3823058c68
Model: fpadovani/eus-latn-100mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
30090 lines
824 KiB
JSON
30090 lines
824 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.3246202755210172,
|
|
"eval_steps": 3000,
|
|
"global_step": 15000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 7.639010858535767,
|
|
"epoch": 0.0004415400918403391,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 2e-06,
|
|
"loss": 7.4495,
|
|
"mean_token_accuracy": 0.08912035375833512,
|
|
"num_tokens": 9390.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.592498016357422,
|
|
"epoch": 0.0008830801836806782,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 7.5473,
|
|
"mean_token_accuracy": 0.08600941896438599,
|
|
"num_tokens": 18671.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.60152039527893,
|
|
"epoch": 0.0013246202755210173,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 7e-06,
|
|
"loss": 7.4983,
|
|
"mean_token_accuracy": 0.09218712449073792,
|
|
"num_tokens": 27614.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.6614744663238525,
|
|
"epoch": 0.0017661603673613563,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 7.6113,
|
|
"mean_token_accuracy": 0.0849214605987072,
|
|
"num_tokens": 37850.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.640540361404419,
|
|
"epoch": 0.0022077004592016957,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 7.4958,
|
|
"mean_token_accuracy": 0.10092130824923515,
|
|
"num_tokens": 47166.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.689523506164551,
|
|
"epoch": 0.0026492405510420347,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 7.485,
|
|
"mean_token_accuracy": 0.09342324361205101,
|
|
"num_tokens": 55500.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.649916553497315,
|
|
"epoch": 0.0030907806428823736,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 7.4904,
|
|
"mean_token_accuracy": 0.08857546746730804,
|
|
"num_tokens": 63851.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 7.70954270362854,
|
|
"epoch": 0.0035323207347227126,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 7.5264,
|
|
"mean_token_accuracy": 0.09447742104530335,
|
|
"num_tokens": 73697.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 7.706955003738403,
|
|
"epoch": 0.003973860826563052,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 7.4835,
|
|
"mean_token_accuracy": 0.09832259118556977,
|
|
"num_tokens": 83000.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.693207168579102,
|
|
"epoch": 0.004415400918403391,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 7.4891,
|
|
"mean_token_accuracy": 0.09248929545283317,
|
|
"num_tokens": 92982.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.701184225082398,
|
|
"epoch": 0.00485694101024373,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 7.4475,
|
|
"mean_token_accuracy": 0.0948328971862793,
|
|
"num_tokens": 101455.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.600388383865356,
|
|
"epoch": 0.005298481102084069,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 7.4784,
|
|
"mean_token_accuracy": 0.09275375679135323,
|
|
"num_tokens": 110782.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.643292331695557,
|
|
"epoch": 0.005740021193924408,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 7.3593,
|
|
"mean_token_accuracy": 0.09755741134285927,
|
|
"num_tokens": 119241.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 7.646019697189331,
|
|
"epoch": 0.006181561285764747,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 7.4621,
|
|
"mean_token_accuracy": 0.08904825896024704,
|
|
"num_tokens": 127903.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 7.611093521118164,
|
|
"epoch": 0.006623101377605086,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 7.4256,
|
|
"mean_token_accuracy": 0.09207391366362572,
|
|
"num_tokens": 137370.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.66001524925232,
|
|
"epoch": 0.007064641469445425,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 7.3699,
|
|
"mean_token_accuracy": 0.09808079078793526,
|
|
"num_tokens": 146582.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.637924289703369,
|
|
"epoch": 0.007506181561285765,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 7.3648,
|
|
"mean_token_accuracy": 0.09920610412955284,
|
|
"num_tokens": 154933.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.600069618225097,
|
|
"epoch": 0.007947721653126103,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 7.4711,
|
|
"mean_token_accuracy": 0.0958680585026741,
|
|
"num_tokens": 165157.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.64748182296753,
|
|
"epoch": 0.008389261744966443,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 7.379,
|
|
"mean_token_accuracy": 0.09376930147409439,
|
|
"num_tokens": 174958.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.598965072631836,
|
|
"epoch": 0.008830801836806783,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 7.4361,
|
|
"mean_token_accuracy": 0.0984335981309414,
|
|
"num_tokens": 184256.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 7.684039211273193,
|
|
"epoch": 0.009272341928647121,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 7.367,
|
|
"mean_token_accuracy": 0.10001294463872909,
|
|
"num_tokens": 192894.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.646014642715454,
|
|
"epoch": 0.00971388202048746,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 7.4273,
|
|
"mean_token_accuracy": 0.09812369421124459,
|
|
"num_tokens": 202675.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.599092102050781,
|
|
"epoch": 0.010155422112327799,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 7.4314,
|
|
"mean_token_accuracy": 0.09605375379323959,
|
|
"num_tokens": 212261.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 7.727504396438599,
|
|
"epoch": 0.010596962204168139,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 7.5105,
|
|
"mean_token_accuracy": 0.09431948810815811,
|
|
"num_tokens": 222329.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.697684812545776,
|
|
"epoch": 0.011038502296008477,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 7.4354,
|
|
"mean_token_accuracy": 0.09025316089391708,
|
|
"num_tokens": 231247.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 7.657842016220092,
|
|
"epoch": 0.011480042387848817,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.379,
|
|
"mean_token_accuracy": 0.1007770724594593,
|
|
"num_tokens": 239978.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 7.621602201461792,
|
|
"epoch": 0.011921582479689156,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.4038,
|
|
"mean_token_accuracy": 0.09848067536950111,
|
|
"num_tokens": 249735.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.6923524856567385,
|
|
"epoch": 0.012363122571529495,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.4418,
|
|
"mean_token_accuracy": 0.09509150311350822,
|
|
"num_tokens": 259369.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.714404106140137,
|
|
"epoch": 0.012804662663369834,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.4701,
|
|
"mean_token_accuracy": 0.09397952705621719,
|
|
"num_tokens": 268645.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 7.6344895362854,
|
|
"epoch": 0.013246202755210172,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.3506,
|
|
"mean_token_accuracy": 0.10026702061295509,
|
|
"num_tokens": 276667.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.631509923934937,
|
|
"epoch": 0.013687742847050512,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.3888,
|
|
"mean_token_accuracy": 0.10270725786685944,
|
|
"num_tokens": 286017.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 7.641970491409301,
|
|
"epoch": 0.01412928293889085,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.4111,
|
|
"mean_token_accuracy": 0.09624978005886078,
|
|
"num_tokens": 295631.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.598629140853882,
|
|
"epoch": 0.01457082303073119,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.4006,
|
|
"mean_token_accuracy": 0.10352006703615188,
|
|
"num_tokens": 304704.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.7567332744598385,
|
|
"epoch": 0.01501236312257153,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.4231,
|
|
"mean_token_accuracy": 0.10067867860198021,
|
|
"num_tokens": 314195.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.665441656112671,
|
|
"epoch": 0.015453903214411868,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.4392,
|
|
"mean_token_accuracy": 0.09234830960631371,
|
|
"num_tokens": 323379.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.631372451782227,
|
|
"epoch": 0.015895443306252206,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.3662,
|
|
"mean_token_accuracy": 0.10526679679751397,
|
|
"num_tokens": 332322.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.573805236816407,
|
|
"epoch": 0.016336983398092548,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.3379,
|
|
"mean_token_accuracy": 0.10242495015263557,
|
|
"num_tokens": 341735.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.7565899848937985,
|
|
"epoch": 0.016778523489932886,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.4344,
|
|
"mean_token_accuracy": 0.09886153489351272,
|
|
"num_tokens": 351209.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.6179423332214355,
|
|
"epoch": 0.017220063581773224,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.3605,
|
|
"mean_token_accuracy": 0.10053950771689416,
|
|
"num_tokens": 360467.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.6365471363067625,
|
|
"epoch": 0.017661603673613566,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.4033,
|
|
"mean_token_accuracy": 0.10138513222336769,
|
|
"num_tokens": 370361.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.720054578781128,
|
|
"epoch": 0.018103143765453904,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.4181,
|
|
"mean_token_accuracy": 0.09296029135584831,
|
|
"num_tokens": 380366.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.615629529953003,
|
|
"epoch": 0.018544683857294242,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.3449,
|
|
"mean_token_accuracy": 0.10289899110794068,
|
|
"num_tokens": 390690.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.594337797164917,
|
|
"epoch": 0.01898622394913458,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.4248,
|
|
"mean_token_accuracy": 0.09637770131230354,
|
|
"num_tokens": 400722.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.605887174606323,
|
|
"epoch": 0.01942776404097492,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.3072,
|
|
"mean_token_accuracy": 0.09810378924012184,
|
|
"num_tokens": 410223.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.63714017868042,
|
|
"epoch": 0.01986930413281526,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.3788,
|
|
"mean_token_accuracy": 0.10300084874033928,
|
|
"num_tokens": 420214.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.656309795379639,
|
|
"epoch": 0.020310844224655598,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.3416,
|
|
"mean_token_accuracy": 0.09932817742228509,
|
|
"num_tokens": 429407.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.613865327835083,
|
|
"epoch": 0.02075238431649594,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.2821,
|
|
"mean_token_accuracy": 0.0999271385371685,
|
|
"num_tokens": 438403.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.571551370620727,
|
|
"epoch": 0.021193924408336277,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.3115,
|
|
"mean_token_accuracy": 0.10332573652267456,
|
|
"num_tokens": 447466.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.66993556022644,
|
|
"epoch": 0.021635464500176615,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.4665,
|
|
"mean_token_accuracy": 0.09346566423773765,
|
|
"num_tokens": 457141.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.626456832885742,
|
|
"epoch": 0.022077004592016954,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.3079,
|
|
"mean_token_accuracy": 0.09943239539861679,
|
|
"num_tokens": 465708.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.6611328125,
|
|
"epoch": 0.022518544683857295,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.3345,
|
|
"mean_token_accuracy": 0.09984651207923889,
|
|
"num_tokens": 475369.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.552011871337891,
|
|
"epoch": 0.022960084775697633,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.2893,
|
|
"mean_token_accuracy": 0.10191124230623246,
|
|
"num_tokens": 484249.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.669333648681641,
|
|
"epoch": 0.02340162486753797,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.4184,
|
|
"mean_token_accuracy": 0.09950976893305778,
|
|
"num_tokens": 493303.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.627326536178589,
|
|
"epoch": 0.023843164959378313,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.3782,
|
|
"mean_token_accuracy": 0.10428153648972512,
|
|
