899646206547986,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004892320314861855,
|
|
"loss": 5.1851,
|
|
"mean_token_accuracy": 0.20293384343385695,
|
|
"num_tokens": 21670577.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.436867141723633,
|
|
"epoch": 1.0905261975627563,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004892197564226568,
|
|
"loss": 5.1329,
|
|
"mean_token_accuracy": 0.20987384170293807,
|
|
"num_tokens": 21679882.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.49023928642273,
|
|
"epoch": 1.0910877744707137,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004892074745382878,
|
|
"loss": 5.2676,
|
|
"mean_token_accuracy": 0.20245472937822342,
|
|
"num_tokens": 21690595.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.464753103256226,
|
|
"epoch": 1.0916493513786714,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004891951858334698,
|
|
"loss": 5.136,
|
|
"mean_token_accuracy": 0.2062764808535576,
|
|
"num_tokens": 21701251.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.532423591613769,
|
|
"epoch": 1.0922109282866288,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004891828903085939,
|
|
"loss": 5.3047,
|
|
"mean_token_accuracy": 0.19762960970401763,
|
|
"num_tokens": 21713286.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.527106380462646,
|
|
"epoch": 1.0927725051945865,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004891705879640518,
|
|
"loss": 5.3512,
|
|
"mean_token_accuracy": 0.1951225608587265,
|
|
"num_tokens": 21725508.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.4577264308929445,
|
|
"epoch": 1.093334082102544,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004891582788002351,
|
|
"loss": 5.157,
|
|
"mean_token_accuracy": 0.200393471121788,
|
|
"num_tokens": 21736467.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.542578458786011,
|
|
"epoch": 1.0938956590105016,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004891459628175358,
|
|
"loss": 5.2538,
|
|
"mean_token_accuracy": 0.20124907940626144,
|
|
"num_tokens": 21746114.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.439834117889404,
|
|
"epoch": 1.094457235918459,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000489133640016346,
|
|
"loss": 5.2539,
|
|
"mean_token_accuracy": 0.20151838213205336,
|
|
"num_tokens": 21757145.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.491384601593017,
|
|
"epoch": 1.0950188128264167,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004891213103970579,
|
|
"loss": 5.2419,
|
|
"mean_token_accuracy": 0.1950704574584961,
|
|
"num_tokens": 21768294.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.5173389434814455,
|
|
"epoch": 1.095580389734374,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004891089739600643,
|
|
"loss": 5.2482,
|
|
"mean_token_accuracy": 0.198778235912323,
|
|
"num_tokens": 21779667.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.372928142547607,
|
|
"epoch": 1.0961419666423318,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004890966307057581,
|
|
"loss": 5.1024,
|
|
"mean_token_accuracy": 0.20430002510547637,
|
|
"num_tokens": 21789635.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.38895993232727,
|
|
"epoch": 1.0967035435502892,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000489084280634532,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.2070479452610016,
|
|
"num_tokens": 21799462.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.384057474136353,
|
|
"epoch": 1.0972651204582466,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004890719237467794,
|
|
"loss": 5.1536,
|
|
"mean_token_accuracy": 0.2038656949996948,
|
|
"num_tokens": 21811520.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.5412544250488285,
|
|
"epoch": 1.0978266973662043,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004890595600428937,
|
|
"loss": 5.2188,
|
|
"mean_token_accuracy": 0.2000924363732338,
|
|
"num_tokens": 21821997.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.500632238388062,
|
|
"epoch": 1.0983882742741617,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004890471895232684,
|
|
"loss": 5.3001,
|
|
"mean_token_accuracy": 0.19372042864561081,
|
|
"num_tokens": 21833353.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.440681743621826,
|
|
"epoch": 1.0989498511821194,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004890348121882978,
|
|
"loss": 5.1997,
|
|
"mean_token_accuracy": 0.2040751725435257,
|
|
"num_tokens": 21843691.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.427799654006958,
|
|
"epoch": 1.0995114280900768,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004890224280383758,
|
|
"loss": 5.1678,
|
|
"mean_token_accuracy": 0.20187733620405196,
|
|
"num_tokens": 21853771.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.376798343658447,
|
|
"epoch": 1.1000730049980345,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004890100370738966,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.20886366069316864,
|
|
"num_tokens": 21863424.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.479954528808594,
|
|
"epoch": 1.100634581905992,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004889976392952548,
|
|
"loss": 5.1764,
|
|
"mean_token_accuracy": 0.20241716057062148,
|
|
"num_tokens": 21875407.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.504074382781982,
|
|
"epoch": 1.1011961588139496,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004889852347028452,
|
|
"loss": 5.2538,
|
|
"mean_token_accuracy": 0.19704989045858384,
|
|
"num_tokens": 21887081.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.442853927612305,
|
|
"epoch": 1.101757735721907,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004889728232970626,
|
|
"loss": 5.1446,
|
|
"mean_token_accuracy": 0.20125831961631774,
|
|
"num_tokens": 21897858.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.461687278747559,
|
|
"epoch": 1.1023193126298647,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004889604050783025,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.2005182236433029,
|
|
"num_tokens": 21907985.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.402402591705322,
|
|
"epoch": 1.1028808895378222,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048894798004696,
|
|
"loss": 5.2321,
|
|
"mean_token_accuracy": 0.19613478630781173,
|
|
"num_tokens": 21918726.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.437289237976074,
|
|
"epoch": 1.1034424664457798,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004889355482034309,
|
|
"loss": 5.155,
|
|
"mean_token_accuracy": 0.2014207124710083,
|
|
"num_tokens": 21929027.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.447432661056519,
|
|
"epoch": 1.1040040433537373,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004889231095481111,
|
|
"loss": 5.0969,
|
|
"mean_token_accuracy": 0.20712201595306395,
|
|
"num_tokens": 21938356.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.424928522109985,
|
|
"epoch": 1.104565620261695,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004889106640813964,
|
|
"loss": 5.145,
|
|
"mean_token_accuracy": 0.19907539188861847,
|
|
"num_tokens": 21947889.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.466288805007935,
|
|
"epoch": 1.1051271971696524,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004888982118036831,
|
|
"loss": 5.2122,
|
|
"mean_token_accuracy": 0.20456399768590927,
|
|
"num_tokens": 21958409.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.431293201446533,
|
|
"epoch": 1.10568877407761,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004888857527153679,
|
|
"loss": 5.2104,
|
|
"mean_token_accuracy": 0.1990182027220726,
|
|
"num_tokens": 21970120.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.476894378662109,
|
|
"epoch": 1.1062503509855675,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004888732868168473,
|
|
"loss": 5.175,
|
|
"mean_token_accuracy": 0.20790013670921326,
|
|
"num_tokens": 21981499.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.395249557495117,
|
|
"epoch": 1.1068119278935251,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004888608141085183,
|
|
"loss": 5.0804,
|
|
"mean_token_accuracy": 0.20860708951950074,
|
|
"num_tokens": 21991263.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.4008495807647705,
|
|
"epoch": 1.1073735048014826,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004888483345907781,
|
|
"loss": 5.0736,
|
|
"mean_token_accuracy": 0.2011837899684906,
|
|
"num_tokens": 22001582.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.442922353744507,
|
|
"epoch": 1.10793508170944,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000488835848264024,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.2074039801955223,
|
|
"num_tokens": 22012447.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.4711754322052,
|
|
"epoch": 1.1084966586173977,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004888233551286534,
|
|
"loss": 5.2498,
|
|
"mean_token_accuracy": 0.19839707762002945,
|
|
"num_tokens": 22024865.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.407338285446167,
|
|
"epoch": 1.109058235525355,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004888108551850644,
|
|
"loss": 5.1585,
|
|
"mean_token_accuracy": 0.20068008899688722,
|
|
"num_tokens": 22036298.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.506173849105835,
|
|
"epoch": 1.1096198124333128,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004887983484336548,
|
|
"loss": 5.1779,
|
|
"mean_token_accuracy": 0.20358308255672455,
|
|
"num_tokens": 22047499.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.49197359085083,
|
|
"epoch": 1.1101813893412702,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004887858348748229,
|
|
"loss": 5.2004,
|
|
"mean_token_accuracy": 0.204771189391613,
|
|
"num_tokens": 22057612.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.463781356811523,
|
|
"epoch": 1.1107429662492279,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000488773314508967,
|
|
"loss": 5.2476,
|
|
"mean_token_accuracy": 0.19992247968912125,
|
|
"num_tokens": 22068566.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.419338655471802,
|
|
"epoch": 1.1113045431571853,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004887607873364859,
|
|
"loss": 5.1273,
|
|
"mean_token_accuracy": 0.20196017026901245,
|
|
"num_tokens": 22079821.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.438948631286621,
|
|
"epoch": 1.111866120065143,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004887482533577786,
|
|
"loss": 5.1689,
|
|
"mean_token_accuracy": 0.19802613258361818,
|
|
"num_tokens": 22090143.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.403488731384277,
|
|
"epoch": 1.1124276969731004,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004887357125732438,
|
|
"loss": 5.2256,
|
|
"mean_token_accuracy": 0.20469283014535905,
|
|
"num_tokens": 22101601.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.418672657012939,
|
|
"epoch": 1.112989273881058,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000488723164983281,
|
|
"loss": 5.1314,
|
|
"mean_token_accuracy": 0.20835370272397996,
|
|
"num_tokens": 22113102.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.528254222869873,
|
|
"epoch": 1.1135508507890155,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004887106105882898,
|
|
"loss": 5.2779,
|
|
"mean_token_accuracy": 0.1999873161315918,
|
|
"num_tokens": 22124650.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.521338939666748,
|
|
"epoch": 1.1141124276969732,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004886980493886699,
|
|
"loss": 5.2067,
|
|
"mean_token_accuracy": 0.2058244228363037,
|
|
"num_tokens": 22136637.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.4421162605285645,
|
|
"epoch": 1.1146740046049306,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004886854813848212,
|
|
"loss": 5.1248,
|
|
"mean_token_accuracy": 0.20553045719861984,
|
|
"num_tokens": 22149318.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.325225496292115,
|
|
"epoch": 1.1152355815128883,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004886729065771439,
|
|
"loss": 5.0283,
|
|
"mean_token_accuracy": 0.20389310419559478,
|
|
"num_tokens": 22159410.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.426838827133179,
|
|
"epoch": 1.1157971584208457,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004886603249660384,
|
|
"loss": 5.1286,
|
|
"mean_token_accuracy": 0.20301332771778108,
|
|
"num_tokens": 22170017.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.4066869735717775,
|
|
"epoch": 1.1163587353288034,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004886477365519052,
|
|
"loss": 5.1446,
|
|
"mean_token_accuracy": 0.20368731021881104,
|
|
"num_tokens": 22179961.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.476810169219971,
|
|
"epoch": 1.1169203122367608,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004886351413351453,
|
|
"loss": 5.2501,
|
|
"mean_token_accuracy": 0.1994064450263977,
|
|
"num_tokens": 22191415.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.526557970046997,
|
|
"epoch": 1.1174818891447185,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004886225393161596,
|
|
"loss": 5.2173,
|
|
"mean_token_accuracy": 0.21241141259670257,
|
|
"num_tokens": 22205354.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.5682755470275875,
|
|
"epoch": 1.118043466052676,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004886099304953495,
|
|
"loss": 5.247,
|
|
"mean_token_accuracy": 0.19583525955677034,
|
|
"num_tokens": 22216989.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.50190839767456,
|
|
"epoch": 1.1186050429606333,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004885973148731162,
|
|
"loss": 5.2484,
|
|
"mean_token_accuracy": 0.19580172151327133,
|
|
"num_tokens": 22228421.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.464150047302246,
|
|
"epoch": 1.119166619868591,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004885846924498617,
|
|
"loss": 5.121,
|
|
"mean_token_accuracy": 0.20090800225734712,
|
|
"num_tokens": 22240621.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.37536358833313,
|
|
"epoch": 1.1197281967765484,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004885720632259876,
|
|
"loss": 5.1199,
|
|
"mean_token_accuracy": 0.20998639315366746,
|
|
"num_tokens": 22250936.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.427014493942261,
|
|
"epoch": 1.120289773684506,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004885594272018963,
|
|
"loss": 5.2387,
|
|
"mean_token_accuracy": 0.2014521688222885,
|
|
"num_tokens": 22261766.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.487332344055176,
|
|
"epoch": 1.1208513505924635,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048854678437799,
|
|
"loss": 5.1579,
|
|
"mean_token_accuracy": 0.20486941784620286,
|
|
"num_tokens": 22271831.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.405507898330688,
|
|
"epoch": 1.1214129275004212,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004885341347546713,
|
|
"loss": 5.1642,
|
|
"mean_token_accuracy": 0.20529917031526565,
|
|
"num_tokens": 22283756.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.389522361755371,
|
|
"epoch": 1.1219745044083786,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004885214783323428,
|
|
"loss": 5.1341,
|
|
"mean_token_accuracy": 0.19990193098783493,
|
|
"num_tokens": 22294576.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.433452892303467,
|
|
"epoch": 1.1225360813163363,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004885088151114076,
|
|
"loss": 5.194,
|
|
"mean_token_accuracy": 0.20485766381025314,
|
|
"num_tokens": 22305003.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.4245411396026615,
|
|
"epoch": 1.1230976582242937,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004884961450922691,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.20570219159126282,
|
|
"num_tokens": 22316505.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.469008493423462,
|
|
"epoch": 1.1236592351322514,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004884834682753305,
|
|
"loss": 5.2264,
|
|
"mean_token_accuracy": 0.20076436698436737,
|
|
"num_tokens": 22327853.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.483531427383423,
|
|
"epoch": 1.1242208120402089,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004884707846609953,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.20654843151569366,
|
|
"num_tokens": 22337386.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.4929742336273195,
|
|
"epoch": 1.1247823889481665,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004884580942496677,
|
|
"loss": 5.318,
|
|
"mean_token_accuracy": 0.1976382926106453,
|
|
"num_tokens": 22348742.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.5046240329742435,
|
|
"epoch": 1.125343965856124,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004884453970417515,
|
|
"loss": 5.2387,
|
|
"mean_token_accuracy": 0.1997467577457428,
|
|
"num_tokens": 22360083.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.460844087600708,
|
|
"epoch": 1.1259055427640816,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000488432693037651,
|
|
"loss": 5.1693,
|
|
"mean_token_accuracy": 0.19988480806350709,
|
|
"num_tokens": 22370982.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.420691251754761,
|
|
"epoch": 1.126467119672039,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000488419982237771,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.2097501888871193,
|
|
"num_tokens": 22382383.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.4389097690582275,
|
|
"epoch": 1.1270286965799967,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004884072646425157,
|
|
"loss": 5.1665,
|
|
"mean_token_accuracy": 0.19761568903923035,
|
|
"num_tokens": 22393994.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.352759122848511,
|
|
"epoch": 1.1275902734879542,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004883945402522907,
|
|
"loss": 5.0692,
|
|
"mean_token_accuracy": 0.2109847366809845,
|
|
"num_tokens": 22405354.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.398524761199951,
|
|
"epoch": 1.1281518503959118,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004883818090675005,
|
|
"loss": 5.1288,
|
|
"mean_token_accuracy": 0.20210367292165757,
|
|
"num_tokens": 22416708.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.3918815612792965,
|
|
"epoch": 1.1287134273038693,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004883690710885507,
|
|
"loss": 5.1226,
|
|
"mean_token_accuracy": 0.20373654812574388,
|
|
"num_tokens": 22427724.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.479042482376099,
|
|
"epoch": 1.1292750042118267,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004883563263158471,
|
|
"loss": 5.2148,
|
|
"mean_token_accuracy": 0.19887548238039016,
|
|
"num_tokens": 22437823.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.485242176055908,
|
|
"epoch": 1.1298365811197844,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004883435747497952,
|
|
"loss": 5.2367,
|
|
"mean_token_accuracy": 0.2065964385867119,
|
|
"num_tokens": 22450155.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.501348257064819,
|
|
"epoch": 1.130398158027742,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004883308163908012,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.19969362765550613,
|
|
"num_tokens": 22460484.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.432768678665161,
|
|
"epoch": 1.1309597349356995,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004883180512392714,
|
|
"loss": 5.1926,
|
|
"mean_token_accuracy": 0.20196976214647294,
|
|
"num_tokens": 22472063.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.421315336227417,
|
|
"epoch": 1.131521311843657,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004883052792956119,
|
|
"loss": 5.1724,
|
|
"mean_token_accuracy": 0.20803795158863067,
|
|
"num_tokens": 22483669.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.5212242126464846,
|
|
"epoch": 1.1320828887516146,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004882925005602296,
|
|
"loss": 5.2428,
|
|
"mean_token_accuracy": 0.19664522558450698,
|
|
"num_tokens": 22495505.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.4770959377288815,
|
|
"epoch": 1.132644465659572,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004882797150335314,
|
|
"loss": 5.2166,
|
|
"mean_token_accuracy": 0.198384989798069,
|
|
"num_tokens": 22505260.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.46422848701477,
|
|
"epoch": 1.1332060425675297,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048826692271592434,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.19802864491939545,
|
|
"num_tokens": 22516362.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.519613647460938,
|
|
"epoch": 1.133767619475487,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004882541236078158,
|
|
"loss": 5.2171,
|
|
"mean_token_accuracy": 0.19751207828521727,
|
|
"num_tokens": 22527760.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.597751760482788,
|
|
"epoch": 1.1343291963834448,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048824131770961316,
|
|
"loss": 5.314,
|
|
"mean_token_accuracy": 0.192897330224514,
|
|
"num_tokens": 22540601.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.436729574203492,
|
|
"epoch": 1.1348907732914022,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048822850502172437,
|
|
"loss": 5.2103,
|
|
"mean_token_accuracy": 0.19936495274305344,
|
|
"num_tokens": 22552469.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.3802038669586185,
|
|
"epoch": 1.1354523501993599,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004882156855445571,
|
|
"loss": 5.16,
|
|
"mean_token_accuracy": 0.2056436613202095,
|
|
"num_tokens": 22563552.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.454670095443726,
|
|
"epoch": 1.1360139271073173,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004882028592785199,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.20039760023355485,
|
|
"num_tokens": 22575619.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.393833065032959,
|
|
"epoch": 1.136575504015275,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048819002622402095,
|
|
"loss": 5.1408,
|
|
"mean_token_accuracy": 0.20351850092411042,
|
|
"num_tokens": 22585854.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.495423936843872,
|
|
"epoch": 1.1371370809232324,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004881771863814688,
|
|
"loss": 5.1452,
|
|
"mean_token_accuracy": 0.21022045910358428,
|
|
"num_tokens": 22595899.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.46891565322876,
|
|
"epoch": 1.13769865783119,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048816433975127244,
|
|
"loss": 5.1262,
|
|
"mean_token_accuracy": 0.2041967362165451,
|
|
"num_tokens": 22607517.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.447305297851562,
|
|
"epoch": 1.1382602347391475,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004881514863338407,
|
|
"loss": 5.2343,
|
|
"mean_token_accuracy": 0.201247338950634,
|
|
"num_tokens": 22618531.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.369872903823852,
|
|
"epoch": 1.1388218116471052,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048813862612958307,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.2056419864296913,
|
|
"num_tokens": 22629193.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.504584550857544,
|
|
"epoch": 1.1393833885550626,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004881257591389089,
|
|
"loss": 5.2001,
|
|
"mean_token_accuracy": 0.20484146624803543,
|
|
"num_tokens": 22639794.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.500708436965942,
|
|
"epoch": 1.13994496546302,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048811288536222794,
|
|
"loss": 5.1459,
|
|
"mean_token_accuracy": 0.2108313485980034,
|
|
"num_tokens": 22650061.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.47721037864685,
|
|
"epoch": 1.1405065423709777,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.00048810000479995,
|
|
"loss": 5.2162,
|
|
"mean_token_accuracy": 0.19785867333412172,
|
|
"num_tokens": 22661399.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.5784751892089846,
|
|
"epoch": 1.1410681192789354,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048808711745248524,
|
|
"loss": 5.3067,
|
|
"mean_token_accuracy": 0.19488762468099594,
|
|
"num_tokens": 22672445.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.492064809799194,
|
|
"epoch": 1.1416296961868928,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048807422332024404,
|
|
"loss": 5.1285,
|
|
"mean_token_accuracy": 0.20528274178504943,
|
|
"num_tokens": 22682545.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.460781526565552,
|
|
"epoch": 1.1421912730948502,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004880613224036369,
|
|
"loss": 5.1952,
|
|
"mean_token_accuracy": 0.19861621856689454,
|
|
"num_tokens": 22693885.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.429856681823731,
|
|
"epoch": 1.142752850002808,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048804841470307466,
|
|
"loss": 5.1185,
|
|
"mean_token_accuracy": 0.2062612310051918,
|
|
"num_tokens": 22703841.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.505462884902954,
|
|
"epoch": 1.1433144269107653,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.00048803550021896824,
|
|
"loss": 5.276,
|
|
"mean_token_accuracy": 0.19903681725263594,
|
|
"num_tokens": 22714142.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.498914051055908,
|
|
"epoch": 1.143876003818723,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004880225789517289,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.1991946205496788,
|
|
"num_tokens": 22725056.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.409213209152222,
|
|
"epoch": 1.1444375807266804,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000488009650901768,
|
|
"loss": 5.1839,
|
|
"mean_token_accuracy": 0.2094482570886612,
|
|
"num_tokens": 22735664.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.412260246276856,
|
|
"epoch": 1.144999157634638,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048799671606949724,
|
|
"loss": 5.1714,
|
|
"mean_token_accuracy": 0.20313270390033722,
|
|
"num_tokens": 22748071.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.5024231433868405,
|
|
"epoch": 1.1455607345425955,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048798377445532837,
|
|
"loss": 5.2221,
|
|
"mean_token_accuracy": 0.20186836272478104,
|
|
"num_tokens": 22759477.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.418139171600342,
|
|
"epoch": 1.1461223114505532,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004879708260596736,
|
|
"loss": 5.0972,
|
|
"mean_token_accuracy": 0.2112067773938179,
|
|
"num_tokens": 22769955.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.372469854354859,
|
|
"epoch": 1.1466838883585107,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004879578708829451,
|
|
"loss": 5.1874,
|
|
"mean_token_accuracy": 0.20161296129226686,
|
|
"num_tokens": 22781216.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.448965740203858,
|
|
"epoch": 1.1472454652664683,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004879449089255553,
|
|
"loss": 5.1296,
|
|
"mean_token_accuracy": 0.20125143676996232,
|
|
"num_tokens": 22792581.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.421170234680176,
|
|
"epoch": 1.1478070421744258,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004879319401879171,
|
|
"loss": 5.0927,
|
|
"mean_token_accuracy": 0.205929633975029,
|
|
"num_tokens": 22803305.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.489952230453492,
|
|
"epoch": 1.1483686190823834,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048791896467044335,
|
|
"loss": 5.205,
|
|
"mean_token_accuracy": 0.20840319842100144,
|
|
"num_tokens": 22815558.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.416747665405273,
|
|
"epoch": 1.1489301959903409,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048790598237354716,
|
|
"loss": 5.1374,
|
|
"mean_token_accuracy": 0.20226485431194305,
|
|
"num_tokens": 22825428.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.494300413131714,
|
|
"epoch": 1.1494917728982985,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004878929932976419,
|
|
"loss": 5.1723,
|
|
"mean_token_accuracy": 0.2065751373767853,
|
|
"num_tokens": 22836294.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.503645753860473,
|
|
"epoch": 1.150053349806256,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004878799974431412,
|
|
"loss": 5.2625,
|
|
"mean_token_accuracy": 0.20460931211709976,
|
|
"num_tokens": 22847835.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.4766439437866214,
|
|
"epoch": 1.1506149267142134,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004878669948104588,
|
|
"loss": 5.2098,
|
|
"mean_token_accuracy": 0.20376038998365403,
|
|
"num_tokens": 22859726.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.381437492370606,
|
|
"epoch": 1.151176503622171,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00048785398540000867,
|
|
"loss": 5.1593,
|
|
"mean_token_accuracy": 0.2043628767132759,
|
|
"num_tokens": 22871250.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.486570644378662,
|
|
"epoch": 1.1517380805301287,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048784096921220514,
|
|
"loss": 5.2188,
|
|
"mean_token_accuracy": 0.19860162287950517,
|
|
"num_tokens": 22882034.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.564865493774414,
|
|
"epoch": 1.1522996574380862,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004878279462474627,
|
|
"loss": 5.3111,
|
|
"mean_token_accuracy": 0.19359066486358642,
|
|
"num_tokens": 22894606.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.424198007583618,
|
|
"epoch": 1.1528612343460436,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048781491650619574,
|
|
"loss": 5.1371,
|
|
"mean_token_accuracy": 0.20448300540447234,
|
|
"num_tokens": 22905246.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.418663549423218,
|
|
"epoch": 1.1534228112540013,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048780187998881944,
|
|
"loss": 5.1001,
|
|
"mean_token_accuracy": 0.19922555088996888,
|
|
"num_tokens": 22916202.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.474135875701904,
|
|
"epoch": 1.1539843881619587,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004877888366957486,
|
|
"loss": 5.0901,
|
|
"mean_token_accuracy": 0.20679617822170257,
|
|
"num_tokens": 22926451.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.475333261489868,
|
|
"epoch": 1.1545459650699164,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004877757866273988,
|
|
"loss": 5.1615,
|
|
"mean_token_accuracy": 0.20335488319396972,
|
|
"num_tokens": 22936618.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.454792308807373,
|
|
"epoch": 1.1551075419778738,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004877627297841853,
|
|
"loss": 5.2257,
|
|
"mean_token_accuracy": 0.1988489806652069,
|
|
"num_tokens": 22948278.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.392830848693848,
|
|
"epoch": 1.1556691188858315,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004877496661665241,
|
|
"loss": 5.1031,
|
|
"mean_token_accuracy": 0.2060924395918846,
|
|
"num_tokens": 22959928.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.403790426254273,
|
|
"epoch": 1.156230695793789,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000487736595774831,
|
|
"loss": 5.1643,
|
|
"mean_token_accuracy": 0.19947277158498763,
|
|
"num_tokens": 22971050.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.35574369430542,
|
|
"epoch": 1.1567922727017466,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048772351860952215,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.2012922391295433,
|
|
"num_tokens": 22981471.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.515440988540649,
|
|
"epoch": 1.157353849609704,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004877104346710139,
|
|
"loss": 5.3299,
|
|
"mean_token_accuracy": 0.2002103105187416,
|
|
"num_tokens": 22992526.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.466501665115357,
|
|
"epoch": 1.1579154265176617,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000487697343959723,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.2042958766222,
|
|
"num_tokens": 23003408.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.4243903160095215,
|
|
"epoch": 1.158477003425619,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004876842464760661,
|
|
"loss": 5.0855,
|
|
"mean_token_accuracy": 0.206155401468277,
|
|
"num_tokens": 23013406.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.3888379573822025,
|
|
"epoch": 1.1590385803335768,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048767114222046036,
|
|
"loss": 5.1601,
|
|
"mean_token_accuracy": 0.20603561401367188,
|
|
"num_tokens": 23024960.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.507277536392212,
|
|
"epoch": 1.1596001572415342,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000487658031193323,
|
|
"loss": 5.1695,
|
|
"mean_token_accuracy": 0.20135279297828673,
|
|
"num_tokens": 23037514.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.502745771408081,
|
|
"epoch": 1.1601617341494919,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004876449133950714,
|
|
"loss": 5.2796,
|
|
"mean_token_accuracy": 0.19563647657632827,
|
|
"num_tokens": 23048460.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.487990093231201,
|
|
"epoch": 1.1607233110574493,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004876317888261233,
|
|
"loss": 5.1362,
|
|
"mean_token_accuracy": 0.20132656991481782,
|
|
"num_tokens": 23058866.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.396505355834961,
|
|
"epoch": 1.1612848879654067,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048761865748689657,
|
|
"loss": 5.1956,
|
|
"mean_token_accuracy": 0.1960831567645073,
|
|
"num_tokens": 23069097.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.519156169891358,
|
|
"epoch": 1.1618464648733644,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048760551937780927,
|
|
"loss": 5.1699,
|
|
"mean_token_accuracy": 0.20661058872938157,
|
|
"num_tokens": 23079553.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.427708721160888,
|
|
"epoch": 1.162408041781322,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048759237449927986,
|
|
"loss": 5.164,
|
|
"mean_token_accuracy": 0.2044447660446167,
|
|
"num_tokens": 23090554.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.380775690078735,
|
|
"epoch": 1.1629696186892795,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048757922285172674,
|
|
"loss": 5.0798,
|
|
"mean_token_accuracy": 0.20737981349229812,
|
|
"num_tokens": 23101740.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.528803014755249,
|
|
"epoch": 1.163531195597237,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048756606443556874,
|
|
"loss": 5.1714,
|
|
"mean_token_accuracy": 0.2024669960141182,
|
|
"num_tokens": 23112842.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.425769233703614,
|
|
"epoch": 1.1640927725051946,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048755289925122474,
|
|
"loss": 5.1718,
|
|
"mean_token_accuracy": 0.20082434713840486,
|
|
"num_tokens": 23123822.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.48276653289795,
|
|
"epoch": 1.164654349413152,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004875397272991141,
|
|
"loss": 5.1842,
|
|
"mean_token_accuracy": 0.19915650337934493,
|
|
"num_tokens": 23134045.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.461555242538452,
|
|
"epoch": 1.1652159263211097,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000487526548579656,
|
|
"loss": 5.2123,
|
|
"mean_token_accuracy": 0.1933575764298439,
|
|
"num_tokens": 23144200.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.4488602638244625,
|
|
"epoch": 1.1657775032290671,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048751336309327026,
|
|
"loss": 5.1307,
|
|
"mean_token_accuracy": 0.2122505247592926,
|
|
"num_tokens": 23155671.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.553076314926147,
|
|
"epoch": 1.1663390801370248,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004875001708403766,
|
|
"loss": 5.2824,
|
|
"mean_token_accuracy": 0.202136991918087,
|
|
"num_tokens": 23166644.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.429000329971314,
|
|
"epoch": 1.1669006570449822,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048748697182139503,
|
|
"loss": 5.1709,
|
|
"mean_token_accuracy": 0.19815527349710466,
|
|
"num_tokens": 23177074.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.527188014984131,
|
|
"epoch": 1.16746223395294,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004874737660367459,
|
|
"loss": 5.2801,
|
|
"mean_token_accuracy": 0.19702013581991196,
|
|
"num_tokens": 23188724.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.453551006317139,
|
|
"epoch": 1.1680238108608973,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048746055348684967,
|
|
"loss": 5.2035,
|
|
"mean_token_accuracy": 0.19932918548583983,
|
|
"num_tokens": 23198459.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.491748809814453,
|
|
"epoch": 1.168585387768855,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000487447334172127,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.20066653937101364,
|
|
"num_tokens": 23208991.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.4116840839385985,
|
|
"epoch": 1.1691469646768125,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048743410809299877,
|
|
"loss": 5.1101,
|
|
"mean_token_accuracy": 0.20399949699640274,
|
|
"num_tokens": 23219309.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.481403589248657,
|
|
"epoch": 1.1697085415847701,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004874208752498862,
|
|
"loss": 5.2303,
|
|
"mean_token_accuracy": 0.19908248484134675,
|
|
"num_tokens": 23230551.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.541622686386108,
|
|
"epoch": 1.1702701184927276,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004874076356432106,
|
|
"loss": 5.299,
|
|
"mean_token_accuracy": 0.19814835637807846,
|
|
"num_tokens": 23242799.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.526991558074951,
|
|
"epoch": 1.1708316954006852,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048739438927339346,
|
|
"loss": 5.2995,
|
|
"mean_token_accuracy": 0.19496002346277236,
|
|
"num_tokens": 23255112.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.430134677886963,
|
|
"epoch": 1.1713932723086427,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048738113614085656,
|
|
"loss": 5.1987,
|
|
"mean_token_accuracy": 0.20294931679964065,
|
|
"num_tokens": 23264800.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.430749320983887,
|
|
"epoch": 1.1719548492166,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000487367876246022,
|
|
"loss": 5.1214,
|
|
"mean_token_accuracy": 0.2002952590584755,
|
|
"num_tokens": 23276672.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.4335911750793455,
|
|
"epoch": 1.1725164261245578,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004873546095893118,
|
|
"loss": 5.1626,
|
|
"mean_token_accuracy": 0.20360282361507415,
|
|
"num_tokens": 23288282.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.475942707061767,
|
|
"epoch": 1.1730780030325154,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004873413361711485,
|
|
"loss": 5.1875,
|
|
"mean_token_accuracy": 0.19931413233280182,
|
|
"num_tokens": 23299078.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.4522277355194095,
|
|
"epoch": 1.1736395799404729,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048732805599195465,
|
|
"loss": 5.1803,
|
|
"mean_token_accuracy": 0.20039283484220505,
|
|
"num_tokens": 23310036.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.439061450958252,
|
|
"epoch": 1.1742011568484303,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048731476905215326,
|
|
"loss": 5.1034,
|
|
"mean_token_accuracy": 0.21084504574537277,
|
|
"num_tokens": 23321029.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.468477344512939,
|
|
"epoch": 1.174762733756388,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004873014753521673,
|
|
"loss": 5.2109,
|
|
"mean_token_accuracy": 0.19901111871004104,
|
|
"num_tokens": 23331584.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.5725603103637695,
|
|
"epoch": 1.1753243106643454,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004872881748924199,
|
|
"loss": 5.274,
|
|
"mean_token_accuracy": 0.1877749890089035,
|
|
"num_tokens": 23343171.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.559176826477051,
|
|
"epoch": 1.175885887572303,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004872748676733347,
|
|
"loss": 5.1924,
|
|
"mean_token_accuracy": 0.20036645382642745,
|
|
"num_tokens": 23353047.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.48087739944458,
|
|
"epoch": 1.1764474644802605,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048726155369533547,
|
|
"loss": 5.1956,
|
|
"mean_token_accuracy": 0.19847763925790787,
|
|
"num_tokens": 23364447.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.4802289485931395,
|
|
"epoch": 1.1770090413882182,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000487248232958846,
|
|
"loss": 5.2206,
|
|
"mean_token_accuracy": 0.1980299934744835,
|
|
"num_tokens": 23375616.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.5473105907440186,
|
|
"epoch": 1.1775706182961756,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004872349054642904,
|
|
"loss": 5.3356,
|
|
"mean_token_accuracy": 0.19207555204629898,
|
|
"num_tokens": 23388176.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.543276929855347,
|
|
"epoch": 1.1781321952041333,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004872215712120932,
|
|
"loss": 5.2672,
|
|
"mean_token_accuracy": 0.2016679286956787,
|
|
"num_tokens": 23400563.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.5292072772979735,
|
|
"epoch": 1.1786937721120907,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004872082302026788,
|
|
"loss": 5.2022,
|
|
"mean_token_accuracy": 0.19479056894779206,
|
|
"num_tokens": 23410740.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.482979726791382,
|
|
"epoch": 1.1792553490200484,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004871948824364721,
|
|
"loss": 5.2787,
|
|
"mean_token_accuracy": 0.19374168217182158,
|
|
"num_tokens": 23423086.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.52589602470398,
|
|
"epoch": 1.1798169259280058,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000487181527913898,
|
|
"loss": 5.2759,
|
|
"mean_token_accuracy": 0.20016781687736512,
|
|
"num_tokens": 23435869.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.4544442653656,
|
|
"epoch": 1.1803785028359635,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048716816663538177,
|
|
"loss": 5.1453,
|
|
"mean_token_accuracy": 0.21112471967935562,
|
|
"num_tokens": 23446635.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.41698145866394,
|
|
"epoch": 1.180940079743921,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004871547986013488,
|
|
"loss": 5.1737,
|
|
"mean_token_accuracy": 0.20363107323646545,
|
|
"num_tokens": 23458214.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.498543357849121,
|
|
"epoch": 1.1815016566518786,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004871414238122248,
|
|
"loss": 5.1998,
|
|
"mean_token_accuracy": 0.20429729670286179,
|
|
"num_tokens": 23469383.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.4363365650177,
|
|
"epoch": 1.182063233559836,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004871280422684355,
|
|
"loss": 5.1624,
|
|
"mean_token_accuracy": 0.20632849037647247,
|
|
"num_tokens": 23480841.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.401475667953491,
|
|
"epoch": 1.1826248104677934,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048711465397040726,
|
|
"loss": 5.1317,
|
|
"mean_token_accuracy": 0.20598978996276857,
|
|
"num_tokens": 23490796.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.431342697143554,
|
|
"epoch": 1.183186387375751,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048710125891856604,
|
|
"loss": 5.1337,
|
|
"mean_token_accuracy": 0.2041391983628273,
|
|
"num_tokens": 23501759.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.466823291778565,
|
|
"epoch": 1.1837479642837088,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048708785711333845,
|
|
"loss": 5.1702,
|
|
"mean_token_accuracy": 0.20600284337997438,
|
|
"num_tokens": 23512209.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.526998853683471,
|
|
"epoch": 1.1843095411916662,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.00048707444855515124,
|
|
"loss": 5.2572,
|
|
"mean_token_accuracy": 0.20000497847795487,
|
|
"num_tokens": 23524316.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.462821006774902,
|
|
"epoch": 1.1848711180996236,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004870610332444314,
|
|
"loss": 5.2265,
|
|
"mean_token_accuracy": 0.20672667920589446,
|
|
"num_tokens": 23536199.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.4836501121521,
|
|
"epoch": 1.1854326950075813,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004870476111816059,
|
|
"loss": 5.2278,
|
|
"mean_token_accuracy": 0.19707887768745422,
|
|
"num_tokens": 23548034.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.517248106002808,
|
|
"epoch": 1.1859942719155387,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048703418236710234,
|
|
"loss": 5.188,
|
|
"mean_token_accuracy": 0.20197130590677262,
|
|
"num_tokens": 23559280.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.46593918800354,
|
|
"epoch": 1.1865558488234964,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004870207468013481,
|
|
"loss": 5.1591,
|
|
"mean_token_accuracy": 0.20195926278829573,
|
|
"num_tokens": 23569163.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.484252405166626,
|
|
"epoch": 1.1871174257314538,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004870073044847711,
|
|
"loss": 5.2334,
|
|
"mean_token_accuracy": 0.2005589172244072,
|
|
"num_tokens": 23580526.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.418462133407592,
|
|
"epoch": 1.1876790026394115,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004869938554177993,
|
|
"loss": 5.1224,
|
|
"mean_token_accuracy": 0.20061395168304444,
|
|
"num_tokens": 23590552.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.359176158905029,
|
|
"epoch": 1.188240579547369,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048698039960086084,
|
|
"loss": 5.0041,
|
|
"mean_token_accuracy": 0.21109791994094848,
|
|
"num_tokens": 23601889.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.500014162063598,
|
|
"epoch": 1.1888021564553266,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004869669370343843,
|
|
"loss": 5.2873,
|
|
"mean_token_accuracy": 0.20560032576322557,
|
|
"num_tokens": 23613833.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.528821897506714,
|
|
"epoch": 1.189363733363284,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004869534677187983,
|
|
"loss": 5.2405,
|
|
"mean_token_accuracy": 0.2039456471800804,
|
|
"num_tokens": 23625404.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.4273459911346436,
|
|
"epoch": 1.1899253102712417,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004869399916545317,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.21329526454210282,
|
|
"num_tokens": 23635670.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.422181940078735,
|
|
"epoch": 1.1904868871791991,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004869265088420135,
|
|
"loss": 5.1136,
|
|
"mean_token_accuracy": 0.20950076431035997,
|
|
"num_tokens": 23646893.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.382355546951294,
|
|
"epoch": 1.1910484640871568,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004869130192816731,
|
|
"loss": 5.2188,
|
|
"mean_token_accuracy": 0.20114482641220094,
|
|
"num_tokens": 23657733.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.361873626708984,
|
|
"epoch": 1.1916100409951143,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00048689952297394,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.2130013331770897,
|
|
"num_tokens": 23668100.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.543952322006225,
|
|
"epoch": 1.192171617903072,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004868860199192438,
|
|
"loss": 5.2399,
|
|
"mean_token_accuracy": 0.19444207102060318,
|
|
"num_tokens": 23678295.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.437207508087158,
|
|
"epoch": 1.1927331948110294,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004868725101180146,
|
|
"loss": 5.0724,
|
|
"mean_token_accuracy": 0.20954830944538116,
|
|
"num_tokens": 23689310.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.394340705871582,
|
|
"epoch": 1.1932947717189868,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004868589935706826,
|
|
"loss": 5.2243,
|
|
"mean_token_accuracy": 0.19757401943206787,
|
|
"num_tokens": 23699475.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.569411849975586,
|
|
"epoch": 1.1938563486269445,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048684547027767793,
|
|
"loss": 5.2217,
|
|
"mean_token_accuracy": 0.2028184324502945,
|
|
"num_tokens": 23710186.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.379452133178711,
|
|
"epoch": 1.1944179255349021,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004868319402394314,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.20852069705724716,
|
|
"num_tokens": 23720449.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.522710561752319,
|
|
"epoch": 1.1949795024428596,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048681840345637375,
|
|
"loss": 5.2949,
|
|
"mean_token_accuracy": 0.19844478964805604,
|
|
"num_tokens": 23732295.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.436313629150391,
|
|
"epoch": 1.195541079350817,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048680485992893597,
|
|
"loss": 5.1985,
|
|
"mean_token_accuracy": 0.20026141703128814,
|
|
"num_tokens": 23743616.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.547460079193115,
|
|
"epoch": 1.1961026562587747,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048679130965754926,
|
|
"loss": 5.2263,
|
|
"mean_token_accuracy": 0.1993878036737442,
|
|
"num_tokens": 23755288.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.4789165496826175,
|
|
"epoch": 1.196664233166732,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004867777526426451,
|
|
"loss": 5.1004,
|
|
"mean_token_accuracy": 0.2067498356103897,
|
|
"num_tokens": 23765916.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.32796459197998,
|
|
"epoch": 1.1972258100746898,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00048676418888465525,
|
|
"loss": 5.0536,
|
|
"mean_token_accuracy": 0.20764026194810867,
|
|
"num_tokens": 23778891.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.469976377487183,
|
|
"epoch": 1.1977873869826472,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004867506183840114,
|
|
"loss": 5.2073,
|
|
"mean_token_accuracy": 0.2060576245188713,
|
|
"num_tokens": 23790402.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.490409898757934,
|
|
"epoch": 1.1983489638906049,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004867370411411459,
|
|
"loss": 5.1503,
|
|
"mean_token_accuracy": 0.20888323932886124,
|
|
"num_tokens": 23801928.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.4994309425354,
|
|
"epoch": 1.1989105407985623,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048672345715649066,
|
|
"loss": 5.2279,
|
|
"mean_token_accuracy": 0.19480618238449096,
|
|
"num_tokens": 23812302.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.4917809009552006,
|
|
"epoch": 1.19947211770652,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004867098664304785,
|
|
"loss": 5.1897,
|
|
"mean_token_accuracy": 0.21261890828609467,
|
|
"num_tokens": 23824033.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.448282527923584,
|
|
"epoch": 1.2000336946144774,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004866962689635422,
|
|
"loss": 5.1493,
|
|
"mean_token_accuracy": 0.20728238821029663,
|
|
"num_tokens": 23834907.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.517509269714355,
|
|
"epoch": 1.200595271522435,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048668266475611447,
|
|
"loss": 5.3365,
|
|
"mean_token_accuracy": 0.1988241881132126,
|
|
"num_tokens": 23846418.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.59075403213501,
|
|
"epoch": 1.2011568484303925,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004866690538086286,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.19889292865991592,
|
|
"num_tokens": 23858423.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.479468297958374,
|
|
"epoch": 1.2017184253383502,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048665543612151803,
|
|
"loss": 5.1608,
|
|
"mean_token_accuracy": 0.20260724276304246,
|
|
"num_tokens": 23868340.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.385057020187378,
|
|
"epoch": 1.2022800022463076,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048664181169521625,
|
|
"loss": 5.0955,
|
|
"mean_token_accuracy": 0.20785311758518218,
|
|
"num_tokens": 23878752.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.496807289123535,
|
|
"epoch": 1.2028415791542653,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004866281805301571,
|
|
"loss": 5.1426,
|
|
"mean_token_accuracy": 0.21058329939842224,
|
|
"num_tokens": 23889374.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.563439416885376,
|
|
"epoch": 1.2034031560622227,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004866145426267746,
|
|
"loss": 5.2108,
|
|
"mean_token_accuracy": 0.1995503157377243,
|
|
"num_tokens": 23901651.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.381554174423218,
|
|
"epoch": 1.2039647329701804,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000486600897985503,
|
|
"loss": 5.1467,
|
|
"mean_token_accuracy": 0.20176431089639663,
|
|
"num_tokens": 23911818.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.4619310855865475,
|
|
"epoch": 1.2045263098781378,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048658724660677674,
|
|
"loss": 5.1772,
|
|
"mean_token_accuracy": 0.20634490698575975,
|
|
"num_tokens": 23923840.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.409549140930176,
|
|
"epoch": 1.2050878867860955,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004865735884910305,
|
|
"loss": 5.0751,
|
|
"mean_token_accuracy": 0.2146542862057686,
|
|
"num_tokens": 23935406.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.452820348739624,
|
|
"epoch": 1.205649463694053,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004865599236386991,
|
|
"loss": 5.1717,
|
|
"mean_token_accuracy": 0.20672981441020966,
|
|
"num_tokens": 23946350.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.372952604293824,
|
|
"epoch": 1.2062110406020103,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004865462520502177,
|
|
"loss": 5.1288,
|
|
"mean_token_accuracy": 0.20743412524461746,
|
|
"num_tokens": 23956315.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.4654529094696045,
|
|
"epoch": 1.206772617509968,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004865325737260216,
|
|
"loss": 5.0573,
|
|
"mean_token_accuracy": 0.20352966636419295,
|
|
"num_tokens": 23966649.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.573237705230713,
|
|
"epoch": 1.2073341944179254,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048651888866654624,
|
|
"loss": 5.3107,
|
|
"mean_token_accuracy": 0.1902357503771782,
|
|
"num_tokens": 23977674.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.4229268550872805,
|
|
"epoch": 1.207895771325883,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004865051968722275,
|
|
"loss": 5.1958,
|
|
"mean_token_accuracy": 0.20081054270267487,
|
|
"num_tokens": 23987985.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.516906642913819,
|
|
"epoch": 1.2084573482338405,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048649149834350126,
|
|
"loss": 5.3134,
|
|
"mean_token_accuracy": 0.1920422911643982,
|
|
"num_tokens": 23998730.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.43920488357544,
|
|
"epoch": 1.2090189251417982,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004864777930808037,
|
|
"loss": 5.1175,
|
|
"mean_token_accuracy": 0.1964148297905922,
|
|
"num_tokens": 24008743.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.443512105941773,
|
|
"epoch": 1.2095805020497556,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004864640810845711,
|
|
"loss": 5.1677,
|
|
"mean_token_accuracy": 0.2087377980351448,
|
|
"num_tokens": 24019805.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.486453628540039,
|
|
"epoch": 1.2101420789577133,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004864503623552402,
|
|
"loss": 5.1634,
|
|
"mean_token_accuracy": 0.20224840193986893,
|
|
"num_tokens": 24031437.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.548153305053711,
|
|
"epoch": 1.2107036558656707,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004864366368932478,
|
|
"loss": 5.2921,
|
|
"mean_token_accuracy": 0.1932049050927162,
|
|
"num_tokens": 24043922.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.472371435165405,
|
|
"epoch": 1.2112652327736284,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048642290469903083,
|
|
"loss": 5.1144,
|
|
"mean_token_accuracy": 0.2126319393515587,
|
|
"num_tokens": 24054755.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.415264511108399,
|
|
"epoch": 1.2118268096815858,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.00048640916577302664,
|
|
"loss": 5.1249,
|
|
"mean_token_accuracy": 0.19344184547662735,
|
|
"num_tokens": 24067347.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.47366189956665,
|
|
"epoch": 1.2123883865895435,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048639542011567243,
|
|
"loss": 5.1871,
|
|
"mean_token_accuracy": 0.20277249217033386,
|
|
"num_tokens": 24078938.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.45726752281189,
|
|
"epoch": 1.212949963497501,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004863816677274062,
|
|
"loss": 5.1776,
|
|
"mean_token_accuracy": 0.19966355562210084,
|
|
"num_tokens": 24090275.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.412062549591065,
|
|
"epoch": 1.2135115404054586,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048636790860866576,
|
|
"loss": 5.1919,
|
|
"mean_token_accuracy": 0.20711246728897095,
|
|
"num_tokens": 24101518.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.506921720504761,
|
|
"epoch": 1.214073117313416,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004863541427598889,
|
|
"loss": 5.295,
|
|
"mean_token_accuracy": 0.19296726137399672,
|
|
"num_tokens": 24113320.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.426114940643311,
|
|
"epoch": 1.2146346942213737,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004863403701815144,
|
|
"loss": 5.1204,
|
|
"mean_token_accuracy": 0.20659309476614,
|
|
"num_tokens": 24124842.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.5163712978363035,
|
|
"epoch": 1.2151962711293312,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004863265908739805,
|
|
"loss": 5.2611,
|
|
"mean_token_accuracy": 0.20111954510211943,
|
|
"num_tokens": 24136391.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.548802280426026,
|
|
"epoch": 1.2157578480372888,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004863128048377259,
|
|
"loss": 5.2166,
|
|
"mean_token_accuracy": 0.20157045125961304,
|
|
"num_tokens": 24147194.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.518996667861939,
|
|
"epoch": 1.2163194249452463,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004862990120731896,
|
|
"loss": 5.2752,
|
|
"mean_token_accuracy": 0.19721537530422212,
|
|
"num_tokens": 24158170.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.4756945133209225,
|
|
"epoch": 1.2168810018532037,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048628521258081096,
|
|
"loss": 5.1292,
|
|
"mean_token_accuracy": 0.20673321634531022,
|
|
"num_tokens": 24168671.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.464004802703857,
|
|
"epoch": 1.2174425787611614,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048627140636102906,
|
|
"loss": 5.1714,
|
|
"mean_token_accuracy": 0.19875272810459138,
|
|
"num_tokens": 24179898.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.399494647979736,
|
|
"epoch": 1.2180041556691188,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004862575934142837,
|
|
"loss": 5.1426,
|
|
"mean_token_accuracy": 0.20442479401826857,
|
|
"num_tokens": 24190622.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.607158136367798,
|
|
"epoch": 1.2185657325770765,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004862437737410147,
|
|
"loss": 5.3196,
|
|
"mean_token_accuracy": 0.19658107310533524,
|
|
"num_tokens": 24202526.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.4285320281982425,
|
|
"epoch": 1.219127309485034,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004862299473416619,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.20412747710943221,
|
|
"num_tokens": 24213186.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.414621591567993,
|
|
"epoch": 1.2196888863929916,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00048621611421666573,
|
|
"loss": 5.1718,
|
|
"mean_token_accuracy": 0.20253748297691346,
|
|
"num_tokens": 24225490.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.472359466552734,
|
|
"epoch": 1.220250463300949,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004862022743664665,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.20252657383680345,
|
|
"num_tokens": 24236653.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.406805372238159,
|
|
"epoch": 1.2208120402089067,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048618842779150494,
|
|
"loss": 5.1188,
|
|
"mean_token_accuracy": 0.21016918867826462,
|
|
"num_tokens": 24247843.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.416406679153442,
|
|
"epoch": 1.221373617116864,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00048617457449222205,
|
|
"loss": 5.1972,
|
|
"mean_token_accuracy": 0.20435844659805297,
|
|
"num_tokens": 24258332.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.469857454299927,
|
|
"epoch": 1.2219351940248218,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004861607144690587,
|
|
"loss": 5.1766,
|
|
"mean_token_accuracy": 0.20377371162176133,
|
|
"num_tokens": 24268685.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.480464601516724,
|
|
"epoch": 1.2224967709327792,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004861468477224563,
|
|
"loss": 5.2216,
|
|
"mean_token_accuracy": 0.1970214933156967,
|
|
"num_tokens": 24280660.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.505575656890869,
|
|
"epoch": 1.2230583478407369,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048613297425285635,
|
|
"loss": 5.1466,
|
|
"mean_token_accuracy": 0.2031639412045479,
|
|
"num_tokens": 24291649.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.464556360244751,
|
|
"epoch": 1.2236199247486943,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004861190940607007,
|
|
"loss": 5.1683,
|
|
"mean_token_accuracy": 0.201264625787735,
|
|
"num_tokens": 24303108.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.432361030578614,
|
|
"epoch": 1.224181501656652,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004861052071464312,
|
|
"loss": 5.1958,
|
|
"mean_token_accuracy": 0.19480210691690444,
|
|
"num_tokens": 24315939.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.437289237976074,
|
|
"epoch": 1.2247430785646094,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048609131351048994,
|
|
"loss": 5.172,
|
|
"mean_token_accuracy": 0.20418543219566346,
|
|
"num_tokens": 24326916.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.464480352401734,
|
|
"epoch": 1.225304655472567,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004860774131533195,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.2050207659602165,
|
|
"num_tokens": 24337790.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.4242981433868405,
|
|
"epoch": 1.2258662323805245,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048606350607536235,
|
|
"loss": 5.0345,
|
|
"mean_token_accuracy": 0.21056256145238877,
|
|
"num_tokens": 24347930.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.456901550292969,
|
|
"epoch": 1.2264278092884822,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004860495922770612,
|
|
"loss": 5.1384,
|
|
"mean_token_accuracy": 0.20334243923425674,
|
|
"num_tokens": 24359213.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.4033571720123295,
|
|
"epoch": 1.2269893861964396,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048603567175885926,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.20321608781814576,
|
|
"num_tokens": 24371000.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.375303888320923,
|
|
"epoch": 1.227550963104397,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004860217445211997,
|
|
"loss": 5.0316,
|
|
"mean_token_accuracy": 0.20741177648305892,
|
|
"num_tokens": 24381301.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.5339268207550045,
|
|
"epoch": 1.2281125400123547,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004860078105645259,
|
|
"loss": 5.2733,
|
|
"mean_token_accuracy": 0.191807122528553,
|
|
"num_tokens": 24391808.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.547538089752197,
|
|
"epoch": 1.2286741169203121,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004859938698892816,
|
|
"loss": 5.4052,
|
|
"mean_token_accuracy": 0.19819806516170502,
|
|
"num_tokens": 24404220.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.517003870010376,
|
|
"epoch": 1.2292356938282698,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048597992249591065,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.203224977850914,
|
|
"num_tokens": 24414906.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.440996313095093,
|
|
"epoch": 1.2297972707362272,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.00048596596838485704,
|
|
"loss": 5.1872,
|
|
"mean_token_accuracy": 0.19764235615730286,
|
|
"num_tokens": 24426469.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.34379768371582,
|
|
"epoch": 1.230358847644185,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004859520075565654,
|
|
"loss": 5.1571,
|
|
"mean_token_accuracy": 0.20072033256292343,
|
|
"num_tokens": 24437683.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.355475902557373,
|
|
"epoch": 1.2309204245521423,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048593804001147986,
|
|
"loss": 5.0452,
|
|
"mean_token_accuracy": 0.20771514028310775,
|
|
"num_tokens": 24449038.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.527215957641602,
|
|
"epoch": 1.2314820014601,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004859240657500453,
|
|
"loss": 5.1871,
|
|
"mean_token_accuracy": 0.20605241358280182,
|
|
"num_tokens": 24460228.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.4582466125488285,
|
|
"epoch": 1.2320435783680574,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048591008477270675,
|
|
"loss": 5.2425,
|
|
"mean_token_accuracy": 0.20028189420700074,
|
|
"num_tokens": 24471222.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.398322248458863,
|
|
"epoch": 1.232605155276015,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048589609707990925,
|
|
"loss": 5.1741,
|
|
"mean_token_accuracy": 0.19482695907354355,
|
|
"num_tokens": 24482127.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.483496284484863,
|
|
"epoch": 1.2331667321839725,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048588210267209823,
|
|
"loss": 5.1482,
|
|
"mean_token_accuracy": 0.1991759181022644,
|
|
"num_tokens": 24492963.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.550104093551636,
|
|
"epoch": 1.2337283090919302,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048586810154971935,
|
|
"loss": 5.1802,
|
|
"mean_token_accuracy": 0.2066708415746689,
|
|
"num_tokens": 24502885.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.5322870254516605,
|
|
"epoch": 1.2342898859998876,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048585409371321826,
|
|
"loss": 5.2664,
|
|
"mean_token_accuracy": 0.20242838710546493,
|
|
"num_tokens": 24514990.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.49631929397583,
|
|
"epoch": 1.2348514629078453,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048584007916304106,
|
|
"loss": 5.1829,
|
|
"mean_token_accuracy": 0.19860262125730516,
|
|
"num_tokens": 24525555.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.542101716995239,
|
|
"epoch": 1.2354130398158027,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048582605789963395,
|
|
"loss": 5.229,
|
|
"mean_token_accuracy": 0.19425695687532424,
|
|
"num_tokens": 24536350.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.568210029602051,
|
|
"epoch": 1.2359746167237604,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004858120299234434,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.19715877771377563,
|
|
"num_tokens": 24547756.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.382920217514038,
|
|
"epoch": 1.2365361936317179,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.00048579799523491607,
|
|
"loss": 5.1328,
|
|
"mean_token_accuracy": 0.20450157076120376,
|
|
"num_tokens": 24559897.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.426002359390258,
|
|
"epoch": 1.2370977705396755,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004857839538344988,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.20201408118009567,
|
|
"num_tokens": 24570168.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.467796277999878,
|
|
"epoch": 1.237659347447633,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048576990572263875,
|
|
"loss": 5.0934,
|
|
"mean_token_accuracy": 0.2145301192998886,
|
|
"num_tokens": 24580918.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.4157970428466795,
|
|
"epoch": 1.2382209243555904,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004857558508997831,
|
|
"loss": 5.1342,
|
|
"mean_token_accuracy": 0.1992151290178299,
|
|
"num_tokens": 24592378.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.55806074142456,
|
|
"epoch": 1.238782501263548,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004857417893663794,
|
|
"loss": 5.2255,
|
|
"mean_token_accuracy": 0.2024653360247612,
|
|
"num_tokens": 24603666.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.452266359329224,
|
|
"epoch": 1.2393440781715055,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004857277211228754,
|
|
"loss": 5.189,
|
|
"mean_token_accuracy": 0.20117369592189788,
|
|
"num_tokens": 24615299.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.435538482666016,
|
|
"epoch": 1.2399056550794632,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004857136461697191,
|
|
"loss": 5.1443,
|
|
"mean_token_accuracy": 0.2065530389547348,
|
|
"num_tokens": 24626138.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.3945800304412845,
|
|
"epoch": 1.2404672319874206,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048569956450735853,
|
|
"loss": 5.1293,
|
|
"mean_token_accuracy": 0.20395744144916533,
|
|
"num_tokens": 24636720.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.486225175857544,
|
|
"epoch": 1.2410288088953783,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00048568547613624206,
|
|
"loss": 5.1512,
|
|
"mean_token_accuracy": 0.19981513917446136,
|
|
"num_tokens": 24648147.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.487588167190552,
|
|
"epoch": 1.2415903858033357,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048567138105681833,
|
|
"loss": 5.1931,
|
|
"mean_token_accuracy": 0.20424194931983947,
|
|
"num_tokens": 24659825.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.433658409118652,
|
|
"epoch": 1.2421519627112934,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048565727926953617,
|
|
"loss": 5.1537,
|
|
"mean_token_accuracy": 0.20468665510416031,
|
|
"num_tokens": 24671583.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.405447626113892,
|
|
"epoch": 1.2427135396192508,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004856431707748445,
|
|
"loss": 5.0836,
|
|
"mean_token_accuracy": 0.2054637387394905,
|
|
"num_tokens": 24682034.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.4570588111877445,
|
|
"epoch": 1.2432751165272085,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004856290555731926,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.20111593455076218,
|
|
"num_tokens": 24693624.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.522160196304322,
|
|
"epoch": 1.243836693435166,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004856149336650299,
|
|
"loss": 5.1827,
|
|
"mean_token_accuracy": 0.20202843695878983,
|
|
"num_tokens": 24705340.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.522665119171142,
|
|
"epoch": 1.2443982703431236,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004856008050508059,
|
|
"loss": 5.2435,
|
|
"mean_token_accuracy": 0.198203207552433,
|
|
"num_tokens": 24717115.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.455497360229492,
|
|
"epoch": 1.244959847251081,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004855866697309707,
|
|
"loss": 5.0737,
|
|
"mean_token_accuracy": 0.20833736211061477,
|
|
"num_tokens": 24727768.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.496109104156494,
|
|
"epoch": 1.2455214241590387,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004855725277059742,
|
|
"loss": 5.2545,
|
|
"mean_token_accuracy": 0.1944260910153389,
|
|
"num_tokens": 24740054.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.526373100280762,
|
|
"epoch": 1.246083001066996,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004855583789762668,
|
|
"loss": 5.1288,
|
|
"mean_token_accuracy": 0.20010430216789246,
|
|
"num_tokens": 24750658.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.564990377426147,
|
|
"epoch": 1.2466445779749538,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000485544223542299,
|
|
"loss": 5.3215,
|
|
"mean_token_accuracy": 0.19970221519470216,
|
|
"num_tokens": 24762730.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.395041131973267,
|
|
"epoch": 1.2472061548829112,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004855300614045214,
|
|
"loss": 5.0793,
|
|
"mean_token_accuracy": 0.2079702153801918,
|
|
"num_tokens": 24773865.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.4118711948394775,
|
|
"epoch": 1.2477677317908689,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048551589256338497,
|
|
"loss": 5.1863,
|
|
"mean_token_accuracy": 0.20108642876148225,
|
|
"num_tokens": 24783030.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.443980979919433,
|
|
"epoch": 1.2483293086988263,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048550171701934087,
|
|
"loss": 5.103,
|
|
"mean_token_accuracy": 0.20783449411392213,
|
|
"num_tokens": 24793177.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.536599254608154,
|
|
"epoch": 1.2488908856067837,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048548753477284053,
|
|
"loss": 5.2105,
|
|
"mean_token_accuracy": 0.20435337275266646,
|
|
"num_tokens": 24804796.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.532714796066284,
|
|
"epoch": 1.2494524625147414,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004854733458243354,
