171de99300
Model: fpadovani/eng-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.3369461447745269,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"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
|
|
}
|
|
],
|
|
"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": 1549103788523520.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|