"num_tokens": 501503.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.684601449966431,
|
|
"epoch": 0.02428470505121865,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.2836,
|
|
"mean_token_accuracy": 0.10307212695479392,
|
|
"num_tokens": 509661.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.573146200180053,
|
|
"epoch": 0.02472624514305899,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.2937,
|
|
"mean_token_accuracy": 0.0982547052204609,
|
|
"num_tokens": 519464.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.555501937866211,
|
|
"epoch": 0.025167785234899327,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.2655,
|
|
"mean_token_accuracy": 0.1019679419696331,
|
|
"num_tokens": 527968.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.598510599136352,
|
|
"epoch": 0.02560932532673967,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.3321,
|
|
"mean_token_accuracy": 0.10574981644749641,
|
|
"num_tokens": 537234.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.564266014099121,
|
|
"epoch": 0.026050865418580007,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.2971,
|
|
"mean_token_accuracy": 0.1034348577260971,
|
|
"num_tokens": 546398.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.582965517044068,
|
|
"epoch": 0.026492405510420345,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.3228,
|
|
"mean_token_accuracy": 0.10241033658385276,
|
|
"num_tokens": 555362.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.702879476547241,
|
|
"epoch": 0.026933945602260687,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.3457,
|
|
"mean_token_accuracy": 0.09650135710835457,
|
|
"num_tokens": 564575.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.648530769348144,
|
|
"epoch": 0.027375485694101025,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.3769,
|
|
"mean_token_accuracy": 0.10071438252925873,
|
|
"num_tokens": 573915.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.583766126632691,
|
|
"epoch": 0.027817025785941363,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.2641,
|
|
"mean_token_accuracy": 0.1006499283015728,
|
|
"num_tokens": 583216.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.5586583614349365,
|
|
"epoch": 0.0282585658777817,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.322,
|
|
"mean_token_accuracy": 0.10538614764809609,
|
|
"num_tokens": 591955.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.593068265914917,
|
|
"epoch": 0.028700105969622042,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.3037,
|
|
"mean_token_accuracy": 0.10241075083613396,
|
|
"num_tokens": 600999.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.519618797302246,
|
|
"epoch": 0.02914164606146238,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.2217,
|
|
"mean_token_accuracy": 0.1135806605219841,
|
|
"num_tokens": 609478.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.557135772705078,
|
|
"epoch": 0.02958318615330272,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.3182,
|
|
"mean_token_accuracy": 0.1028580516576767,
|
|
"num_tokens": 618348.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.581590604782105,
|
|
"epoch": 0.03002472624514306,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.3462,
|
|
"mean_token_accuracy": 0.10086702331900596,
|
|
"num_tokens": 628548.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.617287588119507,
|
|
"epoch": 0.0304662663369834,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.2931,
|
|
"mean_token_accuracy": 0.10549068599939346,
|
|
"num_tokens": 637489.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.5078435897827145,
|
|
"epoch": 0.030907806428823736,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.2827,
|
|
"mean_token_accuracy": 0.10264097377657891,
|
|
"num_tokens": 646715.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.540816068649292,
|
|
"epoch": 0.031349346520664075,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.2795,
|
|
"mean_token_accuracy": 0.10515663996338845,
|
|
"num_tokens": 656858.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.596448993682861,
|
|
"epoch": 0.03179088661250441,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.2682,
|
|
"mean_token_accuracy": 0.10302142426371574,
|
|
"num_tokens": 665968.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.53389573097229,
|
|
"epoch": 0.03223242670434476,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.2449,
|
|
"mean_token_accuracy": 0.10066767483949661,
|
|
"num_tokens": 674295.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.472217559814453,
|
|
"epoch": 0.032673966796185096,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.2024,
|
|
"mean_token_accuracy": 0.1055987648665905,
|
|
"num_tokens": 683559.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.468035459518433,
|
|
"epoch": 0.033115506888025434,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.2347,
|
|
"mean_token_accuracy": 0.104932302236557,
|
|
"num_tokens": 692402.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.603985595703125,
|
|
"epoch": 0.03355704697986577,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.3376,
|
|
"mean_token_accuracy": 0.09718681424856186,
|
|
"num_tokens": 702052.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.571860313415527,
|
|
"epoch": 0.03399858707170611,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.2579,
|
|
"mean_token_accuracy": 0.103890460729599,
|
|
"num_tokens": 711926.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.518250036239624,
|
|
"epoch": 0.03444012716354645,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.2055,
|
|
"mean_token_accuracy": 0.10119849517941475,
|
|
"num_tokens": 720948.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.473824882507325,
|
|
"epoch": 0.034881667255386786,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.2572,
|
|
"mean_token_accuracy": 0.1049205407500267,
|
|
"num_tokens": 729611.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.686066150665283,
|
|
"epoch": 0.03532320734722713,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.2316,
|
|
"mean_token_accuracy": 0.0993150919675827,
|
|
"num_tokens": 738433.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.416238927841187,
|
|
"epoch": 0.03576474743906747,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.2808,
|
|
"mean_token_accuracy": 0.10098983719944954,
|
|
"num_tokens": 747310.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.518594074249267,
|
|
"epoch": 0.03620628753090781,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.2464,
|
|
"mean_token_accuracy": 0.10577662512660027,
|
|
"num_tokens": 756362.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.609608840942383,
|
|
"epoch": 0.036647827622748146,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.2509,
|
|
"mean_token_accuracy": 0.10020640343427659,
|
|
"num_tokens": 764978.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.396434926986695,
|
|
"epoch": 0.037089367714588484,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.2338,
|
|
"mean_token_accuracy": 0.10793569758534431,
|
|
"num_tokens": 774058.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.5231493473052975,
|
|
"epoch": 0.03753090780642882,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.2202,
|
|
"mean_token_accuracy": 0.10111990198493004,
|
|
"num_tokens": 783332.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.536509370803833,
|
|
"epoch": 0.03797244789826916,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.2874,
|
|
"mean_token_accuracy": 0.09968122690916062,
|
|
"num_tokens": 792481.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.3964588165283205,
|
|
"epoch": 0.038413987990109505,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.1932,
|
|
"mean_token_accuracy": 0.10685456469655037,
|
|
"num_tokens": 801396.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.5557657241821286,
|
|
"epoch": 0.03885552808194984,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.2548,
|
|
"mean_token_accuracy": 0.09790834933519363,
|
|
"num_tokens": 809903.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.494475698471069,
|
|
"epoch": 0.03929706817379018,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.2027,
|
|
"mean_token_accuracy": 0.10747286528348923,
|
|
"num_tokens": 819144.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.3877339363098145,
|
|
"epoch": 0.03973860826563052,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.2456,
|
|
"mean_token_accuracy": 0.1021496333181858,
|
|
"num_tokens": 828881.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.51954607963562,
|
|
"epoch": 0.04018014835747086,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.1614,
|
|
"mean_token_accuracy": 0.09784932136535644,
|
|
"num_tokens": 837588.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.3755847930908205,
|
|
"epoch": 0.040621688449311195,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.1635,
|
|
"mean_token_accuracy": 0.1048378475010395,
|
|
"num_tokens": 847002.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.388737916946411,
|
|
"epoch": 0.041063228541151534,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.1795,
|
|
"mean_token_accuracy": 0.10455363765358924,
|
|
"num_tokens": 855791.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.4601222515106205,
|
|
"epoch": 0.04150476863299188,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.2059,
|
|
"mean_token_accuracy": 0.11087375283241271,
|
|
"num_tokens": 865392.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.434926748275757,
|
|
"epoch": 0.04194630872483222,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.2927,
|
|
"mean_token_accuracy": 0.10048188641667366,
|
|
"num_tokens": 874807.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.5444385528564455,
|
|
"epoch": 0.042387848816672555,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.25,
|
|
"mean_token_accuracy": 0.1069977454841137,
|
|
"num_tokens": 883928.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.370575952529907,
|
|
"epoch": 0.04282938890851289,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.1509,
|
|
"mean_token_accuracy": 0.10749021843075753,
|
|
"num_tokens": 893047.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.429861927032471,
|
|
"epoch": 0.04327092900035323,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.1449,
|
|
"mean_token_accuracy": 0.10997916385531425,
|
|
"num_tokens": 901645.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.455361604690552,
|
|
"epoch": 0.04371246909219357,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.1695,
|
|
"mean_token_accuracy": 0.1042562760412693,
|
|
"num_tokens": 911169.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.393462133407593,
|
|
"epoch": 0.04415400918403391,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.2024,
|
|
"mean_token_accuracy": 0.10118649303913116,
|
|
"num_tokens": 921382.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.3356465816497805,
|
|
"epoch": 0.04459554927587425,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.1024,
|
|
"mean_token_accuracy": 0.11079763695597648,
|
|
"num_tokens": 930409.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.3716787815094,
|
|
"epoch": 0.04503708936771459,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.077,
|
|
"mean_token_accuracy": 0.11271328553557396,
|
|
"num_tokens": 939049.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.437454271316528,
|
|
"epoch": 0.04547862945955493,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.1052,
|
|
"mean_token_accuracy": 0.10970233231782914,
|
|
"num_tokens": 947575.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.417500114440918,
|
|
"epoch": 0.045920169551395267,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.2637,
|
|
"mean_token_accuracy": 0.10168002024292946,
|
|
"num_tokens": 957848.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.374029064178467,
|
|
"epoch": 0.046361709643235605,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.1028,
|
|
"mean_token_accuracy": 0.10596310794353485,
|
|
"num_tokens": 966521.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.3952889919281,
|
|
"epoch": 0.04680324973507594,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.1719,
|
|
"mean_token_accuracy": 0.110343337059021,
|
|
"num_tokens": 975827.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.375133419036866,
|
|
"epoch": 0.04724478982691628,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.1173,
|
|
"mean_token_accuracy": 0.11087020114064217,
|
|
"num_tokens": 985292.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.2821883201599125,
|
|
"epoch": 0.047686329918756626,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.1083,
|
|
"mean_token_accuracy": 0.11026296317577362,
|
|
"num_tokens": 994791.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.3696636199951175,
|
|
"epoch": 0.048127870010596964,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.0853,
|
|
"mean_token_accuracy": 0.11716266572475434,
|
|
"num_tokens": 1003700.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.283825445175171,
|
|
"epoch": 0.0485694101024373,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.1168,