|
|
"loss": 5.2097,
|
|
"mean_token_accuracy": 0.20136349648237228,
|
|
"num_tokens": 24816806.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.456060934066772,
|
|
"epoch": 1.250014039422699,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004854591501742773,
|
|
"loss": 5.161,
|
|
"mean_token_accuracy": 0.20636742562055588,
|
|
"num_tokens": 24826888.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.468593978881836,
|
|
"epoch": 1.2505756163306565,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048544494782311825,
|
|
"loss": 5.1188,
|
|
"mean_token_accuracy": 0.20324206501245498,
|
|
"num_tokens": 24837731.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.426183652877808,
|
|
"epoch": 1.251137193238614,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048543073877131037,
|
|
"loss": 5.1305,
|
|
"mean_token_accuracy": 0.20506934374570845,
|
|
"num_tokens": 24847900.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.436147308349609,
|
|
"epoch": 1.2516987701465716,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048541652301930627,
|
|
"loss": 5.2296,
|
|
"mean_token_accuracy": 0.19481280148029329,
|
|
"num_tokens": 24858878.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.443544912338257,
|
|
"epoch": 1.252260347054529,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004854023005675585,
|
|
"loss": 5.1642,
|
|
"mean_token_accuracy": 0.20288995802402496,
|
|
"num_tokens": 24870051.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.446250152587891,
|
|
"epoch": 1.2528219239624867,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004853880714165197,
|
|
"loss": 5.2615,
|
|
"mean_token_accuracy": 0.1973303362727165,
|
|
"num_tokens": 24881671.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.491633129119873,
|
|
"epoch": 1.2533835008704441,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048537383556664315,
|
|
"loss": 5.1039,
|
|
"mean_token_accuracy": 0.20208802074193954,
|
|
"num_tokens": 24892944.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.46076545715332,
|
|
"epoch": 1.2539450777784018,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004853595930183822,
|
|
"loss": 5.1902,
|
|
"mean_token_accuracy": 0.20062874257564545,
|
|
"num_tokens": 24903346.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.431779241561889,
|
|
"epoch": 1.2545066546863592,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004853453437721901,
|
|
"loss": 5.1845,
|
|
"mean_token_accuracy": 0.20402949750423433,
|
|
"num_tokens": 24913904.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.443333768844605,
|
|
"epoch": 1.255068231594317,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004853310878285208,
|
|
"loss": 5.1325,
|
|
"mean_token_accuracy": 0.20814678817987442,
|
|
"num_tokens": 24924635.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.53477258682251,
|
|
"epoch": 1.2556298085022743,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048531682518782797,
|
|
"loss": 5.3233,
|
|
"mean_token_accuracy": 0.19479757696390151,
|
|
"num_tokens": 24935466.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.540110635757446,
|
|
"epoch": 1.256191385410232,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048530255585056594,
|
|
"loss": 5.2816,
|
|
"mean_token_accuracy": 0.19894088357686995,
|
|
"num_tokens": 24948348.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.453719186782837,
|
|
"epoch": 1.2567529623181894,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004852882798171889,
|
|
"loss": 5.1108,
|
|
"mean_token_accuracy": 0.2054199367761612,
|
|
"num_tokens": 24959242.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.401065111160278,
|
|
"epoch": 1.2573145392261469,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004852739970881515,
|
|
"loss": 5.0811,
|
|
"mean_token_accuracy": 0.20700909495353698,
|
|
"num_tokens": 24969855.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.419329643249512,
|
|
"epoch": 1.2578761161341045,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048525970766390847,
|
|
"loss": 5.1084,
|
|
"mean_token_accuracy": 0.20535863935947418,
|
|
"num_tokens": 24980378.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.498160409927368,
|
|
"epoch": 1.2584376930420622,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004852454115449148,
|
|
"loss": 5.2021,
|
|
"mean_token_accuracy": 0.19778600484132766,
|
|
"num_tokens": 24990646.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.592801570892334,
|
|
"epoch": 1.2589992699500197,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004852311087316257,
|
|
"loss": 5.2931,
|
|
"mean_token_accuracy": 0.19426003843545914,
|
|
"num_tokens": 25002644.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.5401918411254885,
|
|
"epoch": 1.259560846857977,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004852167992244966,
|
|
"loss": 5.199,
|
|
"mean_token_accuracy": 0.20457497835159302,
|
|
"num_tokens": 25012635.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.463432455062867,
|
|
"epoch": 1.2601224237659348,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000485202483023983,
|
|
"loss": 5.314,
|
|
"mean_token_accuracy": 0.19231504648923875,
|
|
"num_tokens": 25024289.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.45431547164917,
|
|
"epoch": 1.2606840006738924,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048518816013054083,
|
|
"loss": 5.0729,
|
|
"mean_token_accuracy": 0.20552338659763336,
|
|
"num_tokens": 25035316.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.462117767333984,
|
|
"epoch": 1.2612455775818499,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048517383054462617,
|
|
"loss": 5.1318,
|
|
"mean_token_accuracy": 0.20711493492126465,
|
|
"num_tokens": 25046011.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.504916143417359,
|
|
"epoch": 1.2618071544898073,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004851594942666952,
|
|
"loss": 5.1261,
|
|
"mean_token_accuracy": 0.20258721709251404,
|
|
"num_tokens": 25057402.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.396705627441406,
|
|
"epoch": 1.262368731397765,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00048514515129720445,
|
|
"loss": 5.143,
|
|
"mean_token_accuracy": 0.20553721934556962,
|
|
"num_tokens": 25068287.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.369332790374756,
|
|
"epoch": 1.2629303083057224,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004851308016366105,
|
|
"loss": 5.1246,
|
|
"mean_token_accuracy": 0.20623514652252198,
|
|
"num_tokens": 25079534.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.372199773788452,
|
|
"epoch": 1.26349188521368,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048511644528537043,
|
|
"loss": 5.0711,
|
|
"mean_token_accuracy": 0.205873604118824,
|
|
"num_tokens": 25090825.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.48745584487915,
|
|
"epoch": 1.2640534621216375,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004851020822439412,
|
|
"loss": 5.179,
|
|
"mean_token_accuracy": 0.20095258951187134,
|
|
"num_tokens": 25101859.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.397821140289307,
|
|
"epoch": 1.2646150390295952,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048508771251278015,
|
|
"loss": 5.1107,
|
|
"mean_token_accuracy": 0.2097848579287529,
|
|
"num_tokens": 25111416.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.455532360076904,
|
|
"epoch": 1.2651766159375526,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004850733360923449,
|
|
"loss": 5.2124,
|
|
"mean_token_accuracy": 0.19858232140541077,
|
|
"num_tokens": 25122129.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.469708251953125,
|
|
"epoch": 1.2657381928455103,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004850589529830931,
|
|
"loss": 5.1951,
|
|
"mean_token_accuracy": 0.20311749577522278,
|
|
"num_tokens": 25132429.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.446085739135742,
|
|
"epoch": 1.2662997697534677,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048504456318548285,
|
|
"loss": 5.2332,
|
|
"mean_token_accuracy": 0.20629845261573793,
|
|
"num_tokens": 25144242.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.529765605926514,
|
|
"epoch": 1.2668613466614254,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004850301666999722,
|
|
"loss": 5.2235,
|
|
"mean_token_accuracy": 0.20506616681814194,
|
|
"num_tokens": 25155332.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.51335186958313,
|
|
"epoch": 1.2674229235693828,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004850157635270196,
|
|
"loss": 5.1317,
|
|
"mean_token_accuracy": 0.2070830434560776,
|
|
"num_tokens": 25166024.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.408167886734009,
|
|
"epoch": 1.2679845004773402,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004850013536670836,
|
|
"loss": 5.0906,
|
|
"mean_token_accuracy": 0.2088567242026329,
|
|
"num_tokens": 25176697.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.465492391586304,
|
|
"epoch": 1.268546077385298,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004849869371206231,
|
|
"loss": 5.1892,
|
|
"mean_token_accuracy": 0.20691042691469191,
|
|
"num_tokens": 25187421.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.4739899158477785,
|
|
"epoch": 1.2691076542932556,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048497251388809697,
|
|
"loss": 5.1947,
|
|
"mean_token_accuracy": 0.20538371354341506,
|
|
"num_tokens": 25198851.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.529881715774536,
|
|
"epoch": 1.269669231201213,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004849580839699647,
|
|
"loss": 5.2498,
|
|
"mean_token_accuracy": 0.19940355271100998,
|
|
"num_tokens": 25209984.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.468442010879516,
|
|
"epoch": 1.2702308081091704,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00048494364736668554,
|
|
"loss": 5.1364,
|
|
"mean_token_accuracy": 0.20520361363887787,
|
|
"num_tokens": 25220672.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.479077625274658,
|
|
"epoch": 1.270792385017128,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004849292040787192,
|
|
"loss": 5.1742,
|
|
"mean_token_accuracy": 0.20183171182870865,
|
|
"num_tokens": 25231906.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.472109699249268,
|
|
"epoch": 1.2713539619250858,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004849147541065256,
|
|
"loss": 5.1973,
|
|
"mean_token_accuracy": 0.19674336910247803,
|
|
"num_tokens": 25242902.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.454363536834717,
|
|
"epoch": 1.2719155388330432,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004849002974505649,
|
|
"loss": 5.251,
|
|
"mean_token_accuracy": 0.19797829538583755,
|
|
"num_tokens": 25254363.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.445118999481201,
|
|
"epoch": 1.2724771157410006,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.00048488583411129723,
|
|
"loss": 5.1761,
|
|
"mean_token_accuracy": 0.2032540336251259,
|
|
"num_tokens": 25267108.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.450331544876098,
|
|
"epoch": 1.2730386926489583,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004848713640891832,
|
|
"loss": 5.1342,
|
|
"mean_token_accuracy": 0.20622156262397767,
|
|
"num_tokens": 25278583.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.533629417419434,
|
|
"epoch": 1.2736002695569157,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004848568873846835,
|
|
"loss": 5.2091,
|
|
"mean_token_accuracy": 0.20306390523910522,
|
|
"num_tokens": 25289813.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.403175354003906,
|
|
"epoch": 1.2741618464648734,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048484240399825925,
|
|
"loss": 5.125,
|
|
"mean_token_accuracy": 0.19999108612537383,
|
|
"num_tokens": 25301003.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.450924444198608,
|
|
"epoch": 1.2747234233728308,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048482791393037134,
|
|
"loss": 5.1203,
|
|
"mean_token_accuracy": 0.20888183116912842,
|
|
"num_tokens": 25312535.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.439462423324585,
|
|
"epoch": 1.2752850002807885,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048481341718148137,
|
|
"loss": 5.1494,
|
|
"mean_token_accuracy": 0.20261918902397155,
|
|
"num_tokens": 25323333.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.508570623397827,
|
|
"epoch": 1.275846577188746,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048479891375205074,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.19969874769449233,
|
|
"num_tokens": 25334865.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.513240337371826,
|
|
"epoch": 1.2764081540967036,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048478440364254136,
|
|
"loss": 5.2319,
|
|
"mean_token_accuracy": 0.20283337384462358,
|
|
"num_tokens": 25346672.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.468957614898682,
|
|
"epoch": 1.276969731004661,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004847698868534152,
|
|
"loss": 5.2316,
|
|
"mean_token_accuracy": 0.2065620318055153,
|
|
"num_tokens": 25358702.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.472881698608399,
|
|
"epoch": 1.2775313079126187,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004847553633851345,
|
|
"loss": 5.1527,
|
|
"mean_token_accuracy": 0.20115307420492173,
|
|
"num_tokens": 25369813.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.530847454071045,
|
|
"epoch": 1.2780928848205761,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004847408332381616,
|
|
"loss": 5.1907,
|
|
"mean_token_accuracy": 0.20128828138113022,
|
|
"num_tokens": 25381042.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.4648497104644775,
|
|
"epoch": 1.2786544617285336,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048472629641295933,
|
|
"loss": 5.1936,
|
|
"mean_token_accuracy": 0.19565146565437316,
|
|
"num_tokens": 25391286.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.441607522964477,
|
|
"epoch": 1.2792160386364912,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004847117529099904,
|
|
"loss": 5.1328,
|
|
"mean_token_accuracy": 0.20442129224538802,
|
|
"num_tokens": 25402335.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.449425268173218,
|
|
"epoch": 1.279777615544449,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048469720272971797,
|
|
"loss": 5.0706,
|
|
"mean_token_accuracy": 0.21114486455917358,
|
|
"num_tokens": 25413484.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.5259312152862545,
|
|
"epoch": 1.2803391924524063,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004846826458726052,
|
|
"loss": 5.2097,
|
|
"mean_token_accuracy": 0.19536657482385636,
|
|
"num_tokens": 25424276.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.353202772140503,
|
|
"epoch": 1.2809007693603638,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048466808233911567,
|
|
"loss": 5.0689,
|
|
"mean_token_accuracy": 0.20694508105516435,
|
|
"num_tokens": 25435178.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.352679920196533,
|
|
"epoch": 1.2814623462683215,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048465351212971313,
|
|
"loss": 5.0281,
|
|
"mean_token_accuracy": 0.2078810840845108,
|
|
"num_tokens": 25445792.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.429979658126831,
|
|
"epoch": 1.2820239231762791,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004846389352448614,
|
|
"loss": 5.1231,
|
|
"mean_token_accuracy": 0.20382663756608962,
|
|
"num_tokens": 25456598.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.446813011169434,
|
|
"epoch": 1.2825855000842366,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004846243516850247,
|
|
"loss": 5.1952,
|
|
"mean_token_accuracy": 0.2079135850071907,
|
|
"num_tokens": 25468311.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.5507570743560795,
|
|
"epoch": 1.283147076992194,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004846097614506673,
|
|
"loss": 5.2211,
|
|
"mean_token_accuracy": 0.19903699308633804,
|
|
"num_tokens": 25480680.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.561702013015747,
|
|
"epoch": 1.2837086539001517,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048459516454225384,
|
|
"loss": 5.1965,
|
|
"mean_token_accuracy": 0.20443698316812514,
|
|
"num_tokens": 25492255.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.449211072921753,
|
|
"epoch": 1.284270230808109,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000484580560960249,
|
|
"loss": 5.2453,
|
|
"mean_token_accuracy": 0.19804598689079284,
|
|
"num_tokens": 25504530.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.413377380371093,
|
|
"epoch": 1.2848318077160668,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004845659507051178,
|
|
"loss": 5.1894,
|
|
"mean_token_accuracy": 0.20682209730148315,
|
|
"num_tokens": 25515273.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.530810308456421,
|
|
"epoch": 1.2853933846240242,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004845513337773255,
|
|
"loss": 5.2879,
|
|
"mean_token_accuracy": 0.19805059731006622,
|
|
"num_tokens": 25526050.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.519785165786743,
|
|
"epoch": 1.2859549615319819,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048453671017733755,
|
|
"loss": 5.1893,
|
|
"mean_token_accuracy": 0.1991667255759239,
|
|
"num_tokens": 25538372.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.563655519485474,
|
|
"epoch": 1.2865165384399393,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004845220799056194,
|
|
"loss": 5.2899,
|
|
"mean_token_accuracy": 0.2067184716463089,
|
|
"num_tokens": 25549636.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.508194637298584,
|
|
"epoch": 1.287078115347897,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00048450744296263685,
|
|
"loss": 5.2214,
|
|
"mean_token_accuracy": 0.19643103182315827,
|
|
"num_tokens": 25560850.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.457922792434692,
|
|
"epoch": 1.2876396922558544,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048449279934885625,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.2051679864525795,
|
|
"num_tokens": 25572433.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.559819889068604,
|
|
"epoch": 1.288201269163812,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004844781490647435,
|
|
"loss": 5.1964,
|
|
"mean_token_accuracy": 0.20135812610387802,
|
|
"num_tokens": 25582372.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.409285068511963,
|
|
"epoch": 1.2887628460717695,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004844634921107654,
|
|
"loss": 5.0427,
|
|
"mean_token_accuracy": 0.21044907718896866,
|
|
"num_tokens": 25592570.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.465415954589844,
|
|
"epoch": 1.289324422979727,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048444882848738835,
|
|
"loss": 5.1894,
|
|
"mean_token_accuracy": 0.19669198393821716,
|
|
"num_tokens": 25603573.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.538363456726074,
|
|
"epoch": 1.2898859998876846,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048443415819507944,
|
|
"loss": 5.2092,
|
|
"mean_token_accuracy": 0.2019707441329956,
|
|
"num_tokens": 25614233.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.475957727432251,
|
|
"epoch": 1.2904475767956423,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004844194812343057,
|
|
"loss": 5.1754,
|
|
"mean_token_accuracy": 0.19788192361593246,
|
|
"num_tokens": 25625077.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.425382995605469,
|
|
"epoch": 1.2910091537035997,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004844047976055344,
|
|
"loss": 5.2113,
|
|
"mean_token_accuracy": 0.20058429688215257,
|
|
"num_tokens": 25636693.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.38034839630127,
|
|
"epoch": 1.2915707306115571,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048439010730923313,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.203751640021801,
|
|
"num_tokens": 25647644.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.410211277008057,
|
|
"epoch": 1.2921323075195148,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048437541034586964,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.21092393845319748,
|
|
"num_tokens": 25659373.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.485157871246338,
|
|
"epoch": 1.2926938844274725,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048436070671591195,
|
|
"loss": 5.2177,
|
|
"mean_token_accuracy": 0.20779784470796586,
|
|
"num_tokens": 25670479.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.474063301086426,
|
|
"epoch": 1.29325546133543,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00048434599641982806,
|
|
"loss": 5.2252,
|
|
"mean_token_accuracy": 0.2070049911737442,
|
|
"num_tokens": 25682748.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.407731723785401,
|
|
"epoch": 1.2938170382433873,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048433127945808645,
|
|
"loss": 5.0435,
|
|
"mean_token_accuracy": 0.21043873429298401,
|
|
"num_tokens": 25693170.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.4454591274261475,
|
|
"epoch": 1.294378615151345,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004843165558311558,
|
|
"loss": 5.1931,
|
|
"mean_token_accuracy": 0.2012602850794792,
|
|
"num_tokens": 25706009.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.533812046051025,
|
|
"epoch": 1.2949401920593024,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004843018255395048,
|
|
"loss": 5.2137,
|
|
"mean_token_accuracy": 0.2025035187602043,
|
|
"num_tokens": 25716036.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.439382791519165,
|
|
"epoch": 1.29550176896726,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048428708858360244,
|
|
"loss": 5.0278,
|
|
"mean_token_accuracy": 0.20981121212244033,
|
|
"num_tokens": 25726516.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.455747413635254,
|
|
"epoch": 1.2960633458752175,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048427234496391816,
|
|
"loss": 5.1872,
|
|
"mean_token_accuracy": 0.1975255012512207,
|
|
"num_tokens": 25736340.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.373382949829102,
|
|
"epoch": 1.2966249227831752,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048425759468092113,
|
|
"loss": 5.1584,
|
|
"mean_token_accuracy": 0.19684485644102095,
|
|
"num_tokens": 25746439.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.475325679779052,
|
|
"epoch": 1.2971864996911326,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004842428377350811,
|
|
"loss": 5.0736,
|
|
"mean_token_accuracy": 0.2052624061703682,
|
|
"num_tokens": 25757065.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.4440085887908936,
|
|
"epoch": 1.2977480765990903,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048422807412686796,
|
|
"loss": 5.1114,
|
|
"mean_token_accuracy": 0.2017744794487953,
|
|
"num_tokens": 25768021.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.467814111709595,
|
|
"epoch": 1.2983096535070477,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004842133038567519,
|
|
"loss": 5.2243,
|
|
"mean_token_accuracy": 0.20331018716096877,
|
|
"num_tokens": 25780197.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.463663816452026,
|
|
"epoch": 1.2988712304150054,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000484198526925203,
|
|
"loss": 5.114,
|
|
"mean_token_accuracy": 0.2099816843867302,
|
|
"num_tokens": 25790536.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.439821195602417,
|
|
"epoch": 1.2994328073229628,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004841837433326919,
|
|
"loss": 5.1183,
|
|
"mean_token_accuracy": 0.20663629919290544,
|
|
"num_tokens": 25802397.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.4992047309875485,
|
|
"epoch": 1.2999943842309205,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004841689530796893,
|
|
"loss": 5.2305,
|
|
"mean_token_accuracy": 0.20374708175659179,
|
|
"num_tokens": 25813961.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.498616552352905,
|
|
"epoch": 1.300555961138878,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004841541561666661,
|
|
"loss": 5.2565,
|
|
"mean_token_accuracy": 0.19572438150644303,
|
|
"num_tokens": 25825610.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.44111852645874,
|
|
"epoch": 1.3011175380468356,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048413935259409343,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.2041834697127342,
|
|
"num_tokens": 25836076.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.455546188354492,
|
|
"epoch": 1.301679114954793,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00048412454236244267,
|
|
"loss": 5.1961,
|
|
"mean_token_accuracy": 0.20554250329732895,
|
|
"num_tokens": 25847341.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.3581174373626705,
|
|
"epoch": 1.3022406918627505,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048410972547218545,
|
|
"loss": 5.0648,
|
|
"mean_token_accuracy": 0.20857871621847152,
|
|
"num_tokens": 25856912.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.463742589950561,
|
|
"epoch": 1.3028022687707081,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048409490192379337,
|
|
"loss": 5.1118,
|
|
"mean_token_accuracy": 0.20344580411911012,
|
|
"num_tokens": 25868370.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.422854089736939,
|
|
"epoch": 1.3033638456786658,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004840800717177386,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.19839558452367784,
|
|
"num_tokens": 25879104.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.443877029418945,
|
|
"epoch": 1.3039254225866233,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004840652348544931,
|
|
"loss": 5.1832,
|
|
"mean_token_accuracy": 0.1958763599395752,
|
|
"num_tokens": 25889744.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.575684261322022,
|
|
"epoch": 1.3044869994945807,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004840503913345296,
|
|
"loss": 5.3028,
|
|
"mean_token_accuracy": 0.1950350135564804,
|
|
"num_tokens": 25901615.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.508506917953492,
|
|
"epoch": 1.3050485764025384,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004840355411583205,
|
|
"loss": 5.1775,
|
|
"mean_token_accuracy": 0.19562424421310426,
|
|
"num_tokens": 25911418.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.5307636737823485,
|
|
"epoch": 1.3056101533104958,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048402068432633864,
|
|
"loss": 5.251,
|
|
"mean_token_accuracy": 0.20618563294410705,
|
|
"num_tokens": 25922141.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.491657733917236,
|
|
"epoch": 1.3061717302184535,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004840058208390572,
|
|
"loss": 5.2633,
|
|
"mean_token_accuracy": 0.19767802059650422,
|
|
"num_tokens": 25933897.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.506998348236084,
|
|
"epoch": 1.306733307126411,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004839909506969494,
|
|
"loss": 5.1973,
|
|
"mean_token_accuracy": 0.20301807224750518,
|
|
"num_tokens": 25943960.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.594176864624023,
|
|
"epoch": 1.3072948840343686,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004839760739004886,
|
|
"loss": 5.2126,
|
|
"mean_token_accuracy": 0.19951733499765395,
|
|
"num_tokens": 25955104.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.459704113006592,
|
|
"epoch": 1.307856460942326,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048396119045014853,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.2035454422235489,
|
|
"num_tokens": 25965180.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.434148502349854,
|
|
"epoch": 1.3084180378502837,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004839463003464032,
|
|
"loss": 5.1775,
|
|
"mean_token_accuracy": 0.2046498641371727,
|
|
"num_tokens": 25976600.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.451714944839478,
|
|
"epoch": 1.308979614758241,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004839314035897265,
|
|
"loss": 5.1563,
|
|
"mean_token_accuracy": 0.19908519089221954,
|
|
"num_tokens": 25987509.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.469056272506714,
|
|
"epoch": 1.3095411916661988,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000483916500180593,
|
|
"loss": 5.0969,
|
|
"mean_token_accuracy": 0.20938700437545776,
|
|
"num_tokens": 25997962.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.459711647033691,
|
|
"epoch": 1.3101027685741562,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048390159011947706,
|
|
"loss": 5.1428,
|
|
"mean_token_accuracy": 0.20587421357631683,
|
|
"num_tokens": 26008932.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.430537462234497,
|
|
"epoch": 1.3106643454821139,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004838866734068535,
|
|
"loss": 5.1423,
|
|
"mean_token_accuracy": 0.1993084579706192,
|
|
"num_tokens": 26020513.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.495750808715821,
|
|
"epoch": 1.3112259223900713,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048387175004319723,
|
|
"loss": 5.2143,
|
|
"mean_token_accuracy": 0.20191456824541093,
|
|
"num_tokens": 26032526.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.485930252075195,
|
|
"epoch": 1.311787499298029,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004838568200289834,
|
|
"loss": 5.1493,
|
|
"mean_token_accuracy": 0.21214838773012162,
|
|
"num_tokens": 26044216.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.437861728668213,
|
|
"epoch": 1.3123490762059864,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004838418833646875,
|
|
"loss": 5.0629,
|
|
"mean_token_accuracy": 0.20374813079833984,
|
|
"num_tokens": 26054012.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.460941791534424,
|
|
"epoch": 1.3129106531139438,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048382694005078485,
|
|
"loss": 5.2113,
|
|
"mean_token_accuracy": 0.20273168832063676,
|
|
"num_tokens": 26065365.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.4863046169281,
|
|
"epoch": 1.3134722300219015,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048381199008775165,
|
|
"loss": 5.2089,
|
|
"mean_token_accuracy": 0.19587379097938537,
|
|
"num_tokens": 26075964.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.436554956436157,
|
|
"epoch": 1.3140338069298592,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004837970334760635,
|
|
"loss": 5.1805,
|
|
"mean_token_accuracy": 0.20143571645021438,
|
|
"num_tokens": 26087572.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.450084638595581,
|
|
"epoch": 1.3145953838378166,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000483782070216197,
|
|
"loss": 5.0736,
|
|
"mean_token_accuracy": 0.20971333086490632,
|
|
"num_tokens": 26098612.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.492118835449219,
|
|
"epoch": 1.315156960745774,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004837671003086283,
|
|
"loss": 5.2371,
|
|
"mean_token_accuracy": 0.20154134929180145,
|
|
"num_tokens": 26109491.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.451224231719971,
|
|
"epoch": 1.3157185376537317,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004837521237538342,
|
|
"loss": 5.1378,
|
|
"mean_token_accuracy": 0.2013961061835289,
|
|
"num_tokens": 26120544.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.533825063705445,
|
|
"epoch": 1.3162801145616891,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004837371405522915,
|
|
"loss": 5.218,
|
|
"mean_token_accuracy": 0.19877072423696518,
|
|
"num_tokens": 26131549.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.461523771286011,
|
|
"epoch": 1.3168416914696468,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048372215070447734,
|
|
"loss": 5.2072,
|
|
"mean_token_accuracy": 0.20401265770196914,
|
|
"num_tokens": 26142871.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.5595122337341305,
|
|
"epoch": 1.3174032683776042,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048370715421086884,
|
|
"loss": 5.3066,
|
|
"mean_token_accuracy": 0.20428167879581452,
|
|
"num_tokens": 26155293.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.5505678176879885,
|
|
"epoch": 1.317964845285562,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004836921510719438,
|
|
"loss": 5.223,
|
|
"mean_token_accuracy": 0.2081404894590378,
|
|
"num_tokens": 26167069.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.487321853637695,
|
|
"epoch": 1.3185264221935193,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004836771412881795,
|
|
"loss": 5.2136,
|
|
"mean_token_accuracy": 0.19338219165802,
|
|
"num_tokens": 26179142.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.482232666015625,
|
|
"epoch": 1.319087999101477,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004836621248600542,
|
|
"loss": 5.1626,
|
|
"mean_token_accuracy": 0.20442728847265243,
|
|
"num_tokens": 26190059.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.506552076339721,
|
|
"epoch": 1.3196495760094344,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004836471017880459,
|
|
"loss": 5.1684,
|
|
"mean_token_accuracy": 0.20677920579910278,
|
|
"num_tokens": 26199859.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.50367841720581,
|
|
"epoch": 1.320211152917392,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004836320720726329,
|
|
"loss": 5.2075,
|
|
"mean_token_accuracy": 0.1983455240726471,
|
|
"num_tokens": 26211920.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.465070009231567,
|
|
"epoch": 1.3207727298253495,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004836170357142939,
|
|
"loss": 5.1618,
|
|
"mean_token_accuracy": 0.20120519548654556,
|
|
"num_tokens": 26222875.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.475478029251098,
|
|
"epoch": 1.3213343067333072,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004836019927135076,
|
|
"loss": 5.2014,
|
|
"mean_token_accuracy": 0.20030269920825958,
|
|
"num_tokens": 26233549.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.4200211524963375,
|
|
"epoch": 1.3218958836412646,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004835869430707529,
|
|
"loss": 5.0754,
|
|
"mean_token_accuracy": 0.21423650830984114,
|
|
"num_tokens": 26243886.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.416882038116455,
|
|
"epoch": 1.3224574605492223,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048357188678650905,
|
|
"loss": 5.1065,
|
|
"mean_token_accuracy": 0.20935882329940797,
|
|
"num_tokens": 26254475.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.542265462875366,
|
|
"epoch": 1.3230190374571797,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004835568238612553,
|
|
"loss": 5.3059,
|
|
"mean_token_accuracy": 0.1964566320180893,
|
|
"num_tokens": 26265412.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.55201096534729,
|
|
"epoch": 1.3235806143651372,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048354175429547155,
|
|
"loss": 5.2227,
|
|
"mean_token_accuracy": 0.2014821782708168,
|
|
"num_tokens": 26276942.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.533633899688721,
|
|
"epoch": 1.3241421912730948,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004835266780896374,
|
|
"loss": 5.1803,
|
|
"mean_token_accuracy": 0.2036018192768097,
|
|
"num_tokens": 26288009.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.531124925613403,
|
|
"epoch": 1.3247037681810525,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004835115952442329,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.1918231353163719,
|
|
"num_tokens": 26301583.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.5593818664550785,
|
|
"epoch": 1.32526534508901,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048349650575973843,
|
|
"loss": 5.2334,
|
|
"mean_token_accuracy": 0.20014299750328063,
|
|
"num_tokens": 26312922.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.514520692825317,
|
|
"epoch": 1.3258269219969674,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048348140963663436,
|
|
"loss": 5.1904,
|
|
"mean_token_accuracy": 0.20839452892541885,
|
|
"num_tokens": 26324108.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.502158784866333,
|
|
"epoch": 1.326388498904925,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004834663068754012,
|
|
"loss": 5.1988,
|
|
"mean_token_accuracy": 0.20654161423444747,
|
|
"num_tokens": 26335669.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.386802387237549,
|
|
"epoch": 1.3269500758128827,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004834511974765202,
|
|
"loss": 5.1043,
|
|
"mean_token_accuracy": 0.20874847322702408,
|
|
"num_tokens": 26346065.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.475204086303711,
|
|
"epoch": 1.3275116527208402,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048343608144047194,
|
|
"loss": 5.0872,
|
|
"mean_token_accuracy": 0.20399933755397798,
|
|
"num_tokens": 26357567.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.473665332794189,
|
|
"epoch": 1.3280732296287976,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048342095876773825,
|
|
"loss": 5.1341,
|
|
"mean_token_accuracy": 0.20347937047481537,
|
|
"num_tokens": 26367805.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.417301416397095,
|
|
"epoch": 1.3286348065367553,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004834058294588003,
|
|
"loss": 5.0542,
|
|
"mean_token_accuracy": 0.2077891618013382,
|
|
"num_tokens": 26379343.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.500841093063355,
|
|
"epoch": 1.3291963834447127,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.00048339069351413993,
|
|
"loss": 5.2879,
|
|
"mean_token_accuracy": 0.19741900116205216,
|
|
"num_tokens": 26392039.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.3539954662323,
|
|
"epoch": 1.3297579603526704,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000483375550934239,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.2151583731174469,
|
|
"num_tokens": 26403324.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.414818334579468,
|
|
"epoch": 1.3303195372606278,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004833604017195798,
|
|
"loss": 5.1417,
|
|
"mean_token_accuracy": 0.20471826940774918,
|
|
"num_tokens": 26413435.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.462999868392944,
|
|
"epoch": 1.3308811141685855,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004833452458706445,
|
|
"loss": 5.2483,
|
|
"mean_token_accuracy": 0.19662725329399108,
|
|
"num_tokens": 26424254.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.52613377571106,
|
|
"epoch": 1.331442691076543,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004833300833879159,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.2063932716846466,
|
|
"num_tokens": 26435658.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.5593963146209715,
|
|
"epoch": 1.3320042679845006,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004833149142718765,
|
|
"loss": 5.2046,
|
|
"mean_token_accuracy": 0.2018562972545624,
|
|
"num_tokens": 26447174.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.541952466964721,
|
|
"epoch": 1.332565844892458,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004832997385230096,
|
|
"loss": 5.2961,
|
|
"mean_token_accuracy": 0.1981729656457901,
|
|
"num_tokens": 26459303.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.471814203262329,
|
|
"epoch": 1.3331274218004157,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004832845561417981,
|
|
"loss": 5.1701,
|
|
"mean_token_accuracy": 0.1970518112182617,
|
|
"num_tokens": 26469981.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.430123233795166,
|
|
"epoch": 1.333688998708373,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004832693671287256,
|
|
"loss": 5.1681,
|
|
"mean_token_accuracy": 0.20668212324380875,
|
|
"num_tokens": 26481176.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.432497978210449,
|
|
"epoch": 1.3342505756163305,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004832541714842757,
|
|
"loss": 5.1223,
|
|
"mean_token_accuracy": 0.20593966394662858,
|
|
"num_tokens": 26492795.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.516925382614136,
|
|
"epoch": 1.3348121525242882,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004832389692089321,
|
|
"loss": 5.2748,
|
|
"mean_token_accuracy": 0.1994077369570732,
|
|
"num_tokens": 26504731.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.546652984619141,
|
|
"epoch": 1.3353737294322459,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048322376030317905,
|
|
"loss": 5.1481,
|
|
"mean_token_accuracy": 0.20360081940889357,
|
|
"num_tokens": 26516816.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.492306327819824,
|
|
"epoch": 1.3359353063402033,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004832085447675007,
|
|
"loss": 5.2653,
|
|
"mean_token_accuracy": 0.20224468559026718,
|
|
"num_tokens": 26528861.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.547552871704101,
|
|
"epoch": 1.3364968832481607,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048319332260238153,
|
|
"loss": 5.22,
|
|
"mean_token_accuracy": 0.20258211195468903,
|
|
"num_tokens": 26538816.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.58981499671936,
|
|
"epoch": 1.3370584601561184,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048317809380830624,
|
|
"loss": 5.2639,
|
|
"mean_token_accuracy": 0.1990650162100792,
|
|
"num_tokens": 26548959.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.390769195556641,
|
|
"epoch": 1.337620037064076,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004831628583857597,
|
|
"loss": 5.1278,
|
|
"mean_token_accuracy": 0.20601357370615006,
|
|
"num_tokens": 26559189.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.428310394287109,
|
|
"epoch": 1.3381816139720335,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048314761633522696,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.21442463546991347,
|
|
"num_tokens": 26570066.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.528180932998657,
|
|
"epoch": 1.338743190879991,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004831323676571934,
|
|
"loss": 5.264,
|
|
"mean_token_accuracy": 0.20499378442764282,
|
|
"num_tokens": 26581489.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.541092777252198,
|
|
"epoch": 1.3393047677879486,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004831171123521446,
|
|
"loss": 5.1896,
|
|
"mean_token_accuracy": 0.19802570939064026,
|
|
"num_tokens": 26592051.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.507169008255005,
|
|
"epoch": 1.339866344695906,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004831018504205662,
|
|
"loss": 5.1857,
|
|
"mean_token_accuracy": 0.20604109019041061,
|
|
"num_tokens": 26602296.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.451931715011597,
|
|
"epoch": 1.3404279216038637,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048308658186294414,
|
|
"loss": 5.1866,
|
|
"mean_token_accuracy": 0.19702045023441314,
|
|
"num_tokens": 26613837.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.490351581573487,
|
|
"epoch": 1.3409894985118211,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004830713066797646,
|
|
"loss": 5.2221,
|
|
"mean_token_accuracy": 0.19948205053806306,
|
|
"num_tokens": 26624898.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.468191623687744,
|
|
"epoch": 1.3415510754197788,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00048305602487151396,
|
|
"loss": 5.2077,
|
|
"mean_token_accuracy": 0.20306269824504852,
|
|
"num_tokens": 26636449.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.6156463623046875,
|
|
"epoch": 1.3421126523277362,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004830407364386789,
|
|
"loss": 5.2994,
|
|
"mean_token_accuracy": 0.19780701100826265,
|
|
"num_tokens": 26649192.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.46129789352417,
|
|
"epoch": 1.342674229235694,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000483025441381746,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.2069813773036003,
|
|
"num_tokens": 26660005.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.548576545715332,
|
|
"epoch": 1.3432358061436513,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048301013970120235,
|
|
"loss": 5.2574,
|
|
"mean_token_accuracy": 0.19758400022983552,
|
|
"num_tokens": 26672165.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.449719429016113,
|
|
"epoch": 1.343797383051609,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048299483139753517,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.20835707783699037,
|
|
"num_tokens": 26683135.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.4656572341918945,
|
|
"epoch": 1.3443589599595664,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004829795164712319,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.21054854840040207,
|
|
"num_tokens": 26693724.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.51731243133545,
|
|
"epoch": 1.3449205368675239,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048296419492278023,
|
|
"loss": 5.2863,
|
|
"mean_token_accuracy": 0.19961208552122117,
|
|
"num_tokens": 26705880.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.526037311553955,
|
|
"epoch": 1.3454821137754815,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004829488667526679,
|
|
"loss": 5.2702,
|
|
"mean_token_accuracy": 0.20107422024011612,
|
|
"num_tokens": 26716978.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.580895280838012,
|
|
"epoch": 1.3460436906834392,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048293353196138294,
|
|
"loss": 5.1931,
|
|
"mean_token_accuracy": 0.21192722767591476,
|
|
"num_tokens": 26728380.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.41425085067749,
|
|
"epoch": 1.3466052675913966,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048291819054941375,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.2044837862253189,
|
|
"num_tokens": 26739034.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.317131519317627,
|
|
"epoch": 1.347166844499354,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004829028425172487,
|
|
"loss": 4.9723,
|
|
"mean_token_accuracy": 0.2115240603685379,
|
|
"num_tokens": 26750123.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.422116661071778,
|
|
"epoch": 1.3477284214073117,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048288748786537656,
|
|
"loss": 5.1378,
|
|
"mean_token_accuracy": 0.21104429811239242,
|
|
"num_tokens": 26760411.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.3477284214073117,
|
|
"eval_entropy": 5.247241792464828,
|
|
"eval_loss": 5.248316764831543,
|
|
"eval_mean_token_accuracy": 0.20806338551973355,
|
|
"eval_num_tokens": 26760411.0,
|
|
"eval_runtime": 18.4095,
|
|
"eval_samples_per_second": 1684.621,
|
|
"eval_steps_per_second": 210.598,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.4755456924438475,
|
|
"epoch": 1.3482899983152694,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004828721265942861,
|
|
"loss": 5.2038,
|
|
"mean_token_accuracy": 0.2055389776825905,
|
|
"num_tokens": 26770821.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.50641131401062,
|
|
"epoch": 1.3488515752232269,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048285675870446653,
|
|
"loss": 5.1779,
|
|
"mean_token_accuracy": 0.20557235628366471,
|
|
"num_tokens": 26782099.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.571593618392944,
|
|
"epoch": 1.3494131521311843,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00048284138419640724,
|
|
"loss": 5.2992,
|
|
"mean_token_accuracy": 0.20141823291778566,
|
|
"num_tokens": 26794056.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.455738687515259,
|
|
"epoch": 1.349974729039142,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004828260030705976,
|
|
"loss": 5.1305,
|
|
"mean_token_accuracy": 0.20524767637252808,
|
|
"num_tokens": 26804501.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.5493810176849365,
|
|
"epoch": 1.3505363059470994,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048281061532752734,
|
|
"loss": 5.203,
|
|
"mean_token_accuracy": 0.2008921205997467,
|
|
"num_tokens": 26814996.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.494820547103882,
|
|
"epoch": 1.351097882855057,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004827952209676866,
|
|
"loss": 5.1394,
|
|
"mean_token_accuracy": 0.21072678714990617,
|
|
"num_tokens": 26825838.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.4804669380187985,
|
|
"epoch": 1.3516594597630145,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048277981999156534,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.2049419865012169,
|
|
"num_tokens": 26836320.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.483975124359131,
|
|
"epoch": 1.3522210366709722,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048276441239965414,
|
|
"loss": 5.1393,
|
|
"mean_token_accuracy": 0.20834504812955856,
|
|
"num_tokens": 26846485.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.588258266448975,
|
|
"epoch": 1.3527826135789296,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004827489981924434,
|
|
"loss": 5.2574,
|
|
"mean_token_accuracy": 0.19489187747240067,
|
|
"num_tokens": 26858554.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.501278686523437,
|
|
"epoch": 1.3533441904868873,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048273357737042393,
|
|
"loss": 5.1941,
|
|
"mean_token_accuracy": 0.20413232147693633,
|
|
"num_tokens": 26869538.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.51456847190857,
|
|
"epoch": 1.3539057673948447,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048271814993408694,
|
|
"loss": 5.2619,
|
|
"mean_token_accuracy": 0.195559298992157,
|
|
"num_tokens": 26880284.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.510677671432495,
|
|
"epoch": 1.3544673443028024,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004827027158839233,
|
|
"loss": 5.2273,
|
|
"mean_token_accuracy": 0.19601806849241257,
|
|
"num_tokens": 26893180.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.453428459167481,
|
|
"epoch": 1.3550289212107598,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004826872752204248,
|
|
"loss": 5.1035,
|
|
"mean_token_accuracy": 0.20847864747047423,
|
|
"num_tokens": 26904213.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.478480052947998,
|
|
"epoch": 1.3555904981187172,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048267182794408276,
|
|
"loss": 5.1921,
|
|
"mean_token_accuracy": 0.20832038074731826,
|
|
"num_tokens": 26915566.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.387891435623169,
|
|
"epoch": 1.356152075026675,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004826563740553893,
|
|
"loss": 5.1452,
|
|
"mean_token_accuracy": 0.20773425847291946,
|
|
"num_tokens": 26926253.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.4375075340271,
|
|
"epoch": 1.3567136519346326,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004826409135548363,
|
|
"loss": 5.1337,
|
|
"mean_token_accuracy": 0.2113666296005249,
|
|
"num_tokens": 26936723.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.441137218475342,
|
|
"epoch": 1.35727522884259,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004826254464429161,
|
|
"loss": 5.126,
|
|
"mean_token_accuracy": 0.20685262978076935,
|
|
"num_tokens": 26947551.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.473425817489624,
|
|
"epoch": 1.3578368057505474,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048260997272012114,
|
|
"loss": 5.2377,
|
|
"mean_token_accuracy": 0.2061762347817421,
|
|
"num_tokens": 26959969.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.567711544036865,
|
|
"epoch": 1.358398382658505,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004825944923869441,
|
|
"loss": 5.315,
|
|
"mean_token_accuracy": 0.20031530112028123,
|
|
"num_tokens": 26972511.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.546752691268921,
|
|
"epoch": 1.3589599595664628,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048257900544387795,
|
|
"loss": 5.2878,
|
|
"mean_token_accuracy": 0.1961741790175438,
|
|
"num_tokens": 26983827.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.5921002388000485,
|
|
"epoch": 1.3595215364744202,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048256351189141574,
|
|
"loss": 5.234,
|
|
"mean_token_accuracy": 0.19696773439645768,
|
|
"num_tokens": 26994668.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.437639904022217,
|
|
"epoch": 1.3600831133823776,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004825480117300508,
|
|
"loss": 5.1133,
|
|
"mean_token_accuracy": 0.2130228951573372,
|
|
"num_tokens": 27006313.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.476600599288941,
|
|
"epoch": 1.3606446902903353,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00048253250496027675,
|
|
"loss": 5.1635,
|
|
"mean_token_accuracy": 0.20102080702781677,
|
|
"num_tokens": 27017628.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.485951232910156,
|
|
"epoch": 1.3612062671982927,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048251699158258714,
|
|
"loss": 5.0766,
|
|
"mean_token_accuracy": 0.2036074712872505,
|
|
"num_tokens": 27028303.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.554651212692261,
|
|
"epoch": 1.3617678441062504,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004825014715974761,
|
|
"loss": 5.2313,
|
|
"mean_token_accuracy": 0.19830369651317598,
|
|
"num_tokens": 27039307.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.4430098056793215,
|
|
"epoch": 1.3623294210142078,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048248594500543767,
|
|
"loss": 5.128,
|
|
"mean_token_accuracy": 0.20548534244298935,
|
|
"num_tokens": 27049271.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.33948917388916,
|
|
"epoch": 1.3628909979221655,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048247041180696633,
|
|
"loss": 5.037,
|
|
"mean_token_accuracy": 0.2095663070678711,
|
|
"num_tokens": 27059510.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.5913416862487795,
|
|
"epoch": 1.363452574830123,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004824548720025566,
|
|
"loss": 5.3602,
|
|
"mean_token_accuracy": 0.19199225753545762,
|
|
"num_tokens": 27071685.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.4333202838897705,
|
|
"epoch": 1.3640141517380806,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004824393255927033,
|
|
"loss": 5.0785,
|
|
"mean_token_accuracy": 0.19921932369470596,
|
|
"num_tokens": 27081957.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.423873090744019,
|
|
"epoch": 1.364575728646038,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048242377257790145,
|
|
"loss": 5.1124,
|
|
"mean_token_accuracy": 0.20965125858783723,
|
|
"num_tokens": 27091609.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.493868350982666,
|
|
"epoch": 1.3651373055539957,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048240821295864614,
|
|
"loss": 5.2821,
|
|
"mean_token_accuracy": 0.1964243918657303,
|
|
"num_tokens": 27103889.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.56975040435791,
|
|
"epoch": 1.3656988824619531,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000482392646735433,
|
|
"loss": 5.218,
|
|
"mean_token_accuracy": 0.20331528335809707,
|
|
"num_tokens": 27114186.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.397453260421753,
|
|
"epoch": 1.3662604593699106,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004823770739087574,
|
|
"loss": 5.0715,
|
|
"mean_token_accuracy": 0.20726438611745834,
|
|
"num_tokens": 27124677.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.566719818115234,
|
|
"epoch": 1.3668220362778682,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004823614944791154,
|
|
"loss": 5.2474,
|
|
"mean_token_accuracy": 0.20322871655225755,
|
|
"num_tokens": 27134873.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.488037204742431,
|
|
"epoch": 1.367383613185826,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004823459084470031,
|
|
"loss": 5.2432,
|
|
"mean_token_accuracy": 0.20298130363225936,
|
|
"num_tokens": 27146107.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.446479988098145,
|
|
"epoch": 1.3679451900937833,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004823303158129165,
|
|
"loss": 5.0958,
|
|
"mean_token_accuracy": 0.2135227158665657,
|
|
"num_tokens": 27158821.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.428579330444336,
|
|
"epoch": 1.3685067670017408,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004823147165773523,
|
|
"loss": 5.1231,
|
|
"mean_token_accuracy": 0.20875139087438582,
|
|
"num_tokens": 27169513.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.406365203857422,
|
|
"epoch": 1.3690683439096984,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048229911074080715,
|
|
"loss": 5.1285,
|
|
"mean_token_accuracy": 0.20999689251184464,
|
|
"num_tokens": 27180059.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.4545081615447994,
|
|
"epoch": 1.369629920817656,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048228349830377787,
|
|
"loss": 5.1922,
|
|
"mean_token_accuracy": 0.20368644893169402,
|
|
"num_tokens": 27190738.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.462658882141113,
|
|
"epoch": 1.3701914977256135,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048226787926676165,
|
|
"loss": 5.0913,
|
|
"mean_token_accuracy": 0.20748201161623,
|
|
"num_tokens": 27200664.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.45639934539795,
|
|
"epoch": 1.370753074633571,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048225225363025576,
|
|
"loss": 5.1573,
|
|
"mean_token_accuracy": 0.20425347983837128,
|
|
"num_tokens": 27211011.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.495973205566406,
|
|
"epoch": 1.3713146515415287,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048223662139475773,
|
|
"loss": 5.2185,
|
|
"mean_token_accuracy": 0.20922895520925522,
|
|
"num_tokens": 27221888.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.507156419754028,
|
|
"epoch": 1.371876228449486,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00048222098256076523,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.19892387837171555,
|
|
"num_tokens": 27234671.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.399673938751221,
|
|
"epoch": 1.3724378053574438,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004822053371287763,
|
|
"loss": 5.0075,
|
|
"mean_token_accuracy": 0.21189790219068527,
|
|
"num_tokens": 27245283.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.458009386062622,
|
|
"epoch": 1.3729993822654012,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004821896850992891,
|
|
"loss": 5.1697,
|
|
"mean_token_accuracy": 0.20680995285511017,
|
|
"num_tokens": 27255056.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.5271751403808596,
|
|
"epoch": 1.3735609591733589,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000482174026472802,
|
|
"loss": 5.2201,
|
|
"mean_token_accuracy": 0.19984131008386613,
|
|
"num_tokens": 27266893.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.452425527572632,
|
|
"epoch": 1.3741225360813163,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004821583612498135,
|
|
"loss": 5.2406,
|
|
"mean_token_accuracy": 0.20188457816839217,
|
|
"num_tokens": 27279504.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.572341346740723,
|
|
"epoch": 1.374684112989274,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048214268943082246,
|
|
"loss": 5.2713,
|
|
"mean_token_accuracy": 0.20340170711278915,
|
|
"num_tokens": 27290525.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.548085880279541,
|
|
"epoch": 1.3752456898972314,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004821270110163278,
|
|
"loss": 5.1554,
|
|
"mean_token_accuracy": 0.2059785917401314,
|
|
"num_tokens": 27301404.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.460307836532593,
|
|
"epoch": 1.375807266805189,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004821113260068288,
|
|
"loss": 5.0776,
|
|
"mean_token_accuracy": 0.2048070177435875,
|
|
"num_tokens": 27312635.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.3788275718688965,
|
|
"epoch": 1.3763688437131465,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004820956344028249,
|
|
"loss": 5.1251,
|
|
"mean_token_accuracy": 0.20740974843502044,
|
|
"num_tokens": 27322485.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.5183103561401365,
|
|
"epoch": 1.376930420621104,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048207993620481566,
|
|
"loss": 5.2027,
|
|
"mean_token_accuracy": 0.2012050524353981,
|
|
"num_tokens": 27332568.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.5855084419250485,
|
|
"epoch": 1.3774919975290616,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004820642314133009,
|
|
"loss": 5.2455,
|
|
"mean_token_accuracy": 0.1964574620127678,
|
|
"num_tokens": 27343058.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.468304395675659,
|
|
"epoch": 1.3780535744370193,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048204852002878073,
|
|
"loss": 5.1143,
|
|
"mean_token_accuracy": 0.2115562677383423,
|
|
"num_tokens": 27355316.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.427171087265014,
|
|
"epoch": 1.3786151513449767,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048203280205175544,
|
|
"loss": 5.0642,
|
|
"mean_token_accuracy": 0.21111166030168532,
|
|
"num_tokens": 27366098.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.408334541320801,
|
|
"epoch": 1.3791767282529341,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004820170774827253,
|
|
"loss": 5.0873,
|
|
"mean_token_accuracy": 0.21402163952589034,
|
|
"num_tokens": 27376923.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.456176233291626,
|
|
"epoch": 1.3797383051608918,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004820013463221912,
|
|
"loss": 5.2352,
|
|
"mean_token_accuracy": 0.20305778980255126,
|
|
"num_tokens": 27386789.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.467389297485352,
|
|
"epoch": 1.3802998820688495,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000481985608570654,
|
|
"loss": 5.1218,
|
|
"mean_token_accuracy": 0.20468004941940307,
|
|
"num_tokens": 27399241.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.4002477645874025,
|
|
"epoch": 1.380861458976807,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004819698642286147,
|
|
"loss": 5.0358,
|
|
"mean_token_accuracy": 0.2179410293698311,
|
|
"num_tokens": 27409123.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.382656002044678,
|
|
"epoch": 1.3814230358847643,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048195411329657464,
|
|
"loss": 5.0984,
|
|
"mean_token_accuracy": 0.20253762304782869,
|
|
"num_tokens": 27419920.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.3557709693908695,
|
|
"epoch": 1.381984612792722,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004819383557750353,
|
|
"loss": 5.0009,
|
|
"mean_token_accuracy": 0.2055969163775444,
|
|
"num_tokens": 27429552.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.489142560958863,
|
|
"epoch": 1.3825461897006794,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048192259166449845,
|
|
"loss": 5.2036,
|
|
"mean_token_accuracy": 0.2049853578209877,
|
|
"num_tokens": 27440404.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.488819217681884,
|
|
"epoch": 1.383107766608637,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048190682096546606,
|
|
"loss": 5.2402,
|
|
"mean_token_accuracy": 0.2003431051969528,
|
|
"num_tokens": 27452231.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.475946092605591,
|
|
"epoch": 1.3836693435165945,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048189104367844034,
|
|
"loss": 5.1388,
|
|
"mean_token_accuracy": 0.20725544095039367,
|
|
"num_tokens": 27463658.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.466873121261597,
|
|
"epoch": 1.3842309204245522,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048187525980392343,
|
|
"loss": 5.1843,
|
|
"mean_token_accuracy": 0.20116572976112365,
|
|
"num_tokens": 27475403.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.524809885025024,
|
|
"epoch": 1.3847924973325096,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000481859469342418,
|
|
"loss": 5.2646,
|
|
"mean_token_accuracy": 0.19959893822669983,
|
|
"num_tokens": 27487056.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.4767341136932375,
|
|
"epoch": 1.3853540742404673,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004818436722944269,
|
|
"loss": 5.1191,
|
|
"mean_token_accuracy": 0.21175259202718735,
|
|
"num_tokens": 27498659.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.587176513671875,
|
|
"epoch": 1.3859156511484247,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004818278686604531,
|
|
"loss": 5.2691,
|
|
"mean_token_accuracy": 0.19665899276733398,
|
|
"num_tokens": 27510577.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.446998548507691,
|
|
"epoch": 1.3864772280563824,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004818120584409996,
|
|
"loss": 5.1659,
|
|
"mean_token_accuracy": 0.20675605088472365,
|
|
"num_tokens": 27521441.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.467502641677856,
|
|
"epoch": 1.3870388049643398,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004817962416365701,
|
|
"loss": 5.1011,
|
|
"mean_token_accuracy": 0.21017972379922867,
|
|
"num_tokens": 27533443.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.5100866794586185,
|
|
"epoch": 1.3876003818722973,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048178041824766796,
|
|
"loss": 5.1485,
|
|
"mean_token_accuracy": 0.2124373808503151,
|
|
"num_tokens": 27543872.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.563232278823852,
|
|
"epoch": 1.388161958780255,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004817645882747971,
|
|
"loss": 5.3531,
|
|
"mean_token_accuracy": 0.19551461786031724,
|
|
"num_tokens": 27556556.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.503177165985107,
|
|
"epoch": 1.3887235356882126,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004817487517184616,
|
|
"loss": 5.2227,
|
|
"mean_token_accuracy": 0.19677228033542632,
|
|
"num_tokens": 27570739.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.522423505783081,
|
|
"epoch": 1.38928511259617,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004817329085791657,
|
|
"loss": 5.2735,
|
|
"mean_token_accuracy": 0.19688376784324646,
|
|
"num_tokens": 27582438.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.53391580581665,
|
|
"epoch": 1.3898466895041275,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004817170588574138,
|
|
"loss": 5.1738,
|
|
"mean_token_accuracy": 0.20429896414279938,
|
|
"num_tokens": 27593854.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.539191246032715,
|
|
"epoch": 1.3904082664120851,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004817012025537105,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.20545539259910583,
|
|
"num_tokens": 27604459.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.548080682754517,
|
|
"epoch": 1.3909698433200428,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004816853396685608,
|
|
"loss": 5.354,
|
|
"mean_token_accuracy": 0.1883169785141945,
|
|
"num_tokens": 27617901.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.520606946945191,
|
|
"epoch": 1.3915314202280002,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048166947020246973,
|
|
"loss": 5.2728,
|
|
"mean_token_accuracy": 0.1959784671664238,
|
|
"num_tokens": 27628574.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.478893184661866,
|
|
"epoch": 1.3920929971359577,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048165359415594245,
|
|
"loss": 5.1407,
|
|
"mean_token_accuracy": 0.20215887874364852,
|
|
"num_tokens": 27639195.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.389469146728516,
|
|
"epoch": 1.3926545740439153,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048163771152948473,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.21549398005008696,
|
|
"num_tokens": 27649898.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.482058763504028,
|
|
"epoch": 1.3932161509518728,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000481621822323602,
|
|
"loss": 5.1915,
|
|
"mean_token_accuracy": 0.20455410331487656,
|
|
"num_tokens": 27663617.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.41757116317749,
|
|
"epoch": 1.3937777278598305,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004816059265388004,
|
|
"loss": 5.0674,
|
|
"mean_token_accuracy": 0.21241903454065322,
|
|
"num_tokens": 27674823.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.471855497360229,
|
|
"epoch": 1.394339304767788,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048159002417558596,
|
|
"loss": 5.1816,
|
|
"mean_token_accuracy": 0.20129034668207169,
|
|
"num_tokens": 27686483.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.458209657669068,
|
|
"epoch": 1.3949008816757456,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004815741152344651,
|
|
"loss": 5.1231,
|
|
"mean_token_accuracy": 0.2107679948210716,
|
|
"num_tokens": 27697081.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.486216926574707,
|
|
"epoch": 1.395462458583703,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004815581997159442,
|
|
"loss": 5.189,
|
|
"mean_token_accuracy": 0.20550450682640076,
|
|
"num_tokens": 27706710.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.487536764144897,
|
|
"epoch": 1.3960240354916607,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048154227762053003,
|
|
"loss": 5.2288,
|
|
"mean_token_accuracy": 0.19406247586011888,
|
|
"num_tokens": 27718213.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.411784744262695,
|
|
"epoch": 1.396585612399618,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004815263489487298,
|
|
"loss": 5.1581,
|
|
"mean_token_accuracy": 0.1991487443447113,
|
|
"num_tokens": 27729064.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.541603755950928,
|
|
"epoch": 1.3971471893075758,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004815104137010504,
|
|
"loss": 5.1388,
|
|
"mean_token_accuracy": 0.20811409056186675,
|
|
"num_tokens": 27740121.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.483473110198974,
|
|
"epoch": 1.3977087662155332,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004814944718779993,
|
|
"loss": 5.2108,
|
|
"mean_token_accuracy": 0.20785385519266128,
|
|
"num_tokens": 27751597.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.432009029388428,
|
|
"epoch": 1.3982703431234906,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004814785234800843,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.2107295125722885,
|
|
"num_tokens": 27761539.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.459167385101319,
|
|
"epoch": 1.3988319200314483,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048146256850781287,
|
|
"loss": 5.1216,
|
|
"mean_token_accuracy": 0.20399469435214995,
|
|
"num_tokens": 27772904.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.525432062149048,
|
|
"epoch": 1.399393496939406,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048144660696169327,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.2093617334961891,
|
|
"num_tokens": 27783706.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.44769253730774,
|
|
"epoch": 1.3999550738473634,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048143063884223365,
|
|
"loss": 5.1218,
|
|
"mean_token_accuracy": 0.19786850064992906,
|
|
"num_tokens": 27794503.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.435678100585937,
|
|
"epoch": 1.4005166507553208,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004814146641499424,
|
|
"loss": 5.1398,
|
|
"mean_token_accuracy": 0.2010348618030548,
|
|
"num_tokens": 27805952.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.498334836959839,
|
|
"epoch": 1.4010782276632785,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048139868288532816,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.20386661291122438,
|
|
"num_tokens": 27817530.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.498781347274781,
|
|
"epoch": 1.4016398045712362,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004813826950488998,
|
|
"loss": 5.2098,
|
|
"mean_token_accuracy": 0.19765318930149078,
|
|
"num_tokens": 27829932.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.459283256530762,
|
|
"epoch": 1.4022013814791936,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048136670064116645,
|
|
"loss": 5.1853,
|
|
"mean_token_accuracy": 0.20807783007621766,
|
|
"num_tokens": 27840993.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.47070198059082,
|
|
"epoch": 1.402762958387151,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004813506996626373,
|
|
"loss": 5.1166,
|
|
"mean_token_accuracy": 0.20531768202781678,
|
|
"num_tokens": 27852727.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.497899770736694,
|
|
"epoch": 1.4033245352951087,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004813346921138218,
|
|
"loss": 5.2867,
|
|
"mean_token_accuracy": 0.20217883586883545,
|
|
"num_tokens": 27865183.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.426887464523316,
|
|
"epoch": 1.4038861122030661,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004813186779952297,
|
|
"loss": 5.0433,
|
|
"mean_token_accuracy": 0.21312264502048492,
|
|
"num_tokens": 27877266.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.531505441665649,
|
|
"epoch": 1.4044476891110238,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004813026573073708,
|
|
"loss": 5.1708,
|
|
"mean_token_accuracy": 0.19764145314693451,
|
|
"num_tokens": 27888863.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.466286563873291,
|
|
"epoch": 1.4050092660189812,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004812866300507554,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.210232974588871,
|
|
"num_tokens": 27900443.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.452420806884765,
|
|
"epoch": 1.405570842926939,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004812705962258936,
|
|
"loss": 5.1028,
|
|
"mean_token_accuracy": 0.20642200261354446,
|
|
"num_tokens": 27911241.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.465728139877319,
|
|
"epoch": 1.4061324198348963,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004812545558332961,
|
|
"loss": 5.1254,
|
|
"mean_token_accuracy": 0.20888977199792863,
|
|
"num_tokens": 27922171.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.416845989227295,
|
|
"epoch": 1.406693996742854,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048123850887347346,
|
|
"loss": 5.1005,
|
|
"mean_token_accuracy": 0.207905550301075,
|
|
"num_tokens": 27933627.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.353041362762451,
|
|
"epoch": 1.4072555736508114,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048122245534693676,
|
|
"loss": 5.0436,
|
|
"mean_token_accuracy": 0.2077394977211952,
|
|
"num_tokens": 27943585.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.471788835525513,
|
|
"epoch": 1.407817150558769,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004812063952541971,
|
|
"loss": 5.1497,
|
|
"mean_token_accuracy": 0.20525009483098983,
|
|
"num_tokens": 27955554.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.496187496185303,
|
|
"epoch": 1.4083787274667265,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048119032859576577,
|
|