|
|
"mean_token_accuracy": 0.10780237540602684,
|
|
"num_tokens": 1012682.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.344115352630615,
|
|
"epoch": 0.04901095019427764,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.1338,
|
|
"mean_token_accuracy": 0.10582566857337952,
|
|
"num_tokens": 1021018.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.34993805885315,
|
|
"epoch": 0.04945249028611798,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.0103,
|
|
"mean_token_accuracy": 0.11074965745210648,
|
|
"num_tokens": 1029744.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.1853831768035885,
|
|
"epoch": 0.049894030377958316,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.098,
|
|
"mean_token_accuracy": 0.11121385991573333,
|
|
"num_tokens": 1038805.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.3726812362670895,
|
|
"epoch": 0.050335570469798654,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.1603,
|
|
"mean_token_accuracy": 0.10785874202847481,
|
|
"num_tokens": 1047656.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.3822227954864506,
|
|
"epoch": 0.050777110561639,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.1509,
|
|
"mean_token_accuracy": 0.10956593379378318,
|
|
"num_tokens": 1056598.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.472517013549805,
|
|
"epoch": 0.05121865065347934,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.1581,
|
|
"mean_token_accuracy": 0.10991680398583412,
|
|
"num_tokens": 1065226.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.192884206771851,
|
|
"epoch": 0.051660190745319676,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.0768,
|
|
"mean_token_accuracy": 0.11151133328676224,
|
|
"num_tokens": 1074661.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.38781328201294,
|
|
"epoch": 0.052101730837160014,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.1923,
|
|
"mean_token_accuracy": 0.10381263568997383,
|
|
"num_tokens": 1083921.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.323068380355835,
|
|
"epoch": 0.05254327092900035,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.0614,
|
|
"mean_token_accuracy": 0.11602075025439262,
|
|
"num_tokens": 1093399.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.208582735061645,
|
|
"epoch": 0.05298481102084069,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.1418,
|
|
"mean_token_accuracy": 0.10923573076725006,
|
|
"num_tokens": 1104065.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.303856897354126,
|
|
"epoch": 0.05342635111268103,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.039,
|
|
"mean_token_accuracy": 0.11398651152849197,
|
|
"num_tokens": 1112995.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.268756914138794,
|
|
"epoch": 0.05386789120452137,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.0618,
|
|
"mean_token_accuracy": 0.10772402063012124,
|
|
"num_tokens": 1121637.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.217564678192138,
|
|
"epoch": 0.05430943129636171,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.0115,
|
|
"mean_token_accuracy": 0.11113513186573983,
|
|
"num_tokens": 1131166.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.258164548873902,
|
|
"epoch": 0.05475097138820205,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.0109,
|
|
"mean_token_accuracy": 0.11285025104880334,
|
|
"num_tokens": 1140888.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.336677837371826,
|
|
"epoch": 0.05519251148004239,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.1858,
|
|
"mean_token_accuracy": 0.10437602549791336,
|
|
"num_tokens": 1150278.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.263944149017334,
|
|
"epoch": 0.055634051571882726,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.1197,
|
|
"mean_token_accuracy": 0.1070900171995163,
|
|
"num_tokens": 1159348.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.358008766174317,
|
|
"epoch": 0.056075591663723064,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.1418,
|
|
"mean_token_accuracy": 0.10531127899885177,
|
|
"num_tokens": 1168883.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.3235701560974125,
|
|
"epoch": 0.0565171317555634,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.0476,
|
|
"mean_token_accuracy": 0.11230480372905731,
|
|
"num_tokens": 1178572.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.20401668548584,
|
|
"epoch": 0.05695867184740375,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.1383,
|
|
"mean_token_accuracy": 0.10713300257921218,
|
|
"num_tokens": 1188909.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.316440725326538,
|
|
"epoch": 0.057400211939244085,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.0315,
|
|
"mean_token_accuracy": 0.10825848579406738,
|
|
"num_tokens": 1197705.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.163294839859009,
|
|
"epoch": 0.05784175203108442,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.8835,
|
|
"mean_token_accuracy": 0.11359791234135627,
|
|
"num_tokens": 1206351.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.221329212188721,
|
|
"epoch": 0.05828329212292476,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.9963,
|
|
"mean_token_accuracy": 0.10536118149757386,
|
|
"num_tokens": 1214984.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.231037664413452,
|
|
"epoch": 0.0587248322147651,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.0925,
|
|
"mean_token_accuracy": 0.10655909925699233,
|
|
"num_tokens": 1224485.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.283737277984619,
|
|
"epoch": 0.05916637230660544,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.099,
|
|
"mean_token_accuracy": 0.10594365671277046,
|
|
"num_tokens": 1233560.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.223735809326172,
|
|
"epoch": 0.05960791239844578,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.0297,
|
|
"mean_token_accuracy": 0.1108290746808052,
|
|
"num_tokens": 1242628.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.167131948471069,
|
|
"epoch": 0.06004945249028612,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.9188,
|
|
"mean_token_accuracy": 0.11332646831870079,
|
|
"num_tokens": 1251004.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.260364675521851,
|
|
"epoch": 0.06049099258212646,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.1323,
|
|
"mean_token_accuracy": 0.1082038976252079,
|
|
"num_tokens": 1260344.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.175093746185302,
|
|
"epoch": 0.0609325326739668,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.0298,
|
|
"mean_token_accuracy": 0.11300270706415176,
|
|
"num_tokens": 1269988.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.1856037139892575,
|
|
"epoch": 0.061374072765807135,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.004,
|
|
"mean_token_accuracy": 0.11544976383447647,
|
|
"num_tokens": 1280912.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.1747633934021,
|
|
"epoch": 0.06181561285764747,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.0176,
|
|
"mean_token_accuracy": 0.1107965774834156,
|
|
"num_tokens": 1289684.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.233529663085937,
|
|
"epoch": 0.06225715294948781,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.0457,
|
|
"mean_token_accuracy": 0.10817870572209358,
|
|
"num_tokens": 1298853.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.151789426803589,
|
|
"epoch": 0.06269869304132815,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.9907,
|
|
"mean_token_accuracy": 0.11804186925292015,
|
|
"num_tokens": 1309112.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.147295379638672,
|
|
"epoch": 0.0631402331331685,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.9855,
|
|
"mean_token_accuracy": 0.11006599962711335,
|
|
"num_tokens": 1319064.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.0800573348999025,
|
|
"epoch": 0.06358177322500883,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.9575,
|
|
"mean_token_accuracy": 0.12022612541913986,
|
|
"num_tokens": 1327889.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.178079271316529,
|
|
"epoch": 0.06402331331684917,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.9869,
|
|
"mean_token_accuracy": 0.10886182188987732,
|
|
"num_tokens": 1337241.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.1545867919921875,
|
|
"epoch": 0.06446485340868952,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.0356,
|
|
"mean_token_accuracy": 0.11060537174344062,
|
|
"num_tokens": 1346527.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.176617908477783,
|
|
"epoch": 0.06490639350052985,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.036,
|
|
"mean_token_accuracy": 0.11137905716896057,
|
|
"num_tokens": 1355677.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.172519874572754,
|
|
"epoch": 0.06534793359237019,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.0174,
|
|
"mean_token_accuracy": 0.11485954448580742,
|
|
"num_tokens": 1364874.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.176022386550903,
|
|
"epoch": 0.06578947368421052,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.9532,
|
|
"mean_token_accuracy": 0.11629517674446106,
|
|
"num_tokens": 1373717.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.189621257781982,
|
|
"epoch": 0.06623101377605087,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.9034,
|
|
"mean_token_accuracy": 0.11833730638027191,
|
|
"num_tokens": 1382767.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.006224584579468,
|
|
"epoch": 0.0666725538678912,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.96,
|
|
"mean_token_accuracy": 0.11204482167959214,
|
|
"num_tokens": 1391190.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.079714679718018,
|
|
"epoch": 0.06711409395973154,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.9625,
|
|
"mean_token_accuracy": 0.11262108534574508,
|
|
"num_tokens": 1400722.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.229566478729248,
|
|
"epoch": 0.06755563405157189,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.9853,
|
|
"mean_token_accuracy": 0.1128837876021862,
|
|
"num_tokens": 1409328.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.942206907272339,
|
|
"epoch": 0.06799717414341222,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.8585,
|
|
"mean_token_accuracy": 0.12095727175474166,
|
|
"num_tokens": 1418504.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.204732608795166,
|
|
"epoch": 0.06843871423525257,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.01,
|
|
"mean_token_accuracy": 0.10958118066191673,
|
|
"num_tokens": 1427690.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.102281284332276,
|
|
"epoch": 0.0688802543270929,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.9896,
|
|
"mean_token_accuracy": 0.11304903626441956,
|
|
"num_tokens": 1436798.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.056014490127564,
|
|
"epoch": 0.06932179441893324,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.9927,
|
|
"mean_token_accuracy": 0.11028492376208306,
|
|
"num_tokens": 1446357.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.063942003250122,
|
|
"epoch": 0.06976333451077357,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.9007,
|
|
"mean_token_accuracy": 0.11615959778428078,
|
|
"num_tokens": 1455998.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.0978930473327635,
|
|
"epoch": 0.07020487460261392,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.9697,
|
|
"mean_token_accuracy": 0.10868826881051064,
|
|
"num_tokens": 1465237.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.081945991516113,
|
|
"epoch": 0.07064641469445426,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.9174,
|
|
"mean_token_accuracy": 0.12127232849597931,
|
|
"num_tokens": 1474363.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.076627969741821,
|
|
"epoch": 0.0710879547862946,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.9709,
|
|
"mean_token_accuracy": 0.11975041329860688,
|
|
"num_tokens": 1483379.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.171514463424683,
|
|
"epoch": 0.07152949487813494,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.972,
|
|
"mean_token_accuracy": 0.11165242791175842,
|
|
"num_tokens": 1492507.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.919444894790649,
|
|
"epoch": 0.07197103496997527,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.8347,
|
|
"mean_token_accuracy": 0.12047068104147911,
|
|
"num_tokens": 1500888.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.032200956344605,
|
|
"epoch": 0.07241257506181561,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.9006,
|
|
"mean_token_accuracy": 0.11496629267930984,
|
|
"num_tokens": 1510310.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.029713153839111,
|
|
"epoch": 0.07285411515365595,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.8871,
|
|
"mean_token_accuracy": 0.1200887382030487,
|
|