"loss": 5.0461,
|
|
"mean_token_accuracy": 0.21123435199260712,
|
|
"num_tokens": 27966150.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.414362001419067,
|
|
"epoch": 1.408940304374684,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004811742553721545,
|
|
"loss": 5.0894,
|
|
"mean_token_accuracy": 0.21142808049917222,
|
|
"num_tokens": 27977436.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.485429048538208,
|
|
"epoch": 1.4095018812826416,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048115817558387494,
|
|
"loss": 5.2557,
|
|
"mean_token_accuracy": 0.19952340871095658,
|
|
"num_tokens": 27988325.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.522013711929321,
|
|
"epoch": 1.4100634581905993,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004811420892314391,
|
|
"loss": 5.1072,
|
|
"mean_token_accuracy": 0.20461919158697128,
|
|
"num_tokens": 27999760.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.543334102630615,
|
|
"epoch": 1.4106250350985567,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004811259963153592,
|
|
"loss": 5.2293,
|
|
"mean_token_accuracy": 0.1947714552283287,
|
|
"num_tokens": 28011333.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.43923282623291,
|
|
"epoch": 1.4111866120065142,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004811098968361476,
|
|
"loss": 5.1946,
|
|
"mean_token_accuracy": 0.20771200060844422,
|
|
"num_tokens": 28023464.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.446501684188843,
|
|
"epoch": 1.4117481889144718,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000481093790794317,
|
|
"loss": 5.1465,
|
|
"mean_token_accuracy": 0.19933257550001143,
|
|
"num_tokens": 28034205.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.528965091705322,
|
|
"epoch": 1.4123097658224295,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004810776781903801,
|
|
"loss": 5.1368,
|
|
"mean_token_accuracy": 0.2043679401278496,
|
|
"num_tokens": 28045846.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.518973684310913,
|
|
"epoch": 1.412871342730387,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048106155902485003,
|
|
"loss": 5.1513,
|
|
"mean_token_accuracy": 0.2087111920118332,
|
|
"num_tokens": 28057365.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.48867712020874,
|
|
"epoch": 1.4134329196383444,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004810454332982401,
|
|
"loss": 5.2396,
|
|
"mean_token_accuracy": 0.1994670510292053,
|
|
"num_tokens": 28069098.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.474959516525269,
|
|
"epoch": 1.413994496546302,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004810293010110635,
|
|
"loss": 5.1757,
|
|
"mean_token_accuracy": 0.20220031291246415,
|
|
"num_tokens": 28080008.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.5330305099487305,
|
|
"epoch": 1.4145560734542595,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004810131621638342,
|
|
"loss": 5.1869,
|
|
"mean_token_accuracy": 0.2046856924891472,
|
|
"num_tokens": 28091657.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.415086889266968,
|
|
"epoch": 1.4151176503622171,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048099701675706583,
|
|
"loss": 5.0972,
|
|
"mean_token_accuracy": 0.20730396509170532,
|
|
"num_tokens": 28102586.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.468436861038208,
|
|
"epoch": 1.4156792272701746,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004809808647912725,
|
|
"loss": 5.1733,
|
|
"mean_token_accuracy": 0.21040523648262024,
|
|
"num_tokens": 28113066.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.466883802413941,
|
|
"epoch": 1.4162408041781323,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004809647062669686,
|
|
"loss": 5.1697,
|
|
"mean_token_accuracy": 0.20165132582187653,
|
|
"num_tokens": 28124814.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.55237193107605,
|
|
"epoch": 1.4168023810860897,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00048094854118466856,
|
|
"loss": 5.2247,
|
|
"mean_token_accuracy": 0.19796105176210405,
|
|
"num_tokens": 28138009.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.414374876022339,
|
|
"epoch": 1.4173639579940474,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048093236954488715,
|
|
"loss": 5.1088,
|
|
"mean_token_accuracy": 0.2057243913412094,
|
|
"num_tokens": 28149222.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.437690210342407,
|
|
"epoch": 1.4179255349020048,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004809161913481392,
|
|
"loss": 5.1611,
|
|
"mean_token_accuracy": 0.20204149335622787,
|
|
"num_tokens": 28161323.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.462181043624878,
|
|
"epoch": 1.4184871118099625,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048090000659493985,
|
|
"loss": 5.1617,
|
|
"mean_token_accuracy": 0.20193156003952026,
|
|
"num_tokens": 28173242.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.488607358932495,
|
|
"epoch": 1.41904868871792,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048088381528580445,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.20966652333736419,
|
|
"num_tokens": 28183927.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.492193078994751,
|
|
"epoch": 1.4196102656258773,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048086761742124846,
|
|
"loss": 5.1096,
|
|
"mean_token_accuracy": 0.20702141970396043,
|
|
"num_tokens": 28194375.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.47846622467041,
|
|
"epoch": 1.420171842533835,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048085141300178774,
|
|
"loss": 5.1851,
|
|
"mean_token_accuracy": 0.2080398365855217,
|
|
"num_tokens": 28206492.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.4760016918182375,
|
|
"epoch": 1.4207334194417927,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048083520202793815,
|
|
"loss": 5.2059,
|
|
"mean_token_accuracy": 0.20113577097654342,
|
|
"num_tokens": 28217795.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.4678747177124025,
|
|
"epoch": 1.42129499634975,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004808189845002159,
|
|
"loss": 5.143,
|
|
"mean_token_accuracy": 0.2044993370771408,
|
|
"num_tokens": 28228796.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.497642183303833,
|
|
"epoch": 1.4218565732577075,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004808027604191374,
|
|
"loss": 5.1873,
|
|
"mean_token_accuracy": 0.20616001188755034,
|
|
"num_tokens": 28238873.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.410908126831055,
|
|
"epoch": 1.4224181501656652,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048078652978521914,
|
|
"loss": 4.9799,
|
|
"mean_token_accuracy": 0.21906768679618835,
|
|
"num_tokens": 28249832.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.463288307189941,
|
|
"epoch": 1.4229797270736229,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048077029259897797,
|
|
"loss": 5.1876,
|
|
"mean_token_accuracy": 0.20350343734025955,
|
|
"num_tokens": 28261532.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.576680374145508,
|
|
"epoch": 1.4235413039815803,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048075404886093094,
|
|
"loss": 5.1971,
|
|
"mean_token_accuracy": 0.20575254112482072,
|
|
"num_tokens": 28272008.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.491054105758667,
|
|
"epoch": 1.4241028808895377,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048073779857159504,
|
|
"loss": 5.1723,
|
|
"mean_token_accuracy": 0.20502566695213317,
|
|
"num_tokens": 28283239.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.516871070861816,
|
|
"epoch": 1.4246644577974954,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000480721541731488,
|
|
"loss": 5.2116,
|
|
"mean_token_accuracy": 0.20059361159801484,
|
|
"num_tokens": 28293597.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.484355735778808,
|
|
"epoch": 1.4252260347054528,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048070527834112727,
|
|
"loss": 5.1397,
|
|
"mean_token_accuracy": 0.20740580260753633,
|
|
"num_tokens": 28305124.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.408352613449097,
|
|
"epoch": 1.4257876116134105,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004806890084010306,
|
|
"loss": 5.1395,
|
|
"mean_token_accuracy": 0.20809488296508788,
|
|
"num_tokens": 28315875.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.433827304840088,
|
|
"epoch": 1.426349188521368,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048067273191171615,
|
|
"loss": 5.1292,
|
|
"mean_token_accuracy": 0.2041878119111061,
|
|
"num_tokens": 28327705.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.496900415420532,
|
|
"epoch": 1.4269107654293256,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004806564488737022,
|
|
"loss": 5.0969,
|
|
"mean_token_accuracy": 0.21106772422790526,
|
|
"num_tokens": 28338300.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.4769346714019775,
|
|
"epoch": 1.427472342337283,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004806401592875071,
|
|
"loss": 5.0657,
|
|
"mean_token_accuracy": 0.21399219185113907,
|
|
"num_tokens": 28348485.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.451786661148072,
|
|
"epoch": 1.4280339192452407,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048062386315364964,
|
|
"loss": 5.0883,
|
|
"mean_token_accuracy": 0.21437736302614213,
|
|
"num_tokens": 28359118.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.427522087097168,
|
|
"epoch": 1.4285954961531981,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004806075604726485,
|
|
"loss": 5.1344,
|
|
"mean_token_accuracy": 0.21084635108709335,
|
|
"num_tokens": 28369608.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.51730170249939,
|
|
"epoch": 1.4291570730611558,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048059125124502304,
|
|
"loss": 5.12,
|
|
"mean_token_accuracy": 0.21088398694992067,
|
|
"num_tokens": 28379709.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.464109277725219,
|
|
"epoch": 1.4297186499691132,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004805749354712924,
|
|
"loss": 5.1561,
|
|
"mean_token_accuracy": 0.2023326948285103,
|
|
"num_tokens": 28390758.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.66201171875,
|
|
"epoch": 1.4302802268770707,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000480558613151976,
|
|
"loss": 5.395,
|
|
"mean_token_accuracy": 0.1917519152164459,
|
|
"num_tokens": 28403485.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.537450981140137,
|
|
"epoch": 1.4308418037850283,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004805422842875936,
|
|
"loss": 5.2086,
|
|
"mean_token_accuracy": 0.20338305830955505,
|
|
"num_tokens": 28413627.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.484331035614014,
|
|
"epoch": 1.431403380692986,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048052594887866524,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.20481521636247635,
|
|
"num_tokens": 28424202.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.365954446792602,
|
|
"epoch": 1.4319649576009434,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048050960692571086,
|
|
"loss": 5.069,
|
|
"mean_token_accuracy": 0.20588970184326172,
|
|
"num_tokens": 28435136.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.434122133255005,
|
|
"epoch": 1.4325265345089009,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000480493258429251,
|
|
"loss": 5.1009,
|
|
"mean_token_accuracy": 0.2046312212944031,
|
|
"num_tokens": 28444915.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.488479280471802,
|
|
"epoch": 1.4330881114168585,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000480476903389806,
|
|
"loss": 5.1681,
|
|
"mean_token_accuracy": 0.19834898114204408,
|
|
"num_tokens": 28458295.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.519573593139649,
|
|
"epoch": 1.4336496883248162,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004804605418078968,
|
|
"loss": 5.2075,
|
|
"mean_token_accuracy": 0.20759073197841643,
|
|
"num_tokens": 28469587.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.556804275512695,
|
|
"epoch": 1.4342112652327736,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048044417368404426,
|
|
"loss": 5.1818,
|
|
"mean_token_accuracy": 0.20200895965099336,
|
|
"num_tokens": 28481498.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.546443700790405,
|
|
"epoch": 1.434772842140731,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048042779901876946,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.19586526304483415,
|
|
"num_tokens": 28492626.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.516772222518921,
|
|
"epoch": 1.4353344190486887,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004804114178125939,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.20486706048250197,
|
|
"num_tokens": 28503882.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.508041143417358,
|
|
"epoch": 1.4358959959566462,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004803950300660391,
|
|
"loss": 5.1114,
|
|
"mean_token_accuracy": 0.21730809062719345,
|
|
"num_tokens": 28514786.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.482204437255859,
|
|
"epoch": 1.4364575728646038,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004803786357796269,
|
|
"loss": 5.1372,
|
|
"mean_token_accuracy": 0.2062377005815506,
|
|
"num_tokens": 28526045.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.4685100555419925,
|
|
"epoch": 1.4370191497725613,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048036223495387934,
|
|
"loss": 5.15,
|
|
"mean_token_accuracy": 0.20564915239810944,
|
|
"num_tokens": 28536773.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.4386231899261475,
|
|
"epoch": 1.437580726680519,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004803458275893185,
|
|
"loss": 5.1064,
|
|
"mean_token_accuracy": 0.20556536465883254,
|
|
"num_tokens": 28548099.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.511852025985718,
|
|
"epoch": 1.4381423035884764,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004803294136864669,
|
|
"loss": 5.1536,
|
|
"mean_token_accuracy": 0.2053316429257393,
|
|
"num_tokens": 28559372.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.4550145149230955,
|
|
"epoch": 1.438703880496434,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048031299324584716,
|
|
"loss": 5.1648,
|
|
"mean_token_accuracy": 0.20393643379211426,
|
|
"num_tokens": 28570106.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.442716646194458,
|
|
"epoch": 1.4392654574043915,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000480296566267982,
|
|
"loss": 5.1756,
|
|
"mean_token_accuracy": 0.2047491565346718,
|
|
"num_tokens": 28582417.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.5688739776611325,
|
|
"epoch": 1.4398270343123492,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004802801327533947,
|
|
"loss": 5.299,
|
|
"mean_token_accuracy": 0.20020985305309297,
|
|
"num_tokens": 28594341.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.508680820465088,
|
|
"epoch": 1.4403886112203066,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048026369270260814,
|
|
"loss": 5.174,
|
|
"mean_token_accuracy": 0.20464228689670563,
|
|
"num_tokens": 28605580.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.5399620056152346,
|
|
"epoch": 1.440950188128264,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004802472461161462,
|
|
"loss": 5.2073,
|
|
"mean_token_accuracy": 0.19983220994472503,
|
|
"num_tokens": 28617779.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.519721126556396,
|
|
"epoch": 1.4415117650362217,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004802307929945322,
|
|
"loss": 5.2028,
|
|
"mean_token_accuracy": 0.1919047325849533,
|
|
"num_tokens": 28629714.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.516920661926269,
|
|
"epoch": 1.4420733419441794,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00048021433333829015,
|
|
"loss": 5.205,
|
|
"mean_token_accuracy": 0.19859661012887955,
|
|
"num_tokens": 28641381.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.493727493286133,
|
|
"epoch": 1.4426349188521368,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048019786714794424,
|
|
"loss": 5.1894,
|
|
"mean_token_accuracy": 0.2069296732544899,
|
|
"num_tokens": 28653650.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.473764705657959,
|
|
"epoch": 1.4431964957600942,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004801813944240186,
|
|
"loss": 5.1122,
|
|
"mean_token_accuracy": 0.20553876757621764,
|
|
"num_tokens": 28665252.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.449726390838623,
|
|
"epoch": 1.443758072668052,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004801649151670378,
|
|
"loss": 5.165,
|
|
"mean_token_accuracy": 0.20538520365953444,
|
|
"num_tokens": 28677072.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.424026155471802,
|
|
"epoch": 1.4443196495760096,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004801484293775265,
|
|
"loss": 5.0941,
|
|
"mean_token_accuracy": 0.20484882593154907,
|
|
"num_tokens": 28688767.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.549541664123535,
|
|
"epoch": 1.444881226483967,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004801319370560097,
|
|
"loss": 5.3319,
|
|
"mean_token_accuracy": 0.20201486349105835,
|
|
"num_tokens": 28699773.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.550434923171997,
|
|
"epoch": 1.4454428033919244,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004801154382030124,
|
|
"loss": 5.1748,
|
|
"mean_token_accuracy": 0.20406392514705657,
|
|
"num_tokens": 28710971.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.477548456192016,
|
|
"epoch": 1.446004380299882,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048009893281906004,
|
|
"loss": 5.0843,
|
|
"mean_token_accuracy": 0.20875932425260543,
|
|
"num_tokens": 28721544.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.538469457626343,
|
|
"epoch": 1.4465659572078395,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048008242090467803,
|
|
"loss": 5.3012,
|
|
"mean_token_accuracy": 0.19580515772104262,
|
|
"num_tokens": 28733790.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.577961540222168,
|
|
"epoch": 1.4471275341157972,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004800659024603923,
|
|
"loss": 5.2004,
|
|
"mean_token_accuracy": 0.2073975071310997,
|
|
"num_tokens": 28745218.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.562515020370483,
|
|
"epoch": 1.4476891110237546,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048004937748672864,
|
|
"loss": 5.2528,
|
|
"mean_token_accuracy": 0.20050956010818483,
|
|
"num_tokens": 28758061.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.422244215011597,
|
|
"epoch": 1.4482506879317123,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048003284598421327,
|
|
"loss": 5.0686,
|
|
"mean_token_accuracy": 0.21108701676130295,
|
|
"num_tokens": 28770037.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.511967134475708,
|
|
"epoch": 1.4488122648396697,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004800163079533726,
|
|
"loss": 5.223,
|
|
"mean_token_accuracy": 0.1976005792617798,
|
|
"num_tokens": 28781052.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.401247119903564,
|
|
"epoch": 1.4493738417476274,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004799997633947332,
|
|
"loss": 5.1005,
|
|
"mean_token_accuracy": 0.19951864182949067,
|
|
"num_tokens": 28791225.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.509648370742798,
|
|
"epoch": 1.4499354186555848,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047998321230882174,
|
|
"loss": 5.1317,
|
|
"mean_token_accuracy": 0.20951839983463288,
|
|
"num_tokens": 28803022.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.489766597747803,
|
|
"epoch": 1.4504969955635425,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047996665469616536,
|
|
"loss": 5.1047,
|
|
"mean_token_accuracy": 0.2046004757285118,
|
|
"num_tokens": 28813789.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.551026296615601,
|
|
"epoch": 1.4510585724715,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00047995009055729114,
|
|
"loss": 5.1522,
|
|
"mean_token_accuracy": 0.20666670054197311,
|
|
"num_tokens": 28825015.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.596477079391479,
|
|
"epoch": 1.4516201493794574,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004799335198927266,
|
|
"loss": 5.2803,
|
|
"mean_token_accuracy": 0.20229267179965973,
|
|
"num_tokens": 28835852.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.4911417961120605,
|
|
"epoch": 1.452181726287415,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004799169427029993,
|
|
"loss": 5.1899,
|
|
"mean_token_accuracy": 0.20372844338417054,
|
|
"num_tokens": 28846684.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.495855808258057,
|
|
"epoch": 1.4527433031953727,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047990035898863706,
|
|
"loss": 5.1913,
|
|
"mean_token_accuracy": 0.2003163680434227,
|
|
"num_tokens": 28857402.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.434234714508056,
|
|
"epoch": 1.4533048801033301,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004798837687501679,
|
|
"loss": 5.0262,
|
|
"mean_token_accuracy": 0.2175763502717018,
|
|
"num_tokens": 28867866.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.445178747177124,
|
|
"epoch": 1.4538664570112876,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004798671719881201,
|
|
"loss": 5.1411,
|
|
"mean_token_accuracy": 0.20677025020122528,
|
|
"num_tokens": 28878102.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.588583946228027,
|
|
"epoch": 1.4544280339192452,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004798505687030221,
|
|
"loss": 5.242,
|
|
"mean_token_accuracy": 0.20081905126571656,
|
|
"num_tokens": 28888981.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.442296981811523,
|
|
"epoch": 1.454989610827203,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004798339588954025,
|
|
"loss": 5.1065,
|
|
"mean_token_accuracy": 0.2057306468486786,
|
|
"num_tokens": 28899733.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.418082857131958,
|
|
"epoch": 1.4555511877351603,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004798173425657903,
|
|
"loss": 5.0946,
|
|
"mean_token_accuracy": 0.20657345950603484,
|
|
"num_tokens": 28910701.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.532093238830567,
|
|
"epoch": 1.4561127646431178,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004798007197147144,
|
|
"loss": 5.1761,
|
|
"mean_token_accuracy": 0.20050276815891266,
|
|
"num_tokens": 28922627.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.520030546188354,
|
|
"epoch": 1.4566743415510754,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004797840903427042,
|
|
"loss": 5.22,
|
|
"mean_token_accuracy": 0.20199471116065978,
|
|
"num_tokens": 28933292.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.394319534301758,
|
|
"epoch": 1.4572359184590329,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047976745445028906,
|
|
"loss": 5.0804,
|
|
"mean_token_accuracy": 0.21009878814220428,
|
|
"num_tokens": 28943898.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.460964202880859,
|
|
"epoch": 1.4577974953669905,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047975081203799883,
|
|
"loss": 5.1848,
|
|
"mean_token_accuracy": 0.20172940641641618,
|
|
"num_tokens": 28955248.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.477160310745239,
|
|
"epoch": 1.458359072274948,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047973416310636327,
|
|
"loss": 5.0597,
|
|
"mean_token_accuracy": 0.212305711209774,
|
|
"num_tokens": 28966905.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.506209850311279,
|
|
"epoch": 1.4589206491829056,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004797175076559126,
|
|
"loss": 5.181,
|
|
"mean_token_accuracy": 0.210268734395504,
|
|
"num_tokens": 28978515.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.438519716262817,
|
|
"epoch": 1.459482226090863,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00047970084568717703,
|
|
"loss": 5.165,
|
|
"mean_token_accuracy": 0.19923397600650788,
|
|
"num_tokens": 28990185.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.452360057830811,
|
|
"epoch": 1.4600438029988208,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004796841772006872,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.20202868133783342,
|
|
"num_tokens": 29000779.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.549176788330078,
|
|
"epoch": 1.4606053799067782,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047966750219697376,
|
|
"loss": 5.2552,
|
|
"mean_token_accuracy": 0.20228233486413955,
|
|
"num_tokens": 29012066.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.6248729705810545,
|
|
"epoch": 1.4611669568147359,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004796508206765677,
|
|
"loss": 5.2966,
|
|
"mean_token_accuracy": 0.19542959481477737,
|
|
"num_tokens": 29023416.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.503637075424194,
|
|
"epoch": 1.4617285337226933,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047963413264000005,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.20476240664720535,
|
|
"num_tokens": 29034469.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.453005456924439,
|
|
"epoch": 1.4622901106306507,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004796174380878023,
|
|
"loss": 5.1037,
|
|
"mean_token_accuracy": 0.20023581087589265,
|
|
"num_tokens": 29045306.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.4390764236450195,
|
|
"epoch": 1.4628516875386084,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000479600737020506,
|
|
"loss": 5.0963,
|
|
"mean_token_accuracy": 0.2090238317847252,
|
|
"num_tokens": 29057114.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.4582654476165775,
|
|
"epoch": 1.463413264446566,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004795840294386429,
|
|
"loss": 5.0866,
|
|
"mean_token_accuracy": 0.19895012229681014,
|
|
"num_tokens": 29067250.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.445709133148194,
|
|
"epoch": 1.4639748413545235,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00047956731534274483,
|
|
"loss": 5.1126,
|
|
"mean_token_accuracy": 0.21051748394966124,
|
|
"num_tokens": 29078582.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.4906774997711185,
|
|
"epoch": 1.464536418262481,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047955059473334425,
|
|
"loss": 5.1486,
|
|
"mean_token_accuracy": 0.21105076223611832,
|
|
"num_tokens": 29090113.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.427413702011108,
|
|
"epoch": 1.4650979951704386,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004795338676109733,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.2052920252084732,
|
|
"num_tokens": 29101117.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.534099531173706,
|
|
"epoch": 1.4656595720783963,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004795171339761647,
|
|
"loss": 5.1587,
|
|
"mean_token_accuracy": 0.20264400094747542,
|
|
"num_tokens": 29112569.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.5404692649841305,
|
|
"epoch": 1.4662211489863537,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047950039382945126,
|
|
"loss": 5.2492,
|
|
"mean_token_accuracy": 0.2044188603758812,
|
|
"num_tokens": 29124462.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.4422135829925535,
|
|
"epoch": 1.4667827258943111,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047948364717136587,
|
|
"loss": 5.1189,
|
|
"mean_token_accuracy": 0.2060721069574356,
|
|
"num_tokens": 29135401.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.480085706710815,
|
|
"epoch": 1.4673443028022688,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047946689400244196,
|
|
"loss": 5.1336,
|
|
"mean_token_accuracy": 0.2062096118927002,
|
|
"num_tokens": 29146601.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.481954145431518,
|
|
"epoch": 1.4679058797102262,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047945013432321284,
|
|
"loss": 5.1265,
|
|
"mean_token_accuracy": 0.2071948990225792,
|
|
"num_tokens": 29157299.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.567254304885864,
|
|
"epoch": 1.468467456618184,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047943336813421205,
|
|
"loss": 5.2233,
|
|
"mean_token_accuracy": 0.1984789177775383,
|
|
"num_tokens": 29169101.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.378282737731934,
|
|
"epoch": 1.4690290335261413,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004794165954359736,
|
|
"loss": 5.0536,
|
|
"mean_token_accuracy": 0.21008046567440034,
|
|
"num_tokens": 29181286.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.495277786254883,
|
|
"epoch": 1.469590610434099,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004793998162290315,
|
|
"loss": 5.226,
|
|
"mean_token_accuracy": 0.201323439180851,
|
|
"num_tokens": 29191181.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.417777824401855,
|
|
"epoch": 1.4701521873420564,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004793830305139199,
|
|
"loss": 5.0796,
|
|
"mean_token_accuracy": 0.20867829918861389,
|
|
"num_tokens": 29202426.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.3995689868927,
|
|
"epoch": 1.470713764250014,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004793662382911734,
|
|
"loss": 5.0877,
|
|
"mean_token_accuracy": 0.2065662920475006,
|
|
"num_tokens": 29212817.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.461744594573974,
|
|
"epoch": 1.4712753411579715,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004793494395613265,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.20269558131694793,
|
|
"num_tokens": 29224644.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.506007528305053,
|
|
"epoch": 1.4718369180659292,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004793326343249144,
|
|
"loss": 5.1163,
|
|
"mean_token_accuracy": 0.20634000301361083,
|
|
"num_tokens": 29236443.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.540659093856812,
|
|
"epoch": 1.4723984949738866,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004793158225824718,
|
|
"loss": 5.2541,
|
|
"mean_token_accuracy": 0.19870007932186126,
|
|
"num_tokens": 29247687.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.53632287979126,
|
|
"epoch": 1.4729600718818443,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047929900433453423,
|
|
"loss": 5.1653,
|
|
"mean_token_accuracy": 0.19968986213207246,
|
|
"num_tokens": 29259739.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.510801124572754,
|
|
"epoch": 1.4735216487898017,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047928217958163703,
|
|
"loss": 5.1844,
|
|
"mean_token_accuracy": 0.20789009779691697,
|
|
"num_tokens": 29270834.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.491941642761231,
|
|
"epoch": 1.4740832256977594,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047926534832431615,
|
|
"loss": 5.1455,
|
|
"mean_token_accuracy": 0.2055303454399109,
|
|
"num_tokens": 29282291.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.520731115341187,
|
|
"epoch": 1.4746448026057168,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004792485105631073,
|
|
"loss": 5.1965,
|
|
"mean_token_accuracy": 0.1997177168726921,
|
|
"num_tokens": 29293836.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.4909240245819095,
|
|
"epoch": 1.4752063795136743,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004792316662985467,
|
|
"loss": 5.2003,
|
|
"mean_token_accuracy": 0.19660606533288955,
|
|
"num_tokens": 29305550.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.523720121383667,
|
|
"epoch": 1.475767956421632,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00047921481553117053,
|
|
"loss": 5.1836,
|
|
"mean_token_accuracy": 0.2036956235766411,
|
|
"num_tokens": 29316973.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.476486587524414,
|
|
"epoch": 1.4763295333295896,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00047919795826151544,
|
|
"loss": 5.0542,
|
|
"mean_token_accuracy": 0.2100991800427437,
|
|
"num_tokens": 29327743.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.42023868560791,
|
|
"epoch": 1.476891110237547,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004791810944901183,
|
|
"loss": 5.0653,
|
|
"mean_token_accuracy": 0.20388011634349823,
|
|
"num_tokens": 29338286.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.438933229446411,
|
|
"epoch": 1.4774526871455045,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004791642242175158,
|
|
"loss": 5.203,
|
|
"mean_token_accuracy": 0.19936581403017045,
|
|
"num_tokens": 29348877.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.410045480728149,
|
|
"epoch": 1.4780142640534621,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00047914734744424517,
|
|
"loss": 4.9674,
|
|
"mean_token_accuracy": 0.21752348393201829,
|
|
"num_tokens": 29360072.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.513800144195557,
|
|
"epoch": 1.4785758409614196,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047913046417084393,
|
|
"loss": 5.2137,
|
|
"mean_token_accuracy": 0.20630625784397125,
|
|
"num_tokens": 29370744.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.522347116470337,
|
|
"epoch": 1.4791374178693772,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047911357439784947,
|
|
"loss": 5.1379,
|
|
"mean_token_accuracy": 0.20243710428476333,
|
|
"num_tokens": 29381463.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.500744342803955,
|
|
"epoch": 1.4796989947773347,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00047909667812579964,
|
|
"loss": 5.1826,
|
|
"mean_token_accuracy": 0.20441703498363495,
|
|
"num_tokens": 29394227.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.426384735107422,
|
|
"epoch": 1.4802605716852923,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047907977535523253,
|
|
"loss": 5.0986,
|
|
"mean_token_accuracy": 0.20749824345111847,
|
|
"num_tokens": 29404754.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.423990058898926,
|
|
"epoch": 1.4808221485932498,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004790628660866861,
|
|
"loss": 5.142,
|
|
"mean_token_accuracy": 0.21275347769260405,
|
|
"num_tokens": 29416161.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.449864149093628,
|
|
"epoch": 1.4813837255012074,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004790459503206989,
|
|
"loss": 5.0314,
|
|
"mean_token_accuracy": 0.21738106459379197,
|
|
"num_tokens": 29426587.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.494637823104858,
|
|
"epoch": 1.4819453024091649,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004790290280578095,
|
|
"loss": 5.1899,
|
|
"mean_token_accuracy": 0.1964538276195526,
|
|
"num_tokens": 29437488.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.451122140884399,
|
|
"epoch": 1.4825068793171226,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047901209929855675,
|
|
"loss": 5.158,
|
|
"mean_token_accuracy": 0.20798053443431855,
|
|
"num_tokens": 29448244.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.548648357391357,
|
|
"epoch": 1.48306845622508,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004789951640434796,
|
|
"loss": 5.2446,
|
|
"mean_token_accuracy": 0.20025039315223694,
|
|
"num_tokens": 29458260.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.603910875320435,
|
|
"epoch": 1.4836300331330377,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004789782222931173,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.20077601224184036,
|
|
"num_tokens": 29470874.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.41795244216919,
|
|
"epoch": 1.484191610040995,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047896127404800935,
|
|
"loss": 5.0994,
|
|
"mean_token_accuracy": 0.20298130810260773,
|
|
"num_tokens": 29481442.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.549015760421753,
|
|
"epoch": 1.4847531869489528,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004789443193086953,
|
|
"loss": 5.2512,
|
|
"mean_token_accuracy": 0.2030337229371071,
|
|
"num_tokens": 29492727.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.57514796257019,
|
|
"epoch": 1.4853147638569102,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047892735807571505,
|
|
"loss": 5.1879,
|
|
"mean_token_accuracy": 0.19736639857292176,
|
|
"num_tokens": 29502729.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.5533716678619385,
|
|
"epoch": 1.4858763407648676,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004789103903496086,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.20643337666988373,
|
|
"num_tokens": 29514315.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.490795993804932,
|
|
"epoch": 1.4864379176728253,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004788934161309161,
|
|
"loss": 5.0835,
|
|
"mean_token_accuracy": 0.21079244315624238,
|
|
"num_tokens": 29526030.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.45865387916565,
|
|
"epoch": 1.486999494580783,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047887643542017836,
|
|
"loss": 5.1081,
|
|
"mean_token_accuracy": 0.20463404506444932,
|
|
"num_tokens": 29536972.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.406656122207641,
|
|
"epoch": 1.4875610714887404,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047885944821793574,
|
|
"loss": 5.1241,
|
|
"mean_token_accuracy": 0.20604779273271562,
|
|
"num_tokens": 29547325.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.5179516792297365,
|
|
"epoch": 1.4881226483966978,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047884245452472926,
|
|
"loss": 5.1656,
|
|
"mean_token_accuracy": 0.20583217293024064,
|
|
"num_tokens": 29557944.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.429768323898315,
|
|
"epoch": 1.4886842253046555,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004788254543410999,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.20905335396528243,
|
|
"num_tokens": 29568618.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.499443531036377,
|
|
"epoch": 1.489245802212613,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047880844766758914,
|
|
"loss": 5.1496,
|
|
"mean_token_accuracy": 0.2003599688410759,
|
|
"num_tokens": 29580682.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.5412647247314455,
|
|
"epoch": 1.4898073791205706,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047879143450473824,
|
|
"loss": 5.204,
|
|
"mean_token_accuracy": 0.20136342644691468,
|
|
"num_tokens": 29592302.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.554577350616455,
|
|
"epoch": 1.490368956028528,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047877441485308917,
|
|
"loss": 5.205,
|
|
"mean_token_accuracy": 0.2014056697487831,
|
|
"num_tokens": 29603591.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.447190618515014,
|
|
"epoch": 1.4909305329364857,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047875738871318356,
|
|
"loss": 5.1682,
|
|
"mean_token_accuracy": 0.20276699662208558,
|
|
"num_tokens": 29615542.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.551174640655518,
|
|
"epoch": 1.4914921098444431,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004787403560855637,
|
|
"loss": 5.1888,
|
|
"mean_token_accuracy": 0.21355810165405273,
|
|
"num_tokens": 29626650.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.468151187896728,
|
|
"epoch": 1.4920536867524008,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004787233169707719,
|
|
"loss": 5.1359,
|
|
"mean_token_accuracy": 0.20220291763544082,
|
|
"num_tokens": 29637135.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.492263269424439,
|
|
"epoch": 1.4926152636603582,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004787062713693507,
|
|
"loss": 5.1789,
|
|
"mean_token_accuracy": 0.20043986588716506,
|
|
"num_tokens": 29648862.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.472868776321411,
|
|
"epoch": 1.493176840568316,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047868921928184276,
|
|
"loss": 5.1482,
|
|
"mean_token_accuracy": 0.2028573378920555,
|
|
"num_tokens": 29661015.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.58891339302063,
|
|
"epoch": 1.4937384174762733,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004786721607087911,
|
|
"loss": 5.1402,
|
|
"mean_token_accuracy": 0.1992519497871399,
|
|
"num_tokens": 29673521.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.544138336181641,
|
|
"epoch": 1.494299994384231,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004786550956507389,
|
|
"loss": 5.2147,
|
|
"mean_token_accuracy": 0.2113247260451317,
|
|
"num_tokens": 29685379.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.488175249099731,
|
|
"epoch": 1.4948615712921884,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004786380241082294,
|
|
"loss": 5.1334,
|
|
"mean_token_accuracy": 0.20022862702608107,
|
|
"num_tokens": 29696372.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.500126600265503,
|
|
"epoch": 1.495423148200146,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047862094608180623,
|
|
"loss": 5.1431,
|
|
"mean_token_accuracy": 0.20842529982328414,
|
|
"num_tokens": 29707401.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.431816911697387,
|
|
"epoch": 1.4959847251081035,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004786038615720132,
|
|
"loss": 5.1222,
|
|
"mean_token_accuracy": 0.2076442390680313,
|
|
"num_tokens": 29717524.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.511350870132446,
|
|
"epoch": 1.496546302016061,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047858677057939427,
|
|
"loss": 5.2424,
|
|
"mean_token_accuracy": 0.19728194177150726,
|
|
"num_tokens": 29728235.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.586638069152832,
|
|
"epoch": 1.4971078789240186,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047856967310449356,
|
|
"loss": 5.24,
|
|
"mean_token_accuracy": 0.19504618942737578,
|
|
"num_tokens": 29738800.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.555594253540039,
|
|
"epoch": 1.4976694558319763,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047855256914785556,
|
|
"loss": 5.1673,
|
|
"mean_token_accuracy": 0.20222549438476561,
|
|
"num_tokens": 29750346.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.454142665863037,
|
|
"epoch": 1.4982310327399337,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047853545871002476,
|
|
"loss": 5.0805,
|
|
"mean_token_accuracy": 0.2097135826945305,
|
|
"num_tokens": 29761931.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.391069126129151,
|
|
"epoch": 1.4987926096478912,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047851834179154595,
|
|
"loss": 5.0718,
|
|
"mean_token_accuracy": 0.2105358362197876,
|
|
"num_tokens": 29773333.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.414756536483765,
|
|
"epoch": 1.4993541865558488,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004785012183929643,
|
|
"loss": 5.0653,
|
|
"mean_token_accuracy": 0.212247596681118,
|
|
"num_tokens": 29785125.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.435869598388672,
|
|
"epoch": 1.4999157634638065,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004784840885148249,
|
|
"loss": 5.1782,
|
|
"mean_token_accuracy": 0.20986656248569488,
|
|
"num_tokens": 29796288.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.5364643096923825,
|
|
"epoch": 1.500477340371764,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004784669521576732,
|
|
"loss": 5.1953,
|
|
"mean_token_accuracy": 0.2044151559472084,
|
|
"num_tokens": 29806348.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.5060771942138675,
|
|
"epoch": 1.5010389172797214,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004784498093220549,
|
|
"loss": 5.0903,
|
|
"mean_token_accuracy": 0.2109503373503685,
|
|
"num_tokens": 29816342.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.406218242645264,
|
|
"epoch": 1.501600494187679,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004784326600085157,
|
|
"loss": 5.0911,
|
|
"mean_token_accuracy": 0.20413004904985427,
|
|
"num_tokens": 29826789.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.496536493301392,
|
|
"epoch": 1.5021620710956367,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047841550421760164,
|
|
"loss": 5.1868,
|
|
"mean_token_accuracy": 0.20478349030017853,
|
|
"num_tokens": 29837633.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.5469011783599855,
|
|
"epoch": 1.502723648003594,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047839834194985916,
|
|
"loss": 5.2329,
|
|
"mean_token_accuracy": 0.20279349386692047,
|
|
"num_tokens": 29848498.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.54252142906189,
|
|
"epoch": 1.5032852249115516,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004783811732058345,
|
|
"loss": 5.2057,
|
|
"mean_token_accuracy": 0.20127368122339248,
|
|
"num_tokens": 29859777.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.718990612030029,
|
|
"epoch": 1.5038468018195092,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047836399798607446,
|
|
"loss": 5.3868,
|
|
"mean_token_accuracy": 0.19448302388191224,
|
|
"num_tokens": 29873373.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.546049451828003,
|
|
"epoch": 1.5044083787274667,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047834681629112583,
|
|
"loss": 5.1472,
|
|
"mean_token_accuracy": 0.2054397717118263,
|
|
"num_tokens": 29884749.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.415380764007568,
|
|
"epoch": 1.5049699556354241,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004783296281215357,
|
|
"loss": 5.0754,
|
|
"mean_token_accuracy": 0.20518286973237992,
|
|
"num_tokens": 29895059.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.392477560043335,
|
|
"epoch": 1.5055315325433818,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004783124334778513,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.2021928146481514,
|
|
"num_tokens": 29906611.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.370140790939331,
|
|
"epoch": 1.5060931094513395,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004782952323606202,
|
|
"loss": 5.0101,
|
|
"mean_token_accuracy": 0.21246108114719392,
|
|
"num_tokens": 29918179.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.509697294235229,
|
|
"epoch": 1.506654686359297,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004782780247703901,
|
|
"loss": 5.1691,
|
|
"mean_token_accuracy": 0.20233879536390303,
|
|
"num_tokens": 29929612.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.491402673721313,
|
|
"epoch": 1.5072162632672543,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004782608107077088,
|
|
"loss": 5.0597,
|
|
"mean_token_accuracy": 0.21546249240636825,
|
|
"num_tokens": 29939569.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.478633022308349,
|
|
"epoch": 1.507777840175212,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047824359017312445,
|
|
"loss": 5.0862,
|
|
"mean_token_accuracy": 0.20860920548439027,
|
|
"num_tokens": 29950344.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.435837888717652,
|
|
"epoch": 1.5083394170831697,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004782263631671854,
|
|
"loss": 5.1028,
|
|
"mean_token_accuracy": 0.2105194792151451,
|
|
"num_tokens": 29960748.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.588251638412475,
|
|
"epoch": 1.508900993991127,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047820912969044014,
|
|
"loss": 5.285,
|
|
"mean_token_accuracy": 0.1966715157032013,
|
|
"num_tokens": 29971678.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.416446542739868,
|
|
"epoch": 1.5094625708990845,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047819188974343734,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.20558972209692,
|
|
"num_tokens": 29982477.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.444994974136352,
|
|
"epoch": 1.5100241478070422,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004781746433267259,
|
|
"loss": 5.161,
|
|
"mean_token_accuracy": 0.21009932905435563,
|
|
"num_tokens": 29994539.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.513435792922974,
|
|
"epoch": 1.5105857247149999,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047815739044085515,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.21252892911434174,
|
|
"num_tokens": 30004821.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.609660911560058,
|
|
"epoch": 1.5111473016229573,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047814013108637423,
|
|
"loss": 5.1657,
|
|
"mean_token_accuracy": 0.20085231214761734,
|
|
"num_tokens": 30016343.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.454044580459595,
|
|
"epoch": 1.5117088785309147,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047812286526383274,
|
|
"loss": 5.0867,
|
|
"mean_token_accuracy": 0.21451688855886458,
|
|
"num_tokens": 30027719.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.426101160049439,
|
|
"epoch": 1.5122704554388724,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004781055929737804,
|
|
"loss": 5.0707,
|
|
"mean_token_accuracy": 0.2172236144542694,
|
|
"num_tokens": 30037988.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.4582665920257565,
|
|
"epoch": 1.51283203234683,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047808831421676724,
|
|
"loss": 5.0804,
|
|
"mean_token_accuracy": 0.21147372126579284,
|
|
"num_tokens": 30049736.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.537223529815674,
|
|
"epoch": 1.5133936092547875,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004780710289933435,
|
|
"loss": 5.2069,
|
|
"mean_token_accuracy": 0.20294972658157348,
|
|
"num_tokens": 30061963.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.569507360458374,
|
|
"epoch": 1.513955186162745,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004780537373040593,
|
|
"loss": 5.1057,
|
|
"mean_token_accuracy": 0.21471622735261917,
|
|
"num_tokens": 30072256.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.460702514648437,
|
|
"epoch": 1.5145167630707026,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047803643914946537,
|
|
"loss": 5.1706,
|
|
"mean_token_accuracy": 0.20563367158174514,
|
|
"num_tokens": 30084804.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.479845857620239,
|
|
"epoch": 1.51507833997866,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004780191345301125,
|
|
"loss": 5.1436,
|
|
"mean_token_accuracy": 0.20428748577833175,
|
|
"num_tokens": 30096938.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.505037069320679,
|
|
"epoch": 1.5156399168866175,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047800182344655165,
|
|
"loss": 5.1227,
|
|
"mean_token_accuracy": 0.20337493419647218,
|
|
"num_tokens": 30108233.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.50295672416687,
|
|
"epoch": 1.5162014937945751,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000477984505899334,
|
|
"loss": 5.14,
|
|
"mean_token_accuracy": 0.21044730097055436,
|
|
"num_tokens": 30120246.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.458343076705932,
|
|
"epoch": 1.5167630707025328,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047796718188901095,
|
|
"loss": 4.9939,
|
|
"mean_token_accuracy": 0.21335820704698563,
|
|
"num_tokens": 30131213.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.397097158432007,
|
|
"epoch": 1.5173246476104902,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00047794985141613413,
|
|
"loss": 5.0444,
|
|
"mean_token_accuracy": 0.2153217688202858,
|
|
"num_tokens": 30143300.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.437649822235107,
|
|
"epoch": 1.5178862245184477,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047793251448125526,
|
|
"loss": 5.0802,
|
|
"mean_token_accuracy": 0.20531620532274247,
|
|
"num_tokens": 30153794.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.500084114074707,
|
|
"epoch": 1.5184478014264053,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004779151710849265,
|
|
"loss": 5.2161,
|
|
"mean_token_accuracy": 0.19907034784555436,
|
|
"num_tokens": 30165152.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.4851343631744385,
|
|
"epoch": 1.519009378334363,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004778978212276999,
|
|
"loss": 5.1327,
|
|
"mean_token_accuracy": 0.20664205253124238,
|
|
"num_tokens": 30176338.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.464123392105103,
|
|
"epoch": 1.5195709552423204,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004778804649101281,
|
|
"loss": 5.1704,
|
|
"mean_token_accuracy": 0.20037916749715806,
|
|
"num_tokens": 30187666.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.48260989189148,
|
|
"epoch": 1.5201325321502779,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004778631021327636,
|
|
"loss": 5.2133,
|
|
"mean_token_accuracy": 0.19810021072626113,
|
|
"num_tokens": 30198892.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.453015661239624,
|
|
"epoch": 1.5206941090582355,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004778457328961592,
|
|
"loss": 5.1627,
|
|
"mean_token_accuracy": 0.1998189389705658,
|
|
"num_tokens": 30210677.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.519055509567261,
|
|
"epoch": 1.5212556859661932,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047782835720086797,
|
|
"loss": 5.0944,
|
|
"mean_token_accuracy": 0.2124049633741379,
|
|
"num_tokens": 30221217.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.560549926757813,
|
|
"epoch": 1.5218172628741506,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004778109750474432,
|
|
"loss": 5.236,
|
|
"mean_token_accuracy": 0.20007369220256804,
|
|
"num_tokens": 30233576.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.461468458175659,
|
|
"epoch": 1.522378839782108,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004777935864364383,
|
|
"loss": 5.0853,
|
|
"mean_token_accuracy": 0.20346295982599258,
|
|
"num_tokens": 30244787.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.4790794372558596,
|
|
"epoch": 1.5229404166900657,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000477776191368407,
|
|
"loss": 5.1388,
|
|
"mean_token_accuracy": 0.20858580768108367,
|
|
"num_tokens": 30256656.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.558883762359619,
|
|
"epoch": 1.5235019935980234,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004777587898439031,
|
|
"loss": 5.2076,
|
|
"mean_token_accuracy": 0.20844527930021287,
|
|
"num_tokens": 30267715.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.556528377532959,
|
|
"epoch": 1.5240635705059808,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047774138186348073,
|
|
"loss": 5.1963,
|
|
"mean_token_accuracy": 0.2015288919210434,
|
|
"num_tokens": 30278119.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.525978851318359,
|
|
"epoch": 1.5246251474139383,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004777239674276941,
|
|
"loss": 5.1146,
|
|
"mean_token_accuracy": 0.20381217449903488,
|
|
"num_tokens": 30289899.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.430830812454223,
|
|
"epoch": 1.525186724321896,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004777065465370977,
|
|
"loss": 5.1271,
|
|
"mean_token_accuracy": 0.20787773430347442,
|
|
"num_tokens": 30300799.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.5626091957092285,
|
|
"epoch": 1.5257483012298534,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004776891191922463,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.20186955183744432,
|
|
"num_tokens": 30312955.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.537404870986938,
|
|
"epoch": 1.5263098781378108,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004776716853936947,
|
|
"loss": 5.1053,
|
|
"mean_token_accuracy": 0.205371630191803,
|
|
"num_tokens": 30323089.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.489454984664917,
|
|
"epoch": 1.5268714550457685,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000477654245141998,
|
|
"loss": 5.0512,
|
|
"mean_token_accuracy": 0.21588983833789827,
|
|
"num_tokens": 30333926.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.4234906196594235,
|
|
"epoch": 1.5274330319537262,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004776367984377116,
|
|
"loss": 5.1617,
|
|
"mean_token_accuracy": 0.20579976886510848,
|
|
"num_tokens": 30346347.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.4525346755981445,
|
|
"epoch": 1.5279946088616836,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00047761934528139086,
|
|
"loss": 5.1416,
|
|
"mean_token_accuracy": 0.1997246116399765,
|
|
"num_tokens": 30357757.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.596718072891235,
|
|
"epoch": 1.528556185769641,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004776018856735916,
|
|
"loss": 5.1881,
|
|
"mean_token_accuracy": 0.2084172859787941,
|
|
"num_tokens": 30369323.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.464363765716553,
|
|
"epoch": 1.5291177626775987,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004775844196148698,
|
|
"loss": 5.0557,
|
|
"mean_token_accuracy": 0.21078469157218932,
|
|
"num_tokens": 30380335.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.402562236785888,
|
|
"epoch": 1.5296793395855564,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047756694710578146,
|
|
"loss": 5.0762,
|
|
"mean_token_accuracy": 0.2053290605545044,
|
|
"num_tokens": 30391338.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.493469095230102,
|
|
"epoch": 1.5302409164935138,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000477549468146883,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.1947053089737892,
|
|
"num_tokens": 30402917.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.439848947525024,
|
|
"epoch": 1.5308024934014712,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004775319827387309,
|
|
"loss": 4.9802,
|
|
"mean_token_accuracy": 0.21650879383087157,
|
|
"num_tokens": 30412690.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.448499393463135,
|
|
"epoch": 1.531364070309429,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004775144908818818,
|
|
"loss": 5.1884,
|
|
"mean_token_accuracy": 0.19989157170057298,
|
|
"num_tokens": 30423020.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.581812238693237,
|
|
"epoch": 1.5319256472173866,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047749699257689296,
|
|
"loss": 5.3771,
|
|
"mean_token_accuracy": 0.18942070752382278,
|
|
"num_tokens": 30434039.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.563929796218872,
|
|
"epoch": 1.532487224125344,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004774794878243212,
|
|
"loss": 5.1627,
|
|
"mean_token_accuracy": 0.20131921023130417,
|
|
"num_tokens": 30446743.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.518055868148804,
|
|
"epoch": 1.5330488010333014,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000477461976624724,
|
|
"loss": 5.1509,
|
|
"mean_token_accuracy": 0.20493233948946,
|
|
"num_tokens": 30456969.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.398975658416748,
|
|
"epoch": 1.533610377941259,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047744445897865905,
|
|
"loss": 5.2021,
|
|
"mean_token_accuracy": 0.19790499955415725,
|
|
"num_tokens": 30467497.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.478356122970581,
|
|
"epoch": 1.5341719548492168,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000477426934886684,
|
|
"loss": 5.1447,
|
|
"mean_token_accuracy": 0.20651963502168655,
|
|
"num_tokens": 30479428.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.526005125045776,
|
|
"epoch": 1.5347335317571742,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047740940434935677,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.20874049216508866,
|
|
"num_tokens": 30490193.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.522428846359253,
|
|
"epoch": 1.5352951086651316,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004773918673672356,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.20612497478723527,
|
|
"num_tokens": 30500311.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.3809489727020265,
|
|
"epoch": 1.5358566855730893,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047737432394087887,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.21350422352552414,
|
|
"num_tokens": 30512485.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.45035457611084,
|
|
"epoch": 1.5364182624810467,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047735677407084525,
|
|
"loss": 5.0719,
|
|
"mean_token_accuracy": 0.20744231790304185,
|
|
"num_tokens": 30523495.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.458536672592163,
|
|
"epoch": 1.5369798393890042,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004773392177576934,
|
|
"loss": 5.1258,
|
|
"mean_token_accuracy": 0.20961540043354035,
|
|
"num_tokens": 30533964.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.402696990966797,
|
|
"epoch": 1.5375414162969618,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004773216550019824,
|
|
"loss": 5.0133,
|
|
"mean_token_accuracy": 0.21492202281951905,
|
|
"num_tokens": 30544798.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.47240047454834,
|
|
"epoch": 1.5381029932049195,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047730408580427136,
|
|
"loss": 5.2052,
|
|
"mean_token_accuracy": 0.19995270669460297,
|
|
"num_tokens": 30555991.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.499682283401489,
|
|
"epoch": 1.538664570112877,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047728651016511994,
|
|
"loss": 5.0546,
|
|
"mean_token_accuracy": 0.21119318455457686,
|
|
"num_tokens": 30566848.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.491256618499756,
|
|
"epoch": 1.5392261470208344,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047726892808508744,
|
|
"loss": 5.07,
|
|
"mean_token_accuracy": 0.21484928727149963,
|
|
"num_tokens": 30577361.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.452073669433593,
|
|
"epoch": 1.539787723928792,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004772513395647339,
|
|
"loss": 5.1236,
|
|
"mean_token_accuracy": 0.20703460276126862,
|
|
"num_tokens": 30587685.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.447957944869995,
|
|
"epoch": 1.5403493008367497,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004772337446046192,
|
|
"loss": 5.1631,
|
|
"mean_token_accuracy": 0.20866415947675704,
|
|
"num_tokens": 30599864.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.489260244369507,
|
|
"epoch": 1.5409108777447071,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047721614320530366,
|
|
"loss": 5.1403,
|
|
"mean_token_accuracy": 0.20871280878782272,
|
|
"num_tokens": 30610885.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.468125247955323,
|
|
"epoch": 1.5414724546526646,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047719853536734764,
|
|
"loss": 5.1157,
|
|
"mean_token_accuracy": 0.203450009226799,
|
|
"num_tokens": 30622537.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.542632532119751,
|
|
"epoch": 1.5420340315606222,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004771809210913119,
|
|
"loss": 5.253,
|
|
"mean_token_accuracy": 0.19639279693365097,
|
|
"num_tokens": 30635045.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.470077896118164,
|
|
"epoch": 1.54259560846858,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047716330037775724,
|
|
"loss": 5.0929,
|
|
"mean_token_accuracy": 0.19972793608903885,
|
|
"num_tokens": 30645998.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.455017995834351,
|
|
"epoch": 1.5431571853765373,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004771456732272446,
|
|
"loss": 5.137,
|
|
"mean_token_accuracy": 0.20381448417901993,
|
|
"num_tokens": 30658744.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.393810892105103,
|
|
"epoch": 1.5437187622844948,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047712803964033545,
|
|
"loss": 5.0143,
|
|
"mean_token_accuracy": 0.21443181931972505,
|
|
"num_tokens": 30669420.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.391561222076416,
|
|
"epoch": 1.5442803391924524,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047711039961759107,
|
|
"loss": 5.0946,
|
|
"mean_token_accuracy": 0.2059645727276802,
|
|
"num_tokens": 30680037.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.534412050247193,
|
|
"epoch": 1.54484191610041,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004770927531595731,
|
|
"loss": 5.1367,
|
|
"mean_token_accuracy": 0.21158429682254792,
|
|
"num_tokens": 30691650.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.451357793807984,
|
|
"epoch": 1.5454034930083675,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047707510026684353,
|
|
"loss": 5.1424,
|
|
"mean_token_accuracy": 0.20709216445684434,
|
|
"num_tokens": 30701876.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.616465425491333,
|
|
"epoch": 1.545965069916325,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047705744093996447,
|
|
"loss": 5.3349,
|
|
"mean_token_accuracy": 0.20009353905916213,
|
|
"num_tokens": 30714484.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.50636305809021,
|
|
"epoch": 1.5465266468242826,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000477039775179498,
|
|
"loss": 5.1581,
|
|
"mean_token_accuracy": 0.2003595307469368,
|
|
"num_tokens": 30725185.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.472897386550903,
|
|
"epoch": 1.54708822373224,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047702210298600684,
|
|
"loss": 5.1346,
|
|
"mean_token_accuracy": 0.2099891945719719,
|
|
"num_tokens": 30735522.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.4250202655792235,
|
|
"epoch": 1.5476498006401975,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047700442436005356,
|
|
"loss": 5.1414,
|
|
"mean_token_accuracy": 0.21014324426651002,
|
|
"num_tokens": 30746353.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.479766178131103,
|
|
"epoch": 1.5482113775481552,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000476986739302201,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.20711538791656495,
|
|
"num_tokens": 30756245.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.510843181610108,
|
|
"epoch": 1.5487729544561128,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047696904781301233,
|
|
"loss": 5.2278,
|
|
"mean_token_accuracy": 0.20635064989328383,
|
|
"num_tokens": 30767387.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.470912456512451,
|
|
"epoch": 1.5493345313640703,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004769513498930508,
|
|
"loss": 5.1819,
|
|
"mean_token_accuracy": 0.21047525703907013,
|
|
"num_tokens": 30780140.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.483899545669556,
|
|
"epoch": 1.5498961082720277,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047693364554288,
|
|
"loss": 5.0921,
|
|
"mean_token_accuracy": 0.21013399809598923,
|
|
"num_tokens": 30791137.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.4625725746154785,
|
|
"epoch": 1.5504576851799854,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047691593476306373,
|
|
"loss": 5.0913,
|
|
"mean_token_accuracy": 0.2136094644665718,
|
|
"num_tokens": 30801708.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.513564729690552,
|
|
"epoch": 1.551019262087943,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004768982175541656,
|
|
"loss": 5.1699,
|
|
"mean_token_accuracy": 0.204835344851017,
|
|
"num_tokens": 30813519.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.532550096511841,
|
|
"epoch": 1.5515808389959005,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047688049391675006,
|
|
"loss": 5.2338,
|
|
"mean_token_accuracy": 0.20518066585063935,
|
|
"num_tokens": 30823786.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.473483276367188,
|
|
"epoch": 1.552142415903858,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004768627638513813,
|
|
"loss": 5.1036,
|
|
"mean_token_accuracy": 0.21366893500089645,
|
|
"num_tokens": 30834381.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.475982522964477,
|
|
"epoch": 1.5527039928118156,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004768450273586237,
|
|
"loss": 5.1069,
|
|
"mean_token_accuracy": 0.2051657423377037,
|
|
"num_tokens": 30844865.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.5269266128540036,
|
|
"epoch": 1.5532655697197733,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047682728443904223,
|
|
"loss": 5.1935,
|
|
"mean_token_accuracy": 0.20764564573764802,
|
|
"num_tokens": 30857088.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.444524192810059,
|
|
"epoch": 1.5538271466277307,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047680953509320176,
|
|
"loss": 5.2268,
|
|
"mean_token_accuracy": 0.19674571305513383,
|
|
"num_tokens": 30868320.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.4890465259552,
|
|
"epoch": 1.5543887235356881,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004767917793216674,
|
|
"loss": 5.1303,
|
|
"mean_token_accuracy": 0.20868585258722305,
|
|
"num_tokens": 30878598.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.474894428253174,
|
|
"epoch": 1.5549503004436458,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047677401712500455,
|
|
"loss": 5.0653,
|
|
"mean_token_accuracy": 0.20976149886846543,
|
|
"num_tokens": 30889254.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.519720125198364,
|
|
"epoch": 1.5555118773516035,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004767562485037787,
|
|
"loss": 5.2016,
|
|
"mean_token_accuracy": 0.20380555242300033,
|
|
"num_tokens": 30901164.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.4564048767089846,
|
|
"epoch": 1.556073454259561,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047673847345855566,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.20823153853416443,
|
|
"num_tokens": 30911828.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.472623825073242,
|
|
"epoch": 1.5566350311675183,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004767206919899014,
|
|
"loss": 4.971,
|
|
"mean_token_accuracy": 0.2212482586503029,
|
|
"num_tokens": 30922050.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.39045820236206,
|
|
"epoch": 1.557196608075476,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000476702904098382,
|
|
"loss": 5.0427,
|
|
"mean_token_accuracy": 0.21153525561094283,
|
|
"num_tokens": 30932723.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.401630115509033,
|
|
"epoch": 1.5577581849834334,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000476685109784564,
|
|
"loss": 5.0649,
|
|
"mean_token_accuracy": 0.21431580632925035,
|
|
"num_tokens": 30943699.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.478217077255249,
|
|
"epoch": 1.5583197618913909,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047666730904901377,
|
|
"loss": 5.1425,
|
|
"mean_token_accuracy": 0.20613633692264557,
|
|
"num_tokens": 30954315.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.556294202804565,
|
|
"epoch": 1.5588813387993485,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047664950189229833,
|
|
"loss": 5.307,
|
|
"mean_token_accuracy": 0.20023447126150132,
|
|
"num_tokens": 30965840.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.567817831039429,
|
|
"epoch": 1.5594429157073062,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004766316883149845,
|
|
"loss": 5.2152,
|
|
"mean_token_accuracy": 0.20502734780311585,
|
|
"num_tokens": 30977051.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.43372950553894,
|
|
"epoch": 1.5600044926152636,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047661386831763955,
|
|
"loss": 5.0772,
|
|
"mean_token_accuracy": 0.20623415857553482,
|
|
"num_tokens": 30988730.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.4321348667144775,
|
|
"epoch": 1.560566069523221,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00047659604190083076,
|
|
"loss": 5.0807,
|
|
"mean_token_accuracy": 0.21048348546028137,
|
|
"num_tokens": 31000571.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.4009092330932615,
|
|
"epoch": 1.5611276464311787,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047657820906512585,
|
|
"loss": 5.1008,
|
|
"mean_token_accuracy": 0.21363420635461808,
|
|
"num_tokens": 31011003.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.512424945831299,
|
|
"epoch": 1.5616892233391364,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047656036981109256,
|
|
"loss": 5.1044,
|
|
"mean_token_accuracy": 0.2100786566734314,
|
|
"num_tokens": 31022510.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.541799592971802,
|
|
"epoch": 1.5622508002470938,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047654252413929896,
|
|
"loss": 5.1504,
|
|
"mean_token_accuracy": 0.20794539600610734,
|
|
"num_tokens": 31033149.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.52243390083313,
|
|
"epoch": 1.5628123771550513,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047652467205031317,
|
|
"loss": 5.2056,
|
|
"mean_token_accuracy": 0.2090357467532158,
|
|
"num_tokens": 31043626.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.539959287643432,
|
|
"epoch": 1.563373954063009,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047650681354470363,
|
|
"loss": 5.2478,
|
|
"mean_token_accuracy": 0.2010113626718521,
|
|
"num_tokens": 31055083.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.461220693588257,
|
|
"epoch": 1.5639355309709666,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047648894862303907,
|
|
"loss": 5.0798,
|
|
"mean_token_accuracy": 0.20491784065961838,
|
|
"num_tokens": 31066763.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.473897457122803,
|
|
"epoch": 1.564497107878924,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047647107728588826,
|
|
"loss": 5.1596,
|
|
"mean_token_accuracy": 0.20189221799373627,
|
|
"num_tokens": 31078722.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.517248916625976,
|
|
"epoch": 1.5650586847868815,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047645319953382024,
|
|
"loss": 5.1976,
|
|
"mean_token_accuracy": 0.20537666529417037,
|
|
"num_tokens": 31090207.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.496640539169311,
|
|
"epoch": 1.5656202616948391,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047643531536740405,
|
|
"loss": 5.2245,
|
|
"mean_token_accuracy": 0.2039627730846405,
|
|
"num_tokens": 31101943.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.481431484222412,
|
|
"epoch": 1.5661818386027968,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004764174247872094,
|
|
"loss": 5.2176,
|
|
"mean_token_accuracy": 0.1974351242184639,
|
|
"num_tokens": 31115032.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.553815650939941,
|
|
"epoch": 1.5667434155107542,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047639952779380586,
|
|
"loss": 5.1286,
|
|
"mean_token_accuracy": 0.20633062720298767,
|
|
"num_tokens": 31124965.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.527206802368164,
|
|
"epoch": 1.5673049924187117,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004763816243877632,
|
|
"loss": 5.1571,
|
|
"mean_token_accuracy": 0.20625796616077424,
|
|
"num_tokens": 31136692.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.490589666366577,
|
|
"epoch": 1.5678665693266693,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004763637145696515,
|
|
"loss": 5.11,
|
|
"mean_token_accuracy": 0.20351085513830186,
|
|