"num_tokens": 1519427.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.0805525302886965,
|
|
"epoch": 0.07329565524549629,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.9008,
|
|
"mean_token_accuracy": 0.11543082296848298,
|
|
"num_tokens": 1529456.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.988912868499756,
|
|
"epoch": 0.07373719533733664,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.8479,
|
|
"mean_token_accuracy": 0.12111616134643555,
|
|
"num_tokens": 1537695.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.990428161621094,
|
|
"epoch": 0.07417873542917697,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.9813,
|
|
"mean_token_accuracy": 0.1161614142358303,
|
|
"num_tokens": 1547511.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.147986602783203,
|
|
"epoch": 0.07462027552101731,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.9878,
|
|
"mean_token_accuracy": 0.11540340334177017,
|
|
"num_tokens": 1557035.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.997569465637207,
|
|
"epoch": 0.07506181561285764,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.9226,
|
|
"mean_token_accuracy": 0.12383709400892258,
|
|
"num_tokens": 1566773.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.967204141616821,
|
|
"epoch": 0.07550335570469799,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.9218,
|
|
"mean_token_accuracy": 0.11128390282392502,
|
|
"num_tokens": 1576873.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.097699403762817,
|
|
"epoch": 0.07594489579653832,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.9533,
|
|
"mean_token_accuracy": 0.10889460295438766,
|
|
"num_tokens": 1586170.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.129969358444214,
|
|
"epoch": 0.07638643588837866,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.9899,
|
|
"mean_token_accuracy": 0.11445967480540276,
|
|
"num_tokens": 1596054.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.944463539123535,
|
|
"epoch": 0.07682797598021901,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.8683,
|
|
"mean_token_accuracy": 0.1222694993019104,
|
|
"num_tokens": 1604544.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.091968202590943,
|
|
"epoch": 0.07726951607205934,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.8804,
|
|
"mean_token_accuracy": 0.12263753786683082,
|
|
"num_tokens": 1614580.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.969458436965942,
|
|
"epoch": 0.07771105616389969,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.9714,
|
|
"mean_token_accuracy": 0.1178787350654602,
|
|
"num_tokens": 1624701.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.956935214996338,
|
|
"epoch": 0.07815259625574002,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.9033,
|
|
"mean_token_accuracy": 0.11575518846511841,
|
|
"num_tokens": 1634085.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.968543863296508,
|
|
"epoch": 0.07859413634758036,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.8836,
|
|
"mean_token_accuracy": 0.12341264188289643,
|
|
"num_tokens": 1643190.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.951219654083252,
|
|
"epoch": 0.0790356764394207,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.9128,
|
|
"mean_token_accuracy": 0.11554477885365486,
|
|
"num_tokens": 1652705.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.081302642822266,
|
|
"epoch": 0.07947721653126104,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.9005,
|
|
"mean_token_accuracy": 0.10998637154698372,
|
|
"num_tokens": 1662210.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.992254829406738,
|
|
"epoch": 0.07991875662310138,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.9455,
|
|
"mean_token_accuracy": 0.11279257908463478,
|
|
"num_tokens": 1671893.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.003918933868408,
|
|
"epoch": 0.08036029671494171,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.9,
|
|
"mean_token_accuracy": 0.11731264442205429,
|
|
"num_tokens": 1681217.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.996629953384399,
|
|
"epoch": 0.08080183680678206,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.9166,
|
|
"mean_token_accuracy": 0.1132784716784954,
|
|
"num_tokens": 1690447.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.97693395614624,
|
|
"epoch": 0.08124337689862239,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.001,
|
|
"mean_token_accuracy": 0.10703598409891128,
|
|
"num_tokens": 1700355.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.006402778625488,
|
|
"epoch": 0.08168491699046274,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.8873,
|
|
"mean_token_accuracy": 0.11095858663320542,
|
|
"num_tokens": 1709449.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.987693881988525,
|
|
"epoch": 0.08212645708230307,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.9375,
|
|
"mean_token_accuracy": 0.1106826864182949,
|
|
"num_tokens": 1718838.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.954984951019287,
|
|
"epoch": 0.08256799717414341,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.8892,
|
|
"mean_token_accuracy": 0.11695531234145165,
|
|
"num_tokens": 1728594.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.014099025726319,
|
|
"epoch": 0.08300953726598376,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.9301,
|
|
"mean_token_accuracy": 0.11335264146327972,
|
|
"num_tokens": 1738814.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.966581773757935,
|
|
"epoch": 0.08345107735782409,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.8557,
|
|
"mean_token_accuracy": 0.12260387167334556,
|
|
"num_tokens": 1747644.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.951725816726684,
|
|
"epoch": 0.08389261744966443,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.8981,
|
|
"mean_token_accuracy": 0.11759259030222893,
|
|
"num_tokens": 1757489.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.9648946762084964,
|
|
"epoch": 0.08433415754150476,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.8207,
|
|
"mean_token_accuracy": 0.1227583721280098,
|
|
"num_tokens": 1767546.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.863551807403565,
|
|
"epoch": 0.08477569763334511,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.8835,
|
|
"mean_token_accuracy": 0.11026808023452758,
|
|
"num_tokens": 1776035.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.006232595443725,
|
|
"epoch": 0.08521723772518544,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.9522,
|
|
"mean_token_accuracy": 0.11547720953822135,
|
|
"num_tokens": 1786161.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.080778980255127,
|
|
"epoch": 0.08565877781702579,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.0038,
|
|
"mean_token_accuracy": 0.11200195625424385,
|
|
"num_tokens": 1796093.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.917213439941406,
|
|
"epoch": 0.08610031790886613,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.8549,
|
|
"mean_token_accuracy": 0.11064035892486572,
|
|
"num_tokens": 1805574.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.922301959991455,
|
|
"epoch": 0.08654185800070646,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.8877,
|
|
"mean_token_accuracy": 0.11633643060922623,
|
|
"num_tokens": 1815175.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.897391080856323,
|
|
"epoch": 0.08698339809254681,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.8116,
|
|
"mean_token_accuracy": 0.11961451843380928,
|
|
"num_tokens": 1824683.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.917155456542969,
|
|
"epoch": 0.08742493818438714,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.7871,
|
|
"mean_token_accuracy": 0.1191464401781559,
|
|
"num_tokens": 1833174.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.89791784286499,
|
|
"epoch": 0.08786647827622748,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.9069,
|
|
"mean_token_accuracy": 0.1123793788254261,
|
|
"num_tokens": 1842409.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.737509679794312,
|
|
"epoch": 0.08830801836806781,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.8022,
|
|
"mean_token_accuracy": 0.11974574252963066,
|
|
"num_tokens": 1851441.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.128527450561523,
|
|
"epoch": 0.08874955845990816,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499999998589561,
|
|
"loss": 6.9312,
|
|
"mean_token_accuracy": 0.1117840752005577,
|
|
"num_tokens": 1861188.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.797428703308105,
|
|
"epoch": 0.0891910985517485,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999999928596523,
|
|
"loss": 6.8707,
|
|
"mean_token_accuracy": 0.11862308084964752,
|
|
"num_tokens": 1870284.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.825656938552856,
|
|
"epoch": 0.08963263864358884,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999999827221219,
|
|
"loss": 6.8224,
|
|
"mean_token_accuracy": 0.12426056489348411,
|
|
"num_tokens": 1879744.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.9824902534484865,
|
|
"epoch": 0.09007417873542918,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999999681769696,
|
|
"loss": 6.8388,
|
|
"mean_token_accuracy": 0.11695261672139168,
|
|
"num_tokens": 1889241.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.868342161178589,
|
|
"epoch": 0.09051571882726951,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499999949224196,
|
|
"loss": 6.8452,
|
|
"mean_token_accuracy": 0.11889938712120056,
|
|
"num_tokens": 1898247.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.884699106216431,
|
|
"epoch": 0.09095725891910986,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999999258638013,
|
|
"loss": 6.7941,
|
|
"mean_token_accuracy": 0.11864137351512909,
|
|
"num_tokens": 1907559.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.788152074813842,
|
|
"epoch": 0.09139879901095019,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999998980957861,
|
|
"loss": 6.8008,
|
|
"mean_token_accuracy": 0.12519625276327134,
|
|
"num_tokens": 1917072.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.877279567718506,
|
|
"epoch": 0.09184033910279053,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999998659201508,
|
|
"loss": 6.7593,
|
|
"mean_token_accuracy": 0.12310572415590286,
|
|
"num_tokens": 1926597.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.864975309371948,
|
|
"epoch": 0.09228187919463088,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999998293368961,
|
|
"loss": 6.8101,
|
|
"mean_token_accuracy": 0.11514781787991524,
|
|
"num_tokens": 1935978.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.792648220062256,
|
|
"epoch": 0.09272341928647121,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999997883460227,
|
|
"loss": 6.7612,
|
|
"mean_token_accuracy": 0.12067044004797936,
|
|
"num_tokens": 1944424.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.8677427768707275,
|
|
"epoch": 0.09316495937831155,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999997429475314,
|
|
"loss": 6.7275,
|
|
"mean_token_accuracy": 0.12832702696323395,
|
|
"num_tokens": 1953844.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.81104793548584,
|
|
"epoch": 0.09360649947015189,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999996931414232,
|
|
"loss": 6.8238,
|
|
"mean_token_accuracy": 0.12011751234531402,
|
|
"num_tokens": 1963974.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.822019290924072,
|
|
"epoch": 0.09404803956199223,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999996389276988,
|
|
"loss": 6.8032,
|
|
"mean_token_accuracy": 0.1252795398235321,
|
|
"num_tokens": 1973466.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.78282470703125,
|
|
"epoch": 0.09448957965383256,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999995803063596,
|
|
"loss": 6.8039,
|
|
"mean_token_accuracy": 0.12010984346270562,
|
|
"num_tokens": 1983478.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.908577823638916,
|
|
"epoch": 0.0949311197456729,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999995172774065,
|
|
"loss": 6.8817,
|
|
"mean_token_accuracy": 0.11865456476807594,
|
|
"num_tokens": 1992775.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.911471366882324,
|
|
"epoch": 0.09537265983751325,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999994498408408,
|
|
"loss": 6.8435,
|
|
"mean_token_accuracy": 0.11468391343951226,
|
|
"num_tokens": 2002526.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.848548507690429,
|
|
"epoch": 0.09581419992935358,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999993779966639,
|
|
"loss": 6.8681,
|
|
"mean_token_accuracy": 0.11680729538202286,
|
|
"num_tokens": 2012476.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.714018678665161,
|
|
"epoch": 0.09625574002119393,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999993017448771,
|
|
"loss": 6.707,
|
|
"mean_token_accuracy": 0.13380512073636056,
|
|
"num_tokens": 2021252.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.966219282150268,
|
|
"epoch": 0.09669728011303426,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999992210854821,
|
|
"loss": 6.8432,
|
|
"mean_token_accuracy": 0.1207717202603817,
|
|
"num_tokens": 2031438.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.852664613723755,
|
|
"epoch": 0.0971388202048746,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999991360184801,
|
|
"loss": 6.9024,
|
|
"mean_token_accuracy": 0.11384126916527748,
|
|
"num_tokens": 2041319.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.858384132385254,
|
|
"epoch": 0.09758036029671494,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999990465438731,
|
|
"loss": 6.8825,
|
|
"mean_token_accuracy": 0.11868280768394471,
|
|
"num_tokens": 2052060.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.8333351612091064,
|
|
"epoch": 0.09802190038855528,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999989526616628,
|
|
"loss": 6.7546,
|
|
"mean_token_accuracy": 0.12631451785564424,
|
|
"num_tokens": 2061331.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.765726852416992,
|
|
"epoch": 0.09846344048039563,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999988543718509,
|
|
"loss": 6.7792,
|
|
"mean_token_accuracy": 0.11744962036609649,
|
|
"num_tokens": 2070006.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.895434951782226,
|
|
"epoch": 0.09890498057223596,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999987516744394,
|
|
"loss": 6.7292,
|
|
"mean_token_accuracy": 0.12839764803647996,
|
|
"num_tokens": 2079089.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.732869672775268,
|
|
"epoch": 0.0993465206640763,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999986445694303,
|
|
"loss": 6.7255,
|
|
"mean_token_accuracy": 0.12237351760268211,
|
|
"num_tokens": 2087237.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.71789960861206,
|
|
"epoch": 0.09978806075591663,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999985330568258,
|
|
"loss": 6.6987,
|
|
"mean_token_accuracy": 0.1242702692747116,
|
|
"num_tokens": 2096598.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.881210708618164,
|
|
"epoch": 0.10022960084775698,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999984171366278,
|
|
"loss": 6.7841,
|
|
"mean_token_accuracy": 0.1141000434756279,
|
|
"num_tokens": 2106106.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.750670385360718,
|
|
"epoch": 0.10067114093959731,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499998296808839,
|
|
"loss": 6.7573,
|
|
"mean_token_accuracy": 0.12421151250600815,
|
|
"num_tokens": 2115478.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.846238422393799,
|
|
"epoch": 0.10111268103143765,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004999981720734615,
|
|
"loss": 6.7956,
|
|
"mean_token_accuracy": 0.12258475199341774,
|
|
"num_tokens": 2124439.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.845457935333252,
|
|
"epoch": 0.101554221123278,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999980429304977,
|
|
"loss": 6.8113,
|
|
"mean_token_accuracy": 0.1178690455853939,
|
|
"num_tokens": 2133718.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.688090801239014,
|
|
"epoch": 0.10199576121511833,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999979093799502,
|
|
"loss": 6.7085,
|
|
"mean_token_accuracy": 0.12130860090255738,
|
|
"num_tokens": 2142978.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.7933430671691895,
|
|
"epoch": 0.10243730130695868,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999977714218217,
|
|
"loss": 6.7791,
|
|
"mean_token_accuracy": 0.11885071843862534,
|
|
"num_tokens": 2152250.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.853244686126709,
|
|
"epoch": 0.102878841398799,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999976290561147,
|
|
"loss": 6.7725,
|
|
"mean_token_accuracy": 0.1168168194591999,
|
|
"num_tokens": 2161620.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.816542768478394,
|
|
"epoch": 0.10332038149063935,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999974822828322,
|
|
"loss": 6.7835,
|
|
"mean_token_accuracy": 0.12128284797072411,
|
|
"num_tokens": 2170856.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.761290454864502,
|
|
"epoch": 0.10376192158247968,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499997331101977,
|
|
"loss": 6.7743,
|
|
"mean_token_accuracy": 0.11757255122065544,
|
|
"num_tokens": 2180926.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.82963809967041,
|
|
"epoch": 0.10420346167432003,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499997175513552,
|
|
"loss": 6.7584,
|
|
"mean_token_accuracy": 0.11870861351490021,
|
|
"num_tokens": 2190248.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.8007221698760985,
|
|
"epoch": 0.10464500176616037,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999970155175603,
|
|
"loss": 6.7745,
|
|
"mean_token_accuracy": 0.11943883895874023,
|
|
"num_tokens": 2199833.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.701777648925781,
|
|
"epoch": 0.1050865418580007,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499996851114005,
|
|
"loss": 6.7307,
|
|
"mean_token_accuracy": 0.12810362204909326,
|
|
"num_tokens": 2208240.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.828345394134521,
|
|
"epoch": 0.10552808194984105,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999966823028894,
|
|
"loss": 6.7824,
|
|
"mean_token_accuracy": 0.11475062593817711,
|
|
"num_tokens": 2218758.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.8126058101654055,
|
|
"epoch": 0.10596962204168138,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999965090842168,
|
|
"loss": 6.7898,
|
|
"mean_token_accuracy": 0.12589357271790505,
|
|
"num_tokens": 2228443.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.724305534362793,
|
|
"epoch": 0.10641116213352173,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999963314579905,
|
|
"loss": 6.6237,
|
|
"mean_token_accuracy": 0.13539545610547066,
|
|
"num_tokens": 2236787.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.805136013031006,
|
|
"epoch": 0.10685270222536206,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999961494242139,
|
|
"loss": 6.8017,
|
|
"mean_token_accuracy": 0.11990576833486558,
|
|
"num_tokens": 2247089.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.714448690414429,
|
|
"epoch": 0.1072942423172024,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999959629828908,
|
|
"loss": 6.7348,
|
|
"mean_token_accuracy": 0.11736459657549858,
|
|
"num_tokens": 2256045.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.793351697921753,
|
|
"epoch": 0.10773578240904275,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999957721340248,
|
|
"loss": 6.7883,
|
|
"mean_token_accuracy": 0.12527842447161674,
|
|
"num_tokens": 2265835.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.671676206588745,
|
|
"epoch": 0.10817732250088308,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999955768776195,
|
|
"loss": 6.7241,
|
|
"mean_token_accuracy": 0.12204784303903579,
|
|
"num_tokens": 2275318.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.7978355884552,
|
|
"epoch": 0.10861886259272342,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999953772136788,
|
|
"loss": 6.7242,
|
|
"mean_token_accuracy": 0.12499865740537644,
|
|
"num_tokens": 2284821.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.821506834030151,
|
|
"epoch": 0.10906040268456375,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999951731422068,
|
|
"loss": 6.6958,
|
|
"mean_token_accuracy": 0.12446941509842872,
|
|
"num_tokens": 2294013.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.718976879119873,
|
|
"epoch": 0.1095019427764041,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999949646632072,
|
|
"loss": 6.6939,
|
|
"mean_token_accuracy": 0.12443441674113273,
|
|
"num_tokens": 2302727.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.7134024143219,
|
|
"epoch": 0.10994348286824443,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999947517766842,
|
|
"loss": 6.7145,
|
|
"mean_token_accuracy": 0.12263145819306373,
|
|
"num_tokens": 2312032.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.909180307388306,
|
|
"epoch": 0.11038502296008477,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499994534482642,
|
|
"loss": 6.8067,
|
|
"mean_token_accuracy": 0.11781661435961724,
|
|
"num_tokens": 2321839.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.693206644058227,
|
|
"epoch": 0.11082656305192512,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999943127810847,
|
|
"loss": 6.7725,
|
|
"mean_token_accuracy": 0.11574066355824471,
|
|
"num_tokens": 2331255.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.676486921310425,
|
|
"epoch": 0.11126810314376545,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999940866720169,
|
|
"loss": 6.598,
|
|
"mean_token_accuracy": 0.133713548630476,
|
|
"num_tokens": 2340038.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.7074402332305905,
|
|
"epoch": 0.1117096432356058,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999938561554429,
|
|
"loss": 6.7001,
|
|
"mean_token_accuracy": 0.12409981712698936,
|
|
"num_tokens": 2348901.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.729129076004028,
|
|
"epoch": 0.11215118332744613,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999936212313672,
|
|
"loss": 6.7966,
|
|
"mean_token_accuracy": 0.11647377163171768,
|
|
"num_tokens": 2358842.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.7503026008605955,
|
|
"epoch": 0.11259272341928647,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999933818997943,
|
|
"loss": 6.6867,
|
|
"mean_token_accuracy": 0.12584296390414237,
|
|
"num_tokens": 2368650.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.747146368026733,
|
|
"epoch": 0.1130342635111268,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999931381607292,
|
|
"loss": 6.7419,
|
|
"mean_token_accuracy": 0.12453764751553535,
|
|
"num_tokens": 2377916.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.746145820617675,
|
|
"epoch": 0.11347580360296715,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999928900141764,
|
|
"loss": 6.6865,
|
|
"mean_token_accuracy": 0.12603561356663703,
|
|
"num_tokens": 2387507.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.6909308433532715,
|
|
"epoch": 0.1139173436948075,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499992637460141,
|
|
"loss": 6.7423,
|
|
"mean_token_accuracy": 0.1275649629533291,
|
|
"num_tokens": 2396148.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.7133759498596195,
|
|
"epoch": 0.11435888378664782,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999923804986275,
|
|
"loss": 6.6046,
|
|
"mean_token_accuracy": 0.12199260294437408,
|
|
"num_tokens": 2404891.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.716338968276977,
|
|
"epoch": 0.11480042387848817,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999921191296415,
|
|
"loss": 6.6426,
|
|
"mean_token_accuracy": 0.12343374639749527,
|
|
"num_tokens": 2414406.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.697209453582763,
|
|
"epoch": 0.1152419639703285,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999918533531877,
|
|
"loss": 6.7299,
|
|
"mean_token_accuracy": 0.127056036144495,
|
|
"num_tokens": 2424363.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.757014656066895,
|
|
"epoch": 0.11568350406216885,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999915831692714,
|
|
"loss": 6.6775,
|
|
"mean_token_accuracy": 0.12560488805174827,
|
|
"num_tokens": 2433753.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.593924283981323,
|
|
"epoch": 0.11612504415400918,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999913085778981,
|
|
"loss": 6.6861,
|
|
"mean_token_accuracy": 0.12244237959384918,
|
|
"num_tokens": 2443275.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.822639799118042,
|
|
"epoch": 0.11656658424584952,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999910295790729,
|
|
"loss": 6.7075,
|
|
"mean_token_accuracy": 0.12074168473482132,
|
|
"num_tokens": 2452510.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.731257343292237,
|
|
"epoch": 0.11700812433768987,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999907461728014,
|
|
"loss": 6.8117,
|
|
"mean_token_accuracy": 0.11980628594756126,
|
|
"num_tokens": 2462742.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.71476149559021,
|
|
"epoch": 0.1174496644295302,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999904583590893,
|
|
"loss": 6.6781,
|
|
"mean_token_accuracy": 0.12219401150941848,
|
|
"num_tokens": 2471409.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.749363136291504,
|
|
"epoch": 0.11789120452137054,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999901661379418,
|
|
"loss": 6.6228,
|
|
"mean_token_accuracy": 0.13008193373680116,
|
|
"num_tokens": 2481011.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.63396897315979,
|
|