"num_tokens": 31148352.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.433886909484864,
|
|
"epoch": 1.5684281462346268,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000476345798340041,
|
|
"loss": 5.0933,
|
|
"mean_token_accuracy": 0.20816990435123445,
|
|
"num_tokens": 31159892.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.5542994976043705,
|
|
"epoch": 1.5689897231425842,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004763278756995022,
|
|
"loss": 5.2357,
|
|
"mean_token_accuracy": 0.20216581970453262,
|
|
"num_tokens": 31170087.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.358810758590698,
|
|
"epoch": 1.5695513000505419,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047630994664860576,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.2090377017855644,
|
|
"num_tokens": 31180687.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.513645839691162,
|
|
"epoch": 1.5701128769584995,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004762920111879226,
|
|
"loss": 5.2213,
|
|
"mean_token_accuracy": 0.20003449618816377,
|
|
"num_tokens": 31192513.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.50188980102539,
|
|
"epoch": 1.570674453866457,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004762740693180237,
|
|
"loss": 5.1193,
|
|
"mean_token_accuracy": 0.2016259953379631,
|
|
"num_tokens": 31203432.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.546356630325318,
|
|
"epoch": 1.5712360307744144,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00047625612103948035,
|
|
"loss": 5.0958,
|
|
"mean_token_accuracy": 0.2152412474155426,
|
|
"num_tokens": 31214474.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.491615152359008,
|
|
"epoch": 1.571797607682372,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004762381663528641,
|
|
"loss": 5.1592,
|
|
"mean_token_accuracy": 0.19755446761846543,
|
|
"num_tokens": 31226489.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.383515691757202,
|
|
"epoch": 1.5723591845903298,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004762202052587466,
|
|
"loss": 5.0385,
|
|
"mean_token_accuracy": 0.20448143184185028,
|
|
"num_tokens": 31237568.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.45446081161499,
|
|
"epoch": 1.5729207614982872,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004762022377576996,
|
|
"loss": 5.0432,
|
|
"mean_token_accuracy": 0.2189904808998108,
|
|
"num_tokens": 31248587.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.511194324493408,
|
|
"epoch": 1.5734823384062446,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004761842638502954,
|
|
"loss": 5.177,
|
|
"mean_token_accuracy": 0.1997183457016945,
|
|
"num_tokens": 31259513.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.502513027191162,
|
|
"epoch": 1.5740439153142023,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004761662835371062,
|
|
"loss": 5.1678,
|
|
"mean_token_accuracy": 0.20309208929538727,
|
|
"num_tokens": 31270984.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.439129066467285,
|
|
"epoch": 1.57460549222216,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004761482968187045,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.20797574520111084,
|
|
"num_tokens": 31281907.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.403236055374146,
|
|
"epoch": 1.5751670691301174,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004761303036956631,
|
|
"loss": 5.1326,
|
|
"mean_token_accuracy": 0.2057667925953865,
|
|
"num_tokens": 31292903.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.526501417160034,
|
|
"epoch": 1.5757286460380748,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004761123041685547,
|
|
"loss": 5.1396,
|
|
"mean_token_accuracy": 0.2085891082882881,
|
|
"num_tokens": 31304185.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.473230457305908,
|
|
"epoch": 1.5762902229460325,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004760942982379526,
|
|
"loss": 5.1417,
|
|
"mean_token_accuracy": 0.20867830067873,
|
|
"num_tokens": 31314806.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.431953430175781,
|
|
"epoch": 1.5768517998539902,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047607628590443004,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.20455605983734132,
|
|
"num_tokens": 31326361.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.557656908035279,
|
|
"epoch": 1.5774133767619476,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047605826716856056,
|
|
"loss": 5.141,
|
|
"mean_token_accuracy": 0.20891171991825103,
|
|
"num_tokens": 31336549.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.586280488967896,
|
|
"epoch": 1.577974953669905,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004760402420309178,
|
|
"loss": 5.2496,
|
|
"mean_token_accuracy": 0.20191466957330703,
|
|
"num_tokens": 31346994.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.502039051055908,
|
|
"epoch": 1.5785365305778627,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004760222104920759,
|
|
"loss": 5.1502,
|
|
"mean_token_accuracy": 0.20491855293512345,
|
|
"num_tokens": 31358449.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.539928007125854,
|
|
"epoch": 1.5790981074858201,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004760041725526088,
|
|
"loss": 5.1835,
|
|
"mean_token_accuracy": 0.20377593040466307,
|
|
"num_tokens": 31368964.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.522278738021851,
|
|
"epoch": 1.5796596843937776,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047598612821309077,
|
|
"loss": 5.119,
|
|
"mean_token_accuracy": 0.20832561254501342,
|
|
"num_tokens": 31379388.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.444357109069824,
|
|
"epoch": 1.5802212613017352,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004759680774740966,
|
|
"loss": 5.1753,
|
|
"mean_token_accuracy": 0.2067069321870804,
|
|
"num_tokens": 31390757.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.436584568023681,
|
|
"epoch": 1.580782838209693,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004759500203362008,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.20713399946689606,
|
|
"num_tokens": 31402309.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.53011794090271,
|
|
"epoch": 1.5813444151176503,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004759319567999785,
|
|
"loss": 5.1291,
|
|
"mean_token_accuracy": 0.2070261210203171,
|
|
"num_tokens": 31412559.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.49569354057312,
|
|
"epoch": 1.5819059920256078,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004759138868660048,
|
|
"loss": 5.2658,
|
|
"mean_token_accuracy": 0.19862870872020721,
|
|
"num_tokens": 31424982.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.440700101852417,
|
|
"epoch": 1.5824675689335654,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047589581053485494,
|
|
"loss": 5.0118,
|
|
"mean_token_accuracy": 0.20904837250709535,
|
|
"num_tokens": 31434472.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.514515829086304,
|
|
"epoch": 1.583029145841523,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047587772780710455,
|
|
"loss": 5.2239,
|
|
"mean_token_accuracy": 0.20741783380508422,
|
|
"num_tokens": 31445458.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.476921319961548,
|
|
"epoch": 1.5835907227494805,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047585963868332945,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.2124158337712288,
|
|
"num_tokens": 31455851.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.396849822998047,
|
|
"epoch": 1.584152299657438,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004758415431641055,
|
|
"loss": 5.0794,
|
|
"mean_token_accuracy": 0.20829991549253463,
|
|
"num_tokens": 31466279.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.529507398605347,
|
|
"epoch": 1.5847138765653956,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004758234412500089,
|
|
"loss": 5.1302,
|
|
"mean_token_accuracy": 0.21033648997545243,
|
|
"num_tokens": 31477933.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.535827016830444,
|
|
"epoch": 1.5852754534733533,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047580533294161616,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.1991063192486763,
|
|
"num_tokens": 31487640.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.569490623474121,
|
|
"epoch": 1.5858370303813107,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004757872182395036,
|
|
"loss": 5.1151,
|
|
"mean_token_accuracy": 0.21425263881683348,
|
|
"num_tokens": 31499059.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.525071239471435,
|
|
"epoch": 1.5863986072892682,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047576909714424823,
|
|
"loss": 5.1426,
|
|
"mean_token_accuracy": 0.20575840026140213,
|
|
"num_tokens": 31510264.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.459005546569824,
|
|
"epoch": 1.5869601841972258,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047575096965642687,
|
|
"loss": 5.1201,
|
|
"mean_token_accuracy": 0.20768028646707534,
|
|
"num_tokens": 31520873.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.450346946716309,
|
|
"epoch": 1.5875217611051835,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00047573283577661684,
|
|
"loss": 5.1503,
|
|
"mean_token_accuracy": 0.20521388202905655,
|
|
"num_tokens": 31533836.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.463673448562622,
|
|
"epoch": 1.588083338013141,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004757146955053955,
|
|
"loss": 5.1787,
|
|
"mean_token_accuracy": 0.20482372343540192,
|
|
"num_tokens": 31545091.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.491623497009277,
|
|
"epoch": 1.5886449149210984,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047569654884334036,
|
|
"loss": 5.0506,
|
|
"mean_token_accuracy": 0.2070576786994934,
|
|
"num_tokens": 31557139.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.522586679458618,
|
|
"epoch": 1.589206491829056,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004756783957910292,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.20851533263921737,
|
|
"num_tokens": 31567928.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.428273630142212,
|
|
"epoch": 1.5897680687370135,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047566023634904015,
|
|
"loss": 5.1455,
|
|
"mean_token_accuracy": 0.20564700663089752,
|
|
"num_tokens": 31578081.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.421238803863526,
|
|
"epoch": 1.590329645644971,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004756420705179513,
|
|
"loss": 5.062,
|
|
"mean_token_accuracy": 0.20919679403305053,
|
|
"num_tokens": 31589648.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.480953645706177,
|
|
"epoch": 1.5908912225529286,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004756238982983412,
|
|
"loss": 5.1463,
|
|
"mean_token_accuracy": 0.203220696747303,
|
|
"num_tokens": 31601085.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.486854982376099,
|
|
"epoch": 1.5914527994608862,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004756057196907883,
|
|
"loss": 5.201,
|
|
"mean_token_accuracy": 0.20855775177478791,
|
|
"num_tokens": 31612005.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.491432428359985,
|
|
"epoch": 1.5920143763688437,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00047558753469587154,
|
|
"loss": 5.151,
|
|
"mean_token_accuracy": 0.20160801112651824,
|
|
"num_tokens": 31623427.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.632724189758301,
|
|
"epoch": 1.5925759532768011,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047556934331416986,
|
|
"loss": 5.3044,
|
|
"mean_token_accuracy": 0.1924811854958534,
|
|
"num_tokens": 31635086.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.565679883956909,
|
|
"epoch": 1.5931375301847588,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004755511455462624,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.20850237756967543,
|
|
"num_tokens": 31646707.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.409745359420777,
|
|
"epoch": 1.5936991070927164,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004755329413927287,
|
|
"loss": 5.0163,
|
|
"mean_token_accuracy": 0.21165819168090821,
|
|
"num_tokens": 31657327.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.461916923522949,
|
|
"epoch": 1.5942606840006739,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004755147308541485,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.20918234586715698,
|
|
"num_tokens": 31668075.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.511706829071045,
|
|
"epoch": 1.5948222609086313,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00047549651393110145,
|
|
"loss": 5.1757,
|
|
"mean_token_accuracy": 0.19853594303131103,
|
|
"num_tokens": 31680270.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.413037061691284,
|
|
"epoch": 1.595383837816589,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047547829062416757,
|
|
"loss": 5.0345,
|
|
"mean_token_accuracy": 0.21229496747255325,
|
|
"num_tokens": 31691271.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.405726146697998,
|
|
"epoch": 1.5959454147245467,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047546006093392726,
|
|
"loss": 5.0354,
|
|
"mean_token_accuracy": 0.2144663840532303,
|
|
"num_tokens": 31702982.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.468664169311523,
|
|
"epoch": 1.596506991632504,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004754418248609608,
|
|
"loss": 5.1565,
|
|
"mean_token_accuracy": 0.2058590829372406,
|
|
"num_tokens": 31715129.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.534321737289429,
|
|
"epoch": 1.5970685685404615,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004754235824058489,
|
|
"loss": 5.2237,
|
|
"mean_token_accuracy": 0.20576290041208267,
|
|
"num_tokens": 31726392.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.548418998718262,
|
|
"epoch": 1.5976301454484192,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004754053335691724,
|
|
"loss": 5.1866,
|
|
"mean_token_accuracy": 0.2114136591553688,
|
|
"num_tokens": 31738143.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.521101713180542,
|
|
"epoch": 1.5981917223563769,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047538707835151237,
|
|
"loss": 5.1495,
|
|
"mean_token_accuracy": 0.20609493404626847,
|
|
"num_tokens": 31748510.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.372695684432983,
|
|
"epoch": 1.5987532992643343,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047536881675345,
|
|
"loss": 5.033,
|
|
"mean_token_accuracy": 0.21007345020771026,
|
|
"num_tokens": 31759378.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.586735010147095,
|
|
"epoch": 1.5993148761722917,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004753505487755669,
|
|
"loss": 5.2702,
|
|
"mean_token_accuracy": 0.19648339450359345,
|
|
"num_tokens": 31771627.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.464278268814087,
|
|
"epoch": 1.5998764530802494,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047533227441844453,
|
|
"loss": 5.0696,
|
|
"mean_token_accuracy": 0.2142323836684227,
|
|
"num_tokens": 31781990.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.4982294082641605,
|
|
"epoch": 1.6004380299882068,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047531399368266485,
|
|
"loss": 5.1313,
|
|
"mean_token_accuracy": 0.2076670154929161,
|
|
"num_tokens": 31792144.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.515278148651123,
|
|
"epoch": 1.6009996068961643,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004752957065688099,
|
|
"loss": 5.1827,
|
|
"mean_token_accuracy": 0.20987604707479476,
|
|
"num_tokens": 31804022.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.555851173400879,
|
|
"epoch": 1.601561183804122,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000475277413077462,
|
|
"loss": 5.2049,
|
|
"mean_token_accuracy": 0.20333612263202666,
|
|
"num_tokens": 31815108.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.429860401153564,
|
|
"epoch": 1.6021227607120796,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047525911320920363,
|
|
"loss": 5.1719,
|
|
"mean_token_accuracy": 0.20856576412916183,
|
|
"num_tokens": 31825727.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.461634683609009,
|
|
"epoch": 1.602684337620037,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004752408069646174,
|
|
"loss": 5.1202,
|
|
"mean_token_accuracy": 0.21572770327329635,
|
|
"num_tokens": 31836168.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.564251327514649,
|
|
"epoch": 1.6032459145279945,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047522249434428623,
|
|
"loss": 5.2198,
|
|
"mean_token_accuracy": 0.2012143164873123,
|
|
"num_tokens": 31847383.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.437561988830566,
|
|
"epoch": 1.6038074914359521,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004752041753487931,
|
|
"loss": 5.0445,
|
|
"mean_token_accuracy": 0.2169059172272682,
|
|
"num_tokens": 31858679.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.471265840530395,
|
|
"epoch": 1.6043690683439098,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004751858499787215,
|
|
"loss": 5.125,
|
|
"mean_token_accuracy": 0.21637834310531617,
|
|
"num_tokens": 31870195.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.55965633392334,
|
|
"epoch": 1.6049306452518672,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004751675182346547,
|
|
"loss": 5.1501,
|
|
"mean_token_accuracy": 0.20644088089466095,
|
|
"num_tokens": 31881175.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.449311542510986,
|
|
"epoch": 1.6054922221598247,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047514918011717656,
|
|
"loss": 5.0828,
|
|
"mean_token_accuracy": 0.21454456746578215,
|
|
"num_tokens": 31891199.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.5836633205413815,
|
|
"epoch": 1.6060537990677823,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047513083562687085,
|
|
"loss": 5.2539,
|
|
"mean_token_accuracy": 0.19913967102766036,
|
|
"num_tokens": 31903379.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.524294042587281,
|
|
"epoch": 1.60661537597574,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004751124847643217,
|
|
"loss": 5.0143,
|
|
"mean_token_accuracy": 0.22051845937967302,
|
|
"num_tokens": 31913958.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.398765325546265,
|
|
"epoch": 1.6071769528836974,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004750941275301135,
|
|
"loss": 5.024,
|
|
"mean_token_accuracy": 0.21078978329896927,
|
|
"num_tokens": 31924547.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.536068439483643,
|
|
"epoch": 1.6077385297916549,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004750757639248306,
|
|
"loss": 5.2457,
|
|
"mean_token_accuracy": 0.20039306133985518,
|
|
"num_tokens": 31936987.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.473997306823731,
|
|
"epoch": 1.6083001066996125,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047505739394905776,
|
|
"loss": 5.1007,
|
|
"mean_token_accuracy": 0.2050543561577797,
|
|
"num_tokens": 31948165.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.52739839553833,
|
|
"epoch": 1.6088616836075702,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047503901760338003,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.20757828950881957,
|
|
"num_tokens": 31959206.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.507641983032227,
|
|
"epoch": 1.6094232605155276,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047502063488838225,
|
|
"loss": 5.1394,
|
|
"mean_token_accuracy": 0.20667380094528198,
|
|
"num_tokens": 31970804.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.43414273262024,
|
|
"epoch": 1.609984837423485,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00047500224580464994,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.20945317447185516,
|
|
"num_tokens": 31982961.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.493216896057129,
|
|
"epoch": 1.6105464143314427,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00047498385035276856,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.20586385130882262,
|
|
"num_tokens": 31993812.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.494396209716797,
|
|
"epoch": 1.6111079912394002,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004749654485333238,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.20913249552249907,
|
|
"num_tokens": 32004688.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.4740653991699215,
|
|
"epoch": 1.6116695681473576,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047494704034690163,
|
|
"loss": 5.0515,
|
|
"mean_token_accuracy": 0.20601202696561813,
|
|
"num_tokens": 32014653.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.444654703140259,
|
|
"epoch": 1.6122311450553153,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047492862579408816,
|
|
"loss": 5.1168,
|
|
"mean_token_accuracy": 0.2042867660522461,
|
|
"num_tokens": 32025638.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.356553554534912,
|
|
"epoch": 1.612792721963273,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047491020487546966,
|
|
"loss": 5.0363,
|
|
"mean_token_accuracy": 0.2104514479637146,
|
|
"num_tokens": 32036316.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.453169488906861,
|
|
"epoch": 1.6133542988712304,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004748917775916327,
|
|
"loss": 5.0571,
|
|
"mean_token_accuracy": 0.21129222810268403,
|
|
"num_tokens": 32047355.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.488507652282715,
|
|
"epoch": 1.6139158757791878,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047487334394316405,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.19742818176746368,
|
|
"num_tokens": 32058897.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.5156721591949465,
|
|
"epoch": 1.6144774526871455,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004748549039306506,
|
|
"loss": 5.1539,
|
|
"mean_token_accuracy": 0.2039370894432068,
|
|
"num_tokens": 32069932.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.47552490234375,
|
|
"epoch": 1.6150390295951031,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004748364575546795,
|
|
"loss": 5.0533,
|
|
"mean_token_accuracy": 0.2112406700849533,
|
|
"num_tokens": 32081359.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.414346408843994,
|
|
"epoch": 1.6156006065030606,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047481800481583806,
|
|
"loss": 5.0265,
|
|
"mean_token_accuracy": 0.20902552604675292,
|
|
"num_tokens": 32093050.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.539455127716065,
|
|
"epoch": 1.616162183411018,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004747995457147139,
|
|
"loss": 5.1766,
|
|
"mean_token_accuracy": 0.2029839888215065,
|
|
"num_tokens": 32104623.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.440048742294311,
|
|
"epoch": 1.6167237603189757,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047478108025189467,
|
|
"loss": 5.1205,
|
|
"mean_token_accuracy": 0.19632880985736847,
|
|
"num_tokens": 32115845.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.460477352142334,
|
|
"epoch": 1.6172853372269334,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00047476260842796837,
|
|
"loss": 5.084,
|
|
"mean_token_accuracy": 0.20479002594947815,
|
|
"num_tokens": 32127066.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.519058799743652,
|
|
"epoch": 1.6178469141348908,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004747441302435231,
|
|
"loss": 5.2198,
|
|
"mean_token_accuracy": 0.201866115629673,
|
|
"num_tokens": 32138344.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.5276977062225345,
|
|
"epoch": 1.6184084910428482,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047472564569914726,
|
|
"loss": 5.1703,
|
|
"mean_token_accuracy": 0.198178967833519,
|
|
"num_tokens": 32149054.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.483215618133545,
|
|
"epoch": 1.618970067950806,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047470715479542945,
|
|
"loss": 5.0635,
|
|
"mean_token_accuracy": 0.20180138796567917,
|
|
"num_tokens": 32160385.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.532918262481689,
|
|
"epoch": 1.6195316448587636,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004746886575329584,
|
|
"loss": 5.2201,
|
|
"mean_token_accuracy": 0.20075257271528243,
|
|
"num_tokens": 32171856.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.467215824127197,
|
|
"epoch": 1.620093221766721,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00047467015391232305,
|
|
"loss": 5.1475,
|
|
"mean_token_accuracy": 0.20465515404939652,
|
|
"num_tokens": 32182690.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.472300720214844,
|
|
"epoch": 1.6206547986746784,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00047465164393411245,
|
|
"loss": 5.1158,
|
|
"mean_token_accuracy": 0.20631269216537476,
|
|
"num_tokens": 32194045.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.468170261383056,
|
|
"epoch": 1.621216375582636,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047463312759891615,
|
|
"loss": 5.187,
|
|
"mean_token_accuracy": 0.19822951257228852,
|
|
"num_tokens": 32205699.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.553538513183594,
|
|
"epoch": 1.6217779524905935,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004746146049073236,
|
|
"loss": 5.1583,
|
|
"mean_token_accuracy": 0.20397819727659225,
|
|
"num_tokens": 32217974.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.385631847381592,
|
|
"epoch": 1.622339529398551,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047459607585992466,
|
|
"loss": 5.0711,
|
|
"mean_token_accuracy": 0.20507001280784606,
|
|
"num_tokens": 32228723.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.47898588180542,
|
|
"epoch": 1.6229011063065086,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00047457754045730923,
|
|
"loss": 5.2204,
|
|
"mean_token_accuracy": 0.20475900620222093,
|
|
"num_tokens": 32241048.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.438021421432495,
|
|
"epoch": 1.6234626832144663,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047455899870006745,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.21227079778909683,
|
|
"num_tokens": 32251255.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.448459005355835,
|
|
"epoch": 1.6240242601224237,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004745404505887899,
|
|
"loss": 5.1182,
|
|
"mean_token_accuracy": 0.20899780392646788,
|
|
"num_tokens": 32262954.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.468794298171997,
|
|
"epoch": 1.6245858370303812,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004745218961240669,
|
|
"loss": 5.1327,
|
|
"mean_token_accuracy": 0.20763630270957947,
|
|
"num_tokens": 32275445.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.528776502609253,
|
|
"epoch": 1.6251474139383388,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004745033353064893,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.2092886745929718,
|
|
"num_tokens": 32285976.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.417572832107544,
|
|
"epoch": 1.6257089908462965,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004744847681366482,
|
|
"loss": 5.059,
|
|
"mean_token_accuracy": 0.21153971701860427,
|
|
"num_tokens": 32296304.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.433072662353515,
|
|
"epoch": 1.626270567754254,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047446619461513466,
|
|
"loss": 5.11,
|
|
"mean_token_accuracy": 0.21218177825212478,
|
|
"num_tokens": 32307085.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.4493917465209964,
|
|
"epoch": 1.6268321446622114,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004744476147425402,
|
|
"loss": 5.0408,
|
|
"mean_token_accuracy": 0.22019558101892472,
|
|
"num_tokens": 32316814.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.452572202682495,
|
|
"epoch": 1.627393721570169,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047442902851945634,
|
|
"loss": 5.1103,
|
|
"mean_token_accuracy": 0.20507177859544753,
|
|
"num_tokens": 32327820.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.57509217262268,
|
|
"epoch": 1.6279552984781267,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047441043594647486,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.2107645094394684,
|
|
"num_tokens": 32338185.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.426065397262573,
|
|
"epoch": 1.6285168753860841,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047439183702418765,
|
|
"loss": 5.0307,
|
|
"mean_token_accuracy": 0.21276569366455078,
|
|
"num_tokens": 32348537.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.456048107147216,
|
|
"epoch": 1.6290784522940416,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047437323175318716,
|
|
"loss": 5.1686,
|
|
"mean_token_accuracy": 0.2014290764927864,
|
|
"num_tokens": 32359094.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.381970405578613,
|
|
"epoch": 1.6296400292019992,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047435462013406554,
|
|
"loss": 4.988,
|
|
"mean_token_accuracy": 0.2203885406255722,
|
|
"num_tokens": 32370811.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.5212396621704105,
|
|
"epoch": 1.630201606109957,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004743360021674155,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.20606162399053574,
|
|
"num_tokens": 32381522.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.4549699306488035,
|
|
"epoch": 1.6307631830179143,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047431737785382996,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.20090150386095046,
|
|
"num_tokens": 32393221.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.518042850494385,
|
|
"epoch": 1.6313247599258718,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047429874719390165,
|
|
"loss": 5.1159,
|
|
"mean_token_accuracy": 0.19962020516395568,
|
|
"num_tokens": 32404007.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.523869371414184,
|
|
"epoch": 1.6318863368338294,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047428011018822404,
|
|
"loss": 5.2026,
|
|
"mean_token_accuracy": 0.20119993686676024,
|
|
"num_tokens": 32414318.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.4379371166229244,
|
|
"epoch": 1.6324479137417869,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047426146683739043,
|
|
"loss": 5.1242,
|
|
"mean_token_accuracy": 0.21090569943189622,
|
|
"num_tokens": 32425493.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.446884393692017,
|
|
"epoch": 1.6330094906497443,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047424281714199436,
|
|
"loss": 5.1036,
|
|
"mean_token_accuracy": 0.20999828428030015,
|
|
"num_tokens": 32435765.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.5830206871032715,
|
|
"epoch": 1.633571067557702,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047422416110262975,
|
|
"loss": 5.1719,
|
|
"mean_token_accuracy": 0.2110847383737564,
|
|
"num_tokens": 32446478.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.459376525878906,
|
|
"epoch": 1.6341326444656596,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047420549871989053,
|
|
"loss": 5.1765,
|
|
"mean_token_accuracy": 0.20551348179578782,
|
|
"num_tokens": 32456866.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.509270286560058,
|
|
"epoch": 1.634694221373617,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000474186829994371,
|
|
"loss": 5.0617,
|
|
"mean_token_accuracy": 0.21828665137290953,
|
|
"num_tokens": 32466973.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.561855888366699,
|
|
"epoch": 1.6352557982815745,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047416815492666564,
|
|
"loss": 5.2379,
|
|
"mean_token_accuracy": 0.1974301591515541,
|
|
"num_tokens": 32478118.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.433518648147583,
|
|
"epoch": 1.6358173751895322,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004741494735173689,
|
|
"loss": 5.0364,
|
|
"mean_token_accuracy": 0.21908658593893052,
|
|
"num_tokens": 32488255.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.518524789810181,
|
|
"epoch": 1.6363789520974898,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004741307857670757,
|
|
"loss": 5.1333,
|
|
"mean_token_accuracy": 0.20911531299352645,
|
|
"num_tokens": 32498685.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.505541801452637,
|
|
"epoch": 1.6369405290054473,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00047411209167638106,
|
|
"loss": 5.1465,
|
|
"mean_token_accuracy": 0.20214727371931077,
|
|
"num_tokens": 32510457.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.4434216022491455,
|
|
"epoch": 1.6375021059134047,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004740933912458801,
|
|
"loss": 5.1087,
|
|
"mean_token_accuracy": 0.20837015956640242,
|
|
"num_tokens": 32522495.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.575459003448486,
|
|
"epoch": 1.6380636828213624,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047407468447616845,
|
|
"loss": 5.2001,
|
|
"mean_token_accuracy": 0.20501646101474763,
|
|
"num_tokens": 32534891.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.505761051177979,
|
|
"epoch": 1.63862525972932,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047405597136784166,
|
|
"loss": 5.0948,
|
|
"mean_token_accuracy": 0.21115048825740815,
|
|
"num_tokens": 32545555.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.442655324935913,
|
|
"epoch": 1.6391868366372775,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004740372519214955,
|
|
"loss": 5.1061,
|
|
"mean_token_accuracy": 0.20640807300806047,
|
|
"num_tokens": 32556851.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.56503210067749,
|
|
"epoch": 1.639748413545235,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047401852613772604,
|
|
"loss": 5.2767,
|
|
"mean_token_accuracy": 0.19699703603982927,
|
|
"num_tokens": 32569028.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.634431552886963,
|
|
"epoch": 1.6403099904531926,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004739997940171295,
|
|
"loss": 5.2103,
|
|
"mean_token_accuracy": 0.21065267771482468,
|
|
"num_tokens": 32581510.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.445714139938355,
|
|
"epoch": 1.6408715673611503,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047398105556030234,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.20650525987148285,
|
|
"num_tokens": 32592914.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.408236789703369,
|
|
"epoch": 1.6414331442691077,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047396231076784123,
|
|
"loss": 5.0375,
|
|
"mean_token_accuracy": 0.21460332870483398,
|
|
"num_tokens": 32603931.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.5724873542785645,
|
|
"epoch": 1.6419947211770651,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004739435596403429,
|
|
"loss": 5.1816,
|
|
"mean_token_accuracy": 0.20773862004280091,
|
|
"num_tokens": 32614508.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.441210651397705,
|
|
"epoch": 1.6425562980850228,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004739248021784046,
|
|
"loss": 5.0308,
|
|
"mean_token_accuracy": 0.21945724338293077,
|
|
"num_tokens": 32625393.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.362435245513916,
|
|
"epoch": 1.6431178749929805,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004739060383826234,
|
|
"loss": 5.0235,
|
|
"mean_token_accuracy": 0.21119230538606643,
|
|
"num_tokens": 32636645.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.5764477252960205,
|
|
"epoch": 1.6436794519009377,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047388726825359673,
|
|
"loss": 5.295,
|
|
"mean_token_accuracy": 0.20065956860780715,
|
|
"num_tokens": 32648792.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.530441379547119,
|
|
"epoch": 1.6442410288088953,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047386849179192235,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.21125935018062592,
|
|
"num_tokens": 32658825.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.5780431747436525,
|
|
"epoch": 1.644802605716853,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047384970899819813,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.21473995745182037,
|
|
"num_tokens": 32670141.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.327546691894531,
|
|
"epoch": 1.6453641826248104,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004738309198730219,
|
|
"loss": 4.9854,
|
|
"mean_token_accuracy": 0.22079149931669234,
|
|
"num_tokens": 32681804.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.5684239864349365,
|
|
"epoch": 1.6459257595327679,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047381212441699217,
|
|
"loss": 5.2163,
|
|
"mean_token_accuracy": 0.2018399015069008,
|
|
"num_tokens": 32692550.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.482094860076904,
|
|
"epoch": 1.6464873364407255,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004737933226307072,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.212128646671772,
|
|
"num_tokens": 32703833.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.455341005325318,
|
|
"epoch": 1.6470489133486832,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047377451451476586,
|
|
"loss": 5.1378,
|
|
"mean_token_accuracy": 0.20528425574302672,
|
|
"num_tokens": 32713928.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.505896949768067,
|
|
"epoch": 1.6476104902566406,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004737557000697668,
|
|
"loss": 5.1772,
|
|
"mean_token_accuracy": 0.20720291286706924,
|
|
"num_tokens": 32725393.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.544742441177368,
|
|
"epoch": 1.648172067164598,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004737368792963092,
|
|
"loss": 5.1695,
|
|
"mean_token_accuracy": 0.20412420034408568,
|
|
"num_tokens": 32736047.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.487040567398071,
|
|
"epoch": 1.6487336440725557,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047371805219499223,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.2028344303369522,
|
|
"num_tokens": 32747960.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.443016624450683,
|
|
"epoch": 1.6492952209805134,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047369921876641547,
|
|
"loss": 5.1007,
|
|
"mean_token_accuracy": 0.21083234548568724,
|
|
"num_tokens": 32757851.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.464973783493042,
|
|
"epoch": 1.6498567978884708,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047368037901117854,
|
|
"loss": 5.1258,
|
|
"mean_token_accuracy": 0.21135618388652802,
|
|
"num_tokens": 32767317.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.561215448379516,
|
|
"epoch": 1.6504183747964283,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004736615329298812,
|
|
"loss": 5.1582,
|
|
"mean_token_accuracy": 0.20844806581735612,
|
|
"num_tokens": 32777729.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.513482284545899,
|
|
"epoch": 1.650979951704386,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047364268052312367,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.19741781651973725,
|
|
"num_tokens": 32789547.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.489184713363647,
|
|
"epoch": 1.6515415286123436,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004736238217915061,
|
|
"loss": 5.1094,
|
|
"mean_token_accuracy": 0.21159690171480178,
|
|
"num_tokens": 32801487.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.5596295356750485,
|
|
"epoch": 1.652103105520301,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047360495673562906,
|
|
"loss": 5.1585,
|
|
"mean_token_accuracy": 0.21734675467014314,
|
|
"num_tokens": 32813042.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.549701070785522,
|
|
"epoch": 1.6526646824282585,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004735860853560931,
|
|
"loss": 5.1549,
|
|
"mean_token_accuracy": 0.20712797939777375,
|
|
"num_tokens": 32825467.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.480236768722534,
|
|
"epoch": 1.6532262593362161,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047356720765349926,
|
|
"loss": 5.1207,
|
|
"mean_token_accuracy": 0.20850823819637299,
|
|
"num_tokens": 32837113.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.577610826492309,
|
|
"epoch": 1.6537878362441738,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004735483236284485,
|
|
"loss": 5.2291,
|
|
"mean_token_accuracy": 0.19821407943964003,
|
|
"num_tokens": 32849779.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.445672798156738,
|
|
"epoch": 1.654349413152131,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00047352943328154203,
|
|
"loss": 5.1422,
|
|
"mean_token_accuracy": 0.206576469540596,
|
|
"num_tokens": 32861626.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.512395715713501,
|
|
"epoch": 1.6549109900600887,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047351053661338145,
|
|
"loss": 5.1701,
|
|
"mean_token_accuracy": 0.2074434831738472,
|
|
"num_tokens": 32872875.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.477881383895874,
|
|
"epoch": 1.6554725669680463,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004734916336245684,
|
|
"loss": 5.0152,
|
|
"mean_token_accuracy": 0.2107502579689026,
|
|
"num_tokens": 32883899.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.416962766647339,
|
|
"epoch": 1.6560341438760038,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004734727243157047,
|
|
"loss": 5.0027,
|
|
"mean_token_accuracy": 0.2155066102743149,
|
|
"num_tokens": 32894255.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.502555274963379,
|
|
"epoch": 1.6565957207839612,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047345380868739253,
|
|
"loss": 5.1166,
|
|
"mean_token_accuracy": 0.20663869827985765,
|
|
"num_tokens": 32903822.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.472291707992554,
|
|
"epoch": 1.6571572976919189,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004734348867402341,
|
|
"loss": 5.0706,
|
|
"mean_token_accuracy": 0.21425169110298156,
|
|
"num_tokens": 32915879.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.410977840423584,
|
|
"epoch": 1.6577188745998765,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004734159584748319,
|
|
"loss": 5.0894,
|
|
"mean_token_accuracy": 0.20558079779148103,
|
|
"num_tokens": 32928161.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.4737951278686525,
|
|
"epoch": 1.658280451507834,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047339702389178874,
|
|
"loss": 5.0848,
|
|
"mean_token_accuracy": 0.2081681475043297,
|
|
"num_tokens": 32938399.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.451405191421509,
|
|
"epoch": 1.6588420284157914,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047337808299170725,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.212621808052063,
|
|
"num_tokens": 32948221.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.457606172561645,
|
|
"epoch": 1.659403605323749,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047335913577519075,
|
|
"loss": 5.1153,
|
|
"mean_token_accuracy": 0.21022116243839264,
|
|
"num_tokens": 32959802.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.516530227661133,
|
|
"epoch": 1.6599651822317067,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047334018224284244,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.20651769042015075,
|
|
"num_tokens": 32970222.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.5132067680358885,
|
|
"epoch": 1.6605267591396642,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004733212223952657,
|
|
"loss": 5.0944,
|
|
"mean_token_accuracy": 0.21669638454914092,
|
|
"num_tokens": 32982241.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.460661935806274,
|
|
"epoch": 1.6610883360476216,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047330225623306443,
|
|
"loss": 5.0388,
|
|
"mean_token_accuracy": 0.21247430443763732,
|
|
"num_tokens": 32992584.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.524060487747192,
|
|
"epoch": 1.6616499129555793,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047328328375684237,
|
|
"loss": 5.2286,
|
|
"mean_token_accuracy": 0.20400873124599456,
|
|
"num_tokens": 33004080.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.422363233566284,
|
|
"epoch": 1.662211489863537,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004732643049672036,
|
|
"loss": 5.0597,
|
|
"mean_token_accuracy": 0.21065025478601457,
|
|
"num_tokens": 33015290.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.457514429092408,
|
|
"epoch": 1.6627730667714944,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004732453198647525,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.2088946133852005,
|
|
"num_tokens": 33026470.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.411339044570923,
|
|
"epoch": 1.6633346436794518,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004732263284500936,
|
|
"loss": 5.0317,
|
|
"mean_token_accuracy": 0.21732402443885804,
|
|
"num_tokens": 33036766.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.417842006683349,
|
|
"epoch": 1.6638962205874095,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004732073307238314,
|
|
"loss": 5.0562,
|
|
"mean_token_accuracy": 0.2039196088910103,
|
|
"num_tokens": 33047675.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.4877245903015135,
|
|
"epoch": 1.6644577974953672,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000473188326686571,
|
|
"loss": 5.0981,
|
|
"mean_token_accuracy": 0.21342210322618485,
|
|
"num_tokens": 33057613.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.581669855117798,
|
|
"epoch": 1.6650193744033244,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047316931633891736,
|
|
"loss": 5.2239,
|
|
"mean_token_accuracy": 0.199906887114048,
|
|
"num_tokens": 33070498.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.472095394134522,
|
|
"epoch": 1.665580951311282,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004731502996814759,
|
|
"loss": 5.0761,
|
|
"mean_token_accuracy": 0.21086811274290085,
|
|
"num_tokens": 33082026.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.475387144088745,
|
|
"epoch": 1.6661425282192397,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047313127671485194,
|
|
"loss": 5.0862,
|
|
"mean_token_accuracy": 0.2051032692193985,
|
|
"num_tokens": 33093841.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.537317705154419,
|
|
"epoch": 1.6667041051271971,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004731122474396514,
|
|
"loss": 5.1333,
|
|
"mean_token_accuracy": 0.20523856729269027,
|
|
"num_tokens": 33103817.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.527795314788818,
|
|
"epoch": 1.6672656820351546,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047309321185648,
|
|
"loss": 5.1592,
|
|
"mean_token_accuracy": 0.209054858982563,
|
|
"num_tokens": 33116006.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.461910247802734,
|
|
"epoch": 1.6678272589431122,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047307416996594386,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.20389262586832047,
|
|
"num_tokens": 33127649.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.378023672103882,
|
|
"epoch": 1.66838883585107,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004730551217686495,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.21935630738735198,
|
|
"num_tokens": 33138748.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.53667516708374,
|
|
"epoch": 1.6689504127590273,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004730360672652031,
|
|
"loss": 5.1761,
|
|
"mean_token_accuracy": 0.20561397671699524,
|
|
"num_tokens": 33150504.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.4520057201385494,
|
|
"epoch": 1.6695119896669848,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047301700645621154,
|
|
"loss": 5.1981,
|
|
"mean_token_accuracy": 0.2012033224105835,
|
|
"num_tokens": 33160625.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.50270266532898,
|
|
"epoch": 1.6700735665749424,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004729979393422817,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.2151162937283516,
|
|
"num_tokens": 33172229.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.465377712249756,
|
|
"epoch": 1.6706351434829,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004729788659240206,
|
|
"loss": 5.1113,
|
|
"mean_token_accuracy": 0.2084126889705658,
|
|
"num_tokens": 33183234.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.494789981842041,
|
|
"epoch": 1.6711967203908575,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004729597862020358,
|
|
"loss": 5.1581,
|
|
"mean_token_accuracy": 0.2057404786348343,
|
|
"num_tokens": 33193976.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.493765211105346,
|
|
"epoch": 1.671758297298815,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047294070017693453,
|
|
"loss": 5.1168,
|
|
"mean_token_accuracy": 0.21784327626228334,
|
|
"num_tokens": 33205959.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.457241582870483,
|
|
"epoch": 1.6723198742067726,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047292160784932454,
|
|
"loss": 5.0475,
|
|
"mean_token_accuracy": 0.21431664675474166,
|
|
"num_tokens": 33218405.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.443207406997681,
|
|
"epoch": 1.6728814511147303,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047290250921981386,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.20916522890329362,
|
|
"num_tokens": 33230778.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.459868669509888,
|
|
"epoch": 1.6734430280226877,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047288340428901053,
|
|
"loss": 5.0599,
|
|
"mean_token_accuracy": 0.209931942820549,
|
|
"num_tokens": 33242069.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.477905321121216,
|
|
"epoch": 1.6740046049306452,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047286429305752283,
|
|
"loss": 5.1334,
|
|
"mean_token_accuracy": 0.21028407216072081,
|
|
"num_tokens": 33252942.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.586065673828125,
|
|
"epoch": 1.6745661818386028,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047284517552595933,
|
|
"loss": 5.184,
|
|
"mean_token_accuracy": 0.20406026840209962,
|
|
"num_tokens": 33263892.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.429570007324219,
|
|
"epoch": 1.6751277587465605,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004728260516949287,
|
|
"loss": 5.0644,
|
|
"mean_token_accuracy": 0.20687515437602996,
|
|
"num_tokens": 33274383.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.50610237121582,
|
|
"epoch": 1.6756893356545177,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004728069215650399,
|
|
"loss": 5.0826,
|
|
"mean_token_accuracy": 0.210039122402668,
|
|
"num_tokens": 33285897.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.537733840942383,
|
|
"epoch": 1.6762509125624754,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004727877851369019,
|
|
"loss": 5.1607,
|
|
"mean_token_accuracy": 0.20547729581594468,
|
|
"num_tokens": 33297192.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.443004941940307,
|
|
"epoch": 1.676812489470433,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047276864241112417,
|
|
"loss": 5.0644,
|
|
"mean_token_accuracy": 0.21213503032922745,
|
|
"num_tokens": 33308250.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.421862697601318,
|
|
"epoch": 1.6773740663783905,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004727494933883161,
|
|
"loss": 5.0995,
|
|
"mean_token_accuracy": 0.2083527237176895,
|
|
"num_tokens": 33318515.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.53689398765564,
|
|
"epoch": 1.677935643286348,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004727303380690876,
|
|
"loss": 5.196,
|
|
"mean_token_accuracy": 0.2089026913046837,
|
|
"num_tokens": 33329762.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.541815233230591,
|
|
"epoch": 1.6784972201943056,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004727111764540484,
|
|
"loss": 5.1991,
|
|
"mean_token_accuracy": 0.2092477113008499,
|
|
"num_tokens": 33341054.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.4353355884552,
|
|
"epoch": 1.6790587971022632,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047269200854380854,
|
|
"loss": 5.0536,
|
|
"mean_token_accuracy": 0.2144552320241928,
|
|
"num_tokens": 33351524.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.47586498260498,
|
|
"epoch": 1.6796203740102207,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047267283433897854,
|
|
"loss": 5.15,
|
|
"mean_token_accuracy": 0.20320533514022826,
|
|
"num_tokens": 33362953.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.3822277069091795,
|
|
"epoch": 1.6801819509181781,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047265365384016887,
|
|
"loss": 5.0234,
|
|
"mean_token_accuracy": 0.21975015848875046,
|
|
"num_tokens": 33373209.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.37195520401001,
|
|
"epoch": 1.6807435278261358,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047263446704799017,
|
|
"loss": 5.0311,
|
|
"mean_token_accuracy": 0.20979778617620468,
|
|
"num_tokens": 33384775.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.423147392272949,
|
|
"epoch": 1.6813051047340934,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047261527396305343,
|
|
"loss": 5.0762,
|
|
"mean_token_accuracy": 0.20761286616325378,
|
|
"num_tokens": 33395457.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.578161001205444,
|
|
"epoch": 1.6818666816420509,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047259607458596966,
|
|
"loss": 5.216,
|
|
"mean_token_accuracy": 0.20890212059020996,
|
|
"num_tokens": 33407506.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.5212071418762205,
|
|
"epoch": 1.6824282585500083,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047257686891735023,
|
|
"loss": 5.1077,
|
|
"mean_token_accuracy": 0.21759800761938095,
|
|
"num_tokens": 33418154.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.442839241027832,
|
|
"epoch": 1.682989835457966,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047255765695780665,
|
|
"loss": 5.1294,
|
|
"mean_token_accuracy": 0.21438449174165725,
|
|
"num_tokens": 33428319.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.4437727451324465,
|
|
"epoch": 1.6835514123659236,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004725384387079507,
|
|
"loss": 5.049,
|
|
"mean_token_accuracy": 0.20992681831121446,
|
|
"num_tokens": 33440429.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.648414611816406,
|
|
"epoch": 1.684112989273881,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047251921416839425,
|
|
"loss": 5.2617,
|
|
"mean_token_accuracy": 0.19861510545015335,
|
|
"num_tokens": 33451736.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.5062929630279545,
|
|
"epoch": 1.6846745661818385,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004724999833397494,
|
|
"loss": 5.033,
|
|
"mean_token_accuracy": 0.2050390586256981,
|
|
"num_tokens": 33461991.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.6846745661818385,
|
|
"eval_entropy": 5.232175178124421,
|
|
"eval_loss": 5.187971591949463,
|
|
"eval_mean_token_accuracy": 0.21247658614133602,
|
|
"eval_num_tokens": 33461991.0,
|
|
"eval_runtime": 18.3219,
|
|
"eval_samples_per_second": 1692.673,
|
|
"eval_steps_per_second": 211.605,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 5.44553918838501,
|
|
"epoch": 1.6852361430897962,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004724807462226285,
|
|
"loss": 5.1798,
|
|
"mean_token_accuracy": 0.20041977167129515,
|
|
"num_tokens": 33473646.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 5.432424688339234,
|
|
"epoch": 1.6857977199977539,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000472461502817644,
|
|
"loss": 5.1101,
|
|
"mean_token_accuracy": 0.20865580141544343,
|
|
"num_tokens": 33485444.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 5.6253444194793705,
|
|
"epoch": 1.6863592969057113,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004724422531254087,
|
|
"loss": 5.2776,
|
|
"mean_token_accuracy": 0.20015684515237808,
|
|
"num_tokens": 33497199.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 5.578074884414673,
|
|
"epoch": 1.6869208738136687,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004724229971465355,
|
|
"loss": 5.2189,
|
|
"mean_token_accuracy": 0.2022972285747528,
|
|
"num_tokens": 33509045.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 5.448271703720093,
|
|
"epoch": 1.6874824507216264,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004724037348816375,
|
|
"loss": 5.0016,
|
|
"mean_token_accuracy": 0.21786488592624664,
|
|
"num_tokens": 33519730.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 5.469680643081665,
|
|
"epoch": 1.6880440276295838,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000472384466331328,
|
|
"loss": 5.1991,
|
|
"mean_token_accuracy": 0.20163263529539108,
|
|
"num_tokens": 33530393.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 5.506126165390015,
|
|
"epoch": 1.6886056045375413,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004723651914962205,
|
|
"loss": 5.1577,
|
|
"mean_token_accuracy": 0.2064269080758095,
|
|
"num_tokens": 33543592.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 5.52133846282959,
|
|
"epoch": 1.689167181445499,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047234591037692884,
|
|
"loss": 5.1037,
|
|
"mean_token_accuracy": 0.20329122841358185,
|
|
"num_tokens": 33554736.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 5.468460559844971,
|
|
"epoch": 1.6897287583534566,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047232662297406683,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.21586479395627975,
|
|
"num_tokens": 33565428.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 5.553099727630615,
|
|
"epoch": 1.690290335261414,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004723073292882485,
|
|
"loss": 5.3281,
|
|
"mean_token_accuracy": 0.2001742333173752,
|
|
"num_tokens": 33577102.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 5.5601544857025145,
|
|
"epoch": 1.6908519121693715,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047228802932008836,
|
|
"loss": 5.1621,
|
|
"mean_token_accuracy": 0.2123165100812912,
|
|
"num_tokens": 33587325.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 5.5672807693481445,
|
|
"epoch": 1.6914134890773291,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004722687230702009,
|
|
"loss": 5.1826,
|
|
"mean_token_accuracy": 0.20312864035367967,
|
|
"num_tokens": 33599294.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 5.5499523162841795,
|
|
"epoch": 1.6919750659852868,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004722494105392007,
|
|
"loss": 5.2524,
|
|
"mean_token_accuracy": 0.2018488749861717,
|
|
"num_tokens": 33609025.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 5.596439170837402,
|
|
"epoch": 1.6925366428932442,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004722300917277029,
|
|
"loss": 5.166,
|
|
"mean_token_accuracy": 0.20324416309595109,
|
|
"num_tokens": 33620881.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 5.527262496948242,
|
|
"epoch": 1.6930982198012017,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004722107666363224,
|
|
"loss": 5.1091,
|
|
"mean_token_accuracy": 0.21146733462810516,
|
|
"num_tokens": 33631505.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 5.510390186309815,
|
|
"epoch": 1.6936597967091593,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004721914352656746,
|
|
"loss": 5.2832,
|
|
"mean_token_accuracy": 0.2002302035689354,
|
|
"num_tokens": 33642560.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 5.553929042816162,
|
|
"epoch": 1.694221373617117,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000472172097616375,
|
|
"loss": 5.1528,
|
|
"mean_token_accuracy": 0.20899198204278946,
|
|
"num_tokens": 33654706.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 5.584413671493531,
|
|
"epoch": 1.6947829505250744,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004721527536890394,
|
|
"loss": 5.1985,
|
|
"mean_token_accuracy": 0.19373446553945542,
|
|
"num_tokens": 33665392.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 5.367098474502564,
|
|
"epoch": 1.6953445274330319,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004721334034842836,
|
|
"loss": 5.0242,
|
|
"mean_token_accuracy": 0.21408725529909134,
|
|
"num_tokens": 33675504.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 5.5141242980957035,
|
|
"epoch": 1.6959061043409895,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004721140470027238,
|
|
"loss": 5.1549,
|
|
"mean_token_accuracy": 0.20816438049077987,
|
|
"num_tokens": 33686505.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 5.557978343963623,
|
|
"epoch": 1.6964676812489472,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047209468424497627,
|
|
"loss": 5.157,
|
|
"mean_token_accuracy": 0.20750323981046676,
|
|
"num_tokens": 33698752.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 5.562022304534912,
|
|
"epoch": 1.6970292581569046,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004720753152116576,
|
|
"loss": 5.2016,
|
|
"mean_token_accuracy": 0.20154131650924684,
|
|
"num_tokens": 33710323.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 5.593322467803955,
|
|
"epoch": 1.697590835064862,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047205593990338443,
|
|
"loss": 5.2761,
|
|
"mean_token_accuracy": 0.19099510312080384,
|
|
"num_tokens": 33721875.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 5.499043798446655,
|
|
"epoch": 1.6981524119728197,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004720365583207737,
|
|
"loss": 4.977,
|
|
"mean_token_accuracy": 0.21811393201351165,
|
|
"num_tokens": 33731520.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 5.554244136810302,
|
|
"epoch": 1.6987139888807772,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004720171704644425,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.19921279102563857,
|
|
"num_tokens": 33743351.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 5.546348237991333,
|
|
"epoch": 1.6992755657887346,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004719977763350083,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.21103411614894868,
|
|
"num_tokens": 33754879.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 5.430835437774658,
|
|
"epoch": 1.6998371426966923,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047197837593308833,
|
|
"loss": 5.0925,
|
|
"mean_token_accuracy": 0.20844728499650955,
|
|
"num_tokens": 33766671.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 5.527913570404053,
|
|
"epoch": 1.70039871960465,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004719589692593006,
|
|
"loss": 5.1249,
|
|
"mean_token_accuracy": 0.20766616612672806,
|
|
"num_tokens": 33778236.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 5.481860828399658,
|
|
"epoch": 1.7009602965126074,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004719395563142629,
|
|
"loss": 5.0485,
|
|
"mean_token_accuracy": 0.20752263814210892,
|
|
"num_tokens": 33788898.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 5.503481388092041,
|
|
"epoch": 1.7015218734205648,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004719201370985933,
|
|
"loss": 5.2029,
|
|
"mean_token_accuracy": 0.20233033299446107,
|
|
"num_tokens": 33800641.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 5.553616380691528,
|
|
"epoch": 1.7020834503285225,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047190071161291007,
|
|
"loss": 5.107,
|
|
"mean_token_accuracy": 0.20703384429216384,
|
|
"num_tokens": 33812581.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 5.441648197174072,
|
|
"epoch": 1.7026450272364801,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047188127985783195,
|
|
"loss": 5.0605,
|
|
"mean_token_accuracy": 0.21562660336494446,
|
|
"num_tokens": 33823378.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 5.476008319854737,
|
|
"epoch": 1.7032066041444376,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047186184183397754,
|
|
"loss": 5.1672,
|
|
"mean_token_accuracy": 0.20512134283781053,
|
|
"num_tokens": 33834804.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 5.449408864974975,
|
|
"epoch": 1.703768181052395,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047184239754196564,
|
|
"loss": 5.131,
|
|
"mean_token_accuracy": 0.20889237374067307,
|
|
"num_tokens": 33847044.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 5.5294944763183596,
|
|
"epoch": 1.7043297579603527,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004718229469824155,
|
|
"loss": 5.0855,
|
|
"mean_token_accuracy": 0.2038659244775772,
|
|
"num_tokens": 33858077.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 5.484337854385376,
|
|
"epoch": 1.7048913348683103,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047180349015594634,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.2047533482313156,
|
|
"num_tokens": 33868765.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 5.43833475112915,
|
|
"epoch": 1.7054529117762678,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004717840270631778,
|
|
"loss": 5.0709,
|
|
"mean_token_accuracy": 0.21182419508695602,
|
|
"num_tokens": 33880415.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 5.487602281570434,
|
|
"epoch": 1.7060144886842252,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047176455770472946,
|
|
"loss": 5.1251,
|
|
"mean_token_accuracy": 0.20670740008354188,
|
|
"num_tokens": 33892081.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 5.575546455383301,
|
|
"epoch": 1.706576065592183,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047174508208122135,
|
|
"loss": 5.2542,
|
|
"mean_token_accuracy": 0.20220078229904176,
|
|
"num_tokens": 33903433.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 5.546103191375733,
|
|
"epoch": 1.7071376425001406,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004717256001932735,
|
|
"loss": 5.1226,
|
|
"mean_token_accuracy": 0.2091883361339569,
|
|
"num_tokens": 33914706.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 5.480507898330688,
|
|
"epoch": 1.707699219408098,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047170611204150624,
|
|
"loss": 5.2388,
|
|
"mean_token_accuracy": 0.20728666484355926,
|
|
"num_tokens": 33927195.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 5.505918407440186,
|
|
"epoch": 1.7082607963160554,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004716866176265401,
|
|
"loss": 5.1261,
|
|
"mean_token_accuracy": 0.21205178052186965,
|
|
"num_tokens": 33938422.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 5.579632568359375,
|
|
"epoch": 1.708822373224013,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047166711694899573,
|
|
"loss": 5.1436,
|
|
"mean_token_accuracy": 0.21102875471115112,
|
|
"num_tokens": 33949775.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 5.493266582489014,
|
|
"epoch": 1.7093839501319705,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047164761000949404,
|
|
"loss": 5.1162,
|
|
"mean_token_accuracy": 0.20836064219474792,
|
|
"num_tokens": 33960371.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 5.412378931045533,
|
|
"epoch": 1.709945527039928,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004716280968086563,
|
|
"loss": 5.0689,
|
|
"mean_token_accuracy": 0.20634318888187408,
|
|
"num_tokens": 33971326.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 5.541870260238648,
|
|
"epoch": 1.7105071039478856,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004716085773471036,
|
|
"loss": 5.1858,
|
|
"mean_token_accuracy": 0.20716300010681152,
|
|
"num_tokens": 33982744.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 5.5545313358306885,
|
|
"epoch": 1.7110686808558433,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047158905162545756,
|
|
"loss": 5.2274,
|
|
"mean_token_accuracy": 0.20111105293035508,
|
|
"num_tokens": 33993647.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 5.457699489593506,
|
|
"epoch": 1.7116302577638007,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047156951964433984,
|
|
"loss": 5.074,
|
|
"mean_token_accuracy": 0.20902696698904039,
|
|
"num_tokens": 34004026.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 5.475416469573974,
|
|
"epoch": 1.7121918346717582,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00047154998140437246,
|
|
"loss": 5.1451,
|
|
"mean_token_accuracy": 0.21045226454734803,
|
|
"num_tokens": 34014882.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 5.473147296905518,
|
|
"epoch": 1.7127534115797158,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047153043690617737,
|
|
"loss": 5.1701,
|
|
"mean_token_accuracy": 0.20746184885501862,
|
|
"num_tokens": 34026548.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 5.456924057006836,
|
|
"epoch": 1.7133149884876735,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000471510886150377,
|
|
"loss": 5.0418,
|
|
"mean_token_accuracy": 0.21107793897390364,
|
|
"num_tokens": 34038393.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 5.5369831085205075,
|
|
"epoch": 1.713876565395631,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004714913291375938,
|
|
"loss": 5.1601,
|
|
"mean_token_accuracy": 0.20325452834367752,
|
|
"num_tokens": 34050257.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 5.507985544204712,
|
|
"epoch": 1.7144381423035884,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047147176586845036,
|
|
"loss": 5.1255,
|
|
"mean_token_accuracy": 0.20985889434814453,
|
|
"num_tokens": 34061860.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 5.550496912002563,
|
|
"epoch": 1.714999719211546,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004714521963435698,
|
|
"loss": 5.1786,
|
|
"mean_token_accuracy": 0.202415731549263,
|
|
"num_tokens": 34075247.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 5.512369871139526,
|
|
"epoch": 1.7155612961195037,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00047143262056357506,
|
|
"loss": 5.0516,
|
|
"mean_token_accuracy": 0.20393330305814744,
|
|
"num_tokens": 34085801.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 5.533247232437134,
|
|
"epoch": 1.7161228730274611,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047141303852908965,
|
|
"loss": 5.1329,
|
|
"mean_token_accuracy": 0.20642355382442473,
|
|
"num_tokens": 34095686.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 5.4551043033599855,
|
|
"epoch": 1.7166844499354186,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004713934502407367,
|
|
"loss": 5.0952,
|
|
"mean_token_accuracy": 0.2121119812130928,
|
|
"num_tokens": 34106518.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 5.502656698226929,
|
|
"epoch": 1.7172460268433762,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004713738556991402,
|
|
"loss": 5.1367,
|
|
"mean_token_accuracy": 0.21238022446632385,
|
|
"num_tokens": 34117793.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 5.543705701828003,
|
|
"epoch": 1.717807603751334,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000471354254904924,
|
|
"loss": 5.2046,
|
|
"mean_token_accuracy": 0.20887165814638137,
|
|
"num_tokens": 34128748.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 5.488872241973877,
|
|
"epoch": 1.7183691806592913,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047133464785871216,
|
|
"loss": 5.1311,
|
|
"mean_token_accuracy": 0.21063185781240462,
|
|
"num_tokens": 34140597.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 5.578644800186157,
|
|
"epoch": 1.7189307575672488,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000471315034561129,
|
|
"loss": 5.1218,
|
|
"mean_token_accuracy": 0.20001179575920106,
|
|
"num_tokens": 34151823.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 5.4561553478240965,
|
|
"epoch": 1.7194923344752064,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047129541501279897,
|
|
"loss": 5.0687,
|
|
"mean_token_accuracy": 0.2141604408621788,
|
|
"num_tokens": 34163697.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 5.496334600448608,
|
|
"epoch": 1.7200539113831639,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004712757892143468,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.21214486807584762,
|
|
"num_tokens": 34175058.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 5.550631427764893,
|
|
"epoch": 1.7206154882911213,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047125615716639744,
|
|
"loss": 5.2306,
|
|
"mean_token_accuracy": 0.20638849288225175,
|
|
"num_tokens": 34186883.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 5.465950059890747,
|
|
"epoch": 1.721177065199079,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004712365188695758,
|
|
"loss": 5.1005,
|
|
"mean_token_accuracy": 0.21199408024549485,
|
|
"num_tokens": 34198103.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 5.4663896560668945,
|
|
"epoch": 1.7217386421070366,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004712168743245074,
|
|
"loss": 5.0781,
|
|
"mean_token_accuracy": 0.21162348687648774,
|
|
"num_tokens": 34208747.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 5.495966386795044,
|
|
"epoch": 1.722300219014994,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047119722353181754,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.20605195164680482,
|
|
"num_tokens": 34220775.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 5.5106219291687015,
|
|
"epoch": 1.7228617959229515,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047117756649213204,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.21309981048107146,
|
|
"num_tokens": 34231031.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 5.530784797668457,
|
|
"epoch": 1.7234233728309092,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004711579032060767,
|
|
"loss": 5.1828,
|
|
"mean_token_accuracy": 0.2067065492272377,
|
|
"num_tokens": 34241850.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 5.504141616821289,
|
|
"epoch": 1.7239849497388668,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004711382336742777,
|
|
"loss": 5.0622,
|
|
"mean_token_accuracy": 0.21268633008003235,
|
|
"num_tokens": 34252732.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 5.420687675476074,
|
|
"epoch": 1.7245465266468243,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004711185578973612,
|
|
"loss": 5.0717,
|
|
"mean_token_accuracy": 0.20594823956489564,
|
|
"num_tokens": 34264066.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 5.562918663024902,
|
|
"epoch": 1.7251081035547817,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004710988758759538,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.19903359860181807,
|
|
"num_tokens": 34275239.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 5.4476464748382565,
|
|
"epoch": 1.7256696804627394,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004710791876106821,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.20853817611932754,
|
|
"num_tokens": 34285723.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 5.497724485397339,
|
|
"epoch": 1.726231257370697,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047105949310217304,
|
|
"loss": 5.0993,
|
|
"mean_token_accuracy": 0.212528495490551,
|
|
"num_tokens": 34296292.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 5.4754719734191895,