"epoch": 0.11833274461321087,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999898695093652,
|
|
"loss": 6.7195,
|
|
"mean_token_accuracy": 0.12151179760694504,
|
|
"num_tokens": 2490664.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.728178644180298,
|
|
"epoch": 0.11877428470505122,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999895684733648,
|
|
"loss": 6.6462,
|
|
"mean_token_accuracy": 0.1303670547902584,
|
|
"num_tokens": 2499799.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.716060447692871,
|
|
"epoch": 0.11921582479689156,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004999892630299467,
|
|
"loss": 6.6483,
|
|
"mean_token_accuracy": 0.12420448064804077,
|
|
"num_tokens": 2508780.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.657323360443115,
|
|
"epoch": 0.1196573648887319,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999889531791171,
|
|
"loss": 6.6462,
|
|
"mean_token_accuracy": 0.12205975502729416,
|
|
"num_tokens": 2517741.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.71348876953125,
|
|
"epoch": 0.12009890498057224,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999886389208817,
|
|
"loss": 6.7302,
|
|
"mean_token_accuracy": 0.12077968642115593,
|
|
"num_tokens": 2528742.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.5724108695983885,
|
|
"epoch": 0.12054044507241257,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999883202552468,
|
|
"loss": 6.6741,
|
|
"mean_token_accuracy": 0.1292316846549511,
|
|
"num_tokens": 2538609.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.831192445755005,
|
|
"epoch": 0.12098198516425292,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999879971822189,
|
|
"loss": 6.6579,
|
|
"mean_token_accuracy": 0.12047442719340325,
|
|
"num_tokens": 2547772.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.59716944694519,
|
|
"epoch": 0.12142352525609325,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999876697018038,
|
|
"loss": 6.6253,
|
|
"mean_token_accuracy": 0.12871280014514924,
|
|
"num_tokens": 2556114.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.76294059753418,
|
|
"epoch": 0.1218650653479336,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999873378140085,
|
|
"loss": 6.6682,
|
|
"mean_token_accuracy": 0.1281101770699024,
|
|
"num_tokens": 2566814.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.600197601318359,
|
|
"epoch": 0.12230660543977394,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999870015188389,
|
|
"loss": 6.6317,
|
|
"mean_token_accuracy": 0.12663180232048035,
|
|
"num_tokens": 2576030.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.6567483901977536,
|
|
"epoch": 0.12274814553161427,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999866608163021,
|
|
"loss": 6.6546,
|
|
"mean_token_accuracy": 0.12772715091705322,
|
|
"num_tokens": 2585756.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.739302158355713,
|
|
"epoch": 0.12318968562345461,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999863157064045,
|
|
"loss": 6.6928,
|
|
"mean_token_accuracy": 0.12649391070008278,
|
|
"num_tokens": 2595676.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.681546878814697,
|
|
"epoch": 0.12363122571529495,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999859661891529,
|
|
"loss": 6.7124,
|
|
"mean_token_accuracy": 0.12418720349669457,
|
|
"num_tokens": 2606197.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.692468786239624,
|
|
"epoch": 0.12407276580713529,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999856122645543,
|
|
"loss": 6.6308,
|
|
"mean_token_accuracy": 0.12420927360653877,
|
|
"num_tokens": 2615311.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.625854730606079,
|
|
"epoch": 0.12451430589897562,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999852539326154,
|
|
"loss": 6.551,
|
|
"mean_token_accuracy": 0.1275542564690113,
|
|
"num_tokens": 2624074.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.581278514862061,
|
|
"epoch": 0.12495584599081597,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999848911933434,
|
|
"loss": 6.6894,
|
|
"mean_token_accuracy": 0.12939536869525908,
|
|
"num_tokens": 2633877.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.65780930519104,
|
|
"epoch": 0.1253973860826563,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999845240467453,
|
|
"loss": 6.6164,
|
|
"mean_token_accuracy": 0.12634376361966132,
|
|
"num_tokens": 2643330.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.688624095916748,
|
|
"epoch": 0.12583892617449666,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999841524928282,
|
|
"loss": 6.5957,
|
|
"mean_token_accuracy": 0.130678478628397,
|
|
"num_tokens": 2652070.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.651975011825561,
|
|
"epoch": 0.126280466266337,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999837765315997,
|
|
"loss": 6.6467,
|
|
"mean_token_accuracy": 0.13028737679123878,
|
|
"num_tokens": 2660546.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.5479024887084964,
|
|
"epoch": 0.12672200635817732,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999833961630669,
|
|
"loss": 6.5377,
|
|
"mean_token_accuracy": 0.12899447232484818,
|
|
"num_tokens": 2669938.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.7292591571807865,
|
|
"epoch": 0.12716354645001765,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999830113872374,
|
|
"loss": 6.6675,
|
|
"mean_token_accuracy": 0.12595592364668845,
|
|
"num_tokens": 2679814.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.554772853851318,
|
|
"epoch": 0.127605086541858,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999826222041186,
|
|
"loss": 6.571,
|
|
"mean_token_accuracy": 0.13299084976315498,
|
|
"num_tokens": 2688733.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.636107873916626,
|
|
"epoch": 0.12804662663369834,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999822286137182,
|
|
"loss": 6.5779,
|
|
"mean_token_accuracy": 0.12820412516593932,
|
|
"num_tokens": 2697744.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.6388514041900635,
|
|
"epoch": 0.12848816672553867,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999818306160439,
|
|
"loss": 6.5266,
|
|
"mean_token_accuracy": 0.1340452216565609,
|
|
"num_tokens": 2707037.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.645256471633911,
|
|
"epoch": 0.12892970681737903,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999814282111034,
|
|
"loss": 6.6874,
|
|
"mean_token_accuracy": 0.12385595068335534,
|
|
"num_tokens": 2717345.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.667556524276733,
|
|
"epoch": 0.12937124690921936,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999810213989047,
|
|
"loss": 6.638,
|
|
"mean_token_accuracy": 0.11816325932741165,
|
|
"num_tokens": 2726892.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.621801376342773,
|
|
"epoch": 0.1298127870010597,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999806101794558,
|
|
"loss": 6.6041,
|
|
"mean_token_accuracy": 0.1266481436789036,
|
|
"num_tokens": 2736479.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.701800394058227,
|
|
"epoch": 0.13025432709290002,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999801945527648,
|
|
"loss": 6.6545,
|
|
"mean_token_accuracy": 0.12567580863833427,
|
|
"num_tokens": 2745998.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.620102596282959,
|
|
"epoch": 0.13069586718474038,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999797745188395,
|
|
"loss": 6.641,
|
|
"mean_token_accuracy": 0.1308413989841938,
|
|
"num_tokens": 2754346.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.6592470645904545,
|
|
"epoch": 0.13113740727658071,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999793500776886,
|
|
"loss": 6.5835,
|
|
"mean_token_accuracy": 0.13052424117922784,
|
|
"num_tokens": 2763391.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.62844033241272,
|
|
"epoch": 0.13157894736842105,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999789212293201,
|
|
"loss": 6.6395,
|
|
"mean_token_accuracy": 0.12945614531636238,
|
|
"num_tokens": 2772764.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.712308549880982,
|
|
"epoch": 0.1320204874602614,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999784879737423,
|
|
"loss": 6.7289,
|
|
"mean_token_accuracy": 0.12319694384932518,
|
|
"num_tokens": 2782312.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.650492525100708,
|
|
"epoch": 0.13246202755210174,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999780503109642,
|
|
"loss": 6.6299,
|
|
"mean_token_accuracy": 0.12477036267518997,
|
|
"num_tokens": 2791159.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.561451959609985,
|
|
"epoch": 0.13290356764394207,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999776082409939,
|
|
"loss": 6.4526,
|
|
"mean_token_accuracy": 0.13791982010006903,
|
|
"num_tokens": 2799319.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.534754419326783,
|
|
"epoch": 0.1333451077357824,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999771617638401,
|
|
"loss": 6.582,
|
|
"mean_token_accuracy": 0.13077868148684502,
|
|
"num_tokens": 2807401.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.649140977859497,
|
|
"epoch": 0.13378664782762276,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999767108795118,
|
|
"loss": 6.642,
|
|
"mean_token_accuracy": 0.12535738274455072,
|
|
"num_tokens": 2817734.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.605966520309448,
|
|
"epoch": 0.1342281879194631,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999762555880176,
|
|
"loss": 6.6236,
|
|
"mean_token_accuracy": 0.1270806223154068,
|
|
"num_tokens": 2828235.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.663729429244995,
|
|
"epoch": 0.13466972801130342,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999757958893666,
|
|
"loss": 6.651,
|
|
"mean_token_accuracy": 0.1310298413038254,
|
|
"num_tokens": 2837453.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.549145174026489,
|
|
"epoch": 0.13511126810314378,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999753317835677,
|
|
"loss": 6.6279,
|
|
"mean_token_accuracy": 0.12039558663964271,
|
|
"num_tokens": 2847055.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.707547044754028,
|
|
"epoch": 0.1355528081949841,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999748632706299,
|
|
"loss": 6.611,
|
|
"mean_token_accuracy": 0.13395099639892577,
|
|
"num_tokens": 2857101.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.556164789199829,
|
|
"epoch": 0.13599434828682444,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999743903505626,
|
|
"loss": 6.515,
|
|
"mean_token_accuracy": 0.13099609762430192,
|
|
"num_tokens": 2866685.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.649285745620728,
|
|
"epoch": 0.13643588837866477,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999739130233749,
|
|
"loss": 6.6349,
|
|
"mean_token_accuracy": 0.12779910936951638,
|
|
"num_tokens": 2876022.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.624913215637207,
|
|
"epoch": 0.13687742847050513,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999734312890761,
|
|
"loss": 6.5416,
|
|
"mean_token_accuracy": 0.12898361757397653,
|
|
"num_tokens": 2885560.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.541625452041626,
|
|
"epoch": 0.13731896856234546,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999729451476757,
|
|
"loss": 6.5757,
|
|
"mean_token_accuracy": 0.1289501816034317,
|
|
"num_tokens": 2894686.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.620435476303101,
|
|
"epoch": 0.1377605086541858,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999724545991835,
|
|
"loss": 6.5948,
|
|
"mean_token_accuracy": 0.13569336235523224,
|
|
"num_tokens": 2904390.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.616004848480225,
|
|
"epoch": 0.13820204874602615,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999719596436086,
|
|
"loss": 6.6554,
|
|
"mean_token_accuracy": 0.1249268040060997,
|
|
"num_tokens": 2913311.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.633422946929931,
|
|
"epoch": 0.13864358883786648,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999714602809611,
|
|
"loss": 6.5368,
|
|
"mean_token_accuracy": 0.13287945315241814,
|
|
"num_tokens": 2923196.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.549054431915283,
|
|
"epoch": 0.1390851289297068,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999709565112506,
|
|
"loss": 6.6,
|
|
"mean_token_accuracy": 0.12382271289825439,
|
|
"num_tokens": 2932813.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.6186319351196286,
|
|
"epoch": 0.13952666902154715,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499970448334487,
|
|
"loss": 6.5139,
|
|
"mean_token_accuracy": 0.12139623984694481,
|
|
"num_tokens": 2942694.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.508273315429688,
|
|
"epoch": 0.1399682091133875,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999699357506803,
|
|