|
|
"epoch": 1.7267928342786545,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004710397923510537,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.21450895816087723,
|
|
"num_tokens": 34307232.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 5.468585395812989,
|
|
"epoch": 1.727354411186612,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047102008535795134,
|
|
"loss": 5.1296,
|
|
"mean_token_accuracy": 0.21698434203863143,
|
|
"num_tokens": 34318933.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 5.518647527694702,
|
|
"epoch": 1.7279159880945696,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004710003721234934,
|
|
"loss": 5.0727,
|
|
"mean_token_accuracy": 0.2157742887735367,
|
|
"num_tokens": 34330431.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 5.541515827178955,
|
|
"epoch": 1.7284775650025272,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047098065264830754,
|
|
"loss": 5.1741,
|
|
"mean_token_accuracy": 0.20666055381298065,
|
|
"num_tokens": 34342006.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 5.526775598526001,
|
|
"epoch": 1.7290391419104847,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047096092693302174,
|
|
"loss": 5.0857,
|
|
"mean_token_accuracy": 0.20858652591705323,
|
|
"num_tokens": 34353390.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 5.407729434967041,
|
|
"epoch": 1.7296007188184421,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047094119497826406,
|
|
"loss": 5.0803,
|
|
"mean_token_accuracy": 0.20938567072153091,
|
|
"num_tokens": 34364211.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 5.485868453979492,
|
|
"epoch": 1.7301622957263998,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047092145678466273,
|
|
"loss": 5.0868,
|
|
"mean_token_accuracy": 0.2073808416724205,
|
|
"num_tokens": 34375362.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 5.4084801197052,
|
|
"epoch": 1.7307238726343572,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004709017123528462,
|
|
"loss": 4.9783,
|
|
"mean_token_accuracy": 0.21943629831075667,
|
|
"num_tokens": 34385511.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 5.488828182220459,
|
|
"epoch": 1.7312854495423147,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047088196168344315,
|
|
"loss": 5.2217,
|
|
"mean_token_accuracy": 0.20403611212968825,
|
|
"num_tokens": 34397060.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 5.4864503860473635,
|
|
"epoch": 1.7318470264502723,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047086220477708256,
|
|
"loss": 5.1221,
|
|
"mean_token_accuracy": 0.20844440013170243,
|
|
"num_tokens": 34407703.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 5.49847297668457,
|
|
"epoch": 1.73240860335823,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047084244163439335,
|
|
"loss": 5.1447,
|
|
"mean_token_accuracy": 0.21463810801506042,
|
|
"num_tokens": 34418929.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 5.425997543334961,
|
|
"epoch": 1.7329701802661874,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004708226722560049,
|
|
"loss": 5.0426,
|
|
"mean_token_accuracy": 0.21104160249233245,
|
|
"num_tokens": 34430693.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 5.448315000534057,
|
|
"epoch": 1.7335317571741449,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004708028966425465,
|
|
"loss": 5.0997,
|
|
"mean_token_accuracy": 0.2069340541958809,
|
|
"num_tokens": 34442299.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 5.512123918533325,
|
|
"epoch": 1.7340933340821025,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047078311479464797,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.20963587760925292,
|
|
"num_tokens": 34453426.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 5.466936779022217,
|
|
"epoch": 1.7346549109900602,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047076332671293917,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.21304211020469666,
|
|
"num_tokens": 34463601.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 5.515047788619995,
|
|
"epoch": 1.7352164878980176,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047074353239805005,
|
|
"loss": 5.0716,
|
|
"mean_token_accuracy": 0.21345555335283278,
|
|
"num_tokens": 34474938.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 5.435859251022339,
|
|
"epoch": 1.735778064805975,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004707237318506111,
|
|
"loss": 5.0244,
|
|
"mean_token_accuracy": 0.21603488624095918,
|
|
"num_tokens": 34485244.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 5.417296314239502,
|
|
"epoch": 1.7363396417139327,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047070392507125245,
|
|
"loss": 5.0233,
|
|
"mean_token_accuracy": 0.21657561659812927,
|
|
"num_tokens": 34496912.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 5.469209384918213,
|
|
"epoch": 1.7369012186218904,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000470684112060605,
|
|
"loss": 5.1054,
|
|
"mean_token_accuracy": 0.20672615617513657,
|
|
"num_tokens": 34508122.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 5.520959901809692,
|
|
"epoch": 1.7374627955298478,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047066429281929944,
|
|
"loss": 5.1022,
|
|
"mean_token_accuracy": 0.21297637671232222,
|
|
"num_tokens": 34519522.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 5.486133193969726,
|
|
"epoch": 1.7380243724378053,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000470644467347967,
|
|
"loss": 5.089,
|
|
"mean_token_accuracy": 0.21493441313505174,
|
|
"num_tokens": 34532832.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 5.499406433105468,
|
|
"epoch": 1.738585949345763,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047062463564723884,
|
|
"loss": 5.2114,
|
|
"mean_token_accuracy": 0.2051677480340004,
|
|
"num_tokens": 34544817.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 5.4390730381011965,
|
|
"epoch": 1.7391475262537206,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004706047977177464,
|
|
"loss": 5.04,
|
|
"mean_token_accuracy": 0.21157858967781068,
|
|
"num_tokens": 34555391.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 5.424674701690674,
|
|
"epoch": 1.739709103161678,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047058495356012135,
|
|
"loss": 5.0706,
|
|
"mean_token_accuracy": 0.21034435629844667,
|
|
"num_tokens": 34567531.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 5.505863666534424,
|
|
"epoch": 1.7402706800696355,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047056510317499545,
|
|
"loss": 5.1268,
|
|
"mean_token_accuracy": 0.20759210288524627,
|
|
"num_tokens": 34578212.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 5.432086086273193,
|
|
"epoch": 1.7408322569775931,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047054524656300087,
|
|
"loss": 5.0204,
|
|
"mean_token_accuracy": 0.21777308583259583,
|
|
"num_tokens": 34589331.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 5.418513917922974,
|
|
"epoch": 1.7413938338855506,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00047052538372476985,
|
|
"loss": 5.109,
|
|
"mean_token_accuracy": 0.21111343204975128,
|
|
"num_tokens": 34601467.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 5.414806699752807,
|
|
"epoch": 1.741955410793508,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047050551466093466,
|
|
"loss": 5.0767,
|
|
"mean_token_accuracy": 0.2150661826133728,
|
|
"num_tokens": 34611608.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 5.475686407089233,
|
|
"epoch": 1.7425169877014657,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004704856393721281,
|
|
"loss": 5.0192,
|
|
"mean_token_accuracy": 0.21589724719524384,
|
|
"num_tokens": 34622495.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 5.583570766448974,
|
|
"epoch": 1.7430785646094233,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047046575785898297,
|
|
"loss": 5.2391,
|
|
"mean_token_accuracy": 0.20443634688854218,
|
|
"num_tokens": 34633279.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 5.4607751846313475,
|
|
"epoch": 1.7436401415173808,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004704458701221323,
|
|
"loss": 5.0923,
|
|
"mean_token_accuracy": 0.20940332263708114,
|
|
"num_tokens": 34644030.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 5.589746570587158,
|
|
"epoch": 1.7442017184253382,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004704259761622094,
|
|
"loss": 5.1854,
|
|
"mean_token_accuracy": 0.1998036801815033,
|
|
"num_tokens": 34655540.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 5.5024128437042235,
|
|
"epoch": 1.7447632953332959,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047040607597984745,
|
|
"loss": 5.1189,
|
|
"mean_token_accuracy": 0.2082844704389572,
|
|
"num_tokens": 34666752.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 5.498738765716553,
|
|
"epoch": 1.7453248722412535,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004703861695756804,
|
|
"loss": 5.1105,
|
|
"mean_token_accuracy": 0.20718310326337813,
|
|
"num_tokens": 34678670.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 5.5130092144012455,
|
|
"epoch": 1.745886449149211,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004703662569503419,
|
|
"loss": 5.1373,
|
|
"mean_token_accuracy": 0.20873839855194093,
|
|
"num_tokens": 34690848.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 5.533270835876465,
|
|
"epoch": 1.7464480260571684,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047034633810446604,
|
|
"loss": 5.1441,
|
|
"mean_token_accuracy": 0.2038038730621338,
|
|
"num_tokens": 34703135.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 5.489834880828857,
|
|
"epoch": 1.747009602965126,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004703264130386869,
|
|
"loss": 5.0836,
|
|
"mean_token_accuracy": 0.20878920704126358,
|
|
"num_tokens": 34714329.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 5.515345478057862,
|
|
"epoch": 1.7475711798730837,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00047030648175363913,
|
|
"loss": 5.1475,
|
|
"mean_token_accuracy": 0.1987304389476776,
|
|
"num_tokens": 34727032.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 5.530332756042481,
|
|
"epoch": 1.7481327567810412,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004702865442499572,
|
|
"loss": 5.1431,
|
|
"mean_token_accuracy": 0.2069760039448738,
|
|
"num_tokens": 34738600.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 5.551826143264771,
|
|
"epoch": 1.7486943336889986,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004702666005282759,
|
|
"loss": 5.1849,
|
|
"mean_token_accuracy": 0.20250886529684067,
|
|
"num_tokens": 34749810.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 5.679680919647216,
|
|
"epoch": 1.7492559105969563,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004702466505892304,
|
|
"loss": 5.3224,
|
|
"mean_token_accuracy": 0.19772350043058395,
|
|
"num_tokens": 34762029.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 5.4695165157318115,
|
|
"epoch": 1.749817487504914,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047022669443345575,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.20618197619915007,
|
|
"num_tokens": 34773160.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 5.450992393493652,
|
|
"epoch": 1.7503790644128714,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047020673206158743,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.20454892218112947,
|
|
"num_tokens": 34784659.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 5.588104867935181,
|
|
"epoch": 1.7509406413208288,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000470186763474261,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.21105916500091554,
|
|
"num_tokens": 34796976.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 5.450671052932739,
|
|
"epoch": 1.7515022182287865,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004701667886721125,
|
|
"loss": 5.0721,
|
|
"mean_token_accuracy": 0.2078850522637367,
|
|
"num_tokens": 34809271.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 5.518737363815307,
|
|
"epoch": 1.752063795136744,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004701468076557776,
|
|
"loss": 5.1409,
|
|
"mean_token_accuracy": 0.2118055209517479,
|
|
"num_tokens": 34820291.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 5.428896713256836,
|
|
"epoch": 1.7526253720447014,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047012682042589277,
|
|
"loss": 5.0473,
|
|
"mean_token_accuracy": 0.21313309371471406,
|
|
"num_tokens": 34831224.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 5.516469573974609,
|
|
"epoch": 1.753186948952659,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047010682698309423,
|
|
"loss": 5.1307,
|
|
"mean_token_accuracy": 0.20943866819143295,
|
|
"num_tokens": 34842947.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 5.467283105850219,
|
|
"epoch": 1.7537485258606167,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004700868273280186,
|
|
"loss": 5.0801,
|
|
"mean_token_accuracy": 0.2154863640666008,
|
|
"num_tokens": 34853422.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 5.441207838058472,
|
|
"epoch": 1.7543101027685741,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047006682146130273,
|
|
"loss": 5.0984,
|
|
"mean_token_accuracy": 0.2049204781651497,
|
|
"num_tokens": 34864082.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 5.4395575523376465,
|
|
"epoch": 1.7548716796765316,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004700468093835837,
|
|
"loss": 5.0761,
|
|
"mean_token_accuracy": 0.21880912482738496,
|
|
"num_tokens": 34874094.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 5.456491136550904,
|
|
"epoch": 1.7554332565844892,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047002679109549864,
|
|
"loss": 5.1019,
|
|
"mean_token_accuracy": 0.21333929598331453,
|
|
"num_tokens": 34884597.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 5.405950736999512,
|
|
"epoch": 1.755994833492447,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047000676659768477,
|
|
"loss": 4.9953,
|
|
"mean_token_accuracy": 0.21880512535572053,
|
|
"num_tokens": 34894746.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 5.462916088104248,
|
|
"epoch": 1.7565564104004043,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004699867358907799,
|
|
"loss": 5.0089,
|
|
"mean_token_accuracy": 0.21646392196416855,
|
|
"num_tokens": 34906250.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 5.5513204574584964,
|
|
"epoch": 1.7571179873083618,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004699666989754217,
|
|
"loss": 5.2674,
|
|
"mean_token_accuracy": 0.202106811106205,
|
|
"num_tokens": 34917772.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 5.506875991821289,
|
|
"epoch": 1.7576795642163194,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004699466558522482,
|
|
"loss": 5.1012,
|
|
"mean_token_accuracy": 0.21430955976247787,
|
|
"num_tokens": 34930243.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 5.457162189483642,
|
|
"epoch": 1.758241141124277,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046992660652189755,
|
|
"loss": 5.1278,
|
|
"mean_token_accuracy": 0.20771168917417526,
|
|
"num_tokens": 34941357.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 5.581509637832641,
|
|
"epoch": 1.7588027180322345,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046990655098500824,
|
|
"loss": 5.2498,
|
|
"mean_token_accuracy": 0.1956062912940979,
|
|
"num_tokens": 34952116.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 5.529504013061524,
|
|
"epoch": 1.759364294940192,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00046988648924221866,
|
|
"loss": 5.1422,
|
|
"mean_token_accuracy": 0.20517128705978394,
|
|
"num_tokens": 34963707.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 5.562208366394043,
|
|
"epoch": 1.7599258718481496,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004698664212941677,
|
|
"loss": 5.2446,
|
|
"mean_token_accuracy": 0.20399125367403032,
|
|
"num_tokens": 34974376.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 5.528583908081055,
|
|
"epoch": 1.7604874487561073,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00046984634714149437,
|
|
"loss": 5.1281,
|
|
"mean_token_accuracy": 0.2076116606593132,
|
|
"num_tokens": 34986183.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 5.603015613555908,
|
|
"epoch": 1.7610490256640647,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004698262667848377,
|
|
"loss": 5.1428,
|
|
"mean_token_accuracy": 0.21122328341007232,
|
|
"num_tokens": 34997137.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 5.578436374664307,
|
|
"epoch": 1.7616106025720222,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00046980618022483714,
|
|
"loss": 5.2976,
|
|
"mean_token_accuracy": 0.19657762944698334,
|
|
"num_tokens": 35008944.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 5.541048336029053,
|
|
"epoch": 1.7621721794799798,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046978608746213224,
|
|
"loss": 5.1782,
|
|
"mean_token_accuracy": 0.20120044350624083,
|
|
"num_tokens": 35019972.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 5.476521062850952,
|
|
"epoch": 1.7627337563879373,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004697659884973628,
|
|
"loss": 5.064,
|
|
"mean_token_accuracy": 0.2112387552857399,
|
|
"num_tokens": 35031285.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 5.4324907779693605,
|
|
"epoch": 1.7632953332958947,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004697458833311687,
|
|
"loss": 5.0395,
|
|
"mean_token_accuracy": 0.21114134788513184,
|
|
"num_tokens": 35042553.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 5.59822416305542,
|
|
"epoch": 1.7638569102038524,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004697257719641902,
|
|
"loss": 5.2543,
|
|
"mean_token_accuracy": 0.19547551721334458,
|
|
"num_tokens": 35053637.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 5.531178522109985,
|
|
"epoch": 1.76441848711181,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004697056543970676,
|
|
"loss": 5.188,
|
|
"mean_token_accuracy": 0.21026747673749924,
|
|
"num_tokens": 35064754.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 5.539709615707397,
|
|
"epoch": 1.7649800640197675,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00046968553063044146,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.20780241936445237,
|
|
"num_tokens": 35075816.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 5.546365880966187,
|
|
"epoch": 1.765541640927725,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046966540066495247,
|
|
"loss": 5.1951,
|
|
"mean_token_accuracy": 0.20350608974695206,
|
|
"num_tokens": 35088647.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 5.483157014846801,
|
|
"epoch": 1.7661032178356826,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046964526450124164,
|
|
"loss": 5.0789,
|
|
"mean_token_accuracy": 0.20694421231746674,
|
|
"num_tokens": 35099372.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 5.530976581573486,
|
|
"epoch": 1.7666647947436402,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046962512213995,
|
|
"loss": 5.219,
|
|
"mean_token_accuracy": 0.20368565917015075,
|
|
"num_tokens": 35110663.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 5.688347959518433,
|
|
"epoch": 1.7672263716515977,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046960497358171913,
|
|
"loss": 5.3034,
|
|
"mean_token_accuracy": 0.19481257051229478,
|
|
"num_tokens": 35122406.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 5.46981725692749,
|
|
"epoch": 1.7677879485595551,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046958481882719035,
|
|
"loss": 5.069,
|
|
"mean_token_accuracy": 0.21117494702339173,
|
|
"num_tokens": 35133444.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 5.4243584156036375,
|
|
"epoch": 1.7683495254675128,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046956465787700554,
|
|
"loss": 5.1018,
|
|
"mean_token_accuracy": 0.20845517069101333,
|
|
"num_tokens": 35143840.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 5.591473197937011,
|
|
"epoch": 1.7689111023754704,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046954449073180644,
|
|
"loss": 5.2738,
|
|
"mean_token_accuracy": 0.19550443440675735,
|
|
"num_tokens": 35155050.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 5.544423151016235,
|
|
"epoch": 1.7694726792834279,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004695243173922354,
|
|
"loss": 5.1877,
|
|
"mean_token_accuracy": 0.20177470296621322,
|
|
"num_tokens": 35167649.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 5.491764163970947,
|
|
"epoch": 1.7700342561913853,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046950413785893465,
|
|
"loss": 5.1146,
|
|
"mean_token_accuracy": 0.21210612058639527,
|
|
"num_tokens": 35179238.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 5.558326864242554,
|
|
"epoch": 1.770595833099343,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046948395213254667,
|
|
"loss": 5.1659,
|
|
"mean_token_accuracy": 0.20976133346557618,
|
|
"num_tokens": 35189510.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 5.563194131851196,
|
|
"epoch": 1.7711574100073006,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004694637602137143,
|
|
"loss": 5.1543,
|
|
"mean_token_accuracy": 0.20395326614379883,
|
|
"num_tokens": 35199727.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 5.467804193496704,
|
|
"epoch": 1.771718986915258,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004694435621030803,
|
|
"loss": 5.1097,
|
|
"mean_token_accuracy": 0.21488792449235916,
|
|
"num_tokens": 35210311.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 5.526813936233521,
|
|
"epoch": 1.7722805638232155,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00046942335780128785,
|
|
"loss": 5.1397,
|
|
"mean_token_accuracy": 0.212800133228302,
|
|
"num_tokens": 35222755.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 5.510811376571655,
|
|
"epoch": 1.7728421407311732,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046940314730898035,
|
|
"loss": 5.1725,
|
|
"mean_token_accuracy": 0.20129836201667786,
|
|
"num_tokens": 35234337.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 5.491893148422241,
|
|
"epoch": 1.7734037176391306,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004693829306268012,
|
|
"loss": 5.1254,
|
|
"mean_token_accuracy": 0.20320425927639008,
|
|
"num_tokens": 35245736.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 5.4725401401519775,
|
|
"epoch": 1.773965294547088,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004693627077553942,
|
|
"loss": 5.0821,
|
|
"mean_token_accuracy": 0.21413436979055406,
|
|
"num_tokens": 35256368.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 5.476490163803101,
|
|
"epoch": 1.7745268714550457,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004693424786954031,
|
|
"loss": 5.1542,
|
|
"mean_token_accuracy": 0.20727033913135529,
|
|
"num_tokens": 35267238.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 5.5224419116973875,
|
|
"epoch": 1.7750884483630034,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046932224344747224,
|
|
"loss": 5.1033,
|
|
"mean_token_accuracy": 0.2042641207575798,
|
|
"num_tokens": 35277113.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 5.4780128479003904,
|
|
"epoch": 1.7756500252709608,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046930200201224573,
|
|
"loss": 5.0415,
|
|
"mean_token_accuracy": 0.2058327704668045,
|
|
"num_tokens": 35288504.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 5.479607009887696,
|
|
"epoch": 1.7762116021789183,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004692817543903681,
|
|
"loss": 5.0657,
|
|
"mean_token_accuracy": 0.21436280608177186,
|
|
"num_tokens": 35301215.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 5.442288064956665,
|
|
"epoch": 1.776773179086876,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000469261500582484,
|
|
"loss": 5.0728,
|
|
"mean_token_accuracy": 0.2079812318086624,
|
|
"num_tokens": 35311997.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 5.525636100769043,
|
|
"epoch": 1.7773347559948336,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046924124058923843,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.20737137645483017,
|
|
"num_tokens": 35323217.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 5.526032400131226,
|
|
"epoch": 1.777896332902791,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004692209744112765,
|
|
"loss": 5.1699,
|
|
"mean_token_accuracy": 0.21151493042707442,
|
|
"num_tokens": 35333102.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 5.562783288955688,
|
|
"epoch": 1.7784579098107485,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004692007020492433,
|
|
"loss": 5.1959,
|
|
"mean_token_accuracy": 0.20669854283332825,
|
|
"num_tokens": 35346394.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 5.415058898925781,
|
|
"epoch": 1.7790194867187061,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004691804235037845,
|
|
"loss": 4.9987,
|
|
"mean_token_accuracy": 0.21598448604345322,
|
|
"num_tokens": 35357827.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 5.479741525650025,
|
|
"epoch": 1.7795810636266638,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004691601387755456,
|
|
"loss": 5.1335,
|
|
"mean_token_accuracy": 0.20664003044366835,
|
|
"num_tokens": 35370517.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 5.5027184009552,
|
|
"epoch": 1.7801426405346212,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046913984786517275,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.20750885754823684,
|
|
"num_tokens": 35381830.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 5.584297227859497,
|
|
"epoch": 1.7807042174425787,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00046911955077331177,
|
|
"loss": 5.1994,
|
|
"mean_token_accuracy": 0.19884348511695862,
|
|
"num_tokens": 35393161.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 5.5473456382751465,
|
|
"epoch": 1.7812657943505363,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046909924750060893,
|
|
"loss": 5.0877,
|
|
"mean_token_accuracy": 0.21679302603006362,
|
|
"num_tokens": 35403338.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 5.535284900665284,
|
|
"epoch": 1.781827371258494,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004690789380477109,
|
|
"loss": 5.1797,
|
|
"mean_token_accuracy": 0.2024092271924019,
|
|
"num_tokens": 35415862.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 5.424515962600708,
|
|
"epoch": 1.7823889481664514,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004690586224152641,
|
|
"loss": 5.0734,
|
|
"mean_token_accuracy": 0.20500966012477875,
|
|
"num_tokens": 35426696.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 5.494702529907227,
|
|
"epoch": 1.7829505250744089,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004690383006039156,
|
|
"loss": 5.1068,
|
|
"mean_token_accuracy": 0.21053788512945176,
|
|
"num_tokens": 35438624.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 5.57385835647583,
|
|
"epoch": 1.7835121019823665,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004690179726143123,
|
|
"loss": 5.2522,
|
|
"mean_token_accuracy": 0.20170057713985443,
|
|
"num_tokens": 35449841.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 5.667948913574219,
|
|
"epoch": 1.784073678890324,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004689976384471014,
|
|
"loss": 5.3342,
|
|
"mean_token_accuracy": 0.19652565121650695,
|
|
"num_tokens": 35462081.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 5.4623558044433596,
|
|
"epoch": 1.7846352557982814,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004689772981029306,
|
|
"loss": 5.0546,
|
|
"mean_token_accuracy": 0.21292088627815248,
|
|
"num_tokens": 35472834.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 5.444349384307861,
|
|
"epoch": 1.785196832706239,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004689569515824473,
|
|
"loss": 5.0118,
|
|
"mean_token_accuracy": 0.21588788628578187,
|
|
"num_tokens": 35482975.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 5.409834623336792,
|
|
"epoch": 1.7857584096141967,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004689365988862995,
|
|
"loss": 5.1399,
|
|
"mean_token_accuracy": 0.20853421837091446,
|
|
"num_tokens": 35494470.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 5.457488107681274,
|
|
"epoch": 1.7863199865221542,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00046891624001513515,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.21182076632976532,
|
|
"num_tokens": 35505464.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 5.460780143737793,
|
|
"epoch": 1.7868815634301116,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00046889587496960257,
|
|
"loss": 5.1109,
|
|
"mean_token_accuracy": 0.20508903563022612,
|
|
"num_tokens": 35517609.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 5.499519109725952,
|
|
"epoch": 1.7874431403380693,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046887550375034997,
|
|
"loss": 5.0327,
|
|
"mean_token_accuracy": 0.21565255671739578,
|
|
"num_tokens": 35528994.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 5.573452138900757,
|
|
"epoch": 1.788004717246027,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00046885512635802627,
|
|
"loss": 5.2198,
|
|
"mean_token_accuracy": 0.20077406316995622,
|
|
"num_tokens": 35541044.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 5.4689469814300535,
|
|
"epoch": 1.7885662941539844,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004688347427932801,
|
|
"loss": 5.0341,
|
|
"mean_token_accuracy": 0.21211225539445877,
|
|
"num_tokens": 35552660.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 5.576786184310913,
|
|
"epoch": 1.7891278710619418,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046881435305676055,
|
|
"loss": 5.1463,
|
|
"mean_token_accuracy": 0.2024679332971573,
|
|
"num_tokens": 35565144.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 5.540687227249146,
|
|
"epoch": 1.7896894479698995,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046879395714911686,
|
|
"loss": 5.096,
|
|
"mean_token_accuracy": 0.21010931581258774,
|
|
"num_tokens": 35577067.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 5.4537200927734375,
|
|
"epoch": 1.7902510248778571,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046877355507099846,
|
|
"loss": 5.0727,
|
|
"mean_token_accuracy": 0.21291753351688386,
|
|
"num_tokens": 35588712.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 5.493366718292236,
|
|
"epoch": 1.7908126017858146,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004687531468230549,
|
|
"loss": 5.0116,
|
|
"mean_token_accuracy": 0.21327860951423644,
|
|
"num_tokens": 35599212.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 5.518341588973999,
|
|
"epoch": 1.791374178693772,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004687327324059359,
|
|
"loss": 5.1059,
|
|
"mean_token_accuracy": 0.21302772015333177,
|
|
"num_tokens": 35609397.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 5.470599269866943,
|
|
"epoch": 1.7919357556017297,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004687123118202916,
|
|
"loss": 5.0727,
|
|
"mean_token_accuracy": 0.21037781089544297,
|
|
"num_tokens": 35620615.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 5.545458459854126,
|
|
"epoch": 1.7924973325096873,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004686918850667722,
|
|
"loss": 5.1114,
|
|
"mean_token_accuracy": 0.21522961109876632,
|
|
"num_tokens": 35632684.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 5.51549334526062,
|
|
"epoch": 1.7930589094176448,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000468671452146028,
|
|
"loss": 5.1458,
|
|
"mean_token_accuracy": 0.21134270578622819,
|
|
"num_tokens": 35643896.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 5.512136363983155,
|
|
"epoch": 1.7936204863256022,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00046865101305870965,
|
|
"loss": 5.1097,
|
|
"mean_token_accuracy": 0.2080790564417839,
|
|
"num_tokens": 35655752.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 5.439818668365478,
|
|
"epoch": 1.7941820632335599,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000468630567805468,
|
|
"loss": 5.0175,
|
|
"mean_token_accuracy": 0.21380633860826492,
|
|
"num_tokens": 35665870.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 5.487493705749512,
|
|
"epoch": 1.7947436401415173,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000468610116386954,
|
|
"loss": 5.1802,
|
|
"mean_token_accuracy": 0.20478664934635163,
|
|
"num_tokens": 35677792.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 5.454782009124756,
|
|
"epoch": 1.7953052170494748,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004685896588038187,
|
|
"loss": 5.0792,
|
|
"mean_token_accuracy": 0.20663830637931824,
|
|
"num_tokens": 35689059.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 5.506741619110107,
|
|
"epoch": 1.7958667939574324,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004685691950567136,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.2077423095703125,
|
|
"num_tokens": 35699953.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 5.539091634750366,
|
|
"epoch": 1.79642837086539,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046854872514629035,
|
|
"loss": 5.0747,
|
|
"mean_token_accuracy": 0.21003518849611283,
|
|
"num_tokens": 35710894.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 5.4831499576568605,
|
|
"epoch": 1.7969899477733475,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004685282490732005,
|
|
"loss": 5.1394,
|
|
"mean_token_accuracy": 0.2100980430841446,
|
|
"num_tokens": 35722440.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 5.473070573806763,
|
|
"epoch": 1.797551524681305,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046850776683809623,
|
|
"loss": 5.1578,
|
|
"mean_token_accuracy": 0.20651376843452454,
|
|
"num_tokens": 35733768.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 5.490332460403442,
|
|
"epoch": 1.7981131015892626,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004684872784416295,
|
|
"loss": 5.1103,
|
|
"mean_token_accuracy": 0.20746628195047379,
|
|
"num_tokens": 35744211.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 5.474593305587769,
|
|
"epoch": 1.7986746784972203,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004684667838844529,
|
|
"loss": 5.1112,
|
|
"mean_token_accuracy": 0.20941847711801528,
|
|
"num_tokens": 35755498.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 5.5333967208862305,
|
|
"epoch": 1.7992362554051777,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004684462831672188,
|
|
"loss": 5.1329,
|
|
"mean_token_accuracy": 0.2138266995549202,
|
|
"num_tokens": 35767442.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 5.512209749221801,
|
|
"epoch": 1.7997978323131352,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046842577629058006,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.21625768542289733,
|
|
"num_tokens": 35778040.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 5.4857195854187015,
|
|
"epoch": 1.8003594092210928,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004684052632551896,
|
|
"loss": 5.0551,
|
|
"mean_token_accuracy": 0.2176490068435669,
|
|
"num_tokens": 35788139.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 5.4839424133300785,
|
|
"epoch": 1.8009209861290505,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046838474406170046,
|
|
"loss": 5.1017,
|
|
"mean_token_accuracy": 0.20668245404958724,
|
|
"num_tokens": 35799077.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 5.520399045944214,
|
|
"epoch": 1.801482563037008,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046836421871076616,
|
|
"loss": 5.1436,
|
|
"mean_token_accuracy": 0.2059086248278618,
|
|
"num_tokens": 35809748.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 5.597242021560669,
|
|
"epoch": 1.8020441399449654,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004683436872030401,
|
|
"loss": 5.1511,
|
|
"mean_token_accuracy": 0.20932105481624602,
|
|
"num_tokens": 35821621.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 5.522021913528443,
|
|
"epoch": 1.802605716852923,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046832314953917605,
|
|
"loss": 5.1167,
|
|
"mean_token_accuracy": 0.2089120164513588,
|
|
"num_tokens": 35833497.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 5.586480188369751,
|
|
"epoch": 1.8031672937608807,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046830260571982795,
|
|
"loss": 5.2226,
|
|
"mean_token_accuracy": 0.2081691727042198,
|
|
"num_tokens": 35844266.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 5.577649021148682,
|
|
"epoch": 1.8037288706688381,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004682820557456499,
|
|
"loss": 5.2079,
|
|
"mean_token_accuracy": 0.2062609001994133,
|
|
"num_tokens": 35855260.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 5.528383874893189,
|
|
"epoch": 1.8042904475767956,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046826149961729625,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.20990426391363143,
|
|
"num_tokens": 35865950.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 5.561335754394531,
|
|
"epoch": 1.8048520244847532,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046824093733542144,
|
|
"loss": 5.2851,
|
|
"mean_token_accuracy": 0.19930185228586197,
|
|
"num_tokens": 35877028.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 5.496836614608765,
|
|
"epoch": 1.8054136013927107,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046822036890068033,
|
|
"loss": 5.1346,
|
|
"mean_token_accuracy": 0.20585497915744783,
|
|
"num_tokens": 35887831.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 5.513091897964477,
|
|
"epoch": 1.8059751783006681,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046819979431372773,
|
|
"loss": 5.1105,
|
|
"mean_token_accuracy": 0.20903973877429963,
|
|
"num_tokens": 35897946.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 5.5629009246826175,
|
|
"epoch": 1.8065367552086258,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046817921357521865,
|
|
"loss": 5.2464,
|
|
"mean_token_accuracy": 0.20251297801733018,
|
|
"num_tokens": 35910973.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 5.55006775856018,
|
|
"epoch": 1.8070983321165834,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046815862668580854,
|
|
"loss": 5.18,
|
|
"mean_token_accuracy": 0.20721229910850525,
|
|
"num_tokens": 35921478.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 5.523074197769165,
|
|
"epoch": 1.8076599090245409,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004681380336461528,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.21772347688674926,
|
|
"num_tokens": 35932211.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 5.48393931388855,
|
|
"epoch": 1.8082214859324983,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046811743445690724,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.20707104206085206,
|
|
"num_tokens": 35944350.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 5.5646586418151855,
|
|
"epoch": 1.808783062840456,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004680968291187276,
|
|
"loss": 5.2008,
|
|
"mean_token_accuracy": 0.20393282026052476,
|
|
"num_tokens": 35955590.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 5.4751293659210205,
|
|
"epoch": 1.8093446397484136,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004680762176322701,
|
|
"loss": 4.9726,
|
|
"mean_token_accuracy": 0.22462885230779647,
|
|
"num_tokens": 35965872.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 5.426794910430909,
|
|
"epoch": 1.809906216656371,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046805559999819093,
|
|
"loss": 5.1048,
|
|
"mean_token_accuracy": 0.203200101852417,
|
|
"num_tokens": 35976851.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 5.51524076461792,
|
|
"epoch": 1.8104677935643285,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004680349762171465,
|
|
"loss": 5.0702,
|
|
"mean_token_accuracy": 0.20514808744192123,
|
|
"num_tokens": 35986984.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 5.527813577651978,
|
|
"epoch": 1.8110293704722862,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004680143462897936,
|
|
"loss": 5.1405,
|
|
"mean_token_accuracy": 0.2088669568300247,
|
|
"num_tokens": 35999349.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 5.467396688461304,
|
|
"epoch": 1.8115909473802438,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004679937102167891,
|
|
"loss": 5.1537,
|
|
"mean_token_accuracy": 0.21317908465862273,
|
|
"num_tokens": 36011122.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 5.517142963409424,
|
|
"epoch": 1.8121525242882013,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046797306799879,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.20882433652877808,
|
|
"num_tokens": 36022729.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 5.473223686218262,
|
|
"epoch": 1.8127141011961587,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00046795241963645356,
|
|
"loss": 5.0831,
|
|
"mean_token_accuracy": 0.20791100561618805,
|
|
"num_tokens": 36034042.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 5.478951930999756,
|
|
"epoch": 1.8132756781041164,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004679317651304373,
|
|
"loss": 5.1306,
|
|
"mean_token_accuracy": 0.20588796883821486,
|
|
"num_tokens": 36045357.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 5.385507535934448,
|
|
"epoch": 1.813837255012074,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004679111044813987,
|
|
"loss": 4.8927,
|
|
"mean_token_accuracy": 0.21933177560567857,
|
|
"num_tokens": 36055180.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 5.4356471538543705,
|
|
"epoch": 1.8143988319200315,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046789043768999573,
|
|
"loss": 5.0265,
|
|
"mean_token_accuracy": 0.21692266762256623,
|
|
"num_tokens": 36065574.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 5.474743270874024,
|
|
"epoch": 1.814960408827989,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004678697647568865,
|
|
"loss": 5.1266,
|
|
"mean_token_accuracy": 0.2107786700129509,
|
|
"num_tokens": 36077316.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 5.461124753952026,
|
|
"epoch": 1.8155219857359466,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00046784908568272903,
|
|
"loss": 5.0715,
|
|
"mean_token_accuracy": 0.20999224334955216,
|
|
"num_tokens": 36088735.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 5.49382643699646,
|
|
"epoch": 1.8160835626439042,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000467828400468182,
|
|
"loss": 5.1175,
|
|
"mean_token_accuracy": 0.20820717215538026,
|
|
"num_tokens": 36098806.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 5.48393406867981,
|
|
"epoch": 1.8166451395518615,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046780770911390387,
|
|
"loss": 5.1566,
|
|
"mean_token_accuracy": 0.20794095396995543,
|
|
"num_tokens": 36110333.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 5.5452765941619875,
|
|
"epoch": 1.8172067164598191,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004677870116205534,
|
|
"loss": 5.12,
|
|
"mean_token_accuracy": 0.2085841938853264,
|
|
"num_tokens": 36121719.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 5.491519832611084,
|
|
"epoch": 1.8177682933677768,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046776630798878985,
|
|
"loss": 5.0319,
|
|
"mean_token_accuracy": 0.21408172845840454,
|
|
"num_tokens": 36132129.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 5.586021089553833,
|
|
"epoch": 1.8183298702757342,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004677455982192723,
|
|
"loss": 5.3002,
|
|
"mean_token_accuracy": 0.20487173050642013,
|
|
"num_tokens": 36145189.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 5.474322319030762,
|
|
"epoch": 1.8188914471836917,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00046772488231266004,
|
|
"loss": 5.0647,
|
|
"mean_token_accuracy": 0.20783973038196563,
|
|
"num_tokens": 36157896.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 5.5622375965118405,
|
|
"epoch": 1.8194530240916493,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046770416026961284,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.2086881071329117,
|
|
"num_tokens": 36168842.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 5.40425214767456,
|
|
"epoch": 1.820014600999607,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004676834320907904,
|
|
"loss": 5.0095,
|
|
"mean_token_accuracy": 0.21493154913187026,
|
|
"num_tokens": 36180075.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 5.4317741870880125,
|
|
"epoch": 1.8205761779075644,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004676626977768528,
|
|
"loss": 5.0696,
|
|
"mean_token_accuracy": 0.21408002227544784,
|
|
"num_tokens": 36190589.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 5.448160791397095,
|
|
"epoch": 1.8211377548155219,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046764195732846013,
|
|
"loss": 4.9445,
|
|
"mean_token_accuracy": 0.21916674971580505,
|
|
"num_tokens": 36201145.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 5.431320524215698,
|
|
"epoch": 1.8216993317234795,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046762121074627285,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.21231744140386583,
|
|
"num_tokens": 36213243.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 5.372766590118408,
|
|
"epoch": 1.8222609086314372,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046760045803095153,
|
|
"loss": 5.0616,
|
|
"mean_token_accuracy": 0.21231216788291932,
|
|
"num_tokens": 36224491.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 5.435123443603516,
|
|
"epoch": 1.8228224855393946,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004675796991831569,
|
|
"loss": 5.0989,
|
|
"mean_token_accuracy": 0.2125253811478615,
|
|
"num_tokens": 36236006.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 5.611803483963013,
|
|
"epoch": 1.823384062447352,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046755893420355,
|
|
"loss": 5.1896,
|
|
"mean_token_accuracy": 0.20481275618076325,
|
|
"num_tokens": 36246925.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 5.529128360748291,
|
|
"epoch": 1.8239456393553097,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004675381630927919,
|
|
"loss": 5.1179,
|
|
"mean_token_accuracy": 0.2053695559501648,
|
|
"num_tokens": 36258449.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 5.510815000534057,
|
|
"epoch": 1.8245072162632674,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00046751738585154405,
|
|
"loss": 5.1142,
|
|
"mean_token_accuracy": 0.21405246257781982,
|
|
"num_tokens": 36270820.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 5.552372837066651,
|
|
"epoch": 1.8250687931712248,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00046749660248046794,
|
|
"loss": 5.1802,
|
|
"mean_token_accuracy": 0.20924902707338333,
|
|
"num_tokens": 36282346.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 5.551780843734742,
|
|
"epoch": 1.8256303700791823,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046747581298022537,
|
|
"loss": 5.2073,
|
|
"mean_token_accuracy": 0.20106985569000244,
|
|
"num_tokens": 36294111.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 5.476664686203003,
|
|
"epoch": 1.82619194698714,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004674550173514782,
|
|
"loss": 5.0889,
|
|
"mean_token_accuracy": 0.20898337811231613,
|
|
"num_tokens": 36304899.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 5.503116321563721,
|
|
"epoch": 1.8267535238950976,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046743421559488875,
|
|
"loss": 5.195,
|
|
"mean_token_accuracy": 0.206307815015316,
|
|
"num_tokens": 36316272.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 5.474429273605347,
|
|
"epoch": 1.8273151008030548,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046741340771111917,
|
|
"loss": 5.0075,
|
|
"mean_token_accuracy": 0.21395708471536637,
|
|
"num_tokens": 36326624.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 5.4546449184417725,
|
|
"epoch": 1.8278766777110125,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046739259370083205,
|
|
"loss": 5.0034,
|
|
"mean_token_accuracy": 0.21640014350414277,
|
|
"num_tokens": 36338178.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 5.571144962310791,
|
|
"epoch": 1.8284382546189701,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004673717735646902,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.20726884603500367,
|
|
"num_tokens": 36349993.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 5.575223827362061,
|
|
"epoch": 1.8289998315269276,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004673509473033564,
|
|
"loss": 5.1844,
|
|
"mean_token_accuracy": 0.20759999752044678,
|
|
"num_tokens": 36361002.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 5.514489269256591,
|
|
"epoch": 1.829561408434885,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046733011491749383,
|
|
"loss": 5.1271,
|
|
"mean_token_accuracy": 0.20994158685207367,
|
|
"num_tokens": 36371688.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 5.434833145141601,
|
|
"epoch": 1.8301229853428427,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004673092764077658,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.2152921661734581,
|
|
"num_tokens": 36382683.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 5.5578593730926515,
|
|
"epoch": 1.8306845622508003,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004672884317748359,
|
|
"loss": 5.207,
|
|
"mean_token_accuracy": 0.19801284670829772,
|
|
"num_tokens": 36394170.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 5.535651779174804,
|
|
"epoch": 1.8312461391587578,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004672675810193677,
|
|
"loss": 5.1318,
|
|
"mean_token_accuracy": 0.2031713142991066,
|
|
"num_tokens": 36405613.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 5.547235202789307,
|
|
"epoch": 1.8318077160667152,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046724672414202514,
|
|
"loss": 5.1847,
|
|
"mean_token_accuracy": 0.2065509647130966,
|
|
"num_tokens": 36416282.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 5.534456539154053,
|
|
"epoch": 1.8323692929746729,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004672258611434724,
|
|
"loss": 5.1955,
|
|
"mean_token_accuracy": 0.20271504819393157,
|
|
"num_tokens": 36427624.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 5.480709505081177,
|
|
"epoch": 1.8329308698826305,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046720499202437354,
|
|
"loss": 5.0025,
|
|
"mean_token_accuracy": 0.22154767364263533,
|
|
"num_tokens": 36438230.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 5.499330759048462,
|
|
"epoch": 1.833492446790588,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004671841167853933,
|
|
"loss": 5.1359,
|
|
"mean_token_accuracy": 0.20689167082309723,
|
|
"num_tokens": 36448854.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 5.523745155334472,
|
|
"epoch": 1.8340540236985454,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004671632354271962,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.20888641327619553,
|
|
"num_tokens": 36460426.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 5.563951730728149,
|
|
"epoch": 1.834615600606503,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046714234795044724,
|
|
"loss": 5.1174,
|
|
"mean_token_accuracy": 0.20701346099376677,
|
|
"num_tokens": 36470914.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 5.489262104034424,
|
|
"epoch": 1.8351771775144607,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004671214543558113,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.2084989070892334,
|
|
"num_tokens": 36480753.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 5.445824337005615,
|
|
"epoch": 1.8357387544224182,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004671005546439538,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.2117574319243431,
|
|
"num_tokens": 36492858.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 5.399022817611694,
|
|
"epoch": 1.8363003313303756,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046707964881554005,
|
|
"loss": 4.9979,
|
|
"mean_token_accuracy": 0.2150909811258316,
|
|
"num_tokens": 36503912.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 5.462345743179322,
|
|
"epoch": 1.8368619082383333,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00046705873687123586,
|
|
"loss": 5.0765,
|
|
"mean_token_accuracy": 0.2098548948764801,
|
|
"num_tokens": 36515410.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 5.486423492431641,
|
|
"epoch": 1.837423485146291,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046703781881170703,
|
|
"loss": 5.0212,
|
|
"mean_token_accuracy": 0.21367933750152587,
|
|
"num_tokens": 36526310.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 5.43696780204773,
|
|
"epoch": 1.8379850620542482,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046701689463761947,
|
|
"loss": 4.9829,
|
|
"mean_token_accuracy": 0.21390655040740966,
|
|
"num_tokens": 36537081.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 5.450550699234009,
|
|
"epoch": 1.8385466389622058,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046699596434963953,
|
|
"loss": 5.0782,
|
|
"mean_token_accuracy": 0.21097376197576523,
|
|
"num_tokens": 36549419.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 5.407167291641235,
|
|
"epoch": 1.8391082158701635,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004669750279484337,
|
|
"loss": 5.0652,
|
|
"mean_token_accuracy": 0.21898609548807144,
|
|
"num_tokens": 36560842.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 5.468007230758667,
|
|
"epoch": 1.839669792778121,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004669540854346685,
|
|
"loss": 5.0655,
|
|
"mean_token_accuracy": 0.21070052534341813,
|
|
"num_tokens": 36571717.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 5.503949975967407,
|
|
"epoch": 1.8402313696860784,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046693313680901073,
|
|
"loss": 5.0818,
|
|
"mean_token_accuracy": 0.21168841123580934,
|
|
"num_tokens": 36581709.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 5.448351860046387,
|
|
"epoch": 1.840792946594036,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00046691218207212744,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.2082774430513382,
|
|
"num_tokens": 36593033.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 5.498321866989135,
|
|
"epoch": 1.8413545235019937,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004668912212246859,
|
|
"loss": 5.1738,
|
|
"mean_token_accuracy": 0.210365329682827,
|
|
"num_tokens": 36603605.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 5.533682012557984,
|
|
"epoch": 1.8419161004099511,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046687025426735335,
|
|
"loss": 5.191,
|
|
"mean_token_accuracy": 0.20624493509531022,
|
|
"num_tokens": 36616219.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 5.605037593841553,
|
|
"epoch": 1.8424776773179086,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004668492812007976,
|
|
"loss": 5.1406,
|
|
"mean_token_accuracy": 0.21203456223011016,
|
|
"num_tokens": 36627777.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 5.495413827896118,
|
|
"epoch": 1.8430392542258662,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004668283020256863,
|
|
"loss": 5.1022,
|
|
"mean_token_accuracy": 0.2118648812174797,
|
|
"num_tokens": 36638792.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 5.50250654220581,
|
|
"epoch": 1.843600831133824,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00046680731674268744,
|
|
"loss": 5.1166,
|
|
"mean_token_accuracy": 0.2120824784040451,
|
|
"num_tokens": 36650218.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 5.504008388519287,
|
|
"epoch": 1.8441624080417813,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004667863253524692,
|
|
"loss": 5.1004,
|
|
"mean_token_accuracy": 0.209670090675354,
|
|
"num_tokens": 36660987.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 5.484678792953491,
|
|
"epoch": 1.8447239849497388,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046676532785569995,
|
|
"loss": 5.0644,
|
|
"mean_token_accuracy": 0.2035755068063736,
|
|
"num_tokens": 36671270.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 5.462496709823609,
|
|
"epoch": 1.8452855618576964,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004667443242530484,
|
|
"loss": 5.0715,
|
|
"mean_token_accuracy": 0.21600109189748765,
|
|
"num_tokens": 36682484.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 5.52449951171875,
|
|
"epoch": 1.845847138765654,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046672331454518314,
|
|
"loss": 5.1472,
|
|
"mean_token_accuracy": 0.21022522151470185,
|
|
"num_tokens": 36693723.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 5.423861646652222,
|
|
"epoch": 1.8464087156736115,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004667022987327732,
|
|
"loss": 4.9707,
|
|
"mean_token_accuracy": 0.2191660761833191,
|
|
"num_tokens": 36704166.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 5.442873620986939,
|
|
"epoch": 1.846970292581569,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004666812768164877,
|
|
"loss": 5.0316,
|
|
"mean_token_accuracy": 0.2140076130628586,
|
|
"num_tokens": 36714139.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 5.5038642406463625,
|
|
"epoch": 1.8475318694895266,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046666024879699606,
|
|
"loss": 5.0678,
|
|
"mean_token_accuracy": 0.21221577227115632,
|
|
"num_tokens": 36724273.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 5.505935382843018,
|
|
"epoch": 1.8480934463974843,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046663921467496766,
|
|
"loss": 5.132,
|
|
"mean_token_accuracy": 0.20436228066682816,
|
|
"num_tokens": 36735176.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 5.422377729415894,
|
|
"epoch": 1.8486550233054415,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004666181744510724,
|
|
"loss": 5.0635,
|
|
"mean_token_accuracy": 0.21245591342449188,
|
|
"num_tokens": 36746170.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 5.571506643295288,
|
|
"epoch": 1.8492166002133992,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046659712812598017,
|
|
"loss": 5.2286,
|
|
"mean_token_accuracy": 0.20462593734264373,
|
|
"num_tokens": 36756969.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 5.593419694900513,
|
|
"epoch": 1.8497781771213568,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00046657607570036103,
|
|
"loss": 5.0746,
|
|
"mean_token_accuracy": 0.21414605677127838,
|
|
"num_tokens": 36767892.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 5.501107597351075,
|
|
"epoch": 1.8503397540293143,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046655501717488533,
|
|
"loss": 5.0969,
|
|
"mean_token_accuracy": 0.21075148731470109,
|
|
"num_tokens": 36778967.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 5.370328617095947,
|
|
"epoch": 1.8509013309372717,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004665339525502236,
|
|
"loss": 4.9641,
|
|
"mean_token_accuracy": 0.2118169277906418,
|
|
"num_tokens": 36789204.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 5.4745416164398195,
|
|
"epoch": 1.8514629078452294,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046651288182704653,
|
|
"loss": 5.0244,
|
|
"mean_token_accuracy": 0.21928381621837617,
|
|
"num_tokens": 36798990.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 5.554029130935669,
|
|
"epoch": 1.852024484753187,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004664918050060251,
|
|
"loss": 5.138,
|
|
"mean_token_accuracy": 0.2112487867474556,
|
|
"num_tokens": 36809988.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 5.463080310821534,
|
|
"epoch": 1.8525860616611445,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004664707220878302,
|
|
"loss": 5.0762,
|
|
"mean_token_accuracy": 0.21656173020601271,
|
|
"num_tokens": 36821579.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 5.562678432464599,
|
|
"epoch": 1.853147638569102,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004664496330731334,
|
|
"loss": 5.1856,
|
|
"mean_token_accuracy": 0.21041040867567062,
|
|
"num_tokens": 36833141.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 5.543489265441894,
|
|
"epoch": 1.8537092154770596,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004664285379626059,
|
|
"loss": 5.1787,
|
|
"mean_token_accuracy": 0.21282510459423065,
|
|
"num_tokens": 36843347.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 5.5333380699157715,
|
|
"epoch": 1.8542707923850172,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00046640743675691954,
|
|
"loss": 5.2258,
|
|
"mean_token_accuracy": 0.1979595437645912,
|
|
"num_tokens": 36854459.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 5.4644242286682125,
|
|
"epoch": 1.8548323692929747,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004663863294567462,
|
|
"loss": 4.9406,
|
|
"mean_token_accuracy": 0.21523868292570114,
|
|
"num_tokens": 36864761.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 5.611645174026489,
|
|
"epoch": 1.8553939462009321,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004663652160627579,
|
|
"loss": 5.2336,
|
|
"mean_token_accuracy": 0.2005768299102783,
|
|
"num_tokens": 36875413.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 5.497026681900024,
|
|
"epoch": 1.8559555231088898,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046634409657562683,
|
|
"loss": 5.1201,
|
|
"mean_token_accuracy": 0.20424643754959107,
|
|
"num_tokens": 36885350.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 5.477964973449707,
|
|
"epoch": 1.8565171000168474,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004663229709960255,
|
|
"loss": 5.0174,
|
|
"mean_token_accuracy": 0.21442075818777084,
|
|
"num_tokens": 36895355.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 5.558397912979126,
|
|
"epoch": 1.8570786769248049,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046630183932462664,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.21687323451042176,
|
|
"num_tokens": 36907454.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 5.508376884460449,
|
|
"epoch": 1.8576402538327623,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004662807015621031,
|
|
"loss": 5.1136,
|
|
"mean_token_accuracy": 0.20426612347364426,
|
|
"num_tokens": 36919199.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 5.569764471054077,
|
|
"epoch": 1.85820183074072,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046625955770912764,
|
|
"loss": 5.2022,
|
|
"mean_token_accuracy": 0.2058103322982788,
|
|
"num_tokens": 36930499.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 5.491767454147339,
|
|
"epoch": 1.8587634076486776,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00046623840776637384,
|
|
"loss": 5.1276,
|
|
"mean_token_accuracy": 0.2030834972858429,
|
|
"num_tokens": 36943082.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 5.467373514175415,
|
|
"epoch": 1.859324984556635,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004662172517345149,
|
|
"loss": 5.0311,
|
|
"mean_token_accuracy": 0.2111891523003578,
|
|
"num_tokens": 36954591.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 5.481186199188232,
|
|
"epoch": 1.8598865614645925,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004661960896142245,
|
|
"loss": 5.1174,
|
|
"mean_token_accuracy": 0.21151324659585952,
|
|
"num_tokens": 36967028.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 5.484088325500489,
|
|
"epoch": 1.8604481383725502,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046617492140617654,
|
|
"loss": 5.1595,
|
|
"mean_token_accuracy": 0.20402714759111404,
|
|
"num_tokens": 36978716.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 5.447563600540161,
|
|
"epoch": 1.8610097152805076,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004661537471110448,
|
|
"loss": 5.0359,
|
|
"mean_token_accuracy": 0.2113659292459488,
|
|
"num_tokens": 36989416.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 5.493163204193115,
|
|
"epoch": 1.861571292188465,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004661325667295037,
|
|
"loss": 5.0867,
|
|
"mean_token_accuracy": 0.21947369277477263,
|
|
"num_tokens": 37002197.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 5.635228061676026,
|
|
"epoch": 1.8621328690964227,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004661113802622275,
|
|
"loss": 5.1967,
|
|
"mean_token_accuracy": 0.19943866431713103,
|
|
"num_tokens": 37012977.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 5.492608690261841,
|
|
"epoch": 1.8626944460043804,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004660901877098908,
|
|
"loss": 5.107,
|
|
"mean_token_accuracy": 0.20855230540037156,
|
|
"num_tokens": 37024141.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 5.475650882720947,
|
|
"epoch": 1.8632560229123378,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004660689890731685,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.21789149492979049,
|
|
"num_tokens": 37034471.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 5.519156265258789,
|
|
"epoch": 1.8638175998202953,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046604778435273546,
|
|
"loss": 5.0897,
|
|
"mean_token_accuracy": 0.2132817506790161,
|
|
"num_tokens": 37046375.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 5.50539608001709,
|
|
"epoch": 1.864379176728253,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046602657354926686,
|
|
"loss": 5.1191,
|
|
"mean_token_accuracy": 0.2123912066221237,
|
|
"num_tokens": 37056617.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 5.383263063430786,
|
|
"epoch": 1.8649407536362106,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000466005356663438,
|
|
"loss": 4.9568,
|
|
"mean_token_accuracy": 0.21887307614088058,
|
|
"num_tokens": 37066477.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 5.4798565864562985,
|
|
"epoch": 1.865502330544168,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046598413369592463,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.2076435551047325,
|
|
"num_tokens": 37077150.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 5.545440149307251,
|
|
"epoch": 1.8660639074521255,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004659629046474023,
|
|
"loss": 5.1636,
|
|
"mean_token_accuracy": 0.21037871688604354,
|
|
"num_tokens": 37089961.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 5.560234498977661,
|
|
"epoch": 1.8666254843600831,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000465941669518547,
|
|
"loss": 5.1731,
|
|
"mean_token_accuracy": 0.20456912517547607,
|
|
"num_tokens": 37100779.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 5.486607885360717,
|
|
"epoch": 1.8671870612680408,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004659204283100349,
|
|
"loss": 5.0331,
|
|
"mean_token_accuracy": 0.2115027442574501,
|
|
"num_tokens": 37111293.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 5.506576585769653,
|
|
"epoch": 1.8677486381759982,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046589918102254237,
|
|
"loss": 5.1206,
|
|
"mean_token_accuracy": 0.20869044959545135,
|
|
"num_tokens": 37123087.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 5.51568078994751,
|
|
"epoch": 1.8683102150839557,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004658779276567458,
|
|
"loss": 5.1069,
|
|
"mean_token_accuracy": 0.21024658381938935,
|
|
"num_tokens": 37135227.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 5.507825756072998,
|
|
"epoch": 1.8688717919919133,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046585666821332203,
|
|
"loss": 5.0779,
|
|
"mean_token_accuracy": 0.21268498301506042,
|
|
"num_tokens": 37146970.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 5.528319787979126,
|
|
"epoch": 1.869433368899871,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00046583540269294794,
|
|
"loss": 5.0871,
|
|
"mean_token_accuracy": 0.20527649372816087,
|
|
"num_tokens": 37158144.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 5.54538927078247,
|
|
"epoch": 1.8699949458078284,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004658141310963006,
|
|
"loss": 5.1933,
|
|
"mean_token_accuracy": 0.206640787422657,
|
|
"num_tokens": 37169265.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 5.535696029663086,
|
|
"epoch": 1.8705565227157859,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004657928534240573,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.20693681091070176,
|
|
"num_tokens": 37179186.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 5.588586902618408,
|
|
"epoch": 1.8711180996237435,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004657715696768955,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.2120760276913643,
|
|
"num_tokens": 37188906.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 5.452589893341065,
|
|
"epoch": 1.871679676531701,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000465750279855493,
|
|
"loss": 5.0178,
|
|
"mean_token_accuracy": 0.2205213263630867,
|
|
"num_tokens": 37200879.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 5.486661577224732,
|
|
"epoch": 1.8722412534396584,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004657289839605276,
|
|
"loss": 5.0272,
|
|
"mean_token_accuracy": 0.21644734889268874,
|
|
"num_tokens": 37211648.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 5.582305097579956,
|
|
"epoch": 1.872802830347616,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004657076819926774,
|
|
"loss": 5.2132,
|
|
"mean_token_accuracy": 0.21304583102464675,
|
|
"num_tokens": 37223164.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 5.517575216293335,
|
|
"epoch": 1.8733644072555737,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004656863739526206,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.20865258276462556,
|
|
"num_tokens": 37233860.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 5.565133047103882,
|
|
"epoch": 1.8739259841635312,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00046566505984103575,
|
|
"loss": 5.0521,
|
|
"mean_token_accuracy": 0.2139038026332855,
|
|
"num_tokens": 37245431.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 5.549070358276367,
|
|
"epoch": 1.8744875610714886,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004656437396586014,
|
|
"loss": 5.1869,
|
|
"mean_token_accuracy": 0.20393299609422683,
|
|
"num_tokens": 37256394.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 5.483378124237061,
|
|
"epoch": 1.8750491379794463,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004656224134059964,
|
|
"loss": 5.1557,
|
|
"mean_token_accuracy": 0.20865960270166398,
|
|
"num_tokens": 37268367.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 5.519014883041382,
|
|
"epoch": 1.875610714887404,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046560108108389985,
|
|
"loss": 5.1298,
|
|
"mean_token_accuracy": 0.21005660891532899,
|
|
"num_tokens": 37279019.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 5.55357871055603,
|
|
"epoch": 1.8761722917953614,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000465579742692991,
|
|
"loss": 5.0523,
|
|
"mean_token_accuracy": 0.2132042810320854,
|
|
"num_tokens": 37289806.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 5.420429039001465,
|
|
"epoch": 1.8767338687033188,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004655583982339492,
|
|
"loss": 5.1031,
|
|
"mean_token_accuracy": 0.20848310440778733,
|
|
"num_tokens": 37300607.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 5.4932701587677,
|
|
"epoch": 1.8772954456112765,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004655370477074541,
|
|
"loss": 5.1656,
|
|
"mean_token_accuracy": 0.20755331814289094,
|
|
"num_tokens": 37311966.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 5.414129447937012,
|
|
"epoch": 1.8778570225192341,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004655156911141855,
|
|
"loss": 5.0849,
|
|
"mean_token_accuracy": 0.21028892397880555,
|
|
"num_tokens": 37324459.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 5.528072500228882,
|
|
"epoch": 1.8784185994271916,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004654943284548234,
|
|
"loss": 5.0823,
|
|
"mean_token_accuracy": 0.20873494893312455,
|
|
"num_tokens": 37335276.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 5.498196125030518,
|
|
"epoch": 1.878980176335149,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046547295973004807,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.21564596891403198,
|
|
"num_tokens": 37347274.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 5.469661903381348,
|
|
"epoch": 1.8795417532431067,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046545158494053966,
|
|
"loss": 5.1333,
|
|
"mean_token_accuracy": 0.20145306140184402,
|
|
"num_tokens": 37359789.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 5.505513286590576,
|
|
"epoch": 1.8801033301510643,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046543020408697905,
|
|
"loss": 5.0895,
|
|
"mean_token_accuracy": 0.21216436326503754,
|
|
"num_tokens": 37369851.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 5.58355827331543,
|
|
"epoch": 1.8806649070590218,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046540881717004685,
|
|
"loss": 5.2496,
|
|
"mean_token_accuracy": 0.2018754482269287,
|
|
"num_tokens": 37381008.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 5.463074588775635,
|
|
"epoch": 1.8812264839669792,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004653874241904241,
|
|
"loss": 5.0948,
|
|
"mean_token_accuracy": 0.20884383767843245,
|
|
"num_tokens": 37392110.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 5.530291032791138,
|
|
"epoch": 1.8817880608749369,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004653660251487919,
|
|
"loss": 5.0907,
|
|
"mean_token_accuracy": 0.2167768210172653,
|
|
"num_tokens": 37402995.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 5.522855472564697,
|
|
"epoch": 1.8823496377828943,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046534462004583154,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.2122217521071434,
|
|
"num_tokens": 37415072.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 5.578861284255981,
|
|
"epoch": 1.8829112146908518,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004653232088822248,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.196064293384552,
|
|
"num_tokens": 37427375.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 5.420341682434082,
|
|
"epoch": 1.8834727915988094,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004653017916586532,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.21561141759157182,
|
|
"num_tokens": 37436829.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 5.523181486129761,
|
|
"epoch": 1.884034368506767,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004652803683757987,
|
|
"loss": 5.1476,
|
|
"mean_token_accuracy": 0.19952462166547774,
|
|
"num_tokens": 37447875.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 5.442384910583496,
|
|
"epoch": 1.8845959454147245,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004652589390343436,
|
|
"loss": 5.0263,
|
|
"mean_token_accuracy": 0.21096417605876921,
|
|
"num_tokens": 37458408.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 5.465321254730225,
|
|
"epoch": 1.885157522322682,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046523750363497,
|
|
"loss": 5.0932,
|
|
"mean_token_accuracy": 0.20720913559198378,
|
|
"num_tokens": 37468437.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 5.572143793106079,
|
|
"epoch": 1.8857190992306396,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004652160621783605,
|
|
"loss": 5.1715,
|
|
"mean_token_accuracy": 0.20912869423627853,
|
|
"num_tokens": 37479359.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 5.463993740081787,
|
|
"epoch": 1.8862806761385973,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046519461466519785,
|
|
"loss": 5.0873,
|
|
"mean_token_accuracy": 0.21512609273195266,
|
|
"num_tokens": 37491321.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 5.549176549911499,
|
|
"epoch": 1.8868422530465547,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004651731610961649,
|
|
"loss": 5.0916,
|
|
"mean_token_accuracy": 0.21092260330915452,
|
|
"num_tokens": 37501828.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 5.613136863708496,
|
|
"epoch": 1.8874038299545122,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004651517014719446,
|
|
"loss": 5.2364,
|
|
"mean_token_accuracy": 0.20484791845083236,
|
|
"num_tokens": 37514525.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 5.514158487319946,
|
|
"epoch": 1.8879654068624698,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004651302357932206,
|
|
"loss": 5.035,
|
|
"mean_token_accuracy": 0.20797241926193238,
|
|
"num_tokens": 37525588.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 5.467323303222656,
|
|
"epoch": 1.8885269837704275,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000465108764060676,
|
|
"loss": 5.0659,
|
|
"mean_token_accuracy": 0.21335967779159545,
|
|
"num_tokens": 37537941.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 5.5093378067016605,
|
|
"epoch": 1.889088560678385,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046508728627499464,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.20967621803283693,
|
|
"num_tokens": 37549663.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 5.563655233383178,
|
|
"epoch": 1.8896501375863424,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004650658024368604,
|
|
"loss": 5.1653,
|
|
"mean_token_accuracy": 0.21119212955236435,
|
|
"num_tokens": 37559793.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 5.479906988143921,
|
|
"epoch": 1.8902117144943,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004650443125469573,
|
|
"loss": 5.0316,
|
|
"mean_token_accuracy": 0.21199899017810822,
|
|
"num_tokens": 37570203.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 5.43759937286377,
|
|
"epoch": 1.8907732914022577,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004650228166059695,
|
|
"loss": 5.1249,
|
|
"mean_token_accuracy": 0.21079009026288986,
|
|
"num_tokens": 37581858.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 5.470770835876465,
|
|
"epoch": 1.8913348683102151,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004650013146145816,
|
|
"loss": 5.0701,
|
|
"mean_token_accuracy": 0.2109155386686325,
|
|
"num_tokens": 37592311.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 5.594961833953858,
|
|
"epoch": 1.8918964452181726,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004649798065734781,
|
|
"loss": 5.2281,
|
|
"mean_token_accuracy": 0.20618222951889037,
|
|
"num_tokens": 37604721.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 5.6119483470916744,
|
|
"epoch": 1.8924580221261302,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046495829248334393,
|
|
"loss": 5.2977,
|
|
"mean_token_accuracy": 0.2009274885058403,
|
|
"num_tokens": 37616044.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 5.494494915008545,
|
|
"epoch": 1.8930195990340877,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004649367723448641,
|
|
"loss": 5.1662,
|
|
"mean_token_accuracy": 0.21000045388936997,
|
|
"num_tokens": 37626501.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 5.579296350479126,
|
|
"epoch": 1.8935811759420451,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046491524615872366,
|
|
"loss": 5.1485,
|
|
"mean_token_accuracy": 0.2096484810113907,
|
|
"num_tokens": 37637861.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 5.455595636367798,
|
|
"epoch": 1.8941427528500028,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046489371392560816,
|
|
"loss": 5.002,
|
|
"mean_token_accuracy": 0.21168086528778077,
|
|
"num_tokens": 37649288.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 5.422808980941772,
|
|
"epoch": 1.8947043297579604,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046487217564620317,
|
|
"loss": 5.0133,
|
|
"mean_token_accuracy": 0.21992223411798478,
|
|
"num_tokens": 37659700.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 5.500381565093994,
|
|
"epoch": 1.8952659066659179,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004648506313211945,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.20493011325597763,
|
|
"num_tokens": 37671739.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 5.544111347198486,
|
|
"epoch": 1.8958274835738753,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046482908095126803,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.22107810527086258,
|
|
"num_tokens": 37682250.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 5.484669542312622,
|
|
"epoch": 1.896389060481833,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046480752453711,
|
|
"loss": 5.1283,
|
|
"mean_token_accuracy": 0.21625462025403977,
|
|
"num_tokens": 37694052.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 5.5489319324493405,
|
|
"epoch": 1.8969506373897906,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004647859620794068,
|
|
"loss": 5.173,
|
|
"mean_token_accuracy": 0.21634069830179214,
|
|
"num_tokens": 37704818.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 5.605900812149048,
|
|
"epoch": 1.897512214297748,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046476439357884497,
|
|
"loss": 5.2306,
|
|
"mean_token_accuracy": 0.20108183324337006,
|
|
"num_tokens": 37717679.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 5.4793174266815186,
|
|
"epoch": 1.8980737912057055,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046474281903611126,
|
|
"loss": 5.0801,
|
|
"mean_token_accuracy": 0.20846800059080123,
|
|
"num_tokens": 37728711.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 5.512612533569336,
|
|
"epoch": 1.8986353681136632,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046472123845189253,
|
|
"loss": 5.0856,
|
|
"mean_token_accuracy": 0.21195953339338303,
|
|
"num_tokens": 37740082.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 5.580585861206055,
|
|
"epoch": 1.8991969450216208,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000464699651826876,
|
|
"loss": 5.204,
|
|
"mean_token_accuracy": 0.20177604258060455,
|
|
"num_tokens": 37750715.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 5.51938829421997,
|
|
"epoch": 1.8997585219295783,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00046467805916174907,
|
|
"loss": 5.1692,
|
|
"mean_token_accuracy": 0.20542775988578796,
|
|
"num_tokens": 37763230.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 5.488376808166504,
|
|
"epoch": 1.9003200988375357,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046465646045719915,
|
|
"loss": 5.0611,
|
|
"mean_token_accuracy": 0.20421547889709474,
|
|
"num_tokens": 37773621.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 5.543055629730224,
|
|
"epoch": 1.9008816757454934,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004646348557139139,
|
|
"loss": 5.1444,
|
|
"mean_token_accuracy": 0.20714546144008636,
|
|
"num_tokens": 37785068.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 5.5287432193756105,
|
|
"epoch": 1.901443252653451,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00046461324493258133,
|
|
"loss": 5.138,
|
|
"mean_token_accuracy": 0.2144142910838127,
|
|
"num_tokens": 37796925.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 5.471051931381226,
|
|
"epoch": 1.9020048295614085,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046459162811388955,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.20846734642982484,
|
|
"num_tokens": 37808291.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 5.430331563949585,
|
|
"epoch": 1.902566406469366,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004645700052585267,
|
|
"loss": 4.9932,
|
|
"mean_token_accuracy": 0.2222292333841324,
|
|
"num_tokens": 37819337.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 5.538673162460327,
|
|
"epoch": 1.9031279833773236,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004645483763671815,
|
|
"loss": 5.1737,
|
|
"mean_token_accuracy": 0.2089215874671936,
|
|
"num_tokens": 37831832.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 5.53937611579895,
|
|
"epoch": 1.903689560285281,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046452674144054236,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.20860581248998641,
|
|
"num_tokens": 37842586.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 5.490165376663208,
|
|
"epoch": 1.9042511371932385,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046450510047929826,
|
|
"loss": 5.0319,
|
|
"mean_token_accuracy": 0.22052785456180574,
|
|
"num_tokens": 37852198.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 5.49484486579895,
|
|
"epoch": 1.9048127141011961,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046448345348413833,
|
|
"loss": 5.0825,
|
|
"mean_token_accuracy": 0.21098519414663314,
|
|
"num_tokens": 37862967.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 5.492881011962891,
|
|
"epoch": 1.9053742910091538,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004644618004557517,
|
|
"loss": 5.2105,
|
|
"mean_token_accuracy": 0.19650280177593232,
|
|
"num_tokens": 37874501.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 5.462063789367676,
|
|
"epoch": 1.9059358679171112,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004644401413948279,
|
|
"loss": 4.9767,
|
|
"mean_token_accuracy": 0.2200288638472557,
|
|
"num_tokens": 37886404.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 5.571914911270142,
|
|
"epoch": 1.9064974448250687,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004644184763020565,
|
|
"loss": 5.1889,
|
|
"mean_token_accuracy": 0.2027203232049942,
|
|
"num_tokens": 37897344.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 5.448255729675293,
|
|
"epoch": 1.9070590217330263,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004643968051781273,
|
|
"loss": 5.0247,
|
|
"mean_token_accuracy": 0.22057299613952636,
|
|
"num_tokens": 37909226.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 5.535170078277588,
|
|
"epoch": 1.907620598640984,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004643751280237305,
|
|
"loss": 5.1534,
|
|
"mean_token_accuracy": 0.20810251981019973,
|
|
"num_tokens": 37920578.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 5.549870586395263,
|
|
"epoch": 1.9081821755489414,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004643534448395561,
|
|
"loss": 5.0559,
|
|
"mean_token_accuracy": 0.20492344945669175,
|
|
"num_tokens": 37931814.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 5.491148042678833,
|
|
"epoch": 1.9087437524568989,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004643317556262946,
|
|
"loss": 5.0791,
|
|
"mean_token_accuracy": 0.2090654417872429,
|
|
"num_tokens": 37942345.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 5.4702905178070065,
|
|
"epoch": 1.9093053293648565,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046431006038463653,
|
|
"loss": 4.9955,
|
|
"mean_token_accuracy": 0.21522418707609176,
|
|
"num_tokens": 37953027.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 5.531443023681641,
|
|
"epoch": 1.9098669062728142,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004642883591152727,
|
|
"loss": 5.1328,
|
|
"mean_token_accuracy": 0.20836733728647233,
|
|
"num_tokens": 37963290.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 5.513917016983032,
|
|
"epoch": 1.9104284831807716,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004642666518188942,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.20172259211540222,
|
|
"num_tokens": 37974424.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 5.614091968536377,
|
|
"epoch": 1.910990060088729,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00046424493849619205,
|
|
"loss": 5.2333,
|
|
"mean_token_accuracy": 0.20718204081058503,
|
|
"num_tokens": 37987993.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 5.542656326293946,
|
|
"epoch": 1.9115516369966867,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046422321914785757,
|
|
"loss": 5.0122,
|
|
"mean_token_accuracy": 0.21496725380420684,
|
|
"num_tokens": 37999340.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 5.477643394470215,
|
|
"epoch": 1.9121132139046444,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00046420149377458255,
|
|
"loss": 5.0751,
|
|
"mean_token_accuracy": 0.20814482122659683,
|
|
"num_tokens": 38009737.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 5.489460563659668,
|
|
"epoch": 1.9126747908126018,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00046417976237705846,
|
|
"loss": 5.0735,
|
|
"mean_token_accuracy": 0.20965756326913834,
|
|
"num_tokens": 38021283.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 5.635855054855346,
|
|
"epoch": 1.9132363677205593,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046415802495597744,
|
|
"loss": 5.2081,
|
|
"mean_token_accuracy": 0.2019257128238678,
|
|
"num_tokens": 38034044.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 5.49278507232666,
|
|
"epoch": 1.913797944628517,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046413628151203154,
|
|
"loss": 5.0624,
|
|
"mean_token_accuracy": 0.21443053781986238,
|
|
"num_tokens": 38044585.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 5.431963920593262,
|
|
"epoch": 1.9143595215364744,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046411453204591303,
|
|
"loss": 5.0313,
|
|
"mean_token_accuracy": 0.21053629964590073,
|
|
"num_tokens": 38055771.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 5.468029403686524,
|
|
"epoch": 1.9149210984444318,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046409277655831455,
|
|
"loss": 5.102,
|
|
"mean_token_accuracy": 0.20692533850669861,
|
|
"num_tokens": 38066344.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 5.509651517868042,
|
|
"epoch": 1.9154826753523895,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004640710150499287,
|
|
"loss": 5.0471,
|
|
"mean_token_accuracy": 0.2124193713068962,
|
|
"num_tokens": 38077785.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 5.486874103546143,
|
|
"epoch": 1.9160442522603471,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00046404924752144834,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.20800398886203766,
|
|
"num_tokens": 38089023.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 5.517941474914551,
|
|
"epoch": 1.9166058291683046,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00046402747397356666,
|
|
"loss": 4.9997,
|
|
"mean_token_accuracy": 0.2164747402071953,
|
|
"num_tokens": 38099428.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 5.440216398239135,
|
|
"epoch": 1.917167406076262,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004640056944069768,
|
|
"loss": 5.0234,
|
|
"mean_token_accuracy": 0.21029316484928132,
|
|
"num_tokens": 38110757.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 5.529173088073731,
|
|
"epoch": 1.9177289829842197,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004639839088223725,
|
|
"loss": 5.1115,
|
|
"mean_token_accuracy": 0.20887204855680466,
|
|
"num_tokens": 38121442.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 5.526953315734863,
|
|
"epoch": 1.9182905598921773,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046396211722044716,
|
|
"loss": 5.0814,
|
|
"mean_token_accuracy": 0.2084110200405121,
|
|
"num_tokens": 38132917.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 5.43894248008728,
|
|
"epoch": 1.9188521368001348,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046394031960189473,
|
|
"loss": 5.0299,
|
|
"mean_token_accuracy": 0.2077005013823509,
|
|
"num_tokens": 38143188.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 5.601272678375244,
|
|
"epoch": 1.9194137137080922,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004639185159674093,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.2141815021634102,
|
|
"num_tokens": 38154300.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 5.543551874160767,
|
|
"epoch": 1.9199752906160499,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046389670631768494,
|
|
"loss": 5.195,
|
|
"mean_token_accuracy": 0.20772186368703843,
|
|
"num_tokens": 38165697.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 5.505008029937744,
|
|
"epoch": 1.9205368675240075,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004638748906534162,
|
|
"loss": 5.0932,
|
|
"mean_token_accuracy": 0.2104604259133339,
|
|
"num_tokens": 38176601.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 5.552993869781494,
|
|
"epoch": 1.921098444431965,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004638530689752977,
|
|
"loss": 5.1965,
|
|
"mean_token_accuracy": 0.2072519689798355,
|
|
"num_tokens": 38188334.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 5.571506690979004,
|
|
"epoch": 1.9216600213399224,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046383124128402433,
|
|
"loss": 5.1233,
|
|
"mean_token_accuracy": 0.21032475382089616,
|
|
"num_tokens": 38199483.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 5.543706893920898,
|
|
"epoch": 1.92222159824788,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046380940758029095,
|
|
"loss": 5.169,
|
|
"mean_token_accuracy": 0.20641636997461318,
|
|
"num_tokens": 38211391.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 5.511992883682251,
|
|
"epoch": 1.9227831751558377,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00046378756786479274,
|
|
"loss": 5.0808,
|
|
"mean_token_accuracy": 0.21290345638990402,
|
|
"num_tokens": 38223415.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 5.499290513992309,
|
|
"epoch": 1.9233447520637952,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004637657221382252,
|
|
"loss": 5.0374,
|
|
"mean_token_accuracy": 0.21650653183460236,
|
|
"num_tokens": 38235093.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 5.486071968078614,
|
|
"epoch": 1.9239063289717526,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00046374387040128384,
|
|
"loss": 5.1675,
|
|
"mean_token_accuracy": 0.2031059518456459,
|
|
"num_tokens": 38247192.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 5.556863594055176,
|
|
"epoch": 1.9244679058797103,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00046372201265466444,
|
|
"loss": 5.1282,
|
|
"mean_token_accuracy": 0.2048423707485199,
|
|
"num_tokens": 38257965.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 5.593494033813476,
|
|
"epoch": 1.9250294827876677,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000463700148899063,
|
|
"loss": 5.2313,
|
|
"mean_token_accuracy": 0.20051195621490478,
|
|
"num_tokens": 38268529.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 5.49454894065857,
|
|
"epoch": 1.9255910596956252,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004636782791351756,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.20805274248123168,
|
|
"num_tokens": 38279480.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 5.558289480209351,
|
|
"epoch": 1.9261526366035828,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004636564033636987,
|
|
"loss": 5.1723,
|
|
"mean_token_accuracy": 0.20879970192909242,
|
|
"num_tokens": 38291670.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 5.4374833583831785,
|
|
"epoch": 1.9267142135115405,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046363452158532857,
|
|
"loss": 4.9645,
|
|
"mean_token_accuracy": 0.22452065944671631,
|
|
"num_tokens": 38303073.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 5.55133285522461,
|
|
"epoch": 1.927275790419498,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004636126338007622,
|
|
"loss": 5.1136,
|
|
"mean_token_accuracy": 0.20449230670928956,
|
|
"num_tokens": 38313915.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 5.488015031814575,
|
|
"epoch": 1.9278373673274554,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004635907400106965,
|
|
"loss": 5.0869,
|
|
"mean_token_accuracy": 0.20664833337068558,
|
|
"num_tokens": 38324845.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 5.496645975112915,
|
|
"epoch": 1.928398944235413,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004635688402158285,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.21642663478851318,
|
|
"num_tokens": 38335096.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 5.5423304557800295,
|
|
"epoch": 1.9289605211433707,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046354693441685537,
|
|
"loss": 5.0771,
|
|
"mean_token_accuracy": 0.20953764468431474,
|
|
"num_tokens": 38345559.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 5.454735851287841,
|
|
"epoch": 1.9295220980513281,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046352502261447475,
|
|
"loss": 5.0179,
|
|
"mean_token_accuracy": 0.22581692785024643,
|
|
"num_tokens": 38356318.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 5.4991730690002445,
|
|
"epoch": 1.9300836749592856,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004635031048093843,
|
|
"loss": 5.0756,
|
|
"mean_token_accuracy": 0.21269574761390686,
|
|
"num_tokens": 38367246.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 5.50422101020813,
|
|
"epoch": 1.9306452518672432,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004634811810022819,
|
|
"loss": 5.0991,
|
|
"mean_token_accuracy": 0.20993321239948273,
|
|
"num_tokens": 38378767.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 5.511542892456054,
|
|
"epoch": 1.931206828775201,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046345925119386556,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.21711223125457763,
|
|
"num_tokens": 38390414.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 5.504837942123413,
|
|
"epoch": 1.9317684056831583,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004634373153848336,
|
|
"loss": 5.0552,
|
|
"mean_token_accuracy": 0.21715765595436096,
|
|
"num_tokens": 38401569.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 5.57008376121521,
|
|
"epoch": 1.9323299825911158,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004634153735758845,
|
|
"loss": 5.1973,
|
|
"mean_token_accuracy": 0.20708859115839004,
|
|
"num_tokens": 38413561.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 5.5646172046661375,
|
|
"epoch": 1.9328915594990734,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004633934257677167,
|
|
"loss": 5.1172,
|
|
"mean_token_accuracy": 0.2140567660331726,
|
|
"num_tokens": 38423965.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 5.485130405426025,
|
|
"epoch": 1.933453136407031,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004633714719610292,
|
|
"loss": 5.0442,
|
|
"mean_token_accuracy": 0.21017589420080185,
|
|
"num_tokens": 38434158.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 5.456086492538452,
|
|
"epoch": 1.9340147133149885,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046334951215652097,
|
|
"loss": 5.0743,
|
|
"mean_token_accuracy": 0.2119516596198082,
|
|
"num_tokens": 38445449.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 5.549007987976074,
|
|
"epoch": 1.934576290222946,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046332754635489126,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.20987604409456254,
|
|
"num_tokens": 38457601.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 5.514615774154663,
|
|
"epoch": 1.9351378671309036,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004633055745568394,
|
|
"loss": 5.0637,
|
|
"mean_token_accuracy": 0.2161819726228714,
|
|
"num_tokens": 38468631.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 5.4328948020935055,
|
|
"epoch": 1.935699444038861,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046328359676306506,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.21032307893037797,
|
|
"num_tokens": 38479567.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 5.459002304077148,
|
|
"epoch": 1.9362610209468185,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000463261612974268,
|
|
"loss": 5.0743,
|
|
"mean_token_accuracy": 0.21308864206075667,
|
|
"num_tokens": 38489934.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 5.614971017837524,
|
|
"epoch": 1.9368225978547762,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004632396231911481,
|
|
"loss": 5.2704,
|
|
"mean_token_accuracy": 0.20101860761642457,
|
|
"num_tokens": 38502214.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 5.559498596191406,
|
|
"epoch": 1.9373841747627338,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004632176274144056,
|
|
"loss": 5.0951,
|
|
"mean_token_accuracy": 0.20539983808994294,
|
|
"num_tokens": 38513915.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 5.499972009658814,
|
|
"epoch": 1.9379457516706913,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046319562564474083,
|
|
"loss": 5.0416,
|
|
"mean_token_accuracy": 0.21868704557418822,
|
|
"num_tokens": 38525039.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 5.4255469799041744,
|
|
"epoch": 1.9385073285786487,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00046317361788285436,
|
|
"loss": 5.0478,
|
|
"mean_token_accuracy": 0.21705400943756104,
|
|
"num_tokens": 38537264.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 5.50873908996582,
|
|
"epoch": 1.9390689054866064,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004631516041294469,
|
|
"loss": 5.1256,
|
|
"mean_token_accuracy": 0.21171692460775376,
|
|
"num_tokens": 38547926.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 5.533066987991333,
|
|
"epoch": 1.939630482394564,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004631295843852194,
|
|
"loss": 5.1168,
|
|
"mean_token_accuracy": 0.2153423473238945,
|
|
"num_tokens": 38558745.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 5.48057599067688,
|
|
"epoch": 1.9401920593025215,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000463107558650873,
|
|
"loss": 5.0598,
|
|
"mean_token_accuracy": 0.21696562319993973,
|
|
"num_tokens": 38568190.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 5.564253044128418,
|
|
"epoch": 1.940753636210479,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046308552692710895,
|
|
"loss": 5.1462,
|
|
"mean_token_accuracy": 0.20852722674608232,
|
|
"num_tokens": 38578932.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 5.5262538433074955,
|
|
"epoch": 1.9413152131184366,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046306348921462876,
|
|
"loss": 5.1237,
|
|
"mean_token_accuracy": 0.20576460808515548,
|
|
"num_tokens": 38590501.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 5.463390731811524,
|
|
"epoch": 1.9418767900263942,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004630414455141342,
|
|
"loss": 5.0371,
|
|
"mean_token_accuracy": 0.2190954715013504,
|
|
"num_tokens": 38600498.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 5.461698818206787,
|
|
"epoch": 1.9424383669343517,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000463019395826327,
|
|
"loss": 5.0287,
|
|
"mean_token_accuracy": 0.2127041131258011,
|
|
"num_tokens": 38611991.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 5.4473169326782225,
|
|
"epoch": 1.9429999438423091,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046299734015190934,
|
|
"loss": 5.0517,
|
|
"mean_token_accuracy": 0.21374461948871612,
|
|
"num_tokens": 38622284.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 5.520754480361939,
|
|
"epoch": 1.9435615207502668,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046297527849158344,
|
|
"loss": 5.1563,
|
|
"mean_token_accuracy": 0.2070332422852516,
|
|
"num_tokens": 38633777.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 5.554642200469971,
|
|
"epoch": 1.9441230976582244,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004629532108460519,
|
|
"loss": 5.1143,
|
|
"mean_token_accuracy": 0.20368158221244811,
|
|
"num_tokens": 38644360.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 5.466087102890015,
|
|
"epoch": 1.9446846745661819,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046293113721601706,
|
|
"loss": 5.1133,
|
|
"mean_token_accuracy": 0.21449712216854094,
|
|
"num_tokens": 38655242.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 5.512748861312867,
|
|
"epoch": 1.9452462514741393,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046290905760218193,
|
|
"loss": 4.9669,
|
|
"mean_token_accuracy": 0.2246527001261711,
|
|
"num_tokens": 38667792.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 5.441223621368408,
|
|
"epoch": 1.945807828382097,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046288697200524964,
|
|
"loss": 4.9934,
|
|
"mean_token_accuracy": 0.2176685616374016,
|
|
"num_tokens": 38677735.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 5.484303903579712,
|
|
"epoch": 1.9463694052900544,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046286488042592325,
|
|
"loss": 5.0774,
|
|
"mean_token_accuracy": 0.21318703293800353,
|
|
"num_tokens": 38689556.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 5.492072629928589,
|
|
"epoch": 1.9469309821980119,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004628427828649062,
|
|
"loss": 5.0996,
|
|
"mean_token_accuracy": 0.21750720739364623,
|
|
"num_tokens": 38700556.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 5.486243724822998,
|
|
"epoch": 1.9474925591059695,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046282067932290204,
|
|
"loss": 5.0731,
|
|
"mean_token_accuracy": 0.20691203474998474,
|
|
"num_tokens": 38711019.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 5.462958526611328,
|
|
"epoch": 1.9480541360139272,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004627985698006146,
|
|
"loss": 5.0865,
|
|
"mean_token_accuracy": 0.21032506078481675,
|
|
"num_tokens": 38722228.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 5.429541873931885,
|
|
"epoch": 1.9486157129218846,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000462776454298748,
|
|
"loss": 5.0052,
|
|
"mean_token_accuracy": 0.21790332794189454,
|
|
"num_tokens": 38732183.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 5.4275336265563965,
|
|
"epoch": 1.949177289829842,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046275433281800613,
|
|
"loss": 5.0003,
|
|
"mean_token_accuracy": 0.21502691954374314,
|
|
"num_tokens": 38743659.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 5.512891578674316,
|
|
"epoch": 1.9497388667377997,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004627322053590935,
|
|
"loss": 5.1499,
|
|
"mean_token_accuracy": 0.2083219036459923,
|
|
"num_tokens": 38755032.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 5.514606952667236,
|
|
"epoch": 1.9503004436457574,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004627100719227147,
|
|
"loss": 5.0539,
|
|
"mean_token_accuracy": 0.21565451472997665,
|
|
"num_tokens": 38766126.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 5.56097822189331,
|
|
"epoch": 1.9508620205537148,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046268793250957437,
|
|
"loss": 5.1852,
|
|
"mean_token_accuracy": 0.209283684194088,
|
|
"num_tokens": 38776921.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 5.459462976455688,
|
|
"epoch": 1.9514235974616723,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046266578712037747,
|
|
"loss": 5.067,
|
|
"mean_token_accuracy": 0.21421228498220443,
|
|
"num_tokens": 38788884.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 5.61196460723877,
|
|
"epoch": 1.95198517436963,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00046264363575582916,
|
|
"loss": 5.2128,
|
|
"mean_token_accuracy": 0.20367702692747117,
|
|
"num_tokens": 38800505.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 5.499144554138184,
|
|
"epoch": 1.9525467512775876,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004626214784166347,
|
|
"loss": 5.0021,
|
|
"mean_token_accuracy": 0.20915404707193375,
|
|
"num_tokens": 38811132.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 5.573312902450562,
|
|
"epoch": 1.953108328185545,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004625993151034995,
|
|
"loss": 5.1246,
|
|
"mean_token_accuracy": 0.21404734998941422,
|
|
"num_tokens": 38821349.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 5.511688709259033,
|
|
"epoch": 1.9536699050935025,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004625771458171294,
|
|
"loss": 5.1319,
|
|
"mean_token_accuracy": 0.20949177891016008,
|
|
"num_tokens": 38832970.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 5.458802509307861,
|
|
"epoch": 1.9542314820014601,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00046255497055823025,
|
|
"loss": 5.1095,
|
|
"mean_token_accuracy": 0.209658282995224,
|
|
"num_tokens": 38844220.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 5.480219030380249,
|
|
"epoch": 1.9547930589094178,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004625327893275082,
|
|
"loss": 5.0804,
|
|
"mean_token_accuracy": 0.20576697140932082,
|
|
"num_tokens": 38854848.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 5.52643232345581,
|
|
"epoch": 1.9553546358173752,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046251060212566927,
|
|
"loss": 5.2009,
|
|
"mean_token_accuracy": 0.20566636621952056,
|
|
"num_tokens": 38864827.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 5.531147289276123,
|
|
"epoch": 1.9559162127253327,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004624884089534201,
|
|
"loss": 5.047,
|
|
"mean_token_accuracy": 0.2071419432759285,
|
|
"num_tokens": 38875914.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 5.415796232223511,
|
|
"epoch": 1.9564777896332903,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004624662098114672,
|
|
"loss": 5.034,
|
|
"mean_token_accuracy": 0.2120719686150551,
|
|
"num_tokens": 38886565.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 5.53605375289917,
|
|
"epoch": 1.9570393665412478,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046244400470051754,
|
|
"loss": 5.2878,
|
|
"mean_token_accuracy": 0.1968618482351303,
|
|
"num_tokens": 38897319.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 5.488940906524658,
|
|
"epoch": 1.9576009434492052,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000462421793621278,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.21463557779788972,
|
|
"num_tokens": 38908824.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 5.5308998107910154,
|
|
"epoch": 1.9581625203571629,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000462399576574456,
|
|
"loss": 5.1367,
|
|
"mean_token_accuracy": 0.21122062504291533,
|
|
"num_tokens": 38921800.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 5.498126220703125,
|
|
"epoch": 1.9587240972651205,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004623773535607587,
|
|
"loss": 5.0839,
|
|
"mean_token_accuracy": 0.21036441177129744,
|
|
"num_tokens": 38932284.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 5.494027376174927,
|
|
"epoch": 1.959285674173078,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004623551245808938,
|
|
"loss": 5.0903,
|
|
"mean_token_accuracy": 0.21248753666877745,
|
|
"num_tokens": 38943632.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 5.493687105178833,
|
|
"epoch": 1.9598472510810354,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004623328896355691,
|
|
"loss": 5.0301,
|
|
"mean_token_accuracy": 0.21455607414245606,
|
|
"num_tokens": 38954701.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 5.5608988285064695,
|
|
"epoch": 1.960408827988993,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046231064872549244,
|
|
"loss": 5.1293,
|
|
"mean_token_accuracy": 0.2087258979678154,
|
|
"num_tokens": 38965625.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 5.513734006881714,
|
|
"epoch": 1.9609704048969507,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00046228840185137215,
|
|
"loss": 5.0706,
|
|
"mean_token_accuracy": 0.21236360520124437,
|
|
"num_tokens": 38976989.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 5.416563224792481,
|
|
"epoch": 1.9615319818049082,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004622661490139165,
|
|
"loss": 5.1203,
|
|
"mean_token_accuracy": 0.21698066741228103,
|
|
"num_tokens": 38987661.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 5.491742849349976,
|
|
"epoch": 1.9620935587128656,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004622438902138341,
|
|
"loss": 5.0934,
|
|
"mean_token_accuracy": 0.2114655703306198,
|
|
"num_tokens": 38998014.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 5.488398838043213,
|
|
"epoch": 1.9626551356208233,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00046222162545183357,
|
|
"loss": 5.0005,
|
|
"mean_token_accuracy": 0.21660214066505432,
|
|
"num_tokens": 39008843.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 5.524238061904907,
|
|
"epoch": 1.963216712528781,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046219935472862386,
|
|
"loss": 5.1436,
|
|
"mean_token_accuracy": 0.20438172817230224,
|
|
"num_tokens": 39020173.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 5.5069468975067135,
|
|
"epoch": 1.9637782894367384,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046217707804491404,
|
|
"loss": 5.1228,
|
|
"mean_token_accuracy": 0.2057792380452156,
|
|
"num_tokens": 39033087.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 5.581241750717163,
|
|
"epoch": 1.9643398663446958,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004621547954014135,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.21628159135580063,
|
|
"num_tokens": 39045252.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 5.54075984954834,
|
|
"epoch": 1.9649014432526535,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004621325067988317,
|
|
"loss": 5.2374,
|
|
"mean_token_accuracy": 0.20619835704565048,
|
|
"num_tokens": 39056755.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 5.461740446090698,
|
|
"epoch": 1.9654630201606111,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046211021223787827,
|
|
"loss": 5.0201,
|
|
"mean_token_accuracy": 0.21625028252601625,
|
|
"num_tokens": 39066993.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 5.463070344924927,
|
|
"epoch": 1.9660245970685686,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046208791171926315,
|
|
"loss": 5.0765,
|
|
"mean_token_accuracy": 0.21087120473384857,
|
|
"num_tokens": 39078671.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 5.555288648605346,
|
|
"epoch": 1.966586173976526,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046206560524369636,
|
|
"loss": 5.09,
|
|
"mean_token_accuracy": 0.2068958342075348,
|
|
"num_tokens": 39089563.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 5.609184217453003,
|
|
"epoch": 1.9671477508844837,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046204329281188816,
|
|
"loss": 5.147,
|
|
"mean_token_accuracy": 0.20618539601564406,
|
|
"num_tokens": 39099837.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 5.551881122589111,
|
|
"epoch": 1.9677093277924411,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004620209744245489,
|
|
"loss": 5.1504,
|
|
"mean_token_accuracy": 0.20492150634527206,
|
|
"num_tokens": 39112061.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 5.486149740219116,
|
|
"epoch": 1.9682709047003986,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046199865008238937,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.21601057946681976,
|
|
"num_tokens": 39122777.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 5.433051681518554,
|
|
"epoch": 1.9688324816083562,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004619763197861203,
|
|
"loss": 5.0473,
|
|
"mean_token_accuracy": 0.21456861793994902,
|
|
"num_tokens": 39134827.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 5.502239608764649,
|
|
"epoch": 1.9693940585163139,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046195398353645256,
|
|
"loss": 5.0982,
|
|
"mean_token_accuracy": 0.20950087457895278,
|
|
"num_tokens": 39144352.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 5.447834491729736,
|
|
"epoch": 1.9699556354242713,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004619316413340976,
|
|
"loss": 5.0262,
|
|
"mean_token_accuracy": 0.21413307189941405,
|
|
"num_tokens": 39155610.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 5.435008716583252,
|
|
"epoch": 1.9705172123322288,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00046190929317976664,
|
|
"loss": 5.0797,
|
|
"mean_token_accuracy": 0.21072807908058167,
|
|
"num_tokens": 39167058.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 5.5347373485565186,
|
|
"epoch": 1.9710787892401864,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004618869390741713,
|
|
"loss": 5.1895,
|
|
"mean_token_accuracy": 0.20344768166542054,
|
|
"num_tokens": 39178797.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 5.521516418457031,
|
|
"epoch": 1.971640366148144,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004618645790180233,
|
|
"loss": 5.0327,
|
|
"mean_token_accuracy": 0.2178642213344574,
|
|
"num_tokens": 39188980.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 5.476399850845337,
|
|
"epoch": 1.9722019430561015,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004618422130120347,
|
|
"loss": 5.0385,
|
|
"mean_token_accuracy": 0.20950965881347655,
|
|
"num_tokens": 39200058.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 5.456131839752198,
|
|
"epoch": 1.972763519964059,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004618198410569175,
|
|
"loss": 5.1211,
|
|
"mean_token_accuracy": 0.21067933589220048,
|
|
"num_tokens": 39211369.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 5.506629180908203,
|
|
"epoch": 1.9733250968720166,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046179746315338414,
|
|
"loss": 5.1673,
|
|
"mean_token_accuracy": 0.20458319783210754,
|
|
"num_tokens": 39222438.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 5.540224647521972,
|
|
"epoch": 1.9738866737799743,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00046177507930214714,
|
|
"loss": 5.1246,
|
|
"mean_token_accuracy": 0.20280339270830156,
|
|
"num_tokens": 39233047.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 5.501207304000855,
|
|
"epoch": 1.9744482506879317,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004617526895039191,
|
|
"loss": 5.0527,
|
|
"mean_token_accuracy": 0.21280987709760665,
|
|
"num_tokens": 39244547.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 5.5037909030914305,
|
|
"epoch": 1.9750098275958892,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046173029375941305,
|
|
"loss": 5.0183,
|
|
"mean_token_accuracy": 0.21062546819448472,
|
|
"num_tokens": 39255549.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 5.4590222358703615,
|
|
"epoch": 1.9755714045038468,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000461707892069342,
|
|
"loss": 4.9992,
|
|
"mean_token_accuracy": 0.21513874977827072,
|
|
"num_tokens": 39266527.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 5.474949550628662,
|
|
"epoch": 1.9761329814118045,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00046168548443441926,
|
|
"loss": 5.1033,
|
|
"mean_token_accuracy": 0.2163463920354843,
|
|
"num_tokens": 39278013.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 5.500087070465088,
|
|
"epoch": 1.976694558319762,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004616630708553583,
|
|
"loss": 5.0801,
|
|
"mean_token_accuracy": 0.2105663910508156,
|
|
"num_tokens": 39289349.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 5.458623790740967,
|
|
"epoch": 1.9772561352277194,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00046164065133287276,
|
|
"loss": 5.0581,
|
|
"mean_token_accuracy": 0.21383445262908934,
|
|
"num_tokens": 39301213.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 5.414368629455566,
|
|
"epoch": 1.977817712135677,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004616182258676765,
|
|
"loss": 4.9725,
|
|
"mean_token_accuracy": 0.2220798745751381,
|
|
"num_tokens": 39310960.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 5.5328442573547365,
|
|
"epoch": 1.9783792890436345,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004615957944604835,
|
|
"loss": 5.1227,
|
|
"mean_token_accuracy": 0.20953653007745743,
|
|
"num_tokens": 39322603.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 5.52403883934021,
|
|
"epoch": 1.978940865951592,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004615733571120081,
|
|
"loss": 5.0922,
|
|
"mean_token_accuracy": 0.21249038875102996,
|
|
"num_tokens": 39333811.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 5.5889006614685055,
|
|
"epoch": 1.9795024428595496,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004615509138229646,
|
|
"loss": 5.1141,
|
|
"mean_token_accuracy": 0.2104892373085022,
|
|
"num_tokens": 39345218.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 5.44272518157959,
|
|
"epoch": 1.9800640197675072,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00046152846459406765,
|
|
"loss": 4.9388,
|
|
"mean_token_accuracy": 0.21633495688438414,
|
|
"num_tokens": 39356777.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 5.400483083724976,
|
|
"epoch": 1.9806255966754647,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004615060094260321,
|
|
"loss": 5.0792,
|
|
"mean_token_accuracy": 0.20853884369134904,
|
|
"num_tokens": 39368288.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 5.54973258972168,
|
|
"epoch": 1.9811871735834221,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046148354831957285,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.21646516919136047,
|
|
"num_tokens": 39379398.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 5.458340120315552,
|
|
"epoch": 1.9817487504913798,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046146108127540506,
|
|
"loss": 5.0652,
|
|
"mean_token_accuracy": 0.21528061777353286,
|
|
"num_tokens": 39391129.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 5.505998659133911,
|
|
"epoch": 1.9823103273993374,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004614386082942442,
|
|
"loss": 5.1455,
|
|
"mean_token_accuracy": 0.20194572508335112,
|
|
"num_tokens": 39402442.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 5.587158727645874,
|
|
"epoch": 1.9828719043072949,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004614161293768057,
|
|
"loss": 5.1018,
|
|
"mean_token_accuracy": 0.2137361690402031,
|
|
"num_tokens": 39413044.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 5.512194681167602,
|
|
"epoch": 1.9834334812152523,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046139364452380536,
|
|
"loss": 5.0689,
|
|
"mean_token_accuracy": 0.21499471813440324,
|
|
"num_tokens": 39423739.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 5.518840885162353,
|
|
"epoch": 1.98399505812321,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000461371153735959,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.20920741260051728,
|
|
"num_tokens": 39436199.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 5.546721792221069,
|
|
"epoch": 1.9845566350311676,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00046134865701398287,
|
|
"loss": 5.0958,
|
|
"mean_token_accuracy": 0.2184235170483589,
|
|
"num_tokens": 39449302.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 5.5443761348724365,
|
|
"epoch": 1.985118211939125,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046132615435859326,
|
|
"loss": 5.127,
|
|
"mean_token_accuracy": 0.20702789574861527,
|
|
"num_tokens": 39460723.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 5.4941198348999025,
|
|
"epoch": 1.9856797888470825,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046130364577050655,
|
|
"loss": 5.0571,
|
|
"mean_token_accuracy": 0.2145622879266739,
|
|
"num_tokens": 39471251.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 5.514349174499512,
|
|
"epoch": 1.9862413657550402,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046128113125043957,
|
|
"loss": 5.0563,
|
|
"mean_token_accuracy": 0.21840719729661942,
|
|
"num_tokens": 39482613.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 5.493435478210449,
|
|
"epoch": 1.9868029426629978,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046125861079910913,
|
|
"loss": 5.087,
|
|
"mean_token_accuracy": 0.2208486169576645,
|
|
"num_tokens": 39494626.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 5.429390716552734,
|
|
"epoch": 1.9873645195709553,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004612360844172322,
|
|
"loss": 5.02,
|
|
"mean_token_accuracy": 0.2112290158867836,
|
|
"num_tokens": 39505302.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 5.4902407169342045,
|
|
"epoch": 1.9879260964789127,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046121355210552626,
|
|
"loss": 4.9823,
|
|
"mean_token_accuracy": 0.2135127902030945,
|
|
"num_tokens": 39515854.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 5.542556095123291,
|
|
"epoch": 1.9884876733868704,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004611910138647085,
|
|
"loss": 5.1687,
|
|
"mean_token_accuracy": 0.20248592495918274,
|
|
"num_tokens": 39527504.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 5.535033655166626,
|
|
"epoch": 1.989049250294828,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046116846969549666,
|
|
"loss": 5.058,
|
|
"mean_token_accuracy": 0.21445262730121611,
|
|
"num_tokens": 39538885.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 5.46994571685791,
|
|
"epoch": 1.9896108272027853,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004611459195986085,
|
|
"loss": 5.0519,
|
|
"mean_token_accuracy": 0.21494306921958922,
|
|
"num_tokens": 39549401.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 5.48551573753357,
|
|
"epoch": 1.990172404110743,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046112336357476217,
|
|
"loss": 5.1302,
|
|
"mean_token_accuracy": 0.2062358573079109,
|
|
"num_tokens": 39560814.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 5.503226613998413,
|
|
"epoch": 1.9907339810187006,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004611008016246757,
|
|
"loss": 5.0823,
|
|
"mean_token_accuracy": 0.20804405957460403,
|
|
"num_tokens": 39571490.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 5.4573742866516115,
|
|
"epoch": 1.991295557926658,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046107823374906754,
|
|
"loss": 5.0078,
|
|
"mean_token_accuracy": 0.21922310888767244,
|
|
"num_tokens": 39582815.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 5.509768152236939,
|
|
"epoch": 1.9918571348346155,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046105565994865614,
|
|
"loss": 5.0887,
|
|
"mean_token_accuracy": 0.21390316486358643,
|
|
"num_tokens": 39593712.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 5.499211645126342,
|
|
"epoch": 1.9924187117425731,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004610330802241605,
|
|
"loss": 5.0776,
|
|
"mean_token_accuracy": 0.21099428534507753,
|
|
"num_tokens": 39604504.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 5.499092245101929,
|
|
"epoch": 1.9929802886505308,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004610104945762994,
|
|
"loss": 5.0987,
|
|
"mean_token_accuracy": 0.21465860158205033,
|
|
"num_tokens": 39614971.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 5.5031129837036135,
|
|
"epoch": 1.9935418655584882,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000460987903005792,
|
|
"loss": 5.0477,
|
|
"mean_token_accuracy": 0.21754294335842134,
|
|
"num_tokens": 39626647.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 5.518901109695435,
|
|
"epoch": 1.9941034424664457,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004609653055133576,
|
|
"loss": 5.1586,
|
|
"mean_token_accuracy": 0.20872440040111542,
|
|
"num_tokens": 39636432.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 5.5340526580810545,
|
|
"epoch": 1.9946650193744033,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046094270209971576,
|
|
"loss": 5.0869,
|
|
"mean_token_accuracy": 0.2147448793053627,
|
|
"num_tokens": 39647055.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 5.534825611114502,
|
|
"epoch": 1.995226596282361,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004609200927655862,
|
|
"loss": 5.079,
|
|
"mean_token_accuracy": 0.21150288581848145,
|
|
"num_tokens": 39657891.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 5.4525188446044925,
|
|
"epoch": 1.9957881731903184,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004608974775116888,
|
|
"loss": 4.9584,
|
|
"mean_token_accuracy": 0.22385076135396959,
|
|
"num_tokens": 39668023.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 5.463602590560913,
|
|
"epoch": 1.9963497500982759,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004608748563387436,
|
|
"loss": 5.0909,
|
|
"mean_token_accuracy": 0.2162756472826004,
|
|
"num_tokens": 39678398.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 5.456797409057617,
|
|
"epoch": 1.9969113270062335,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004608522292474708,
|
|
"loss": 5.0804,
|
|
"mean_token_accuracy": 0.20805446803569794,
|
|
"num_tokens": 39690619.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 5.396885967254638,
|
|
"epoch": 1.9974729039141912,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004608295962385911,
|
|
"loss": 4.9976,
|
|
"mean_token_accuracy": 0.21658187210559846,
|
|
"num_tokens": 39701690.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 5.471135950088501,
|
|
"epoch": 1.9980344808221486,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046080695731282484,
|
|
"loss": 5.1418,
|
|
"mean_token_accuracy": 0.20364563763141633,
|
|
"num_tokens": 39713878.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 5.55912766456604,
|
|
"epoch": 1.998596057730106,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000460784312470893,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.21329856514930726,
|
|
"num_tokens": 39725164.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 5.487591648101807,
|
|
"epoch": 1.9991576346380637,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046076166171351673,
|
|
"loss": 5.0066,
|
|
"mean_token_accuracy": 0.2124040186405182,
|
|
"num_tokens": 39735354.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 5.567241048812866,
|
|
"epoch": 1.9997192115460214,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000460739005041417,
|
|
"loss": 5.1786,
|
|
"mean_token_accuracy": 0.20215678811073304,
|
|
"num_tokens": 39746618.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 5.5056837399800616,
|
|
"epoch": 2.000224630763183,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004607163424553153,
|
|
"loss": 5.1008,
|
|
"mean_token_accuracy": 0.2133440590567059,
|
|
"num_tokens": 39755697.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 5.430418491363525,
|
|
"epoch": 2.0007862076711405,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046069367395593325,
|
|
"loss": 5.0102,
|
|
"mean_token_accuracy": 0.2154828578233719,
|
|
"num_tokens": 39766311.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 5.548388433456421,
|
|
"epoch": 2.001347784579098,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004606709995439926,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.21145301163196564,
|
|
"num_tokens": 39777504.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 5.533293628692627,
|
|
"epoch": 2.001909361487056,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046064831922021534,
|
|
"loss": 4.9901,
|
|
"mean_token_accuracy": 0.2146280139684677,
|
|
"num_tokens": 39789190.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 5.466887331008911,
|
|
"epoch": 2.002470938395013,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004606256329853235,
|
|
"loss": 4.9923,
|
|
"mean_token_accuracy": 0.2125431478023529,
|
|
"num_tokens": 39801534.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 5.519063568115234,
|
|
"epoch": 2.0030325153029707,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004606029408400396,
|
|
"loss": 5.0209,
|
|
"mean_token_accuracy": 0.21773672103881836,
|
|
"num_tokens": 39812353.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 5.469810628890992,
|
|
"epoch": 2.0035940922109283,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004605802427850861,
|
|
"loss": 4.9285,
|
|
"mean_token_accuracy": 0.22153539210557938,
|
|
"num_tokens": 39823313.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 5.43530421257019,
|
|
"epoch": 2.004155669118886,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046055753882118564,
|
|
"loss": 4.9288,
|
|
"mean_token_accuracy": 0.2247951865196228,
|
|
"num_tokens": 39833966.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 5.499657249450683,
|
|
"epoch": 2.004717246026843,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004605348289490611,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.21671060621738433,
|
|
"num_tokens": 39843963.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 5.506442499160767,
|
|
"epoch": 2.005278822934801,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004605121131694358,
|
|
"loss": 5.0194,
|
|
"mean_token_accuracy": 0.21268052905797957,
|
|
"num_tokens": 39855237.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 5.545067882537841,
|
|
"epoch": 2.0058403998427585,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004604893914830328,
|
|
"loss": 5.1389,
|
|
"mean_token_accuracy": 0.21175451576709747,
|
|
"num_tokens": 39867270.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 5.583662652969361,
|
|
"epoch": 2.006401976750716,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046046666389057563,
|
|
"loss": 5.0497,
|
|
"mean_token_accuracy": 0.21966953277587892,
|
|
"num_tokens": 39878103.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 5.468788051605225,
|
|
"epoch": 2.0069635536586734,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000460443930392788,
|
|
"loss": 4.9848,
|
|
"mean_token_accuracy": 0.2135985389351845,
|
|
"num_tokens": 39888945.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 5.534671211242676,
|
|
"epoch": 2.007525130566631,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046042119099039367,
|
|
"loss": 5.1748,
|
|
"mean_token_accuracy": 0.2087427407503128,
|
|
"num_tokens": 39899848.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 5.524389171600342,
|
|
"epoch": 2.0080867074745887,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00046039844568411667,
|
|
"loss": 5.0287,
|
|
"mean_token_accuracy": 0.21321588903665542,
|
|
"num_tokens": 39911824.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 5.523957443237305,
|
|
"epoch": 2.0086482843825464,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004603756944746813,
|
|
"loss": 4.9831,
|
|
"mean_token_accuracy": 0.21783199310302734,
|
|
"num_tokens": 39923257.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 5.4722949981689455,
|
|
"epoch": 2.0092098612905036,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00046035293736281185,
|
|
"loss": 4.9452,
|
|
"mean_token_accuracy": 0.22077374905347824,
|
|
"num_tokens": 39935312.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 5.4918975830078125,
|
|
"epoch": 2.0097714381984613,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004603301743492331,
|
|
"loss": 4.9862,
|
|
"mean_token_accuracy": 0.21507604867219926,
|
|
"num_tokens": 39946468.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 5.362382125854492,
|
|
"epoch": 2.010333015106419,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004603074054346696,
|
|
"loss": 4.8501,
|
|
"mean_token_accuracy": 0.22720238268375398,
|
|
"num_tokens": 39957517.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 5.457093572616577,
|
|
"epoch": 2.0108945920143766,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004602846306198465,
|
|
"loss": 4.9916,
|
|
"mean_token_accuracy": 0.21380143463611603,
|
|
"num_tokens": 39968385.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 5.458067083358765,
|
|
"epoch": 2.011456168922334,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004602618499054889,
|
|
"loss": 4.932,
|
|
"mean_token_accuracy": 0.2189737692475319,
|
|
"num_tokens": 39979393.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 5.5300391674041744,
|
|
"epoch": 2.0120177458302915,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004602390632923221,
|
|
"loss": 5.0041,
|
|
"mean_token_accuracy": 0.21148758232593537,
|
|
"num_tokens": 39989709.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 5.511027097702026,
|
|
"epoch": 2.012579322738249,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046021627078107177,
|
|
"loss": 4.9337,
|
|
"mean_token_accuracy": 0.21188617795705794,
|
|
"num_tokens": 40000472.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 5.355703210830688,
|
|
"epoch": 2.0131408996462063,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046019347237246343,
|
|
"loss": 4.8423,
|
|
"mean_token_accuracy": 0.22474419474601745,
|
|
"num_tokens": 40011062.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 5.552822828292847,
|
|
"epoch": 2.013702476554164,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004601706680672232,
|
|
"loss": 5.1041,
|
|
"mean_token_accuracy": 0.20089901089668274,
|
|
"num_tokens": 40022430.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 5.460572147369385,
|
|
"epoch": 2.0142640534621217,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004601478578660771,
|
|
"loss": 4.9871,
|
|
"mean_token_accuracy": 0.2144003242254257,
|
|
"num_tokens": 40033077.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 5.531789493560791,
|
|
"epoch": 2.0148256303700793,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004601250417697513,
|
|
"loss": 4.999,
|
|
"mean_token_accuracy": 0.2227654606103897,
|
|
"num_tokens": 40044258.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 5.549270439147949,
|
|
"epoch": 2.0153872072780366,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004601022197789724,
|
|
"loss": 5.0188,
|
|
"mean_token_accuracy": 0.21001608222723006,
|
|
"num_tokens": 40055876.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 5.449124050140381,
|
|
"epoch": 2.015948784185994,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004600793918944671,
|
|
"loss": 4.9312,
|
|
"mean_token_accuracy": 0.2259718045592308,
|
|
"num_tokens": 40066691.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 5.463275718688965,
|
|
"epoch": 2.016510361093952,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004600565581169621,
|
|
"loss": 4.9189,
|
|
"mean_token_accuracy": 0.21821629554033278,
|
|
"num_tokens": 40077335.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 5.472330617904663,
|
|
"epoch": 2.0170719380019095,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046003371844718455,
|
|
"loss": 5.0648,
|
|
"mean_token_accuracy": 0.20822831988334656,
|
|
"num_tokens": 40089053.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 5.4755579948425295,
|
|
"epoch": 2.0176335149098668,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046001087288586164,
|
|
"loss": 4.9512,
|
|
"mean_token_accuracy": 0.22442007064819336,
|
|
"num_tokens": 40099371.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 5.504808044433593,
|
|
"epoch": 2.0181950918178244,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004599880214337208,
|
|
"loss": 5.0635,
|
|
"mean_token_accuracy": 0.21030860990285874,
|
|
"num_tokens": 40110274.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 5.529354095458984,
|
|
"epoch": 2.018756668725782,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004599651640914896,
|
|
"loss": 5.073,
|
|
"mean_token_accuracy": 0.21026033014059067,
|
|
"num_tokens": 40120364.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 5.482689714431762,
|
|
"epoch": 2.0193182456337397,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004599423008598957,
|
|
"loss": 5.0306,
|
|
"mean_token_accuracy": 0.21393043100833892,
|
|
"num_tokens": 40132400.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 5.506116580963135,
|
|
"epoch": 2.019879822541697,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045991943173966744,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.21296658217906952,
|
|
"num_tokens": 40142820.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 5.52550196647644,
|
|
"epoch": 2.0204413994496546,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004598965567315326,
|
|
"loss": 5.0632,
|
|
"mean_token_accuracy": 0.21463638991117479,
|
|
"num_tokens": 40153620.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 5.514501762390137,
|
|
"epoch": 2.0210029763576123,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004598736758362198,
|
|
"loss": 4.9981,
|
|
"mean_token_accuracy": 0.21377922594547272,
|
|
"num_tokens": 40164250.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 5.471903991699219,
|
|
"epoch": 2.02156455326557,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045985078905445734,
|
|
"loss": 4.9292,
|
|
"mean_token_accuracy": 0.2171599328517914,
|
|
"num_tokens": 40175809.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 2.02156455326557,
|
|
"eval_entropy": 5.288749482664276,
|
|
"eval_loss": 5.150600433349609,
|
|
"eval_mean_token_accuracy": 0.2166442650487766,
|
|
"eval_num_tokens": 40175809.0,
|
|
"eval_runtime": 18.4969,
|
|
"eval_samples_per_second": 1676.663,
|
|
"eval_steps_per_second": 209.603,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 5.379497289657593,
|
|
"epoch": 2.022126130173527,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00045982789638697414,
|
|
"loss": 4.891,
|
|
"mean_token_accuracy": 0.2242031827569008,
|
|
"num_tokens": 40187855.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 5.4945213317871096,
|
|
"epoch": 2.022687707081485,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045980499783449897,
|
|
"loss": 4.9695,
|
|
"mean_token_accuracy": 0.22087526321411133,
|
|
"num_tokens": 40198802.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 5.603531408309936,
|
|
"epoch": 2.0232492839894425,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045978209339776104,
|
|
"loss": 5.1675,
|
|
"mean_token_accuracy": 0.20049773007631302,
|
|
"num_tokens": 40210636.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 5.544476652145386,
|
|
"epoch": 2.0238108608973997,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045975918307748965,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.21504127234220505,
|
|
"num_tokens": 40221216.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 5.445092487335205,
|
|
"epoch": 2.0243724378053574,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004597362668744141,
|
|
"loss": 4.8992,
|
|
"mean_token_accuracy": 0.22452698200941085,
|
|
"num_tokens": 40231988.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 5.595971870422363,
|
|
"epoch": 2.024934014713315,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004597133447892642,
|
|
"loss": 5.2083,
|
|
"mean_token_accuracy": 0.20227197408676148,
|
|
"num_tokens": 40243789.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 5.531242895126343,
|
|
"epoch": 2.0254955916212727,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004596904168227698,
|
|
"loss": 5.0047,
|
|
"mean_token_accuracy": 0.2195182576775551,
|
|
"num_tokens": 40254771.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 5.502043533325195,
|
|
"epoch": 2.02605716852923,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045966748297566085,
|
|
"loss": 4.9918,
|
|
"mean_token_accuracy": 0.22369295358657837,
|
|
"num_tokens": 40265444.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 5.499016380310058,
|
|
"epoch": 2.0266187454371876,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045964454324866767,
|
|
"loss": 5.0175,
|
|
"mean_token_accuracy": 0.2110731765627861,
|
|
"num_tokens": 40277146.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 5.493988943099976,
|
|
"epoch": 2.0271803223451452,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045962159764252055,
|
|
"loss": 5.0899,
|
|
"mean_token_accuracy": 0.2147793397307396,
|
|
"num_tokens": 40286493.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 5.541953277587891,
|
|
"epoch": 2.027741899253103,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004595986461579502,
|
|
"loss": 5.0027,
|
|
"mean_token_accuracy": 0.21921555399894715,
|
|
"num_tokens": 40297209.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 5.444691371917725,
|
|
"epoch": 2.02830347616106,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045957568879568736,
|
|
"loss": 4.9672,
|
|
"mean_token_accuracy": 0.21676986068487167,
|
|
"num_tokens": 40308666.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 5.5048667907714846,
|
|
"epoch": 2.0288650530690178,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045955272555646306,
|
|
"loss": 5.0809,
|
|
"mean_token_accuracy": 0.20855429619550706,
|
|
"num_tokens": 40321145.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 5.543835020065307,
|
|
"epoch": 2.0294266299769754,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004595297564410083,
|
|
"loss": 5.0162,
|
|
"mean_token_accuracy": 0.218657548725605,
|
|
"num_tokens": 40332418.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 5.442637205123901,
|
|
"epoch": 2.029988206884933,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045950678145005456,
|
|
"loss": 4.9825,
|
|
"mean_token_accuracy": 0.21859144866466523,
|
|
"num_tokens": 40342838.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 5.4588264465332035,
|
|
"epoch": 2.0305497837928903,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004594838005843333,
|
|
"loss": 4.9571,
|
|
"mean_token_accuracy": 0.22099916338920594,
|
|
"num_tokens": 40352940.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 5.570397138595581,
|
|
"epoch": 2.031111360700848,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045946081384457633,
|
|
"loss": 5.0727,
|
|
"mean_token_accuracy": 0.20862097889184952,
|
|
"num_tokens": 40364273.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 5.5007225513458256,
|
|
"epoch": 2.0316729376088056,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045943782123151556,
|
|
"loss": 4.9415,
|
|
"mean_token_accuracy": 0.2262819305062294,
|
|
"num_tokens": 40374617.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 5.4458253383636475,
|
|
"epoch": 2.0322345145167633,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004594148227458829,
|
|
"loss": 5.0613,
|
|
"mean_token_accuracy": 0.2112346425652504,
|
|
"num_tokens": 40385398.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 5.603299331665039,
|
|
"epoch": 2.0327960914247205,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004593918183884108,
|
|
"loss": 5.1097,
|
|
"mean_token_accuracy": 0.21055574119091033,
|
|
"num_tokens": 40397030.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 5.569251441955567,
|
|
"epoch": 2.033357668332678,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004593688081598318,
|
|
"loss": 5.1002,
|
|
"mean_token_accuracy": 0.20993017554283142,
|
|
"num_tokens": 40408027.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 5.572751474380493,
|
|
"epoch": 2.033919245240636,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045934579206087837,
|
|
"loss": 5.0328,
|
|
"mean_token_accuracy": 0.21790675520896913,
|
|
"num_tokens": 40418755.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 5.528239679336548,
|
|
"epoch": 2.034480822148593,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045932277009228336,
|
|
"loss": 5.054,
|
|
"mean_token_accuracy": 0.22020067870616913,
|
|
"num_tokens": 40430694.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 5.5167765617370605,
|
|
"epoch": 2.0350423990565507,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045929974225477986,
|
|
"loss": 5.0105,
|
|
"mean_token_accuracy": 0.21925848722457886,
|
|
"num_tokens": 40442019.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 5.491471290588379,
|
|
"epoch": 2.0356039759645084,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045927670854910117,
|
|
"loss": 5.0271,
|
|
"mean_token_accuracy": 0.20773710310459137,
|
|
"num_tokens": 40454120.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 5.481816244125366,
|
|
"epoch": 2.036165552872466,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004592536689759806,
|
|
"loss": 5.1573,
|
|
"mean_token_accuracy": 0.21080696880817412,
|
|
"num_tokens": 40467445.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 5.47070083618164,
|
|
"epoch": 2.0367271297804233,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045923062353615167,
|
|
"loss": 4.9413,
|
|
"mean_token_accuracy": 0.21739886999130248,
|
|
"num_tokens": 40477512.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 5.430739879608154,
|
|
"epoch": 2.037288706688381,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045920757223034833,
|
|
"loss": 4.9676,
|
|
"mean_token_accuracy": 0.2223648324608803,
|
|
"num_tokens": 40488209.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 5.544326257705689,
|
|
"epoch": 2.0378502835963386,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004591845150593044,
|
|
"loss": 5.0307,
|
|
"mean_token_accuracy": 0.21513805091381072,
|
|
"num_tokens": 40499793.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 5.547037553787232,
|
|
"epoch": 2.0384118605042962,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045916145202375407,
|
|
"loss": 5.1225,
|
|
"mean_token_accuracy": 0.20552191138267517,
|
|
"num_tokens": 40510598.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 5.566928291320801,
|
|
"epoch": 2.0389734374122535,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004591383831244317,
|
|
"loss": 5.0629,
|
|
"mean_token_accuracy": 0.2161805659532547,
|
|
"num_tokens": 40521289.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 5.6003069400787355,
|
|
"epoch": 2.039535014320211,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045911530836207173,
|
|
"loss": 5.0936,
|
|
"mean_token_accuracy": 0.21076880991458893,
|
|
"num_tokens": 40532048.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 5.516372156143189,
|
|
"epoch": 2.0400965912281688,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00045909222773740904,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.21474754214286804,
|
|
"num_tokens": 40543699.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 5.54240403175354,
|
|
"epoch": 2.0406581681361264,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045906914125117833,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.215559983253479,
|
|
"num_tokens": 40554626.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 5.5363201141357425,
|
|
"epoch": 2.0412197450440837,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045904604890411476,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.2124529168009758,
|
|
"num_tokens": 40567046.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 5.641685533523559,
|
|
"epoch": 2.0417813219520413,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045902295069695373,
|
|
"loss": 5.126,
|
|
"mean_token_accuracy": 0.2017991915345192,
|
|
"num_tokens": 40578472.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 5.526861095428467,
|
|
"epoch": 2.042342898859999,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004589998466304305,
|
|
"loss": 5.0408,
|
|
"mean_token_accuracy": 0.21494200825691223,
|
|