"loss": 6.4663,
|
|
"mean_token_accuracy": 0.13404878079891205,
|
|
"num_tokens": 2950932.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.620526647567749,
|
|
"epoch": 0.14040974920522784,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999694187598406,
|
|
"loss": 6.5628,
|
|
"mean_token_accuracy": 0.13192685768008233,
|
|
"num_tokens": 2960102.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.592943286895752,
|
|
"epoch": 0.14085128929706817,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004999688973619777,
|
|
"loss": 6.5609,
|
|
"mean_token_accuracy": 0.1262449197471142,
|
|
"num_tokens": 2969968.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.520618915557861,
|
|
"epoch": 0.14129282938890853,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999683715571022,
|
|
"loss": 6.5212,
|
|
"mean_token_accuracy": 0.13312431499361993,
|
|
"num_tokens": 2978880.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.610848045349121,
|
|
"epoch": 0.14173436948074886,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999678413452242,
|
|
"loss": 6.554,
|
|
"mean_token_accuracy": 0.1260514296591282,
|
|
"num_tokens": 2988369.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.534283065795899,
|
|
"epoch": 0.1421759095725892,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999673067263542,
|
|
"loss": 6.5949,
|
|
"mean_token_accuracy": 0.12671327590942383,
|
|
"num_tokens": 2997070.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.656943464279175,
|
|
"epoch": 0.14261744966442952,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999667677005026,
|
|
"loss": 6.5329,
|
|
"mean_token_accuracy": 0.13323748856782913,
|
|
"num_tokens": 3006547.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.516927480697632,
|
|
"epoch": 0.14305898975626988,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999662242676799,
|
|
"loss": 6.5522,
|
|
"mean_token_accuracy": 0.13190415725111962,
|
|
"num_tokens": 3015821.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.561876678466797,
|
|
"epoch": 0.1435005298481102,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999656764278968,
|
|
"loss": 6.5403,
|
|
"mean_token_accuracy": 0.1307166889309883,
|
|
"num_tokens": 3024750.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.569908905029297,
|
|
"epoch": 0.14394206993995054,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999651241811642,
|
|
"loss": 6.4929,
|
|
"mean_token_accuracy": 0.13378000110387803,
|
|
"num_tokens": 3033345.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.47226619720459,
|
|
"epoch": 0.1443836100317909,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999645675274925,
|
|
"loss": 6.4813,
|
|
"mean_token_accuracy": 0.1357632078230381,
|
|
"num_tokens": 3042060.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.586079454421997,
|
|
"epoch": 0.14482515012363123,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999640064668931,
|
|
"loss": 6.624,
|
|
"mean_token_accuracy": 0.1263129860162735,
|
|
"num_tokens": 3052490.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.671514511108398,
|
|
"epoch": 0.14526669021547156,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999634409993766,
|
|
"loss": 6.5901,
|
|
"mean_token_accuracy": 0.12612482234835626,
|
|
"num_tokens": 3061934.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.503233861923218,
|
|
"epoch": 0.1457082303073119,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999628711249544,
|
|
"loss": 6.4934,
|
|
"mean_token_accuracy": 0.13857336044311525,
|
|
"num_tokens": 3070890.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.627433586120605,
|
|
"epoch": 0.14614977039915225,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999622968436373,
|
|
"loss": 6.5164,
|
|
"mean_token_accuracy": 0.13164258152246475,
|
|
"num_tokens": 3079933.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.464597463607788,
|
|
"epoch": 0.14659131049099258,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999617181554369,
|
|
"loss": 6.5699,
|
|
"mean_token_accuracy": 0.13076355457305908,
|
|
"num_tokens": 3089910.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.61089825630188,
|
|
"epoch": 0.1470328505828329,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004999611350603643,
|
|
"loss": 6.5471,
|
|
"mean_token_accuracy": 0.13240002393722533,
|
|
"num_tokens": 3098676.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.586600494384766,
|
|
"epoch": 0.14747439067467327,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499960547558431,
|
|
"loss": 6.6647,
|
|
"mean_token_accuracy": 0.1285034753382206,
|
|
"num_tokens": 3109055.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.58641209602356,
|
|
"epoch": 0.1479159307665136,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999599556496486,
|
|
"loss": 6.5113,
|
|
"mean_token_accuracy": 0.13572623655200006,
|
|
"num_tokens": 3117517.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.508319330215454,
|
|
"epoch": 0.14835747085835393,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999593593340286,
|
|
"loss": 6.5022,
|
|
"mean_token_accuracy": 0.13704506903886796,
|
|
"num_tokens": 3126606.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.596501302719116,
|
|
"epoch": 0.14879901095019427,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999587586115826,
|
|
"loss": 6.5136,
|
|
"mean_token_accuracy": 0.13149842694401742,
|
|
"num_tokens": 3135444.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.51367220878601,
|
|
"epoch": 0.14924055104203462,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999581534823226,
|
|
"loss": 6.4727,
|
|
"mean_token_accuracy": 0.13636851012706758,
|
|
"num_tokens": 3144967.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.575021123886108,
|
|
"epoch": 0.14968209113387496,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999575439462601,
|
|
"loss": 6.4868,
|
|
"mean_token_accuracy": 0.1300053507089615,
|
|
"num_tokens": 3153898.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.453029918670654,
|
|
"epoch": 0.1501236312257153,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999569300034075,
|
|
"loss": 6.555,
|
|
"mean_token_accuracy": 0.12720515877008437,
|
|
"num_tokens": 3162341.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.498763990402222,
|
|
"epoch": 0.15056517131755565,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999563116537764,
|
|
"loss": 6.3365,
|
|
"mean_token_accuracy": 0.14578044191002845,
|
|
"num_tokens": 3171420.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.4892902851104735,
|
|
"epoch": 0.15100671140939598,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999556888973792,
|
|
"loss": 6.3966,
|
|
"mean_token_accuracy": 0.1321087971329689,
|
|
"num_tokens": 3180221.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.587397718429566,
|
|
"epoch": 0.1514482515012363,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999550617342279,
|
|
"loss": 6.5511,
|
|
"mean_token_accuracy": 0.12823838815093042,
|
|
"num_tokens": 3189156.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.466203594207764,
|
|
"epoch": 0.15188979159307664,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499954430164335,
|
|
"loss": 6.4738,
|
|
"mean_token_accuracy": 0.13134835958480834,
|
|
"num_tokens": 3199870.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.586092329025268,
|
|
"epoch": 0.152331331684917,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999537941877127,
|
|
"loss": 6.4556,
|
|
"mean_token_accuracy": 0.13151518255472183,
|
|
"num_tokens": 3208815.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.4404736995697025,
|
|
"epoch": 0.15277287177675733,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999531538043735,
|
|
"loss": 6.5381,
|
|
"mean_token_accuracy": 0.13203879222273826,
|
|
"num_tokens": 3218692.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.55628137588501,
|
|
"epoch": 0.15321441186859766,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999525090143298,
|
|
"loss": 6.5023,
|
|
"mean_token_accuracy": 0.14053747728466986,
|
|
"num_tokens": 3227604.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.555537223815918,
|
|
"epoch": 0.15365595196043802,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999518598175946,
|
|
"loss": 6.5109,
|
|
"mean_token_accuracy": 0.13781933188438417,
|
|
"num_tokens": 3237912.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.438277339935302,
|
|
"epoch": 0.15409749205227835,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999512062141805,
|
|
"loss": 6.3744,
|
|
"mean_token_accuracy": 0.13822528719902039,
|
|
"num_tokens": 3246003.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.541148376464844,
|
|
"epoch": 0.15453903214411868,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999505482040999,
|
|
"loss": 6.5237,
|
|
"mean_token_accuracy": 0.13249014243483542,
|
|
"num_tokens": 3256363.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.529036283493042,
|
|
"epoch": 0.154980572235959,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999498857873662,
|
|
"loss": 6.5163,
|
|
"mean_token_accuracy": 0.13468330428004266,
|
|
"num_tokens": 3265822.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.361684417724609,
|
|
"epoch": 0.15542211232779937,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999492189639921,
|
|
"loss": 6.4164,
|
|
"mean_token_accuracy": 0.13653916344046593,
|
|
"num_tokens": 3274614.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.6026630878448485,
|
|
"epoch": 0.1558636524196397,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999485477339907,
|
|
"loss": 6.4873,
|
|
"mean_token_accuracy": 0.13441504836082457,
|
|
"num_tokens": 3283800.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.481634330749512,
|
|
"epoch": 0.15630519251148003,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999478720973753,
|
|
"loss": 6.4147,
|
|
"mean_token_accuracy": 0.1378687009215355,
|
|
"num_tokens": 3293221.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.518844079971314,
|
|
"epoch": 0.1567467326033204,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499947192054159,
|
|
"loss": 6.5621,
|
|
"mean_token_accuracy": 0.1299850597977638,
|
|
"num_tokens": 3302852.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.573839330673218,
|
|
"epoch": 0.15718827269516072,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499946507604355,
|
|
"loss": 6.4284,
|
|
"mean_token_accuracy": 0.13676528111100197,
|
|
"num_tokens": 3311752.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.403056526184082,
|
|
"epoch": 0.15762981278700106,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499945818747977,
|
|
"loss": 6.5135,
|
|
"mean_token_accuracy": 0.1319083459675312,
|
|
"num_tokens": 3321339.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.6045581817626955,
|
|
"epoch": 0.1580713528788414,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999451254850383,
|
|
"loss": 6.5346,
|
|
"mean_token_accuracy": 0.1300017662346363,
|
|
"num_tokens": 3330269.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.480741930007935,
|
|
"epoch": 0.15851289297068175,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999444278155525,
|
|
"loss": 6.4478,
|
|
"mean_token_accuracy": 0.13558795750141145,
|
|
"num_tokens": 3340770.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.4864849090576175,
|
|
"epoch": 0.15895443306252208,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999437257395333,
|
|
"loss": 6.5388,
|
|
"mean_token_accuracy": 0.13693441525101663,
|
|
"num_tokens": 3349976.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.576467275619507,
|
|
"epoch": 0.1593959731543624,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999430192569944,
|
|
"loss": 6.5822,
|
|
"mean_token_accuracy": 0.1267798624932766,
|
|
"num_tokens": 3359764.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.459140777587891,
|
|
"epoch": 0.15983751324620277,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999423083679498,
|
|
"loss": 6.4624,
|
|
"mean_token_accuracy": 0.13131050616502762,
|
|
"num_tokens": 3369939.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.611289548873901,
|
|
"epoch": 0.1602790533380431,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999415930724133,
|
|
"loss": 6.604,
|
|
"mean_token_accuracy": 0.12783848196268083,
|
|
"num_tokens": 3381326.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.5344682216644285,
|
|
"epoch": 0.16072059342988343,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999408733703988,
|
|
"loss": 6.5567,
|
|
"mean_token_accuracy": 0.12708184048533439,
|
|
"num_tokens": 3391016.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.508758783340454,
|
|
"epoch": 0.16116213352172376,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999401492619207,
|
|
"loss": 6.3051,
|
|
"mean_token_accuracy": 0.1379851721227169,
|
|
"num_tokens": 3400294.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.467001914978027,
|
|
"epoch": 0.16160367361356412,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999394207469928,
|
|
"loss": 6.523,
|
|
"mean_token_accuracy": 0.1270366355776787,
|
|