"num_tokens": 40589012.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 5.442477560043335,
|
|
"epoch": 2.0429044757679566,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00045897673670528086,
|
|
"loss": 4.9838,
|
|
"mean_token_accuracy": 0.21925510764122008,
|
|
"num_tokens": 40600807.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 5.6104436874389645,
|
|
"epoch": 2.043466052675914,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004589536209222404,
|
|
"loss": 5.125,
|
|
"mean_token_accuracy": 0.21372979432344436,
|
|
"num_tokens": 40612578.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 5.475525665283203,
|
|
"epoch": 2.0440276295838715,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004589304992820454,
|
|
"loss": 4.8862,
|
|
"mean_token_accuracy": 0.22448095977306365,
|
|
"num_tokens": 40623504.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 5.537428760528565,
|
|
"epoch": 2.044589206491829,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000458907371785432,
|
|
"loss": 5.0651,
|
|
"mean_token_accuracy": 0.21251678317785264,
|
|
"num_tokens": 40633676.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 5.5287086963653564,
|
|
"epoch": 2.0451507833997864,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004588842384331366,
|
|
"loss": 5.1117,
|
|
"mean_token_accuracy": 0.21183071434497833,
|
|
"num_tokens": 40645991.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 5.4644937992095945,
|
|
"epoch": 2.045712360307744,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045886109922589564,
|
|
"loss": 4.9526,
|
|
"mean_token_accuracy": 0.2195266768336296,
|
|
"num_tokens": 40656617.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 5.516165924072266,
|
|
"epoch": 2.0462739372157017,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00045883795416444594,
|
|
"loss": 5.0579,
|
|
"mean_token_accuracy": 0.22006842344999314,
|
|
"num_tokens": 40669708.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 5.496811628341675,
|
|
"epoch": 2.0468355141236594,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00045881480324952455,
|
|
"loss": 5.0332,
|
|
"mean_token_accuracy": 0.20650033801794052,
|
|
"num_tokens": 40680248.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 5.593188047409058,
|
|
"epoch": 2.0473970910316166,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00045879164648186853,
|
|
"loss": 5.1206,
|
|
"mean_token_accuracy": 0.2094391867518425,
|
|
"num_tokens": 40692704.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 5.535466051101684,
|
|
"epoch": 2.0479586679395743,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045876848386221513,
|
|
"loss": 5.0177,
|
|
"mean_token_accuracy": 0.2209407165646553,
|
|
"num_tokens": 40703156.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 5.469901371002197,
|
|
"epoch": 2.048520244847532,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045874531539130204,
|
|
"loss": 4.9821,
|
|
"mean_token_accuracy": 0.2193508118391037,
|
|
"num_tokens": 40713996.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 5.487784290313721,
|
|
"epoch": 2.0490818217554896,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045872214106986684,
|
|
"loss": 4.9106,
|
|
"mean_token_accuracy": 0.22373228818178176,
|
|
"num_tokens": 40724532.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 5.538501787185669,
|
|
"epoch": 2.049643398663447,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00045869896089864733,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.2152457982301712,
|
|
"num_tokens": 40736045.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 5.38323130607605,
|
|
"epoch": 2.0502049755714045,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004586757748783817,
|
|
"loss": 4.919,
|
|
"mean_token_accuracy": 0.21768129616975784,
|
|
"num_tokens": 40747398.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 5.380796766281128,
|
|
"epoch": 2.050766552479362,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045865258300980817,
|
|
"loss": 4.8779,
|
|
"mean_token_accuracy": 0.2271013155579567,
|
|
"num_tokens": 40758219.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 5.5226586818695065,
|
|
"epoch": 2.05132812938732,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045862938529366514,
|
|
"loss": 4.9627,
|
|
"mean_token_accuracy": 0.22624574601650238,
|
|
"num_tokens": 40770002.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 5.449618577957153,
|
|
"epoch": 2.051889706295277,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004586061817306913,
|
|
"loss": 4.9421,
|
|
"mean_token_accuracy": 0.22075289934873582,
|
|
"num_tokens": 40780087.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 5.502636671066284,
|
|
"epoch": 2.0524512832032347,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045858297232162536,
|
|
"loss": 5.0924,
|
|
"mean_token_accuracy": 0.20624615848064423,
|
|
"num_tokens": 40792225.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 5.534949684143067,
|
|
"epoch": 2.0530128601111923,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00045855975706720644,
|
|
"loss": 5.1369,
|
|
"mean_token_accuracy": 0.2085693970322609,
|
|
"num_tokens": 40804437.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 5.444004774093628,
|
|
"epoch": 2.05357443701915,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004585365359681736,
|
|
"loss": 4.9077,
|
|
"mean_token_accuracy": 0.22914239913225173,
|
|
"num_tokens": 40814625.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 5.4335548877716064,
|
|
"epoch": 2.054136013927107,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045851330902526633,
|
|
"loss": 4.9497,
|
|
"mean_token_accuracy": 0.21985217779874802,
|
|
"num_tokens": 40825843.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 5.490375757217407,
|
|
"epoch": 2.054697590835065,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00045849007623922406,
|
|
"loss": 5.1324,
|
|
"mean_token_accuracy": 0.2020561143755913,
|
|
"num_tokens": 40837146.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 5.614725780487061,
|
|
"epoch": 2.0552591677430225,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004584668376107867,
|
|
"loss": 5.191,
|
|
"mean_token_accuracy": 0.20533615946769715,
|
|
"num_tokens": 40849109.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 5.50355019569397,
|
|
"epoch": 2.0558207446509797,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000458443593140694,
|
|
"loss": 4.9675,
|
|
"mean_token_accuracy": 0.21141783148050308,
|
|
"num_tokens": 40861168.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 5.544817495346069,
|
|
"epoch": 2.0563823215589374,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00045842034282968615,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.21235246807336808,
|
|
"num_tokens": 40873403.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 5.47606840133667,
|
|
"epoch": 2.056943898466895,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004583970866785035,
|
|
"loss": 4.9824,
|
|
"mean_token_accuracy": 0.2140461027622223,
|
|
"num_tokens": 40883434.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 5.48830018043518,
|
|
"epoch": 2.0575054753748527,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045837382468788643,
|
|
"loss": 5.009,
|
|
"mean_token_accuracy": 0.21490588039159775,
|
|
"num_tokens": 40894742.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 5.4624017715454105,
|
|
"epoch": 2.05806705228281,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004583505568585757,
|
|
"loss": 4.9998,
|
|
"mean_token_accuracy": 0.2196988970041275,
|
|
"num_tokens": 40905233.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 5.491911602020264,
|
|
"epoch": 2.0586286291907676,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045832728319131205,
|
|
"loss": 4.9599,
|
|
"mean_token_accuracy": 0.22475702911615372,
|
|
"num_tokens": 40915897.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 5.4700355052948,
|
|
"epoch": 2.0591902060987253,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004583040036868367,
|
|
"loss": 4.9794,
|
|
"mean_token_accuracy": 0.21097755581140518,
|
|
"num_tokens": 40928178.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 5.457161951065063,
|
|
"epoch": 2.059751783006683,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004582807183458907,
|
|
"loss": 5.0645,
|
|
"mean_token_accuracy": 0.2080140382051468,
|
|
"num_tokens": 40938988.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 5.441991567611694,
|
|
"epoch": 2.06031335991464,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045825742716921553,
|
|
"loss": 4.9584,
|
|
"mean_token_accuracy": 0.22158170491456985,
|
|
"num_tokens": 40949671.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 5.418078422546387,
|
|
"epoch": 2.060874936822598,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004582341301575529,
|
|
"loss": 4.8986,
|
|
"mean_token_accuracy": 0.21813996285200118,
|
|
"num_tokens": 40960818.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 5.589268159866333,
|
|
"epoch": 2.0614365137305555,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045821082731164445,
|
|
"loss": 5.1508,
|
|
"mean_token_accuracy": 0.20092292726039887,
|
|
"num_tokens": 40973866.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 5.490549516677857,
|
|
"epoch": 2.061998090638513,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004581875186322322,
|
|
"loss": 5.022,
|
|
"mean_token_accuracy": 0.2121705397963524,
|
|
"num_tokens": 40983355.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 5.424019241333008,
|
|
"epoch": 2.0625596675464704,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00045816420412005826,
|
|
"loss": 4.906,
|
|
"mean_token_accuracy": 0.22412308305501938,
|
|
"num_tokens": 40994045.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 5.411766433715821,
|
|
"epoch": 2.063121244454428,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045814088377586505,
|
|
"loss": 4.9373,
|
|
"mean_token_accuracy": 0.22670055329799652,
|
|
"num_tokens": 41003974.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 5.489456272125244,
|
|
"epoch": 2.0636828213623857,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00045811755760039513,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.21575163006782533,
|
|
"num_tokens": 41015262.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 5.5584570407867435,
|
|
"epoch": 2.0642443982703433,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045809422559439113,
|
|
"loss": 5.1138,
|
|
"mean_token_accuracy": 0.2107735976576805,
|
|
"num_tokens": 41027103.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 5.529270076751709,
|
|
"epoch": 2.0648059751783006,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045807088775859595,
|
|
"loss": 5.0019,
|
|
"mean_token_accuracy": 0.21617121398448944,
|
|
"num_tokens": 41037240.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 5.563993883132935,
|
|
"epoch": 2.065367552086258,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004580475440937527,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.2192753165960312,
|
|
"num_tokens": 41048258.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 5.557229328155517,
|
|
"epoch": 2.065929128994216,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045802419460060464,
|
|
"loss": 5.0894,
|
|
"mean_token_accuracy": 0.2110954701900482,
|
|
"num_tokens": 41058204.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 5.601803636550903,
|
|
"epoch": 2.066490705902173,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004580008392798953,
|
|
"loss": 5.0787,
|
|
"mean_token_accuracy": 0.21253258734941483,
|
|
"num_tokens": 41070019.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 5.562759447097778,
|
|
"epoch": 2.0670522828101308,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045797747813236815,
|
|
"loss": 5.0389,
|
|
"mean_token_accuracy": 0.22048287689685822,
|
|
"num_tokens": 41081503.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 5.519818305969238,
|
|
"epoch": 2.0676138597180884,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045795411115876725,
|
|
"loss": 5.0287,
|
|
"mean_token_accuracy": 0.2068215250968933,
|
|
"num_tokens": 41091959.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 5.536817836761474,
|
|
"epoch": 2.068175436626046,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045793073835983644,
|
|
"loss": 5.0455,
|
|
"mean_token_accuracy": 0.21535297185182573,
|
|
"num_tokens": 41103193.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 5.56896276473999,
|
|
"epoch": 2.0687370135340033,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045790735973631996,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.2200862780213356,
|
|
"num_tokens": 41115886.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 5.4808789730072025,
|
|
"epoch": 2.069298590441961,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00045788397528896224,
|
|
"loss": 4.9609,
|
|
"mean_token_accuracy": 0.21946857273578643,
|
|
"num_tokens": 41126868.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 5.557408809661865,
|
|
"epoch": 2.0698601673499186,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045786058501850774,
|
|
"loss": 5.0142,
|
|
"mean_token_accuracy": 0.2221153661608696,
|
|
"num_tokens": 41136417.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 5.509507036209106,
|
|
"epoch": 2.0704217442578763,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045783718892570136,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.20932406485080718,
|
|
"num_tokens": 41149515.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 5.579898834228516,
|
|
"epoch": 2.0709833211658335,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000457813787011288,
|
|
"loss": 5.1039,
|
|
"mean_token_accuracy": 0.21785481721162797,
|
|
"num_tokens": 41160023.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 5.412167930603028,
|
|
"epoch": 2.071544898073791,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004577903792760127,
|
|
"loss": 4.8913,
|
|
"mean_token_accuracy": 0.22888001203536987,
|
|
"num_tokens": 41170909.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 5.559626770019531,
|
|
"epoch": 2.072106474981749,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004577669657206209,
|
|
"loss": 5.1047,
|
|
"mean_token_accuracy": 0.20876959711313248,
|
|
"num_tokens": 41181960.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 5.5878949642181395,
|
|
"epoch": 2.0726680518897065,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004577435463458579,
|
|
"loss": 5.096,
|
|
"mean_token_accuracy": 0.21168456673622132,
|
|
"num_tokens": 41192292.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 5.5581199645996096,
|
|
"epoch": 2.0732296287976637,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004577201211524696,
|
|
"loss": 5.0051,
|
|
"mean_token_accuracy": 0.2213801383972168,
|
|
"num_tokens": 41203826.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 5.4602149486541744,
|
|
"epoch": 2.0737912057056214,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004576966901412018,
|
|
"loss": 5.0666,
|
|
"mean_token_accuracy": 0.21620500236749648,
|
|
"num_tokens": 41215095.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 5.5341572761535645,
|
|
"epoch": 2.074352782613579,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045767325331280044,
|
|
"loss": 4.9755,
|
|
"mean_token_accuracy": 0.2149103358387947,
|
|
"num_tokens": 41224953.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 5.561403608322143,
|
|
"epoch": 2.0749143595215367,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004576498106680119,
|
|
"loss": 5.0449,
|
|
"mean_token_accuracy": 0.20596526563167572,
|
|
"num_tokens": 41235479.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 5.527247953414917,
|
|
"epoch": 2.075475936429494,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004576263622075826,
|
|
"loss": 5.0703,
|
|
"mean_token_accuracy": 0.21642846316099168,
|
|
"num_tokens": 41248520.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 5.576947259902954,
|
|
"epoch": 2.0760375133374516,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000457602907932259,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.2077233985066414,
|
|
"num_tokens": 41259112.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 5.502575874328613,
|
|
"epoch": 2.0765990902454092,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045757944784278803,
|
|
"loss": 4.9915,
|
|
"mean_token_accuracy": 0.219262033700943,
|
|
"num_tokens": 41269554.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 5.542146062850952,
|
|
"epoch": 2.0771606671533664,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004575559819399166,
|
|
"loss": 5.0239,
|
|
"mean_token_accuracy": 0.21835334748029708,
|
|
"num_tokens": 41281339.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 5.476851749420166,
|
|
"epoch": 2.077722244061324,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045753251022439195,
|
|
"loss": 4.9478,
|
|
"mean_token_accuracy": 0.22250728011131288,
|
|
"num_tokens": 41291629.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 5.560992813110351,
|
|
"epoch": 2.0782838209692818,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004575090326969614,
|
|
"loss": 5.088,
|
|
"mean_token_accuracy": 0.21118887960910798,
|
|
"num_tokens": 41302162.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 5.482925939559936,
|
|
"epoch": 2.0788453978772394,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004574855493583723,
|
|
"loss": 5.0096,
|
|
"mean_token_accuracy": 0.2173047974705696,
|
|
"num_tokens": 41313667.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 5.4807651996612545,
|
|
"epoch": 2.0794069747851966,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045746206020937276,
|
|
"loss": 4.9964,
|
|
"mean_token_accuracy": 0.21830037534236907,
|
|
"num_tokens": 41325063.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 5.512169933319091,
|
|
"epoch": 2.0799685516931543,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045743856525071034,
|
|
"loss": 5.0709,
|
|
"mean_token_accuracy": 0.21254366636276245,
|
|
"num_tokens": 41335974.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 5.480447435379029,
|
|
"epoch": 2.080530128601112,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045741506448313327,
|
|
"loss": 4.9921,
|
|
"mean_token_accuracy": 0.21852853149175644,
|
|
"num_tokens": 41347469.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 5.568706083297729,
|
|
"epoch": 2.0810917055090696,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045739155790738975,
|
|
"loss": 5.0903,
|
|
"mean_token_accuracy": 0.21995055079460143,
|
|
"num_tokens": 41358418.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 5.539313411712646,
|
|
"epoch": 2.081653282417027,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045736804552422836,
|
|
"loss": 5.0909,
|
|
"mean_token_accuracy": 0.21096516102552415,
|
|
"num_tokens": 41368859.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 5.5604674339294435,
|
|
"epoch": 2.0822148593249845,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004573445273343976,
|
|
"loss": 5.1294,
|
|
"mean_token_accuracy": 0.20696448981761933,
|
|
"num_tokens": 41380929.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 5.523511362075806,
|
|
"epoch": 2.082776436232942,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004573210033386464,
|
|
"loss": 4.9363,
|
|
"mean_token_accuracy": 0.22523413896560668,
|
|
"num_tokens": 41392190.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 5.605782127380371,
|
|
"epoch": 2.0833380131409,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004572974735377238,
|
|
"loss": 5.0118,
|
|
"mean_token_accuracy": 0.21911531239748,
|
|
"num_tokens": 41402646.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 5.476578187942505,
|
|
"epoch": 2.083899590048857,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004572739379323788,
|
|
"loss": 5.0036,
|
|
"mean_token_accuracy": 0.2140674591064453,
|
|
"num_tokens": 41415179.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 5.504357242584229,
|
|
"epoch": 2.0844611669568147,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045725039652336105,
|
|
"loss": 5.0727,
|
|
"mean_token_accuracy": 0.21215118169784547,
|
|
"num_tokens": 41426695.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 5.499299144744873,
|
|
"epoch": 2.0850227438647724,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004572268493114199,
|
|
"loss": 5.0149,
|
|
"mean_token_accuracy": 0.2138336941599846,
|
|
"num_tokens": 41438078.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 5.540561866760254,
|
|
"epoch": 2.08558432077273,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004572032962973052,
|
|
"loss": 5.0716,
|
|
"mean_token_accuracy": 0.2127721682190895,
|
|
"num_tokens": 41448862.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 5.432217264175415,
|
|
"epoch": 2.0861458976806873,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045717973748176695,
|
|
"loss": 4.8698,
|
|
"mean_token_accuracy": 0.22463872134685517,
|
|
"num_tokens": 41458528.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 5.466809272766113,
|
|
"epoch": 2.086707474588645,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045715617286555516,
|
|
"loss": 4.9808,
|
|
"mean_token_accuracy": 0.2125450000166893,
|
|
"num_tokens": 41469553.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 5.592465782165528,
|
|
"epoch": 2.0872690514966026,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045713260244942017,
|
|
"loss": 5.1517,
|
|
"mean_token_accuracy": 0.21182382106781006,
|
|
"num_tokens": 41482327.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 5.468498706817627,
|
|
"epoch": 2.08783062840456,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004571090262341125,
|
|
"loss": 4.9083,
|
|
"mean_token_accuracy": 0.22608505487442015,
|
|
"num_tokens": 41493126.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 5.504410457611084,
|
|
"epoch": 2.0883922053125175,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00045708544422038284,
|
|
"loss": 5.0713,
|
|
"mean_token_accuracy": 0.2091891959309578,
|
|
"num_tokens": 41505597.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 5.584372425079346,
|
|
"epoch": 2.088953782220475,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004570618564089819,
|
|
"loss": 5.13,
|
|
"mean_token_accuracy": 0.20768361091613768,
|
|
"num_tokens": 41517296.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 5.569519138336181,
|
|
"epoch": 2.089515359128433,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00045703826280066095,
|
|
"loss": 5.015,
|
|
"mean_token_accuracy": 0.2192860797047615,
|
|
"num_tokens": 41529900.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 5.5330963134765625,
|
|
"epoch": 2.09007693603639,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004570146633961711,
|
|
"loss": 5.0556,
|
|
"mean_token_accuracy": 0.21736267805099488,
|
|
"num_tokens": 41540641.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 5.434649801254272,
|
|
"epoch": 2.0906385129443477,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045699105819626374,
|
|
"loss": 5.0404,
|
|
"mean_token_accuracy": 0.2048357054591179,
|
|
"num_tokens": 41551335.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 5.504931211471558,
|
|
"epoch": 2.0912000898523053,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004569674472016904,
|
|
"loss": 5.0073,
|
|
"mean_token_accuracy": 0.22068156599998473,
|
|
"num_tokens": 41562265.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 5.5059041500091555,
|
|
"epoch": 2.091761666760263,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004569438304132031,
|
|
"loss": 4.9271,
|
|
"mean_token_accuracy": 0.21933801621198654,
|
|
"num_tokens": 41574758.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 5.42665376663208,
|
|
"epoch": 2.09232324366822,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045692020783155376,
|
|
"loss": 4.9298,
|
|
"mean_token_accuracy": 0.2153540164232254,
|
|
"num_tokens": 41585007.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 5.427863502502442,
|
|
"epoch": 2.092884820576178,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004568965794574943,
|
|
"loss": 4.9378,
|
|
"mean_token_accuracy": 0.21884457767009735,
|
|
"num_tokens": 41596026.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 5.566444683074951,
|
|
"epoch": 2.0934463974841355,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004568729452917772,
|
|
"loss": 5.0789,
|
|
"mean_token_accuracy": 0.21639298051595687,
|
|
"num_tokens": 41608440.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 5.499663639068603,
|
|
"epoch": 2.094007974392093,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00045684930533515506,
|
|
"loss": 4.973,
|
|
"mean_token_accuracy": 0.2177707701921463,
|
|
"num_tokens": 41620467.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 5.485700035095215,
|
|
"epoch": 2.0945695513000504,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045682565958838045,
|
|
"loss": 4.9996,
|
|
"mean_token_accuracy": 0.21357071101665498,
|
|
"num_tokens": 41630918.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 5.500881147384644,
|
|
"epoch": 2.095131128208008,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004568020080522063,
|
|
"loss": 4.9808,
|
|
"mean_token_accuracy": 0.21469495743513106,
|
|
"num_tokens": 41641148.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 5.5581659317016605,
|
|
"epoch": 2.0956927051159657,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004567783507273858,
|
|
"loss": 5.0309,
|
|
"mean_token_accuracy": 0.2199338674545288,
|
|
"num_tokens": 41652148.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 5.506256818771362,
|
|
"epoch": 2.0962542820239234,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045675468761467204,
|
|
"loss": 4.9993,
|
|
"mean_token_accuracy": 0.21786906868219375,
|
|
"num_tokens": 41662275.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 5.566605854034424,
|
|
"epoch": 2.0968158589318806,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045673101871481853,
|
|
"loss": 5.0586,
|
|
"mean_token_accuracy": 0.20855064541101456,
|
|
"num_tokens": 41673141.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 5.631915950775147,
|
|
"epoch": 2.0973774358398383,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004567073440285789,
|
|
"loss": 5.1686,
|
|
"mean_token_accuracy": 0.20746597796678543,
|
|
"num_tokens": 41683473.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 5.426448345184326,
|
|
"epoch": 2.097939012747796,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00045668366355670697,
|
|
"loss": 4.8098,
|
|
"mean_token_accuracy": 0.22444780468940734,
|
|
"num_tokens": 41693847.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 5.482524967193603,
|
|
"epoch": 2.098500589655753,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004566599772999567,
|
|
"loss": 5.0684,
|
|
"mean_token_accuracy": 0.2175423324108124,
|
|
"num_tokens": 41705810.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 5.495926713943481,
|
|
"epoch": 2.099062166563711,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00045663628525908237,
|
|
"loss": 4.928,
|
|
"mean_token_accuracy": 0.21603805273771287,
|
|
"num_tokens": 41717160.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 5.541777849197388,
|
|
"epoch": 2.0996237434716685,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004566125874348382,
|
|
"loss": 5.0975,
|
|
"mean_token_accuracy": 0.21484368592500686,
|
|
"num_tokens": 41728631.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 5.584958887100219,
|
|
"epoch": 2.100185320379626,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045658888382797886,
|
|
"loss": 5.1469,
|
|
"mean_token_accuracy": 0.2069434106349945,
|
|
"num_tokens": 41738933.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 5.6201997756958,
|
|
"epoch": 2.1007468972875833,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00045656517443925897,
|
|
"loss": 5.1265,
|
|
"mean_token_accuracy": 0.2181014060974121,
|
|
"num_tokens": 41750386.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 5.498168992996216,
|
|
"epoch": 2.101308474195541,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004565414592694336,
|
|
"loss": 5.0418,
|
|
"mean_token_accuracy": 0.2136332720518112,
|
|
"num_tokens": 41760711.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 5.49470329284668,
|
|
"epoch": 2.1018700511034987,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004565177383192577,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.21033832430839539,
|
|
"num_tokens": 41772147.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 5.536369180679321,
|
|
"epoch": 2.1024316280114563,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045649401158948664,
|
|
"loss": 4.9635,
|
|
"mean_token_accuracy": 0.2190065234899521,
|
|
"num_tokens": 41783265.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 5.529592990875244,
|
|
"epoch": 2.1029932049194136,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004564702790808758,
|
|
"loss": 4.9663,
|
|
"mean_token_accuracy": 0.21945076286792756,
|
|
"num_tokens": 41793977.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 5.523620891571045,
|
|
"epoch": 2.103554781827371,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004564465407941809,
|
|
"loss": 4.9753,
|
|
"mean_token_accuracy": 0.2241202637553215,
|
|
"num_tokens": 41804790.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 5.4101275444030765,
|
|
"epoch": 2.104116358735329,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00045642279673015787,
|
|
"loss": 4.9823,
|
|
"mean_token_accuracy": 0.21147693544626237,
|
|
"num_tokens": 41815611.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 5.4383580684661865,
|
|
"epoch": 2.1046779356432865,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004563990468895625,
|
|
"loss": 5.0089,
|
|
"mean_token_accuracy": 0.21274339258670807,
|
|
"num_tokens": 41826935.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 5.450624418258667,
|
|
"epoch": 2.1052395125512438,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004563752912731512,
|
|
"loss": 4.9587,
|
|
"mean_token_accuracy": 0.2177711844444275,
|
|
"num_tokens": 41838932.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 5.433754205703735,
|
|
"epoch": 2.1058010894592014,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004563515298816803,
|
|
"loss": 5.0236,
|
|
"mean_token_accuracy": 0.21329770535230635,
|
|
"num_tokens": 41850771.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 5.459846258163452,
|
|
"epoch": 2.106362666367159,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045632776271590624,
|
|
"loss": 4.9575,
|
|
"mean_token_accuracy": 0.2232426792383194,
|
|
"num_tokens": 41861515.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 5.486744976043701,
|
|
"epoch": 2.1069242432751167,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004563039897765859,
|
|
"loss": 4.8655,
|
|
"mean_token_accuracy": 0.23283354043960572,
|
|
"num_tokens": 41872195.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 5.430644226074219,
|
|
"epoch": 2.107485820183074,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004562802110644764,
|
|
"loss": 4.9571,
|
|
"mean_token_accuracy": 0.2259806588292122,
|
|
"num_tokens": 41882496.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 5.56043004989624,
|
|
"epoch": 2.1080473970910316,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00045625642658033447,
|
|
"loss": 5.1968,
|
|
"mean_token_accuracy": 0.20316258668899537,
|
|
"num_tokens": 41893078.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 5.576148271560669,
|
|
"epoch": 2.1086089739989893,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045623263632491766,
|
|
"loss": 5.044,
|
|
"mean_token_accuracy": 0.21328755468130112,
|
|
"num_tokens": 41905062.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 5.465897083282471,
|
|
"epoch": 2.1091705509069465,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045620884029898344,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.21370731443166732,
|
|
"num_tokens": 41916086.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 5.505476188659668,
|
|
"epoch": 2.109732127814904,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045618503850328954,
|
|
"loss": 5.0772,
|
|
"mean_token_accuracy": 0.21464026421308519,
|
|
"num_tokens": 41925466.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 5.571772527694702,
|
|
"epoch": 2.110293704722862,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004561612309385936,
|
|
"loss": 5.115,
|
|
"mean_token_accuracy": 0.2072063997387886,
|
|
"num_tokens": 41936567.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 5.492284107208252,
|
|
"epoch": 2.1108552816308195,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045613741760565385,
|
|
"loss": 4.9832,
|
|
"mean_token_accuracy": 0.21496164053678513,
|
|
"num_tokens": 41947021.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 5.512422657012939,
|
|
"epoch": 2.1114168585387767,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004561135985052285,
|
|
"loss": 5.0286,
|
|
"mean_token_accuracy": 0.2150877073407173,
|
|
"num_tokens": 41957929.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 5.47967381477356,
|
|
"epoch": 2.1119784354467344,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000456089773638076,
|
|
"loss": 4.9317,
|
|
"mean_token_accuracy": 0.22358918637037278,
|
|
"num_tokens": 41968677.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 5.5085124492645265,
|
|
"epoch": 2.112540012354692,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004560659430049548,
|
|
"loss": 5.0971,
|
|
"mean_token_accuracy": 0.2126852124929428,
|
|
"num_tokens": 41980330.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 5.518780851364136,
|
|
"epoch": 2.1131015892626497,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004560421066066237,
|
|
"loss": 4.9964,
|
|
"mean_token_accuracy": 0.21738462895154953,
|
|
"num_tokens": 41991258.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 5.539147758483887,
|
|
"epoch": 2.113663166170607,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045601826444384175,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.21918980926275253,
|
|
"num_tokens": 42002679.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 5.490826606750488,
|
|
"epoch": 2.1142247430785646,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045599441651736805,
|
|
"loss": 4.9698,
|
|
"mean_token_accuracy": 0.214610455930233,
|
|
"num_tokens": 42012845.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 5.548410558700562,
|
|
"epoch": 2.1147863199865222,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045597056282796196,
|
|
"loss": 5.0547,
|
|
"mean_token_accuracy": 0.21569840759038925,
|
|
"num_tokens": 42024461.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 5.499419832229615,
|
|
"epoch": 2.11534789689448,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004559467033763829,
|
|
"loss": 5.0258,
|
|
"mean_token_accuracy": 0.2102286010980606,
|
|
"num_tokens": 42036996.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 5.581981801986695,
|
|
"epoch": 2.115909473802437,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004559228381633907,
|
|
"loss": 5.0981,
|
|
"mean_token_accuracy": 0.21612170338630676,
|
|
"num_tokens": 42048731.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 5.587025928497314,
|
|
"epoch": 2.1164710507103948,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045589896718974517,
|
|
"loss": 5.0375,
|
|
"mean_token_accuracy": 0.22045449316501617,
|
|
"num_tokens": 42060396.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 5.3889978408813475,
|
|
"epoch": 2.1170326276183524,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004558750904562063,
|
|
"loss": 4.9424,
|
|
"mean_token_accuracy": 0.21314848810434342,
|
|
"num_tokens": 42072037.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 5.4552794933319095,
|
|
"epoch": 2.11759420452631,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004558512079635345,
|
|
"loss": 4.9088,
|
|
"mean_token_accuracy": 0.22514116019010544,
|
|
"num_tokens": 42082577.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 5.402896308898926,
|
|
"epoch": 2.1181557814342673,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004558273197124899,
|
|
"loss": 4.9238,
|
|
"mean_token_accuracy": 0.22545453161001205,
|
|
"num_tokens": 42093978.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 5.512389707565307,
|
|
"epoch": 2.118717358342225,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00045580342570383347,
|
|
"loss": 5.1168,
|
|
"mean_token_accuracy": 0.21387167721986772,
|
|
"num_tokens": 42105773.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 5.513806772232056,
|
|
"epoch": 2.1192789352501826,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004557795259383258,
|
|
"loss": 5.0285,
|
|
"mean_token_accuracy": 0.21928571462631224,
|
|
"num_tokens": 42116232.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 5.491640377044678,
|
|
"epoch": 2.11984051215814,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045575562041672794,
|
|
"loss": 5.0465,
|
|
"mean_token_accuracy": 0.21324197053909302,
|
|
"num_tokens": 42127813.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 5.473332929611206,
|
|
"epoch": 2.1204020890660975,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045573170913980094,
|
|
"loss": 4.987,
|
|
"mean_token_accuracy": 0.2134528711438179,
|
|
"num_tokens": 42138054.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 5.572250032424927,
|
|
"epoch": 2.120963665974055,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045570779210830627,
|
|
"loss": 5.0435,
|
|
"mean_token_accuracy": 0.21087926924228667,
|
|
"num_tokens": 42149575.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 5.518216562271118,
|
|
"epoch": 2.121525242882013,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004556838693230054,
|
|
"loss": 5.0478,
|
|
"mean_token_accuracy": 0.2156390815973282,
|
|
"num_tokens": 42160824.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 5.522684335708618,
|
|
"epoch": 2.12208681978997,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045565994078466005,
|
|
"loss": 5.0881,
|
|
"mean_token_accuracy": 0.21475025564432143,
|
|
"num_tokens": 42171088.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 5.490110731124878,
|
|
"epoch": 2.1226483966979277,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045563600649403213,
|
|
"loss": 5.0228,
|
|
"mean_token_accuracy": 0.21549665033817292,
|
|
"num_tokens": 42182112.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 5.543063020706176,
|
|
"epoch": 2.1232099736058854,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004556120664518838,
|
|
"loss": 4.9359,
|
|
"mean_token_accuracy": 0.22617857158184052,
|
|
"num_tokens": 42193563.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 5.523292398452758,
|
|
"epoch": 2.123771550513843,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004555881206589771,
|
|
"loss": 5.0047,
|
|
"mean_token_accuracy": 0.21772734969854354,
|
|
"num_tokens": 42204891.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 5.535649156570434,
|
|
"epoch": 2.1243331274218002,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004555641691160746,
|
|
"loss": 5.0587,
|
|
"mean_token_accuracy": 0.2203079044818878,
|
|
"num_tokens": 42217226.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 5.544731140136719,
|
|
"epoch": 2.124894704329758,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000455540211823939,
|
|
"loss": 5.0261,
|
|
"mean_token_accuracy": 0.21794724017381667,
|
|
"num_tokens": 42228134.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 5.528731870651245,
|
|
"epoch": 2.1254562812377156,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045551624878333296,
|
|
"loss": 5.0669,
|
|
"mean_token_accuracy": 0.21114152818918228,
|
|
"num_tokens": 42239868.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 5.576525449752808,
|
|
"epoch": 2.1260178581456732,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045549227999501957,
|
|
"loss": 5.0968,
|
|
"mean_token_accuracy": 0.21618064790964125,
|
|
"num_tokens": 42250297.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 5.451301574707031,
|
|
"epoch": 2.1265794350536305,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045546830545976203,
|
|
"loss": 4.7772,
|
|
"mean_token_accuracy": 0.24056749045848846,
|
|
"num_tokens": 42261263.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 5.556567001342773,
|
|
"epoch": 2.127141011961588,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045544432517832356,
|
|
"loss": 5.0823,
|
|
"mean_token_accuracy": 0.2160559728741646,
|
|
"num_tokens": 42272357.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 5.560354089736938,
|
|
"epoch": 2.1277025888695458,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045542033915146787,
|
|
"loss": 5.1073,
|
|
"mean_token_accuracy": 0.2153716042637825,
|
|
"num_tokens": 42283630.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 5.529127168655395,
|
|
"epoch": 2.1282641657775034,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045539634737995857,
|
|
"loss": 5.1096,
|
|
"mean_token_accuracy": 0.19961658865213394,
|
|
"num_tokens": 42294981.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 5.524041223526001,
|
|
"epoch": 2.1288257426854607,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045537234986455964,
|
|
"loss": 4.9596,
|
|
"mean_token_accuracy": 0.22108154892921447,
|
|
"num_tokens": 42304877.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 5.505650186538697,
|
|
"epoch": 2.1293873195934183,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004553483466060351,
|
|
"loss": 5.0668,
|
|
"mean_token_accuracy": 0.21097273677587508,
|
|
"num_tokens": 42316325.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 5.484247922897339,
|
|
"epoch": 2.129948896501376,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045532433760514925,
|
|
"loss": 5.0278,
|
|
"mean_token_accuracy": 0.21446882486343383,
|
|
"num_tokens": 42327437.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 5.421216535568237,
|
|
"epoch": 2.130510473409333,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004553003228626665,
|
|
"loss": 4.933,
|
|
"mean_token_accuracy": 0.22633096426725388,
|
|
"num_tokens": 42337742.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 5.501980781555176,
|
|
"epoch": 2.131072050317291,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004552763023793517,
|
|
"loss": 5.0149,
|
|
"mean_token_accuracy": 0.2165967270731926,
|
|
"num_tokens": 42348511.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 5.494083499908447,
|
|
"epoch": 2.1316336272252485,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004552522761559694,
|
|
"loss": 4.992,
|
|
"mean_token_accuracy": 0.21859514564275742,
|
|
"num_tokens": 42358977.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 5.562210273742676,
|
|
"epoch": 2.132195204133206,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045522824419328475,
|
|
"loss": 5.0601,
|
|
"mean_token_accuracy": 0.212298221886158,
|
|
"num_tokens": 42371609.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 5.544377565383911,
|
|
"epoch": 2.1327567810411634,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045520420649206283,
|
|
"loss": 5.0232,
|
|
"mean_token_accuracy": 0.21839981079101561,
|
|
"num_tokens": 42383150.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 5.4789728164672855,
|
|
"epoch": 2.133318357949121,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004551801630530692,
|
|
"loss": 4.9785,
|
|
"mean_token_accuracy": 0.2150705099105835,
|
|
"num_tokens": 42395150.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 5.522980403900147,
|
|
"epoch": 2.1338799348570787,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004551561138770693,
|
|
"loss": 5.0375,
|
|
"mean_token_accuracy": 0.21387800127267836,
|
|
"num_tokens": 42406348.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 5.5495411396026615,
|
|
"epoch": 2.1344415117650364,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045513205896482875,
|
|
"loss": 5.0568,
|
|
"mean_token_accuracy": 0.20580437928438186,
|
|
"num_tokens": 42417183.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 5.535960721969604,
|
|
"epoch": 2.1350030886729936,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045510799831711366,
|
|
"loss": 4.986,
|
|
"mean_token_accuracy": 0.22771431803703307,
|
|
"num_tokens": 42427805.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 5.5317810535430905,
|
|
"epoch": 2.1355646655809513,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045508393193469,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.2168296217918396,
|
|
"num_tokens": 42439521.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 5.602089262008667,
|
|
"epoch": 2.136126242488909,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004550598598183241,
|
|
"loss": 5.1065,
|
|
"mean_token_accuracy": 0.21246589869260787,
|
|
"num_tokens": 42451201.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 5.529308652877807,
|
|
"epoch": 2.1366878193968666,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004550357819687825,
|
|
"loss": 4.999,
|
|
"mean_token_accuracy": 0.21780294477939605,
|
|
"num_tokens": 42462315.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 5.632309818267823,
|
|
"epoch": 2.137249396304824,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004550116983868317,
|
|
"loss": 5.1645,
|
|
"mean_token_accuracy": 0.20546071231365204,
|
|
"num_tokens": 42473993.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 5.637898254394531,
|
|
"epoch": 2.1378109732127815,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004549876090732386,
|
|
"loss": 5.1771,
|
|
"mean_token_accuracy": 0.20699512213468552,
|
|
"num_tokens": 42484307.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 5.539485931396484,
|
|
"epoch": 2.138372550120739,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004549635140287703,
|
|
"loss": 5.0689,
|
|
"mean_token_accuracy": 0.21453823000192643,
|
|
"num_tokens": 42497305.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 5.562845182418823,
|
|
"epoch": 2.138934127028697,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045493941325419385,
|
|
"loss": 5.0828,
|
|
"mean_token_accuracy": 0.20761047005653382,
|
|
"num_tokens": 42508307.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 5.551513290405273,
|
|
"epoch": 2.139495703936654,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004549153067502768,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.20893438458442687,
|
|
"num_tokens": 42519946.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 5.484661388397217,
|
|
"epoch": 2.1400572808446117,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045489119451778645,
|
|
"loss": 4.91,
|
|
"mean_token_accuracy": 0.2198232963681221,
|
|
"num_tokens": 42530737.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 5.411928272247314,
|
|
"epoch": 2.1406188577525693,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004548670765574908,
|
|
"loss": 4.9149,
|
|
"mean_token_accuracy": 0.22011160850524902,
|
|
"num_tokens": 42542184.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 5.51154317855835,
|
|
"epoch": 2.1411804346605265,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045484295287015757,
|
|
"loss": 5.0329,
|
|
"mean_token_accuracy": 0.21582040190696716,
|
|
"num_tokens": 42553816.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 5.57795524597168,
|
|
"epoch": 2.141742011568484,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004548188234565551,
|
|
"loss": 5.0573,
|
|
"mean_token_accuracy": 0.2195124953985214,
|
|
"num_tokens": 42564685.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 5.503572797775268,
|
|
"epoch": 2.142303588476442,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045479468831745144,
|
|
"loss": 5.0075,
|
|
"mean_token_accuracy": 0.20874025225639342,
|
|
"num_tokens": 42574864.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 5.508390474319458,
|
|
"epoch": 2.1428651653843995,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004547705474536152,
|
|
"loss": 4.9749,
|
|
"mean_token_accuracy": 0.21250364780426026,
|
|
"num_tokens": 42585214.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 5.550159645080567,
|
|
"epoch": 2.1434267422923567,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045474640086581506,
|
|
"loss": 5.0957,
|
|
"mean_token_accuracy": 0.21216932386159898,
|
|
"num_tokens": 42596017.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 5.530079412460327,
|
|
"epoch": 2.1439883192003144,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00045472224855481975,
|
|
"loss": 5.0013,
|
|
"mean_token_accuracy": 0.20888324230909347,
|
|
"num_tokens": 42607903.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 5.54863338470459,
|
|
"epoch": 2.144549896108272,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045469809052139844,
|
|
"loss": 5.0153,
|
|
"mean_token_accuracy": 0.2172306150197983,
|
|
"num_tokens": 42618690.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 5.486841917037964,
|
|
"epoch": 2.1451114730162297,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045467392676632016,
|
|
"loss": 4.9752,
|
|
"mean_token_accuracy": 0.21515931338071823,
|
|
"num_tokens": 42629655.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 5.526285457611084,
|
|
"epoch": 2.145673049924187,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004546497572903543,
|
|
"loss": 5.0905,
|
|
"mean_token_accuracy": 0.21219980865716934,
|
|
"num_tokens": 42641214.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 5.580718994140625,
|
|
"epoch": 2.1462346268321446,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004546255820942706,
|
|
"loss": 5.1167,
|
|
"mean_token_accuracy": 0.20636202543973922,
|
|
"num_tokens": 42653829.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 5.581433629989624,
|
|
"epoch": 2.1467962037401023,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004546014011788386,
|
|
"loss": 5.0758,
|
|
"mean_token_accuracy": 0.21148422807455064,
|
|
"num_tokens": 42665245.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 5.520538568496704,
|
|
"epoch": 2.14735778064806,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004545772145448284,
|
|
"loss": 4.9926,
|
|
"mean_token_accuracy": 0.21245959550142288,
|
|
"num_tokens": 42676409.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 5.443544673919678,
|
|
"epoch": 2.147919357556017,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045455302219301,
|
|
"loss": 4.8613,
|
|
"mean_token_accuracy": 0.2246546819806099,
|
|
"num_tokens": 42686586.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 5.405819606781006,
|
|
"epoch": 2.148480934463975,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004545288241241538,
|
|
"loss": 4.9367,
|
|
"mean_token_accuracy": 0.22098598182201384,
|
|
"num_tokens": 42696597.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 5.57641191482544,
|
|
"epoch": 2.1490425113719325,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004545046203390302,
|
|
"loss": 5.1157,
|
|
"mean_token_accuracy": 0.21626488566398622,
|
|
"num_tokens": 42707447.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 5.69161958694458,
|
|
"epoch": 2.14960408827989,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045448041083840973,
|
|
"loss": 5.1268,
|
|
"mean_token_accuracy": 0.20393733084201812,
|
|
"num_tokens": 42717533.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 5.600433444976806,
|
|
"epoch": 2.1501656651878474,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00045445619562306354,
|
|
"loss": 5.1225,
|
|
"mean_token_accuracy": 0.2111228510737419,
|
|
"num_tokens": 42730563.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 5.502301836013794,
|
|
"epoch": 2.150727242095805,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045443197469376243,
|
|
"loss": 5.0144,
|
|
"mean_token_accuracy": 0.2174910321831703,
|
|
"num_tokens": 42740301.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 5.53596510887146,
|
|
"epoch": 2.1512888190037627,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004544077480512776,
|
|
"loss": 5.0383,
|
|
"mean_token_accuracy": 0.2109946295619011,
|
|
"num_tokens": 42752296.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 5.483240842819214,
|
|
"epoch": 2.15185039591172,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045438351569638055,
|
|
"loss": 4.9196,
|
|
"mean_token_accuracy": 0.21888632774353028,
|
|
"num_tokens": 42762530.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 5.5139813899993895,
|
|
"epoch": 2.1524119728196776,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045435927762984277,
|
|
"loss": 4.9688,
|
|
"mean_token_accuracy": 0.2133881226181984,
|
|
"num_tokens": 42773059.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 5.4664778232574465,
|
|
"epoch": 2.152973549727635,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000454335033852436,
|
|
"loss": 4.9941,
|
|
"mean_token_accuracy": 0.2172984391450882,
|
|
"num_tokens": 42783832.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 5.519624805450439,
|
|
"epoch": 2.153535126635593,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004543107843649322,
|
|
"loss": 5.0948,
|
|
"mean_token_accuracy": 0.21813974231481553,
|
|
"num_tokens": 42794565.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 5.631042385101319,
|
|
"epoch": 2.15409670354355,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004542865291681035,
|
|
"loss": 5.1274,
|
|
"mean_token_accuracy": 0.20971587300300598,
|
|
"num_tokens": 42805536.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 5.571031951904297,
|
|
"epoch": 2.1546582804515078,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00045426226826272213,
|
|
"loss": 5.064,
|
|
"mean_token_accuracy": 0.20922781378030778,
|
|
"num_tokens": 42816718.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 5.5425605297088625,
|
|
"epoch": 2.1552198573594654,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004542380016495607,
|
|
"loss": 5.0365,
|
|
"mean_token_accuracy": 0.21452638655900955,
|
|
"num_tokens": 42830183.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 5.487700891494751,
|
|
"epoch": 2.155781434267423,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045421372932939177,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.2164797767996788,
|
|
"num_tokens": 42841241.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 5.686842346191407,
|
|
"epoch": 2.1563430111753803,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004541894513029881,
|
|
"loss": 5.1241,
|
|
"mean_token_accuracy": 0.21199548095464707,
|
|
"num_tokens": 42852775.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 5.735410356521607,
|
|
"epoch": 2.156904588083338,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045416516757112286,
|
|
"loss": 5.2241,
|
|
"mean_token_accuracy": 0.2041873574256897,
|
|
"num_tokens": 42863947.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 5.49827013015747,
|
|
"epoch": 2.1574661649912956,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045414087813456925,
|
|
"loss": 5.0702,
|
|
"mean_token_accuracy": 0.22008589953184127,
|
|
"num_tokens": 42874794.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 5.524099588394165,
|
|
"epoch": 2.1580277418992533,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004541165829941006,
|
|
"loss": 5.0455,
|
|
"mean_token_accuracy": 0.21243919432163239,
|
|
"num_tokens": 42886038.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 5.558943223953247,
|
|
"epoch": 2.1585893188072105,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004540922821504904,
|
|
"loss": 5.0481,
|
|
"mean_token_accuracy": 0.2110162779688835,
|
|
"num_tokens": 42897243.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 5.507229900360107,
|
|
"epoch": 2.159150895715168,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004540679756045125,
|
|
"loss": 4.9864,
|
|
"mean_token_accuracy": 0.21356573402881623,
|
|
"num_tokens": 42908802.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 5.589541864395142,
|
|
"epoch": 2.159712472623126,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004540436633569407,
|
|
"loss": 5.1414,
|
|
"mean_token_accuracy": 0.20550845712423324,
|
|
"num_tokens": 42921156.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 5.45367693901062,
|
|
"epoch": 2.1602740495310835,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045401934540854937,
|
|
"loss": 4.9606,
|
|
"mean_token_accuracy": 0.21830828934907914,
|
|
"num_tokens": 42931336.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 5.53152871131897,
|
|
"epoch": 2.1608356264390407,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004539950217601127,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.21999713629484177,
|
|
"num_tokens": 42942312.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 5.552735233306885,
|
|
"epoch": 2.1613972033469984,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045397069241240497,
|
|
"loss": 5.0736,
|
|
"mean_token_accuracy": 0.21625786721706391,
|
|
"num_tokens": 42953429.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 5.467890739440918,
|
|
"epoch": 2.161958780254956,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000453946357366201,
|
|
"loss": 4.9527,
|
|
"mean_token_accuracy": 0.21559067368507384,
|
|
"num_tokens": 42963354.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 5.603626823425293,
|
|
"epoch": 2.1625203571629132,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045392201662227565,
|
|
"loss": 5.1022,
|
|
"mean_token_accuracy": 0.2173087030649185,
|
|
"num_tokens": 42974643.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 5.550736665725708,
|
|
"epoch": 2.163081934070871,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045389767018140395,
|
|
"loss": 5.085,
|
|
"mean_token_accuracy": 0.21206020712852477,
|
|
"num_tokens": 42985821.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 5.5998992919921875,
|
|
"epoch": 2.1636435109788286,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045387331804436096,
|
|
"loss": 5.1015,
|
|
"mean_token_accuracy": 0.20934343039989473,
|
|
"num_tokens": 42998258.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 5.534904289245605,
|
|
"epoch": 2.1642050878867862,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004538489602119222,
|
|
"loss": 5.0076,
|
|
"mean_token_accuracy": 0.2169676750898361,
|
|
"num_tokens": 43009117.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 5.47719292640686,
|
|
"epoch": 2.1647666647947434,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004538245966848632,
|
|
"loss": 5.0191,
|
|
"mean_token_accuracy": 0.21428176313638686,
|
|
"num_tokens": 43020437.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 5.530072832107544,
|
|
"epoch": 2.165328241702701,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045380022746395953,
|
|
"loss": 5.0692,
|
|
"mean_token_accuracy": 0.21465242952108382,
|
|
"num_tokens": 43031722.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 5.519904232025146,
|
|
"epoch": 2.1658898186106588,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045377585254998743,
|
|
"loss": 4.9926,
|
|
"mean_token_accuracy": 0.22443864792585372,
|
|
"num_tokens": 43042957.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 5.513291072845459,
|
|
"epoch": 2.1664513955186164,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004537514719437228,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.21128850877285005,
|
|
"num_tokens": 43054086.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 5.608696413040161,
|
|
"epoch": 2.1670129724265736,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045372708564594196,
|
|
"loss": 5.1572,
|
|
"mean_token_accuracy": 0.20577065497636796,
|
|
"num_tokens": 43066259.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 5.464995527267456,
|
|
"epoch": 2.1675745493345313,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045370269365742143,
|
|
"loss": 4.8821,
|
|
"mean_token_accuracy": 0.22134891301393508,
|
|
"num_tokens": 43076837.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 5.496037435531616,
|
|
"epoch": 2.168136126242489,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045367829597893776,
|
|
"loss": 4.9471,
|
|
"mean_token_accuracy": 0.22162239402532577,
|
|
"num_tokens": 43087802.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 5.505429935455322,
|
|
"epoch": 2.1686977031504466,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045365389261126793,
|
|
"loss": 4.9717,
|
|
"mean_token_accuracy": 0.21637981086969377,
|
|
"num_tokens": 43097562.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 5.454412126541138,
|
|
"epoch": 2.169259280058404,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00045362948355518883,
|
|
"loss": 4.9713,
|
|
"mean_token_accuracy": 0.21911730319261552,
|
|
"num_tokens": 43107973.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 5.451364326477051,
|
|
"epoch": 2.1698208569663615,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004536050688114777,
|
|
"loss": 4.9394,
|
|
"mean_token_accuracy": 0.22173949480056762,
|
|
"num_tokens": 43118923.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 5.492047691345215,
|
|
"epoch": 2.170382433874319,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00045358064838091187,
|
|
"loss": 4.9929,
|
|
"mean_token_accuracy": 0.2170213744044304,
|
|
"num_tokens": 43130904.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 5.528943061828613,
|
|
"epoch": 2.170944010782277,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045355622226426903,
|
|
"loss": 4.9934,
|
|
"mean_token_accuracy": 0.2131267160177231,
|
|
"num_tokens": 43142293.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 5.552287960052491,
|
|
"epoch": 2.171505587690234,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00045353179046232674,
|
|
"loss": 5.0463,
|
|
"mean_token_accuracy": 0.22204008549451829,
|
|
"num_tokens": 43154340.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 5.519361162185669,
|
|
"epoch": 2.1720671645981917,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000453507352975863,
|
|
"loss": 5.0071,
|
|
"mean_token_accuracy": 0.22217732667922974,
|
|
"num_tokens": 43165924.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 5.468971204757691,
|
|
"epoch": 2.1726287415061494,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00045348290980565595,
|
|
"loss": 4.9564,
|
|
"mean_token_accuracy": 0.21756821870803833,
|
|
"num_tokens": 43177394.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 5.5049591064453125,
|
|
"epoch": 2.1731903184141066,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045345846095248376,
|
|
"loss": 4.9464,
|
|
"mean_token_accuracy": 0.21580301225185394,
|
|
"num_tokens": 43188043.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 5.520325374603272,
|
|
"epoch": 2.1737518953220643,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045343400641712503,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.20727440118789672,
|
|
"num_tokens": 43199466.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 5.437262487411499,
|
|
"epoch": 2.174313472230022,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045340954620035827,
|
|
"loss": 4.9662,
|
|
"mean_token_accuracy": 0.21733541935682296,
|
|
"num_tokens": 43210673.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 5.536609745025634,
|
|
"epoch": 2.1748750491379796,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045338508030296246,
|
|
"loss": 5.059,
|
|
"mean_token_accuracy": 0.214582721889019,
|
|
"num_tokens": 43221263.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 5.548491907119751,
|
|
"epoch": 2.175436626045937,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045336060872571646,
|
|
"loss": 5.065,
|
|
"mean_token_accuracy": 0.21778450161218643,
|
|
"num_tokens": 43232590.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 5.604807901382446,
|
|
"epoch": 2.1759982029538945,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004533361314693994,
|
|
"loss": 5.0924,
|
|
"mean_token_accuracy": 0.21733055412769317,
|
|
"num_tokens": 43243693.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 5.541410493850708,
|
|
"epoch": 2.176559779861852,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045331164853479084,
|
|
"loss": 4.9943,
|
|
"mean_token_accuracy": 0.21512263119220734,
|
|
"num_tokens": 43254526.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 5.607054567337036,
|
|
"epoch": 2.17712135676981,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045328715992267024,
|
|
"loss": 5.1062,
|
|
"mean_token_accuracy": 0.21070781350135803,
|
|
"num_tokens": 43264490.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 5.511202239990235,
|
|
"epoch": 2.177682933677767,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045326266563381734,
|
|
"loss": 4.9901,
|
|
"mean_token_accuracy": 0.21723948717117308,
|
|
"num_tokens": 43275012.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 5.492418098449707,
|
|
"epoch": 2.1782445105857247,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045323816566901205,
|
|
"loss": 4.9997,
|
|
"mean_token_accuracy": 0.21589162498712539,
|
|
"num_tokens": 43285194.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 5.527652072906494,
|
|
"epoch": 2.1788060874936823,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004532136600290343,
|
|
"loss": 5.062,
|
|
"mean_token_accuracy": 0.21967443376779555,
|
|
"num_tokens": 43298159.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 5.570392704010009,
|
|
"epoch": 2.17936766440164,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004531891487146646,
|
|
"loss": 5.1036,
|
|
"mean_token_accuracy": 0.20800223648548127,
|
|
"num_tokens": 43309664.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 5.514455366134643,
|
|
"epoch": 2.179929241309597,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004531646317266833,
|
|
"loss": 5.032,
|
|
"mean_token_accuracy": 0.21771198511123657,
|
|
"num_tokens": 43320399.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 5.465872097015381,
|
|
"epoch": 2.180490818217555,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045314010906587096,
|
|
"loss": 4.9126,
|
|
"mean_token_accuracy": 0.21656649559736252,
|
|
"num_tokens": 43331510.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 5.597373008728027,
|
|
"epoch": 2.1810523951255125,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045311558073300853,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.21858106553554535,
|
|
"num_tokens": 43342844.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 5.47257513999939,
|
|
"epoch": 2.18161397203347,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004530910467288769,
|
|
"loss": 4.9545,
|
|
"mean_token_accuracy": 0.2133133366703987,
|
|
"num_tokens": 43352556.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 5.419732332229614,
|
|
"epoch": 2.1821755489414274,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045306650705425727,
|
|
"loss": 4.9499,
|
|
"mean_token_accuracy": 0.22044442296028138,
|
|
"num_tokens": 43363357.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 5.568076324462891,
|
|
"epoch": 2.182737125849385,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045304196170993093,
|
|
"loss": 5.0207,
|
|
"mean_token_accuracy": 0.21361021995544432,
|
|
"num_tokens": 43374697.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 5.649209833145141,
|
|
"epoch": 2.1832987027573427,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004530174106966795,
|
|
"loss": 5.1087,
|
|
"mean_token_accuracy": 0.20899368971586227,
|
|
"num_tokens": 43386826.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 5.501683473587036,
|
|
"epoch": 2.1838602796653,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045299285401528475,
|
|
"loss": 5.0533,
|
|
"mean_token_accuracy": 0.21592700481414795,
|
|
"num_tokens": 43398352.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 5.53292293548584,
|
|
"epoch": 2.1844218565732576,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004529682916665285,
|
|
"loss": 5.0114,
|
|
"mean_token_accuracy": 0.22032152265310287,
|
|
"num_tokens": 43409509.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 5.507028532028198,
|
|
"epoch": 2.1849834334812153,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00045294372365119276,
|
|
"loss": 4.9744,
|
|
"mean_token_accuracy": 0.21619485318660736,
|
|
"num_tokens": 43420195.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 5.533158302307129,
|
|
"epoch": 2.185545010389173,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004529191499700598,
|
|
"loss": 5.0829,
|
|
"mean_token_accuracy": 0.21609335988759995,
|
|
"num_tokens": 43430599.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 5.442693471908569,
|
|
"epoch": 2.18610658729713,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004528945706239122,
|
|
"loss": 4.9188,
|
|
"mean_token_accuracy": 0.2183141827583313,
|
|
"num_tokens": 43442212.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 5.478957939147949,
|
|
"epoch": 2.186668164205088,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045286998561353236,
|
|
"loss": 4.9599,
|
|
"mean_token_accuracy": 0.21876858025789261,
|
|
"num_tokens": 43452631.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 5.461137580871582,
|
|
"epoch": 2.1872297411130455,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004528453949397033,
|
|
"loss": 5.0195,
|
|
"mean_token_accuracy": 0.21476077884435654,
|
|
"num_tokens": 43463323.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 5.491626024246216,
|
|
"epoch": 2.187791318021003,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045282079860320786,
|
|
"loss": 5.0666,
|
|
"mean_token_accuracy": 0.20933491438627244,
|
|
"num_tokens": 43474451.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 5.475252437591553,
|
|
"epoch": 2.1883528949289603,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045279619660482925,
|
|
"loss": 4.927,
|
|
"mean_token_accuracy": 0.22053967416286469,
|
|
"num_tokens": 43485948.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 5.5854511737823485,
|
|
"epoch": 2.188914471836918,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00045277158894535075,
|
|
"loss": 5.0193,
|
|
"mean_token_accuracy": 0.21937210112810135,
|
|
"num_tokens": 43498955.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 5.527094602584839,
|
|
"epoch": 2.1894760487448757,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045274697562555584,
|
|
"loss": 5.0003,
|
|
"mean_token_accuracy": 0.22366307973861693,
|
|
"num_tokens": 43509416.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 5.487946462631226,
|
|
"epoch": 2.1900376256528333,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004527223566462284,
|
|
"loss": 5.0197,
|
|
"mean_token_accuracy": 0.21759290993213654,
|
|
"num_tokens": 43520387.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 5.45314302444458,
|
|
"epoch": 2.1905992025607905,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004526977320081522,
|
|
"loss": 5.0107,
|
|
"mean_token_accuracy": 0.21430032700300217,
|
|
"num_tokens": 43532006.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 5.454686021804809,
|
|
"epoch": 2.191160779468748,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004526731017121111,
|
|
"loss": 4.9482,
|
|
"mean_token_accuracy": 0.21870541721582412,
|
|
"num_tokens": 43542303.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 5.57761664390564,
|
|
"epoch": 2.191722356376706,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045264846575888973,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.21262185722589494,
|
|
"num_tokens": 43553711.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 5.44252233505249,
|
|
"epoch": 2.1922839332846635,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045262382414927235,
|
|
"loss": 4.9724,
|
|
"mean_token_accuracy": 0.2136426106095314,
|
|
"num_tokens": 43564488.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 5.476780605316162,
|
|
"epoch": 2.1928455101926208,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045259917688404336,
|
|
"loss": 4.9865,
|
|
"mean_token_accuracy": 0.21852104216814042,
|
|
"num_tokens": 43575414.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 5.461527681350708,
|
|
"epoch": 2.1934070871005784,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004525745239639877,
|
|
"loss": 4.9679,
|
|
"mean_token_accuracy": 0.21877976804971694,
|
|
"num_tokens": 43586789.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 5.484581422805786,
|
|
"epoch": 2.193968664008536,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045254986538989045,
|
|
"loss": 4.9577,
|
|
"mean_token_accuracy": 0.22550459802150727,
|
|
"num_tokens": 43597423.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 5.510950517654419,
|
|
"epoch": 2.1945302409164933,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004525252011625366,
|
|
"loss": 4.9827,
|
|
"mean_token_accuracy": 0.2122252494096756,
|
|
"num_tokens": 43606703.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 5.589262819290161,
|
|
"epoch": 2.195091817824451,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004525005312827114,
|
|
"loss": 5.0935,
|
|
"mean_token_accuracy": 0.21470154374837874,
|
|
"num_tokens": 43617869.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 5.58360652923584,
|
|
"epoch": 2.1956533947324086,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004524758557512005,
|
|
"loss": 5.1733,
|
|
"mean_token_accuracy": 0.2136438637971878,
|
|
"num_tokens": 43629102.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 5.542883443832397,
|
|
"epoch": 2.1962149716403663,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004524511745687895,
|
|
"loss": 5.0668,
|
|
"mean_token_accuracy": 0.2179759442806244,
|
|
"num_tokens": 43640421.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 5.5498213291168215,
|
|
"epoch": 2.1967765485483235,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004524264877362643,
|
|
"loss": 4.972,
|
|
"mean_token_accuracy": 0.22218890488147736,
|
|
"num_tokens": 43650516.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 5.515789604187011,
|
|
"epoch": 2.197338125456281,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045240179525441094,
|
|
"loss": 4.9934,
|
|
"mean_token_accuracy": 0.21932897269725798,
|
|
"num_tokens": 43661439.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 5.520218133926392,
|
|
"epoch": 2.197899702364239,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004523770971240156,
|
|
"loss": 5.0808,
|
|
"mean_token_accuracy": 0.21577452272176742,
|
|
"num_tokens": 43672137.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 5.535954761505127,
|
|
"epoch": 2.1984612792721965,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004523523933458647,
|
|
"loss": 5.0347,
|
|
"mean_token_accuracy": 0.21461211144924164,
|
|
"num_tokens": 43683612.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 5.536217164993286,
|
|
"epoch": 2.1990228561801537,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004523276839207448,
|
|
"loss": 5.0136,
|
|
"mean_token_accuracy": 0.2166285455226898,
|
|
"num_tokens": 43694331.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 5.55322756767273,
|
|
"epoch": 2.1995844330881114,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045230296884944264,
|
|
"loss": 5.0796,
|
|
"mean_token_accuracy": 0.2109744966030121,
|
|
"num_tokens": 43706572.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 5.477943086624146,
|
|
"epoch": 2.200146009996069,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00045227824813274517,
|
|
"loss": 4.9374,
|
|
"mean_token_accuracy": 0.22842492312192916,
|
|
"num_tokens": 43718472.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 5.56979660987854,
|
|
"epoch": 2.2007075869040267,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004522535217714396,
|
|
"loss": 5.0701,
|
|
"mean_token_accuracy": 0.216226464509964,
|
|
"num_tokens": 43729642.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 5.534376382827759,
|
|
"epoch": 2.201269163811984,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004522287897663131,
|
|
"loss": 5.0868,
|
|
"mean_token_accuracy": 0.20783924907445908,
|
|
"num_tokens": 43739846.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 5.482331895828247,
|
|
"epoch": 2.2018307407199416,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045220405211815327,
|
|
"loss": 4.9256,
|
|
"mean_token_accuracy": 0.21548637747764587,
|
|
"num_tokens": 43750265.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 5.557156610488891,
|
|
"epoch": 2.202392317627899,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045217930882774754,
|
|
"loss": 5.0322,
|
|
"mean_token_accuracy": 0.2115569144487381,
|
|
"num_tokens": 43761245.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 5.545237302780151,
|
|
"epoch": 2.202953894535857,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045215455989588396,
|
|
"loss": 5.0229,
|
|
"mean_token_accuracy": 0.2166493773460388,
|
|
"num_tokens": 43772677.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 5.551075410842896,
|
|
"epoch": 2.203515471443814,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00045212980532335055,
|
|
"loss": 5.093,
|
|
"mean_token_accuracy": 0.2074023574590683,
|
|
"num_tokens": 43783128.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 5.4757905960083,
|
|
"epoch": 2.2040770483517718,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045210504511093534,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.21937112808227538,
|
|
"num_tokens": 43795323.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 5.618589115142822,
|
|
"epoch": 2.2046386252597294,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004520802792594269,
|
|
"loss": 5.1022,
|
|
"mean_token_accuracy": 0.21376935243606568,
|
|
"num_tokens": 43806917.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 5.644349241256714,
|
|
"epoch": 2.2052002021676866,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045205550776961366,
|
|
"loss": 5.0859,
|
|
"mean_token_accuracy": 0.21520653516054153,
|
|
"num_tokens": 43818963.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 5.464762830734253,
|
|
"epoch": 2.2057617790756443,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004520307306422844,
|
|
"loss": 4.9886,
|
|
"mean_token_accuracy": 0.20970046669244766,
|
|
"num_tokens": 43830163.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 5.514451122283935,
|
|
"epoch": 2.206323355983602,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045200594787822795,
|
|
"loss": 4.97,
|
|
"mean_token_accuracy": 0.22079598754644394,
|
|
"num_tokens": 43840434.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 5.401845264434814,
|
|
"epoch": 2.2068849328915596,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004519811594782335,
|
|
"loss": 4.8375,
|
|
"mean_token_accuracy": 0.22526646703481673,
|
|
"num_tokens": 43851086.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 5.492336988449097,
|
|
"epoch": 2.207446509799517,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045195636544309033,
|
|
"loss": 5.0499,
|
|
"mean_token_accuracy": 0.21033890098333358,
|
|
"num_tokens": 43862834.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 5.5211890697479244,
|
|
"epoch": 2.2080080867074745,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045193156577358784,
|
|
"loss": 5.0558,
|
|
"mean_token_accuracy": 0.20864915996789932,
|
|
"num_tokens": 43874868.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 5.549234008789062,
|
|
"epoch": 2.208569663615432,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004519067604705157,
|
|
"loss": 5.0302,
|
|
"mean_token_accuracy": 0.22280402034521102,
|
|
"num_tokens": 43886175.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 5.496849155426025,
|
|
"epoch": 2.20913124052339,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045188194953466363,
|
|
"loss": 4.9989,
|
|
"mean_token_accuracy": 0.22176545709371567,
|
|
"num_tokens": 43896489.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 5.4805910110473635,
|
|
"epoch": 2.209692817431347,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045185713296682175,
|
|
"loss": 5.0,
|
|
"mean_token_accuracy": 0.21901033371686934,
|
|
"num_tokens": 43907759.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 5.498042726516724,
|
|
"epoch": 2.2102543943393047,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045183231076778005,
|
|
"loss": 5.0024,
|
|
"mean_token_accuracy": 0.21929456740617753,
|
|
"num_tokens": 43918136.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 5.5516180992126465,
|
|
"epoch": 2.2108159712472624,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045180748293832906,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.21394529938697815,
|
|
"num_tokens": 43929662.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 5.522339153289795,
|
|
"epoch": 2.21137754815522,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045178264947925924,
|
|
"loss": 5.0206,
|
|
"mean_token_accuracy": 0.2238750174641609,
|
|
"num_tokens": 43939599.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 5.50408673286438,
|
|
"epoch": 2.2119391250631772,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045175781039136133,
|
|
"loss": 4.9786,
|
|
"mean_token_accuracy": 0.22214894294738768,
|
|
"num_tokens": 43949728.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 5.580263423919678,
|
|
"epoch": 2.212500701971135,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004517329656754261,
|
|
"loss": 5.0698,
|
|
"mean_token_accuracy": 0.21721083223819732,
|
|
"num_tokens": 43961147.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 5.580533885955811,
|
|
"epoch": 2.2130622788790926,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004517081153322448,
|
|
"loss": 5.0359,
|
|
"mean_token_accuracy": 0.2218971237540245,
|
|
"num_tokens": 43972541.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 5.512256240844726,
|
|
"epoch": 2.2136238557870502,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004516832593626085,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.21487784683704375,
|
|
"num_tokens": 43983540.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 5.476344633102417,
|
|
"epoch": 2.2141854326950074,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004516583977673087,
|
|
"loss": 4.9554,
|
|
"mean_token_accuracy": 0.22504897713661193,
|
|
"num_tokens": 43994255.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 5.614608240127564,
|
|
"epoch": 2.214747009602965,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045163353054713704,
|
|
"loss": 5.1261,
|
|
"mean_token_accuracy": 0.21330010890960693,
|
|
"num_tokens": 44004364.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 5.569414901733398,
|
|
"epoch": 2.2153085865109228,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004516086577028852,
|
|
"loss": 5.104,
|
|
"mean_token_accuracy": 0.2123065322637558,
|
|
"num_tokens": 44015487.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 5.60509934425354,
|
|
"epoch": 2.21587016341888,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004515837792353453,
|
|
"loss": 5.0749,
|
|
"mean_token_accuracy": 0.21828112602233887,
|
|
"num_tokens": 44026974.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 5.560262537002563,
|
|
"epoch": 2.2164317403268377,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004515588951453093,
|
|
"loss": 5.0123,
|
|
"mean_token_accuracy": 0.21647901386022567,
|
|
"num_tokens": 44038718.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 5.4815867900848385,
|
|
"epoch": 2.2169933172347953,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004515340054335696,
|
|
"loss": 4.9396,
|
|
"mean_token_accuracy": 0.22086912840604783,
|
|
"num_tokens": 44048821.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 5.544683313369751,
|
|
"epoch": 2.217554894142753,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004515091101009188,
|
|
"loss": 5.1085,
|
|
"mean_token_accuracy": 0.2082324281334877,
|
|
"num_tokens": 44060973.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 5.653628826141357,
|
|
"epoch": 2.21811647105071,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004514842091481493,
|
|
"loss": 5.0808,
|
|
"mean_token_accuracy": 0.21973627656698227,
|
|
"num_tokens": 44073595.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 5.477323246002197,
|
|
"epoch": 2.218678047958668,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004514593025760543,
|
|
"loss": 5.0063,
|
|
"mean_token_accuracy": 0.2132320448756218,
|
|
"num_tokens": 44084860.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 5.522267055511475,
|
|
"epoch": 2.2192396248666255,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00045143439038542653,
|
|
"loss": 5.094,
|
|
"mean_token_accuracy": 0.20872837901115418,
|
|
"num_tokens": 44096026.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 5.55786247253418,
|
|
"epoch": 2.219801201774583,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004514094725770594,
|
|
"loss": 5.0289,
|
|
"mean_token_accuracy": 0.21249134987592697,
|
|
"num_tokens": 44107981.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 5.548605632781983,
|
|
"epoch": 2.2203627786825404,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045138454915174625,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.21582875400781631,
|
|
"num_tokens": 44119589.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 5.496036195755005,
|
|
"epoch": 2.220924355590498,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045135962011028064,
|
|
"loss": 5.0718,
|
|
"mean_token_accuracy": 0.21270845234394073,
|
|
"num_tokens": 44131094.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 5.541290235519409,
|
|
"epoch": 2.2214859324984557,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004513346854534564,
|
|
"loss": 5.0551,
|
|
"mean_token_accuracy": 0.2077616348862648,
|
|
"num_tokens": 44141348.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 5.641642665863037,
|
|
"epoch": 2.2220475094064134,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004513097451820673,
|
|
"loss": 5.1642,
|
|
"mean_token_accuracy": 0.21126456409692765,
|
|
"num_tokens": 44152085.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 5.537990522384644,
|
|
"epoch": 2.2226090863143706,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045128479929690756,
|
|
"loss": 4.9569,
|
|
"mean_token_accuracy": 0.22720523476600646,
|
|
"num_tokens": 44163518.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 5.46861572265625,
|
|
"epoch": 2.2231706632223283,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004512598477987714,
|
|
"loss": 5.0308,
|
|
"mean_token_accuracy": 0.20946355760097504,
|
|
"num_tokens": 44175513.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 5.574788045883179,
|
|
"epoch": 2.223732240130286,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045123489068845334,
|
|
"loss": 5.0243,
|
|
"mean_token_accuracy": 0.2166624680161476,
|
|
"num_tokens": 44186660.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 5.541599130630493,
|
|
"epoch": 2.2242938170382436,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045120992796674804,
|
|
"loss": 5.0839,
|
|
"mean_token_accuracy": 0.20813322812318802,
|
|
"num_tokens": 44197613.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 5.471748161315918,
|
|
"epoch": 2.224855393946201,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004511849596344503,
|
|
"loss": 5.0073,
|
|
"mean_token_accuracy": 0.20724640190601348,
|
|
"num_tokens": 44209469.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 5.537791633605957,
|
|
"epoch": 2.2254169708541585,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045115998569235507,
|
|
"loss": 5.0402,
|
|
"mean_token_accuracy": 0.2121313765645027,
|
|
"num_tokens": 44220672.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 5.571954822540283,
|
|
"epoch": 2.225978547762116,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00045113500614125756,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.20908642262220384,
|
|
"num_tokens": 44232867.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 5.557937288284302,
|
|
"epoch": 2.2265401246700733,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004511100209819532,
|
|
"loss": 5.0533,
|
|
"mean_token_accuracy": 0.21383792161941528,
|
|
"num_tokens": 44245567.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 5.53202714920044,
|
|
"epoch": 2.227101701578031,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045108503021523737,
|
|
"loss": 4.9816,
|
|
"mean_token_accuracy": 0.22519684731960296,
|
|
"num_tokens": 44257449.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 5.527451992034912,
|
|
"epoch": 2.2276632784859887,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00045106003384190604,
|
|
"loss": 5.095,
|
|
"mean_token_accuracy": 0.21207186728715896,
|
|
"num_tokens": 44268890.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 5.5825995922088625,
|
|
"epoch": 2.2282248553939463,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045103503186275486,
|
|
"loss": 5.0491,
|
|
"mean_token_accuracy": 0.20933411717414857,
|
|
"num_tokens": 44280719.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 5.617470407485962,
|
|
"epoch": 2.2287864323019035,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045101002427857997,
|
|
"loss": 5.1412,
|
|
"mean_token_accuracy": 0.20498011857271195,
|
|
"num_tokens": 44292567.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 5.576122188568116,
|
|
"epoch": 2.229348009209861,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045098501109017765,
|
|
"loss": 5.0723,
|
|
"mean_token_accuracy": 0.2124025121331215,
|
|
"num_tokens": 44304177.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 5.5016676902771,
|
|
"epoch": 2.229909586117819,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045095999229834437,
|
|
"loss": 4.9666,
|
|
"mean_token_accuracy": 0.2205975517630577,
|
|
"num_tokens": 44315142.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 5.487029409408569,
|
|
"epoch": 2.2304711630257765,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004509349679038767,
|
|
"loss": 5.1335,
|
|
"mean_token_accuracy": 0.2149762272834778,
|
|
"num_tokens": 44327457.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 5.617055034637451,
|
|
"epoch": 2.2310327399337337,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045090993790757137,
|
|
"loss": 5.1292,
|
|
"mean_token_accuracy": 0.20898691266775132,
|
|
"num_tokens": 44338978.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 5.61577033996582,
|
|
"epoch": 2.2315943168416914,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004508849023102253,
|
|
"loss": 5.114,
|
|
"mean_token_accuracy": 0.21508942693471908,
|
|
"num_tokens": 44349121.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 5.503602170944214,
|
|
"epoch": 2.232155893749649,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004508598611126359,
|
|
"loss": 4.99,
|
|
"mean_token_accuracy": 0.22268788665533065,
|
|
"num_tokens": 44360753.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 5.5981050491333,
|
|
"epoch": 2.2327174706576067,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004508348143156002,
|
|
"loss": 5.0315,
|
|
"mean_token_accuracy": 0.22305696308612824,
|
|
"num_tokens": 44371977.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 5.505199670791626,
|
|
"epoch": 2.233279047565564,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045080976191991587,
|
|
"loss": 4.966,
|
|
"mean_token_accuracy": 0.2189818173646927,
|
|
"num_tokens": 44383077.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 5.50550217628479,
|
|
"epoch": 2.2338406244735216,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004507847039263805,
|
|
"loss": 4.9949,
|
|
"mean_token_accuracy": 0.2122347518801689,
|
|
"num_tokens": 44394827.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 5.4938231945037845,
|
|
"epoch": 2.2344022013814793,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000450759640335792,
|
|
"loss": 4.9616,
|
|
"mean_token_accuracy": 0.2212918609380722,
|
|
"num_tokens": 44406594.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 5.478568744659424,
|
|
"epoch": 2.234963778289437,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004507345711489484,
|
|
"loss": 4.9608,
|
|
"mean_token_accuracy": 0.22228638231754302,
|
|
"num_tokens": 44417842.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 5.533528900146484,
|
|
"epoch": 2.235525355197394,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045070949636664785,
|
|
"loss": 5.0144,
|
|
"mean_token_accuracy": 0.2144067719578743,
|
|
"num_tokens": 44428234.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 5.443822908401489,
|
|
"epoch": 2.236086932105352,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004506844159896888,
|
|
"loss": 4.9712,
|
|
"mean_token_accuracy": 0.2197059229016304,
|
|
"num_tokens": 44437504.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 5.538375663757324,
|
|
"epoch": 2.2366485090133095,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004506593300188698,
|
|
"loss": 5.0336,
|
|
"mean_token_accuracy": 0.22090145498514174,
|
|
"num_tokens": 44447873.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 5.532779502868652,
|
|
"epoch": 2.2372100859212667,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004506342384549897,
|
|
"loss": 5.0847,
|
|
"mean_token_accuracy": 0.21877450346946717,
|
|
"num_tokens": 44458990.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 5.505418348312378,
|
|
"epoch": 2.2377716628292244,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004506091412988472,
|
|
"loss": 5.0027,
|
|
"mean_token_accuracy": 0.21689185500144958,
|
|
"num_tokens": 44469374.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 5.502139234542847,
|
|
"epoch": 2.238333239737182,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045058403855124165,
|
|
"loss": 5.0186,
|
|
"mean_token_accuracy": 0.21908223628997803,
|
|
"num_tokens": 44479629.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 5.562967014312744,
|
|
"epoch": 2.2388948166451397,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004505589302129721,
|
|
"loss": 5.0676,
|
|
"mean_token_accuracy": 0.2127097502350807,
|
|
"num_tokens": 44490603.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 5.463040685653686,
|
|
"epoch": 2.239456393553097,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004505338162848382,
|
|
"loss": 4.9578,
|
|
"mean_token_accuracy": 0.22412658035755156,
|
|
"num_tokens": 44501527.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 5.580593299865723,
|
|
"epoch": 2.2400179704610546,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004505086967676395,
|
|
"loss": 5.1512,
|
|
"mean_token_accuracy": 0.21155949532985688,
|
|
"num_tokens": 44512619.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 5.623563814163208,
|
|
"epoch": 2.240579547369012,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004504835716621757,
|
|
"loss": 5.163,
|
|
"mean_token_accuracy": 0.20709873884916305,
|
|
"num_tokens": 44524639.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 5.5480992794036865,
|
|
"epoch": 2.24114112427697,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004504584409692471,
|
|
"loss": 5.0225,
|
|
"mean_token_accuracy": 0.2204157218337059,
|
|
"num_tokens": 44535013.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 5.6503355503082275,
|
|
"epoch": 2.241702701184927,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00045043330468965364,
|
|
"loss": 5.1184,
|
|
"mean_token_accuracy": 0.21190449148416518,
|
|
"num_tokens": 44546838.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 5.5199073314666744,
|
|
"epoch": 2.2422642780928848,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045040816282419566,
|
|
"loss": 5.0057,
|
|
"mean_token_accuracy": 0.22054285556077957,
|
|
"num_tokens": 44557984.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 5.466346263885498,
|
|
"epoch": 2.2428258550008424,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045038301537367374,
|
|
"loss": 4.9528,
|
|
"mean_token_accuracy": 0.2222136825323105,
|
|
"num_tokens": 44569029.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 5.506089448928833,
|
|
"epoch": 2.2433874319088,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045035786233888864,
|
|
"loss": 5.0764,
|
|
"mean_token_accuracy": 0.2161836951971054,
|
|
"num_tokens": 44578804.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 5.563601732254028,
|
|
"epoch": 2.2439490088167573,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045033270372064123,
|
|
"loss": 4.9906,
|
|
"mean_token_accuracy": 0.21877280622720718,
|
|
"num_tokens": 44589362.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 5.558225488662719,
|
|
"epoch": 2.244510585724715,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045030753951973243,
|
|
"loss": 5.0686,
|
|
"mean_token_accuracy": 0.2126692146062851,
|
|
"num_tokens": 44600137.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 5.509299087524414,
|
|
"epoch": 2.2450721626326726,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045028236973696363,
|
|
"loss": 5.0272,
|
|
"mean_token_accuracy": 0.22364579141139984,
|
|
"num_tokens": 44611707.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 5.537660694122314,
|
|
"epoch": 2.2456337395406303,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004502571943731362,
|
|
"loss": 5.0344,
|
|
"mean_token_accuracy": 0.2163463979959488,
|
|
"num_tokens": 44621141.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 5.551248931884766,
|
|
"epoch": 2.2461953164485875,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004502320134290517,
|
|
"loss": 5.0901,
|
|
"mean_token_accuracy": 0.21621730029582978,
|
|
"num_tokens": 44632043.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 5.546774578094483,
|
|
"epoch": 2.246756893356545,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045020682690551203,
|
|
"loss": 5.0997,
|
|
"mean_token_accuracy": 0.21187424510717393,
|
|
"num_tokens": 44643905.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 5.532029104232788,
|
|
"epoch": 2.247318470264503,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045018163480331887,
|
|
"loss": 5.0382,
|
|
"mean_token_accuracy": 0.20630647242069244,
|
|
"num_tokens": 44655105.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 5.516870403289795,
|
|
"epoch": 2.24788004717246,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045015643712327465,
|
|
"loss": 4.9778,
|
|
"mean_token_accuracy": 0.2180454507470131,
|
|
"num_tokens": 44667096.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 5.592005062103271,
|
|
"epoch": 2.2484416240804177,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004501312338661815,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.21560201197862625,
|
|
"num_tokens": 44678206.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 5.504658174514771,
|
|
"epoch": 2.2490032009883754,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004501060250328419,
|
|
"loss": 4.9811,
|
|
"mean_token_accuracy": 0.21928033381700515,
|
|
"num_tokens": 44688619.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 5.5198901176452635,
|
|
"epoch": 2.249564777896333,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004500808106240586,
|
|
"loss": 5.0368,
|
|
"mean_token_accuracy": 0.21135976016521454,
|
|
"num_tokens": 44700757.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 5.427563095092774,
|
|
"epoch": 2.2501263548042907,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004500555906406343,
|
|
"loss": 4.8952,
|
|
"mean_token_accuracy": 0.225138384103775,
|
|
"num_tokens": 44710822.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 5.4066441535949705,
|
|
"epoch": 2.250687931712248,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004500303650833722,
|
|
"loss": 4.8925,
|
|
"mean_token_accuracy": 0.22407299131155015,
|
|
"num_tokens": 44722163.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 5.588882875442505,
|
|
"epoch": 2.2512495086202056,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004500051339530754,
|
|
"loss": 5.0743,
|
|
"mean_token_accuracy": 0.21150657385587693,
|
|
"num_tokens": 44734271.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 5.623574876785279,
|
|
"epoch": 2.2518110855281632,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004499798972505472,
|
|
"loss": 5.0447,
|
|
"mean_token_accuracy": 0.2150291845202446,
|
|
"num_tokens": 44745345.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 5.481700658798218,
|
|
"epoch": 2.2523726624361204,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044995465497659127,
|
|
"loss": 5.0138,
|
|
"mean_token_accuracy": 0.21378520429134368,
|
|
"num_tokens": 44756986.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 5.467776203155518,
|
|
"epoch": 2.252934239344078,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004499294071320112,
|
|
"loss": 4.9243,
|
|
"mean_token_accuracy": 0.22258745282888412,
|
|
"num_tokens": 44767259.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 5.47691707611084,
|
|
"epoch": 2.2534958162520358,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000449904153717611,
|
|
"loss": 5.05,
|
|
"mean_token_accuracy": 0.21129870265722275,
|
|
"num_tokens": 44778884.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 5.526091575622559,
|
|
"epoch": 2.2540573931599934,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004498788947341947,
|
|
"loss": 4.9611,
|
|
"mean_token_accuracy": 0.221601140499115,
|
|
"num_tokens": 44789216.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 5.441502857208252,
|
|
"epoch": 2.2546189700679506,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004498536301825665,
|
|
"loss": 4.9238,
|
|
"mean_token_accuracy": 0.22332427501678467,
|
|
"num_tokens": 44799357.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 5.477306222915649,
|
|
"epoch": 2.2551805469759083,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000449828360063531,
|
|
"loss": 5.0555,
|
|
"mean_token_accuracy": 0.2129678398370743,
|
|
"num_tokens": 44811040.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 5.574104928970337,
|
|
"epoch": 2.255742123883866,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044980308437789267,
|
|
"loss": 5.1153,
|
|
"mean_token_accuracy": 0.20677785724401473,
|
|
"num_tokens": 44822103.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 5.537933683395385,
|
|
"epoch": 2.2563037007918236,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004497778031264564,
|
|
"loss": 5.017,
|
|
"mean_token_accuracy": 0.21280057579278946,
|
|
"num_tokens": 44834712.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 5.5099669933319095,
|
|
"epoch": 2.256865277699781,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044975251631002694,
|
|
"loss": 4.9499,
|
|
"mean_token_accuracy": 0.2177702933549881,
|
|
"num_tokens": 44845412.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 5.492259979248047,
|
|
"epoch": 2.2574268546077385,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004497272239294097,
|
|
"loss": 5.0333,
|
|
"mean_token_accuracy": 0.21486400365829467,
|
|
"num_tokens": 44857720.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 5.526381921768189,
|
|
"epoch": 2.257988431515696,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004497019259854099,
|
|
"loss": 5.0162,
|
|
"mean_token_accuracy": 0.21998067051172257,
|
|
"num_tokens": 44868253.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 5.540175342559815,
|
|
"epoch": 2.2585500084236534,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044967662247883295,
|
|
"loss": 4.9949,
|
|
"mean_token_accuracy": 0.2128733828663826,
|
|
"num_tokens": 44878525.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 5.415162229537964,
|
|
"epoch": 2.259111585331611,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044965131341048454,
|
|
"loss": 4.9689,
|
|
"mean_token_accuracy": 0.22038732916116716,
|
|
"num_tokens": 44889565.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 5.434309768676758,
|
|
"epoch": 2.2596731622395687,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004496259987811707,
|
|
"loss": 4.9559,
|
|
"mean_token_accuracy": 0.2187286213040352,
|
|
"num_tokens": 44901191.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 5.497772550582885,
|
|
"epoch": 2.2602347391475264,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004496006785916973,
|
|
"loss": 4.9301,
|
|
"mean_token_accuracy": 0.21891519278287888,
|
|
"num_tokens": 44911483.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 5.6200696468353275,
|
|
"epoch": 2.260796316055484,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00044957535284287055,
|
|
"loss": 5.1022,
|
|
"mean_token_accuracy": 0.21530003398656844,
|
|
"num_tokens": 44923537.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 5.568510961532593,
|
|
"epoch": 2.2613578929634413,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044955002153549686,
|
|
"loss": 5.0317,
|
|
"mean_token_accuracy": 0.2140822157263756,
|
|
"num_tokens": 44935780.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 5.566320133209229,
|
|
"epoch": 2.261919469871399,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004495246846703828,
|
|
"loss": 5.0518,
|
|
"mean_token_accuracy": 0.2156530052423477,
|
|
"num_tokens": 44946879.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 5.566345834732056,
|
|
"epoch": 2.2624810467793566,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044949934224833505,
|
|
"loss": 5.0458,
|
|
"mean_token_accuracy": 0.21842523217201232,
|
|
"num_tokens": 44958385.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 5.548521614074707,
|
|
"epoch": 2.263042623687314,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004494739942701606,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.21350047141313552,
|
|
"num_tokens": 44970597.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 5.520525503158569,
|
|
"epoch": 2.2636042005952715,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044944864073666655,
|
|
"loss": 5.0507,
|
|
"mean_token_accuracy": 0.22157226949930192,
|
|
"num_tokens": 44983123.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 5.5499523162841795,
|
|
"epoch": 2.264165777503229,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044942328164866,
|
|
"loss": 5.0014,
|
|
"mean_token_accuracy": 0.21604295670986176,
|
|
"num_tokens": 44993378.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 5.49625883102417,
|
|
"epoch": 2.2647273544111868,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004493979170069486,
|
|
"loss": 4.9521,
|
|
"mean_token_accuracy": 0.21094827800989152,
|
|
"num_tokens": 45004905.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 5.494584465026856,
|
|
"epoch": 2.265288931319144,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044937254681233984,
|
|
"loss": 5.0203,
|
|
"mean_token_accuracy": 0.21530242264270782,
|
|
"num_tokens": 45016640.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 5.5954962253570555,
|
|
"epoch": 2.2658505082271017,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044934717106564164,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.2048359125852585,
|
|
"num_tokens": 45028285.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 5.58119044303894,
|
|
"epoch": 2.2664120851350593,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044932178976766183,
|
|
"loss": 5.0278,
|
|
"mean_token_accuracy": 0.21442173719406127,
|
|
"num_tokens": 45038924.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 5.5329478740692135,
|
|
"epoch": 2.266973662043017,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044929640291920865,
|
|
"loss": 4.9621,
|
|
"mean_token_accuracy": 0.2222355931997299,
|
|
"num_tokens": 45050483.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 5.593491268157959,
|
|
"epoch": 2.267535238950974,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004492710105210904,
|
|
"loss": 5.1788,
|
|
"mean_token_accuracy": 0.20496722012758256,
|
|
"num_tokens": 45063242.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 5.5104012966156,
|
|
"epoch": 2.268096815858932,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044924561257411554,
|
|
"loss": 5.0321,
|
|
"mean_token_accuracy": 0.2103570967912674,
|
|
"num_tokens": 45074057.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 5.527031517028808,
|
|
"epoch": 2.2686583927668895,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004492202090790928,
|
|
"loss": 5.0829,
|
|
"mean_token_accuracy": 0.21220585852861404,
|
|
"num_tokens": 45085488.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 5.608630704879761,
|
|
"epoch": 2.2692199696748467,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004491948000368311,
|
|
"loss": 5.1257,
|
|
"mean_token_accuracy": 0.21333254873752594,
|
|
"num_tokens": 45096303.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 5.514669942855835,
|
|
"epoch": 2.2697815465828044,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044916938544813936,
|
|
"loss": 4.9096,
|
|
"mean_token_accuracy": 0.22026229053735732,
|
|
"num_tokens": 45106411.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 5.539509248733521,
|
|
"epoch": 2.270343123490762,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044914396531382686,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.2146800473332405,
|
|
"num_tokens": 45117355.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 5.4909828186035154,
|
|
"epoch": 2.2709047003987197,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044911853963470295,
|
|
"loss": 4.9602,
|
|
"mean_token_accuracy": 0.22228717505931855,
|
|
"num_tokens": 45127612.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 5.614795780181884,
|
|
"epoch": 2.2714662773066774,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004490931084115772,
|
|
"loss": 5.127,
|
|
"mean_token_accuracy": 0.21472587585449218,
|
|
"num_tokens": 45138495.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 5.566579532623291,
|
|
"epoch": 2.2720278542146346,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044906767164525936,
|
|
"loss": 4.9726,
|
|
"mean_token_accuracy": 0.223576095700264,
|
|
"num_tokens": 45149727.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 5.5417181015014645,
|
|
"epoch": 2.2725894311225923,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004490422293365594,
|
|
"loss": 5.0437,
|
|
"mean_token_accuracy": 0.21483254581689834,
|
|
"num_tokens": 45160921.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 5.447387075424194,
|
|
"epoch": 2.27315100803055,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004490167814862872,
|
|
"loss": 4.9736,
|
|
"mean_token_accuracy": 0.22045573145151137,
|
|
"num_tokens": 45172607.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 5.603069305419922,
|
|
"epoch": 2.273712584938507,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004489913280952533,
|
|
"loss": 5.1374,
|
|
"mean_token_accuracy": 0.2154537096619606,
|
|
"num_tokens": 45186330.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 5.426331520080566,
|
|
"epoch": 2.274274161846465,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004489658691642681,
|
|
"loss": 4.89,
|
|
"mean_token_accuracy": 0.2276003196835518,
|
|
"num_tokens": 45198239.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 5.430828857421875,
|
|
"epoch": 2.2748357387544225,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044894040469414207,
|
|
"loss": 4.9224,
|
|
"mean_token_accuracy": 0.22258893847465516,
|
|
"num_tokens": 45209295.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 5.541683959960937,
|
|
"epoch": 2.27539731566238,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044891493468568607,
|
|
"loss": 5.0457,
|
|
"mean_token_accuracy": 0.21564511954784393,
|
|
"num_tokens": 45220210.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 5.556733751296997,
|
|
"epoch": 2.2759588925703373,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00044888945913971106,
|
|
"loss": 5.05,
|
|
"mean_token_accuracy": 0.2158108815550804,
|
|
"num_tokens": 45231809.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 5.552735328674316,
|
|
"epoch": 2.276520469478295,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00044886397805702835,
|
|
"loss": 5.0284,
|
|
"mean_token_accuracy": 0.22377929836511612,
|
|
"num_tokens": 45242847.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 5.485146713256836,
|
|
"epoch": 2.2770820463862527,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044883849143844914,
|
|
"loss": 4.9575,
|
|
"mean_token_accuracy": 0.22531650066375733,
|
|
"num_tokens": 45253357.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 5.444186067581176,
|
|
"epoch": 2.2776436232942103,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004488129992847848,
|
|
"loss": 4.8965,
|
|
"mean_token_accuracy": 0.22022038400173188,
|
|
"num_tokens": 45264607.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 5.578175592422485,
|
|
"epoch": 2.2782052002021675,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004487875015968473,
|
|
"loss": 5.0539,
|
|
"mean_token_accuracy": 0.22028457075357438,
|
|
"num_tokens": 45275211.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 5.480272912979126,
|
|
"epoch": 2.278766777110125,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004487619983754483,
|
|
"loss": 4.9251,
|
|
"mean_token_accuracy": 0.23015227317810058,
|
|
"num_tokens": 45286665.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 5.481760406494141,
|
|
"epoch": 2.279328354018083,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00044873648962139983,
|
|
"loss": 5.0647,
|
|
"mean_token_accuracy": 0.2142808198928833,
|
|
"num_tokens": 45298066.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 5.502311706542969,
|
|
"epoch": 2.27988993092604,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004487109753355142,
|
|
"loss": 5.0238,
|
|
"mean_token_accuracy": 0.2139996349811554,
|
|
"num_tokens": 45308799.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 5.501436710357666,
|
|
"epoch": 2.2804515078339977,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004486854555186037,
|
|
"loss": 4.8958,
|
|
"mean_token_accuracy": 0.2249002143740654,
|
|
"num_tokens": 45319932.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 5.565549612045288,
|
|
"epoch": 2.2810130847419554,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004486599301714809,
|
|
"loss": 5.0509,
|
|
"mean_token_accuracy": 0.2173139289021492,
|
|
"num_tokens": 45330008.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 5.547131776809692,
|
|
"epoch": 2.281574661649913,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004486343992949587,
|
|
"loss": 5.0631,
|
|
"mean_token_accuracy": 0.2076545238494873,
|
|
"num_tokens": 45340877.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 5.551836919784546,
|
|
"epoch": 2.2821362385578707,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044860886288984977,
|
|
"loss": 5.012,
|
|
"mean_token_accuracy": 0.21866750717163086,
|
|
"num_tokens": 45351956.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 5.578943872451783,
|
|
"epoch": 2.282697815465828,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004485833209569674,
|
|
"loss": 5.106,
|
|
"mean_token_accuracy": 0.20931802242994307,
|
|
"num_tokens": 45363133.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 5.515356349945068,
|
|
"epoch": 2.2832593923737856,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004485577734971247,
|
|
"loss": 4.9626,
|
|
"mean_token_accuracy": 0.21819316893815993,
|
|
"num_tokens": 45373917.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 5.5602789402008055,
|
|
"epoch": 2.2838209692817433,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044853222051113525,
|
|
"loss": 5.07,
|
|
"mean_token_accuracy": 0.21720924973487854,
|
|
"num_tokens": 45385575.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 5.537344694137573,
|
|
"epoch": 2.2843825461897005,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044850666199981244,
|
|
"loss": 4.9655,
|
|
"mean_token_accuracy": 0.2195739209651947,
|
|
"num_tokens": 45396615.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 5.53484697341919,
|
|
"epoch": 2.284944123097658,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044848109796397035,
|
|
"loss": 4.9901,
|
|
"mean_token_accuracy": 0.21506604850292205,
|
|
"num_tokens": 45408931.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 5.595519781112671,
|
|
"epoch": 2.285505700005616,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044845552840442276,
|
|
"loss": 5.0581,
|
|
"mean_token_accuracy": 0.21388394832611085,
|
|
"num_tokens": 45419993.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 5.547989559173584,
|
|
"epoch": 2.2860672769135735,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044842995332198393,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.20773522853851317,
|
|
"num_tokens": 45431889.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 5.4633935451507565,
|
|
"epoch": 2.2866288538215307,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044840437271746807,
|
|
"loss": 5.0263,
|
|
"mean_token_accuracy": 0.21630053520202636,
|
|
"num_tokens": 45444233.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 5.500809812545777,
|
|
"epoch": 2.2871904307294884,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004483787865916898,
|
|
"loss": 4.9825,
|
|
"mean_token_accuracy": 0.21912205666303636,
|
|
"num_tokens": 45455743.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 5.4943009376525875,
|
|
"epoch": 2.287752007637446,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044835319494546366,
|
|
"loss": 4.931,
|
|
"mean_token_accuracy": 0.21772704273462296,
|
|
"num_tokens": 45466272.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 5.564087772369385,
|
|
"epoch": 2.2883135845454037,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044832759777960456,
|
|
"loss": 4.9727,
|
|
"mean_token_accuracy": 0.21926030218601228,
|
|
"num_tokens": 45477828.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 5.5381693840026855,
|
|
"epoch": 2.288875161453361,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004483019950949276,
|
|
"loss": 4.9995,
|
|
"mean_token_accuracy": 0.21388251334428787,
|
|
"num_tokens": 45489315.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 5.441487073898315,
|
|
"epoch": 2.2894367383613186,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004482763868922478,
|
|
"loss": 4.9714,
|
|
"mean_token_accuracy": 0.22285035252571106,
|
|
"num_tokens": 45499836.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 5.532894277572632,
|
|
"epoch": 2.289998315269276,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004482507731723807,
|
|
"loss": 5.0387,
|
|
"mean_token_accuracy": 0.21364971697330476,
|
|
"num_tokens": 45511106.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 5.542057037353516,
|
|
"epoch": 2.2905598921772334,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004482251539361418,
|
|
"loss": 4.9898,
|
|
"mean_token_accuracy": 0.21543824225664138,
|
|
"num_tokens": 45521314.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 5.583531475067138,
|
|
"epoch": 2.291121469085191,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004481995291843467,
|
|
"loss": 5.0495,
|
|
"mean_token_accuracy": 0.21962677389383317,
|
|
"num_tokens": 45531675.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 5.555460739135742,
|
|
"epoch": 2.2916830459931488,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004481738989178115,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.21404756754636764,
|
|
"num_tokens": 45542064.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 5.522829246520996,
|
|
"epoch": 2.2922446229011064,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004481482631373522,
|
|
"loss": 5.0894,
|
|
"mean_token_accuracy": 0.2153431609272957,
|
|
"num_tokens": 45553764.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 5.621661758422851,
|
|
"epoch": 2.292806199809064,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00044812262184378503,
|
|
"loss": 5.0759,
|
|
"mean_token_accuracy": 0.21525806188583374,
|
|
"num_tokens": 45565302.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 5.457597875595093,
|
|
"epoch": 2.2933677767170213,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044809697503792647,
|
|
"loss": 4.9147,
|
|
"mean_token_accuracy": 0.22829592376947402,
|
|
"num_tokens": 45577165.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 5.505373811721801,
|
|
"epoch": 2.293929353624979,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044807132272059306,
|
|
"loss": 4.979,
|
|
"mean_token_accuracy": 0.22215070575475693,
|
|
"num_tokens": 45587771.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 5.496624279022217,
|
|
"epoch": 2.2944909305329366,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004480456648926016,
|
|
"loss": 4.998,
|
|
"mean_token_accuracy": 0.22650871127843858,
|
|
"num_tokens": 45598815.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 5.497972726821899,
|
|
"epoch": 2.295052507440894,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004480200015547691,
|
|
"loss": 4.9786,
|
|
"mean_token_accuracy": 0.2154836744070053,
|
|
"num_tokens": 45609007.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 5.537816047668457,
|
|
"epoch": 2.2956140843488515,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00044799433270791255,
|
|
"loss": 5.0692,
|
|
"mean_token_accuracy": 0.21754280179739,
|
|
"num_tokens": 45621323.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 5.433668947219848,
|
|
"epoch": 2.296175661256809,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004479686583528494,
|
|
"loss": 4.8565,
|
|
"mean_token_accuracy": 0.22207009345293044,
|
|
"num_tokens": 45631895.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 5.535416841506958,
|
|
"epoch": 2.296737238164767,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004479429784903971,
|
|
"loss": 5.0232,
|
|
"mean_token_accuracy": 0.2190642848610878,
|
|
"num_tokens": 45643204.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 5.58393611907959,
|
|
"epoch": 2.297298815072724,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004479172931213733,
|
|
"loss": 5.0452,
|
|
"mean_token_accuracy": 0.2178732767701149,
|
|
"num_tokens": 45654607.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 5.4296633243560795,
|
|
"epoch": 2.2978603919806817,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004478916022465958,
|
|
"loss": 4.9585,
|
|
"mean_token_accuracy": 0.21905323266983032,
|
|
"num_tokens": 45666746.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 5.499394035339355,
|
|
"epoch": 2.2984219688886394,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004478659058668827,
|
|
"loss": 4.9115,
|
|
"mean_token_accuracy": 0.2198905184864998,
|
|
"num_tokens": 45676663.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 5.49765567779541,
|
|
"epoch": 2.298983545796597,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044784020398305204,
|
|
"loss": 4.9531,
|
|
"mean_token_accuracy": 0.21482738852500916,
|
|
"num_tokens": 45688746.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 5.6275248527526855,
|
|
"epoch": 2.2995451227045542,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004478144965959222,
|
|
"loss": 5.1369,
|
|
"mean_token_accuracy": 0.2159050449728966,
|
|
"num_tokens": 45700199.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 5.536463403701783,
|
|
"epoch": 2.300106699612512,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044778878370631183,
|
|
"loss": 4.9998,
|
|
"mean_token_accuracy": 0.21027853041887284,
|
|
"num_tokens": 45710771.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 5.565132904052734,
|
|
"epoch": 2.3006682765204696,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044776306531503957,
|
|
"loss": 5.1629,
|
|
"mean_token_accuracy": 0.21185825020074844,
|
|
"num_tokens": 45721957.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 5.546128129959106,
|
|
"epoch": 2.301229853428427,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044773734142292425,
|
|
"loss": 5.0313,
|
|
"mean_token_accuracy": 0.21309620141983032,
|
|
"num_tokens": 45733904.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 5.607325220108033,
|
|
"epoch": 2.3017914303363844,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004477116120307851,
|
|
"loss": 5.0279,
|
|
"mean_token_accuracy": 0.21692472249269484,
|
|
"num_tokens": 45744004.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 5.541652584075928,
|
|
"epoch": 2.302353007244342,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004476858771394412,
|
|
"loss": 4.9478,
|
|
"mean_token_accuracy": 0.23010701090097427,
|
|
"num_tokens": 45755130.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 5.524637842178345,
|
|
"epoch": 2.3029145841522998,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004476601367497119,
|
|
"loss": 5.1288,
|
|
"mean_token_accuracy": 0.20721037536859513,
|
|
"num_tokens": 45767353.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 5.578741788864136,
|
|
"epoch": 2.3034761610602574,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000447634390862417,
|
|
"loss": 5.1895,
|
|
"mean_token_accuracy": 0.1998126119375229,
|
|
"num_tokens": 45779266.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 5.6353506565094,
|
|
"epoch": 2.3040377379682146,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044760863947837607,
|
|
"loss": 5.1154,
|
|
"mean_token_accuracy": 0.21289069801568986,
|
|
"num_tokens": 45790601.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 5.537068700790405,
|
|
"epoch": 2.3045993148761723,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00044758288259840904,
|
|
"loss": 4.9998,
|
|
"mean_token_accuracy": 0.21581446826457978,
|
|
"num_tokens": 45801449.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 5.440796613693237,
|
|
"epoch": 2.30516089178413,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004475571202233363,
|
|
"loss": 4.9479,
|
|
"mean_token_accuracy": 0.21947215646505355,
|
|
"num_tokens": 45811737.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 5.532358646392822,
|
|
"epoch": 2.305722468692087,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004475313523539778,
|
|
"loss": 5.0034,
|
|
"mean_token_accuracy": 0.22088104784488677,
|
|
"num_tokens": 45822955.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 5.53133864402771,
|
|
"epoch": 2.306284045600045,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044750557899115407,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.22381386756896973,
|
|
"num_tokens": 45834697.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 5.476288843154907,
|
|
"epoch": 2.3068456225080025,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004474798001356859,
|
|
"loss": 4.9965,
|
|
"mean_token_accuracy": 0.21661789566278458,
|
|
"num_tokens": 45846869.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 5.47454252243042,
|
|
"epoch": 2.30740719941596,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000447454015788394,
|
|
"loss": 4.9797,
|
|
"mean_token_accuracy": 0.2198227360844612,
|
|
"num_tokens": 45858171.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 5.523162937164306,
|
|
"epoch": 2.3079687763239174,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004474282259500992,
|
|
"loss": 4.9859,
|
|
"mean_token_accuracy": 0.2129409983754158,
|
|
"num_tokens": 45868715.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 5.545602226257325,
|
|
"epoch": 2.308530353231875,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000447402430621623,
|
|
"loss": 4.9858,
|
|
"mean_token_accuracy": 0.22567598670721054,
|
|
"num_tokens": 45880569.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 5.541715049743653,
|
|
"epoch": 2.3090919301398327,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004473766298037865,
|
|
"loss": 4.9793,
|
|
"mean_token_accuracy": 0.21914239674806596,
|
|
"num_tokens": 45890452.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 5.592472410202026,
|
|
"epoch": 2.3096535070477904,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00044735082349741116,
|
|
"loss": 5.0968,
|
|
"mean_token_accuracy": 0.213210129737854,
|
|
"num_tokens": 45903125.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 5.487708902359008,
|
|
"epoch": 2.3102150839557476,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00044732501170331886,
|
|
"loss": 4.9632,
|
|
"mean_token_accuracy": 0.22159618884325027,
|
|
"num_tokens": 45914961.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 5.5966212272644045,
|
|
"epoch": 2.3107766608637053,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004472991944223313,
|
|
"loss": 5.1335,
|
|
"mean_token_accuracy": 0.20942577719688416,
|
|
"num_tokens": 45927198.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 5.562869834899902,
|
|
"epoch": 2.311338237771663,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00044727337165527056,
|
|
"loss": 5.0911,
|
|
"mean_token_accuracy": 0.2143895223736763,
|
|
"num_tokens": 45937937.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 5.617971563339234,
|
|
"epoch": 2.31189981467962,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044724754340295887,
|
|
"loss": 5.0379,
|
|
"mean_token_accuracy": 0.20797871500253678,
|
|
"num_tokens": 45948983.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 5.520430374145508,
|
|
"epoch": 2.312461391587578,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004472217096662186,
|
|
"loss": 5.0753,
|
|
"mean_token_accuracy": 0.2134031668305397,
|
|
"num_tokens": 45960674.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 5.5350316047668455,
|
|
"epoch": 2.3130229684955355,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004471958704458723,
|
|
"loss": 5.0064,
|
|
"mean_token_accuracy": 0.21467837542295456,
|
|
"num_tokens": 45971260.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 5.624927568435669,
|
|
"epoch": 2.313584545403493,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00044717002574274267,
|
|
"loss": 5.0127,
|
|
"mean_token_accuracy": 0.22433886528015137,
|
|
"num_tokens": 45983942.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 5.528057956695557,
|
|
"epoch": 2.314146122311451,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004471441755576527,
|
|
"loss": 5.0681,
|
|
"mean_token_accuracy": 0.20806693881750107,
|
|
"num_tokens": 45995983.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 5.543956327438354,
|
|
"epoch": 2.314707699219408,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044711831989142534,
|
|
"loss": 4.9582,
|
|
"mean_token_accuracy": 0.2166326329112053,
|
|
"num_tokens": 46007074.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 5.6087061882019045,
|
|
"epoch": 2.3152692761273657,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044709245874488405,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.21721668243408204,
|
|
"num_tokens": 46018376.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 5.526835107803345,
|
|
"epoch": 2.3158308530353233,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004470665921188519,
|
|
"loss": 4.9915,
|
|
"mean_token_accuracy": 0.217928509414196,
|
|
"num_tokens": 46029192.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 5.502330112457275,
|
|
"epoch": 2.3163924299432805,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044704072001415285,
|
|
"loss": 5.0517,
|
|
"mean_token_accuracy": 0.21590762138366698,
|
|
"num_tokens": 46040735.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 5.484842109680176,
|
|
"epoch": 2.316954006851238,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044701484243161055,
|
|
"loss": 4.9189,
|
|
"mean_token_accuracy": 0.2250294104218483,
|
|
"num_tokens": 46050859.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 5.443659448623658,
|
|
"epoch": 2.317515583759196,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000446988959372049,
|
|
"loss": 4.9999,
|
|
"mean_token_accuracy": 0.2189323663711548,
|
|
"num_tokens": 46060704.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 5.464203882217407,
|
|
"epoch": 2.3180771606671535,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004469630708362922,
|
|
"loss": 5.0189,
|
|
"mean_token_accuracy": 0.21272530555725097,
|
|
"num_tokens": 46072317.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 5.59088659286499,
|
|
"epoch": 2.3186387375751107,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004469371768251646,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.21275742799043657,
|
|
"num_tokens": 46083823.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 5.627917003631592,
|
|
"epoch": 2.3192003144830684,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004469112773394906,
|
|
"loss": 5.0757,
|
|
"mean_token_accuracy": 0.21398030519485473,
|
|
"num_tokens": 46093920.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 5.49130277633667,
|
|
"epoch": 2.319761891391026,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004468853723800948,
|
|
"loss": 4.9974,
|
|
"mean_token_accuracy": 0.22291107773780822,
|
|
"num_tokens": 46104618.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 5.487282657623291,
|
|
"epoch": 2.3203234682989837,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004468594619478021,
|
|
"loss": 4.8819,
|
|
"mean_token_accuracy": 0.2188535898923874,
|
|
"num_tokens": 46114748.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 5.539809608459473,
|
|
"epoch": 2.320885045206941,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004468335460434375,
|
|
"loss": 5.0588,
|
|
"mean_token_accuracy": 0.2204669326543808,
|
|
"num_tokens": 46125125.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 5.437728023529052,
|
|
"epoch": 2.3214466221148986,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004468076246678261,
|
|
"loss": 4.9503,
|
|
"mean_token_accuracy": 0.21401802003383635,
|
|
"num_tokens": 46135877.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 5.57085075378418,
|
|
"epoch": 2.3220081990228563,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044678169782179334,
|
|
"loss": 5.1457,
|
|
"mean_token_accuracy": 0.20827373415231704,
|
|
"num_tokens": 46146769.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 5.514590120315551,
|
|
"epoch": 2.3225697759308135,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044675576550616466,
|
|
"loss": 5.0007,
|
|
"mean_token_accuracy": 0.2178739294409752,
|
|
"num_tokens": 46158408.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 5.567808008193969,
|
|
"epoch": 2.323131352838771,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044672982772176584,
|
|
"loss": 5.126,
|
|
"mean_token_accuracy": 0.2080349236726761,
|
|
"num_tokens": 46169961.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 5.598749399185181,
|
|
"epoch": 2.323692929746729,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004467038844694227,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.21343600749969482,
|
|
"num_tokens": 46181750.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 5.554172515869141,
|
|
"epoch": 2.3242545066546865,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004466779357499612,
|
|
"loss": 4.9574,
|
|
"mean_token_accuracy": 0.2210423991084099,
|
|
"num_tokens": 46192745.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 5.537807416915894,
|
|
"epoch": 2.324816083562644,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044665198156420774,
|
|
"loss": 5.0558,
|
|
"mean_token_accuracy": 0.21833985149860383,
|
|
"num_tokens": 46203267.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 5.502267599105835,
|
|
"epoch": 2.3253776604706013,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044662602191298856,
|
|
"loss": 5.0018,
|
|
"mean_token_accuracy": 0.21790873557329177,
|
|
"num_tokens": 46214966.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 5.507996273040772,
|
|
"epoch": 2.325939237378559,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00044660005679713027,
|
|
"loss": 4.9702,
|
|
"mean_token_accuracy": 0.22030646204948426,
|
|
"num_tokens": 46225755.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 5.550733947753907,
|
|
"epoch": 2.3265008142865167,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00044657408621745964,
|
|
"loss": 5.0399,
|
|
"mean_token_accuracy": 0.21778851449489595,
|
|
"num_tokens": 46237091.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 5.5589512348175045,
|
|
"epoch": 2.327062391194474,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004465481101748036,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.2133980244398117,
|
|
"num_tokens": 46249250.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 5.53260064125061,
|
|
"epoch": 2.3276239681024316,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044652212866998914,
|
|
"loss": 4.9762,
|
|
"mean_token_accuracy": 0.21771362274885178,
|
|
"num_tokens": 46259866.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 5.488447284698486,
|
|
"epoch": 2.328185545010389,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00044649614170384354,
|
|
"loss": 4.9577,
|
|
"mean_token_accuracy": 0.22697565853595733,
|
|
"num_tokens": 46270888.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 5.512794351577758,
|
|
"epoch": 2.328747121918347,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044647014927719436,
|
|
"loss": 5.0293,
|
|
"mean_token_accuracy": 0.2127450093626976,
|
|
"num_tokens": 46281109.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 5.519795846939087,
|
|
"epoch": 2.329308698826304,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044644415139086913,
|
|
"loss": 4.8945,
|
|
"mean_token_accuracy": 0.2285095661878586,
|
|
"num_tokens": 46292171.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 5.52105746269226,
|
|
"epoch": 2.3298702757342618,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004464181480456955,
|
|
"loss": 4.9768,
|
|
"mean_token_accuracy": 0.21827558279037476,
|
|
"num_tokens": 46302919.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 5.428065061569214,
|
|
"epoch": 2.3304318526422194,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004463921392425017,
|
|
"loss": 4.9117,
|
|
"mean_token_accuracy": 0.22453514188528062,
|
|
"num_tokens": 46313199.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 5.598998975753784,
|
|
"epoch": 2.330993429550177,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044636612498211566,
|
|
"loss": 5.0469,
|
|
"mean_token_accuracy": 0.2141270235180855,
|
|
"num_tokens": 46324316.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 5.510714435577393,
|
|
"epoch": 2.3315550064581343,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044634010526536575,
|
|
"loss": 5.0365,
|
|
"mean_token_accuracy": 0.21354566365480424,
|
|
"num_tokens": 46335767.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 5.46871657371521,
|
|
"epoch": 2.332116583366092,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004463140800930804,
|
|
"loss": 4.9588,
|
|
"mean_token_accuracy": 0.21326034367084504,
|
|
"num_tokens": 46347840.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 5.532648086547852,
|
|
"epoch": 2.3326781602740496,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004462880494660883,
|
|
"loss": 5.1086,
|
|
"mean_token_accuracy": 0.20897155702114106,
|
|
"num_tokens": 46359766.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 5.570405960083008,
|
|
"epoch": 2.333239737182007,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044626201338521834,
|
|
"loss": 4.9806,
|
|
"mean_token_accuracy": 0.22979419380426408,
|
|
"num_tokens": 46371426.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 5.541094827651977,
|
|
"epoch": 2.3338013140899645,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004462359718512993,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.21225306391716003,
|
|
"num_tokens": 46382257.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 5.555874681472778,
|
|
"epoch": 2.334362890997922,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00044620992486516073,
|
|
"loss": 5.0307,
|
|
"mean_token_accuracy": 0.2126808762550354,
|
|
"num_tokens": 46393689.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 5.570913362503052,
|
|
"epoch": 2.33492446790588,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004461838724276316,
|
|
"loss": 5.0714,
|
|
"mean_token_accuracy": 0.21686942428350447,
|
|
"num_tokens": 46404856.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 5.635024976730347,
|
|
"epoch": 2.3354860448138375,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044615781453954164,
|
|
"loss": 5.0675,
|
|
"mean_token_accuracy": 0.20711927115917206,
|
|
"num_tokens": 46415395.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 5.621561050415039,
|
|
"epoch": 2.3360476217217947,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044613175120172035,
|
|
"loss": 5.0787,
|
|
"mean_token_accuracy": 0.2147354081273079,
|
|
"num_tokens": 46426773.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 5.470870447158814,
|
|
"epoch": 2.3366091986297524,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004461056824149979,
|
|
"loss": 4.9259,
|
|
"mean_token_accuracy": 0.22235175520181655,
|
|
"num_tokens": 46438206.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 5.523656940460205,
|
|
"epoch": 2.33717077553771,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000446079608180204,
|
|
"loss": 5.047,
|
|
"mean_token_accuracy": 0.21878981292247773,
|
|
"num_tokens": 46449922.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 5.491311359405517,
|
|
"epoch": 2.3377323524456672,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004460535284981692,
|
|
"loss": 4.9295,
|
|
"mean_token_accuracy": 0.2231728881597519,
|
|
"num_tokens": 46461715.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 5.4939055919647215,
|
|
"epoch": 2.338293929353625,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004460274433697235,
|
|
"loss": 4.9979,
|
|
"mean_token_accuracy": 0.21216827929019927,
|
|
"num_tokens": 46473136.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 5.469852018356323,
|
|
"epoch": 2.3388555062615826,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044600135279569784,
|
|
"loss": 4.9004,
|
|
"mean_token_accuracy": 0.22352322638034822,
|
|
"num_tokens": 46483644.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 5.581731176376342,
|
|
"epoch": 2.3394170831695402,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044597525677692273,
|
|
"loss": 5.0644,
|
|
"mean_token_accuracy": 0.2184366136789322,
|
|
"num_tokens": 46494896.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 5.602496242523193,
|
|
"epoch": 2.3399786600774974,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004459491553142291,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.21489936262369155,
|
|
"num_tokens": 46505415.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 5.5247228145599365,
|
|
"epoch": 2.340540236985455,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00044592304840844813,
|
|
"loss": 5.0306,
|
|
"mean_token_accuracy": 0.21800798028707505,
|
|
"num_tokens": 46516280.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 5.443897438049317,
|
|
"epoch": 2.3411018138934128,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000445896936060411,
|
|
"loss": 4.9092,
|
|
"mean_token_accuracy": 0.22214221954345703,
|
|
"num_tokens": 46526456.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 5.5771317958831785,
|
|
"epoch": 2.3416633908013704,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044587081827094906,
|
|
"loss": 5.0357,
|
|
"mean_token_accuracy": 0.217498542368412,
|
|
"num_tokens": 46537547.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 5.461738729476929,
|
|
"epoch": 2.3422249677093276,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00044584469504089407,
|
|
"loss": 4.9492,
|
|
"mean_token_accuracy": 0.22364979684352876,
|
|
"num_tokens": 46549424.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 5.521225166320801,
|
|
"epoch": 2.3427865446172853,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004458185663710777,
|
|
"loss": 4.972,
|
|
"mean_token_accuracy": 0.21903700828552247,
|
|
"num_tokens": 46560234.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 5.531472778320312,
|
|
"epoch": 2.343348121525243,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004457924322623319,
|
|
"loss": 5.0044,
|
|
"mean_token_accuracy": 0.2161193311214447,
|
|
"num_tokens": 46570847.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 5.452326679229737,
|
|
"epoch": 2.3439096984332,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044576629271548884,
|
|
"loss": 4.9792,
|
|
"mean_token_accuracy": 0.2191176414489746,
|
|
"num_tokens": 46582379.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 5.506544303894043,
|
|
"epoch": 2.344471275341158,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004457401477313808,
|
|
"loss": 5.008,
|
|
"mean_token_accuracy": 0.21314579695463182,
|
|
"num_tokens": 46594669.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 5.433322191238403,
|
|
"epoch": 2.3450328522491155,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004457139973108403,
|
|
"loss": 4.8981,
|
|
"mean_token_accuracy": 0.2272897869348526,
|
|
"num_tokens": 46605834.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 5.513880062103271,
|
|
"epoch": 2.345594429157073,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004456878414546998,
|
|
"loss": 5.0054,
|
|
"mean_token_accuracy": 0.22167778313159942,
|
|
"num_tokens": 46616684.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 5.523144149780274,
|
|
"epoch": 2.346156006065031,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044566168016379234,
|
|
"loss": 5.037,
|
|
"mean_token_accuracy": 0.2205515906214714,
|
|
"num_tokens": 46628045.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 5.49727873802185,
|
|
"epoch": 2.346717582972988,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004456355134389507,
|
|
"loss": 5.0074,
|
|
"mean_token_accuracy": 0.21491773575544357,
|
|
"num_tokens": 46639455.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 5.639538383483886,
|
|
"epoch": 2.3472791598809457,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044560934128100814,
|
|
"loss": 5.2038,
|
|
"mean_token_accuracy": 0.2077769637107849,
|
|
"num_tokens": 46651025.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 5.589868640899658,
|
|
"epoch": 2.3478407367889034,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044558316369079805,
|
|
"loss": 5.0149,
|
|
"mean_token_accuracy": 0.21430882811546326,
|
|
"num_tokens": 46661859.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 5.57333197593689,
|
|
"epoch": 2.3484023136968606,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044555698066915385,
|
|
"loss": 4.9865,
|
|
"mean_token_accuracy": 0.21654639691114425,
|
|
"num_tokens": 46673441.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 5.584176397323608,
|
|
"epoch": 2.3489638906048182,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004455307922169092,
|
|
"loss": 5.0659,
|
|
"mean_token_accuracy": 0.21244944483041764,
|
|
"num_tokens": 46684959.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 5.559808158874512,
|
|
"epoch": 2.349525467512776,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004455045983348979,
|
|
"loss": 5.1045,
|
|
"mean_token_accuracy": 0.22493693828582764,
|
|
"num_tokens": 46694940.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 5.5084264278411865,
|
|
"epoch": 2.3500870444207336,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004454783990239542,
|
|
"loss": 4.9865,
|
|
"mean_token_accuracy": 0.22067876011133195,
|
|
"num_tokens": 46706184.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 5.5443846702575685,
|
|
"epoch": 2.350648621328691,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044545219428491215,
|
|
"loss": 5.0053,
|
|
"mean_token_accuracy": 0.2253313645720482,
|
|
"num_tokens": 46718267.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 5.520178318023682,
|
|
"epoch": 2.3512101982366485,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044542598411860605,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.21547778993844985,
|
|
"num_tokens": 46729293.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 5.495725631713867,
|
|
"epoch": 2.351771775144606,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004453997685258706,
|
|
"loss": 5.0126,
|
|
"mean_token_accuracy": 0.21692253798246383,
|
|
"num_tokens": 46740214.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 5.580843353271485,
|
|
"epoch": 2.3523333520525638,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044537354750754033,
|
|
"loss": 5.0847,
|
|
"mean_token_accuracy": 0.21256499290466307,
|
|
"num_tokens": 46751269.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 5.495484685897827,
|
|
"epoch": 2.352894928960521,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004453473210644503,
|
|
"loss": 4.8536,
|
|
"mean_token_accuracy": 0.23038448095321656,
|
|
"num_tokens": 46761851.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 5.478664588928223,
|
|
"epoch": 2.3534565058684787,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004453210891974355,
|
|
"loss": 4.9974,
|
|
"mean_token_accuracy": 0.21962607353925706,
|
|
"num_tokens": 46773441.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 5.432811880111695,
|
|
"epoch": 2.3540180827764363,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00044529485190733113,
|
|
"loss": 4.9807,
|
|
"mean_token_accuracy": 0.21836940795183182,
|
|
"num_tokens": 46785016.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 5.551907348632812,
|
|
"epoch": 2.3545796596843935,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004452686091949727,
|
|
"loss": 5.0248,
|
|
"mean_token_accuracy": 0.21214471459388734,
|
|
"num_tokens": 46796059.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 5.496445226669311,
|
|
"epoch": 2.355141236592351,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044524236106119563,
|
|
"loss": 4.9565,
|
|
"mean_token_accuracy": 0.22076206803321838,
|
|
"num_tokens": 46805725.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 5.534666919708252,
|
|
"epoch": 2.355702813500309,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044521610750683586,
|
|
"loss": 4.9538,
|
|
"mean_token_accuracy": 0.22328146994113923,
|
|
"num_tokens": 46816300.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 5.479611015319824,
|
|
"epoch": 2.3562643904082665,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004451898485327291,
|
|
"loss": 4.9627,
|
|
"mean_token_accuracy": 0.21872564703226088,
|
|
"num_tokens": 46827498.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 5.521636533737182,
|
|
"epoch": 2.356825967316224,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004451635841397116,
|
|
"loss": 4.9951,
|
|
"mean_token_accuracy": 0.21629632264375687,
|
|
"num_tokens": 46838416.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 5.556480884552002,
|
|
"epoch": 2.3573875442241814,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004451373143286195,
|
|
"loss": 5.086,
|
|
"mean_token_accuracy": 0.21370928585529328,
|
|
"num_tokens": 46849371.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 5.4913653373718265,
|
|
"epoch": 2.357949121132139,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044511103910028945,
|
|
"loss": 5.0106,
|
|
"mean_token_accuracy": 0.21929299533367158,
|
|
"num_tokens": 46860095.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 5.60245099067688,
|
|
"epoch": 2.3585106980400967,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004450847584555579,
|
|
"loss": 5.1015,
|
|
"mean_token_accuracy": 0.20974529385566712,
|
|
"num_tokens": 46871217.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 2.3585106980400967,
|
|
"eval_entropy": 5.375346313286664,
|
|
"eval_loss": 5.1246514320373535,
|
|
"eval_mean_token_accuracy": 0.21969848376383386,
|
|
"eval_num_tokens": 46871217.0,
|
|
"eval_runtime": 18.5299,
|
|
"eval_samples_per_second": 1673.676,
|
|
"eval_steps_per_second": 209.23,
|
|
"step": 21000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 89030,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.088086512328704e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|