"num_tokens": 3409685.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.615599775314331,
|
|
"epoch": 0.16204521370540445,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999386878256297,
|
|
"loss": 6.4286,
|
|
"mean_token_accuracy": 0.13395086154341698,
|
|
"num_tokens": 3418946.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.307619047164917,
|
|
"epoch": 0.16248675379724478,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999379504978457,
|
|
"loss": 6.4423,
|
|
"mean_token_accuracy": 0.1329544149339199,
|
|
"num_tokens": 3428245.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.515369462966919,
|
|
"epoch": 0.16292829388908514,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499937208763655,
|
|
"loss": 6.4496,
|
|
"mean_token_accuracy": 0.13294086754322051,
|
|
"num_tokens": 3437580.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.529568195343018,
|
|
"epoch": 0.16336983398092547,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999364626230724,
|
|
"loss": 6.4279,
|
|
"mean_token_accuracy": 0.13660631999373435,
|
|
"num_tokens": 3446393.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.442787027359008,
|
|
"epoch": 0.1638113740727658,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999357120761124,
|
|
"loss": 6.5321,
|
|
"mean_token_accuracy": 0.13097543716430665,
|
|
"num_tokens": 3455956.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.608609199523926,
|
|
"epoch": 0.16425291416460613,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999349571227898,
|
|
"loss": 6.5277,
|
|
"mean_token_accuracy": 0.12765606567263604,
|
|
"num_tokens": 3465722.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.513270521163941,
|
|
"epoch": 0.1646944542564465,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999341977631193,
|
|
"loss": 6.4959,
|
|
"mean_token_accuracy": 0.13204836025834082,
|
|
"num_tokens": 3475467.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.463746118545532,
|
|
"epoch": 0.16513599434828682,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999334339971157,
|
|
"loss": 6.3874,
|
|
"mean_token_accuracy": 0.13608791455626487,
|
|
"num_tokens": 3484931.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.5012932300567625,
|
|
"epoch": 0.16557753444012716,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999326658247942,
|
|
"loss": 6.5008,
|
|
"mean_token_accuracy": 0.1320129007101059,
|
|
"num_tokens": 3494001.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.521371078491211,
|
|
"epoch": 0.16601907453196751,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999318932461696,
|
|
"loss": 6.424,
|
|
"mean_token_accuracy": 0.1406968742609024,
|
|
"num_tokens": 3503021.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.379944896697998,
|
|
"epoch": 0.16646061462380785,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004999311162612571,
|
|
"loss": 6.4661,
|
|
"mean_token_accuracy": 0.1362703375518322,
|
|
"num_tokens": 3513005.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.564940690994263,
|
|
"epoch": 0.16690215471564818,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499930334870072,
|
|
"loss": 6.5404,
|
|
"mean_token_accuracy": 0.13439082428812982,
|
|
"num_tokens": 3523219.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.511162185668946,
|
|
"epoch": 0.1673436948074885,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999295490726296,
|
|
"loss": 6.4859,
|
|
"mean_token_accuracy": 0.13242177516222,
|
|
"num_tokens": 3532917.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.521901321411133,
|
|
"epoch": 0.16778523489932887,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999287588689453,
|
|
"loss": 6.4915,
|
|
"mean_token_accuracy": 0.136155141890049,
|
|
"num_tokens": 3542845.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.521121215820313,
|
|
"epoch": 0.1682267749911692,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999279642590344,
|
|
"loss": 6.5074,
|
|
"mean_token_accuracy": 0.13129648566246033,
|
|
"num_tokens": 3552126.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.5425803661346436,
|
|
"epoch": 0.16866831508300953,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999271652429127,
|
|
"loss": 6.5284,
|
|
"mean_token_accuracy": 0.12366664186120033,
|
|
"num_tokens": 3561254.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.458356142044067,
|
|
"epoch": 0.1691098551748499,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999263618205958,
|
|
"loss": 6.366,
|
|
"mean_token_accuracy": 0.1399925693869591,
|
|
"num_tokens": 3569781.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.48570237159729,
|
|
"epoch": 0.16955139526669022,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999255539920993,
|
|
"loss": 6.4831,
|
|
"mean_token_accuracy": 0.1311805158853531,
|
|
"num_tokens": 3579664.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.526191329956054,
|
|
"epoch": 0.16999293535853055,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999247417574391,
|
|
"loss": 6.5194,
|
|
"mean_token_accuracy": 0.13419721275568008,
|
|
"num_tokens": 3588671.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.495071268081665,
|
|
"epoch": 0.17043447545037088,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999239251166312,
|
|
"loss": 6.3976,
|
|
"mean_token_accuracy": 0.13579057157039642,
|
|
"num_tokens": 3597656.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.4537488460540775,
|
|
"epoch": 0.17087601554221124,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999231040696914,
|
|
"loss": 6.4361,
|
|
"mean_token_accuracy": 0.13407086580991745,
|
|
"num_tokens": 3608017.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.464614009857177,
|
|
"epoch": 0.17131755563405157,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999222786166361,
|
|
"loss": 6.5024,
|
|
"mean_token_accuracy": 0.13418009057641028,
|
|
"num_tokens": 3618189.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.500387525558471,
|
|
"epoch": 0.1717590957258919,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999214487574812,
|
|
"loss": 6.4369,
|
|
"mean_token_accuracy": 0.13329068347811698,
|
|
"num_tokens": 3627211.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.505857801437378,
|
|
"epoch": 0.17220063581773226,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999206144922431,
|
|
"loss": 6.3857,
|
|
"mean_token_accuracy": 0.132901331782341,
|
|
"num_tokens": 3636781.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.490985107421875,
|
|
"epoch": 0.1726421759095726,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499919775820938,
|
|
"loss": 6.4826,
|
|
"mean_token_accuracy": 0.13853701204061508,
|
|
"num_tokens": 3644891.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.4972686767578125,
|
|
"epoch": 0.17308371600141292,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999189327435825,
|
|
"loss": 6.505,
|
|
"mean_token_accuracy": 0.1336333230137825,
|
|
"num_tokens": 3655477.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.5157805442810055,
|
|
"epoch": 0.17352525609325326,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999180852601929,
|
|
"loss": 6.5269,
|
|
"mean_token_accuracy": 0.13449802100658417,
|
|
"num_tokens": 3664542.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.446292495727539,
|
|
"epoch": 0.17396679618509361,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000499917233370786,
|
|
"loss": 6.4281,
|
|
"mean_token_accuracy": 0.1332317002117634,
|
|
"num_tokens": 3673806.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.496902084350586,
|
|
"epoch": 0.17440833627693395,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999163770753784,
|
|
"loss": 6.4363,
|
|
"mean_token_accuracy": 0.13492944985628127,
|
|
"num_tokens": 3683238.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.456824207305909,
|
|
"epoch": 0.17484987636877428,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999155163739869,
|
|
"loss": 6.4036,
|
|
"mean_token_accuracy": 0.13336892798542976,
|
|
"num_tokens": 3692161.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.478030490875244,
|
|
"epoch": 0.17529141646061464,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999146512666284,
|
|
"loss": 6.4329,
|
|
"mean_token_accuracy": 0.13266484811902046,
|
|
"num_tokens": 3701431.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.466426849365234,
|
|
"epoch": 0.17573295655245497,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999137817533197,
|
|
"loss": 6.4202,
|
|
"mean_token_accuracy": 0.14008525460958482,
|
|
"num_tokens": 3710963.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.430937433242798,
|
|
"epoch": 0.1761744966442953,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999129078340779,
|
|
"loss": 6.4103,
|
|
"mean_token_accuracy": 0.1410228542983532,
|
|
"num_tokens": 3720177.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.454744625091553,
|
|
"epoch": 0.17661603673613563,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999120295089202,
|
|
"loss": 6.3475,
|
|
"mean_token_accuracy": 0.1424284115433693,
|
|
"num_tokens": 3728123.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.492793893814087,
|
|
"epoch": 0.177057576827976,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999111467778639,
|
|
"loss": 6.5131,
|
|
"mean_token_accuracy": 0.134304940700531,
|
|
"num_tokens": 3736869.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.4386314868927,
|
|
"epoch": 0.17749911691981632,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499910259640926,
|
|
"loss": 6.3728,
|
|
"mean_token_accuracy": 0.13866495788097383,
|
|
"num_tokens": 3745830.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.426714324951172,
|
|
"epoch": 0.17794065701165665,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499909368098124,
|
|
"loss": 6.4177,
|
|
"mean_token_accuracy": 0.13295648768544197,
|
|
"num_tokens": 3755019.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.44696569442749,
|
|
"epoch": 0.178382197103497,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999084721494754,
|
|
"loss": 6.3988,
|
|
"mean_token_accuracy": 0.13579348400235175,
|
|
"num_tokens": 3764814.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.390467166900635,
|
|
"epoch": 0.17882373719533734,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999075717949978,
|
|
"loss": 6.3543,
|
|
"mean_token_accuracy": 0.14030898809432985,
|
|
"num_tokens": 3774258.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.3934080600738525,
|
|
"epoch": 0.17926527728717767,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999066670347089,
|
|
"loss": 6.406,
|
|
"mean_token_accuracy": 0.13901298716664315,
|
|
"num_tokens": 3783961.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.370501375198364,
|
|
"epoch": 0.179706817379018,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999057578686261,
|
|
"loss": 6.3714,
|
|
"mean_token_accuracy": 0.13467539772391318,
|
|
"num_tokens": 3792417.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.449629449844361,
|
|
"epoch": 0.18014835747085836,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999048442967675,
|
|
"loss": 6.3437,
|
|
"mean_token_accuracy": 0.13966423645615578,
|
|
"num_tokens": 3801479.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.386091041564941,
|
|
"epoch": 0.1805898975626987,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999039263191508,
|
|
"loss": 6.4155,
|
|
"mean_token_accuracy": 0.1346621833741665,
|
|
"num_tokens": 3810799.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.469657516479492,
|
|
"epoch": 0.18103143765453902,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999030039357943,
|
|
"loss": 6.4601,
|
|
"mean_token_accuracy": 0.134067452698946,
|
|
"num_tokens": 3820966.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.439054012298584,
|
|
"epoch": 0.18147297774637938,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999020771467158,
|
|
"loss": 6.4266,
|
|
"mean_token_accuracy": 0.12985620722174646,
|
|
"num_tokens": 3829247.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.5768702030181885,
|
|
"epoch": 0.1819145178382197,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999011459519335,
|
|
"loss": 6.3752,
|
|
"mean_token_accuracy": 0.14039287865161895,
|
|
"num_tokens": 3838114.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.355933761596679,
|
|
"epoch": 0.18235605793006004,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999002103514655,
|
|
"loss": 6.4479,
|
|
"mean_token_accuracy": 0.13630082532763482,
|
|
"num_tokens": 3848075.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.573451566696167,
|
|
"epoch": 0.18279759802190038,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998992703453304,
|
|
"loss": 6.4793,
|
|
"mean_token_accuracy": 0.13254386261105539,
|
|
"num_tokens": 3857934.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.425156974792481,
|
|
"epoch": 0.18323913811374073,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998983259335466,
|
|
"loss": 6.3334,
|
|
"mean_token_accuracy": 0.14134026542305947,
|
|
"num_tokens": 3866707.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.496882581710816,
|
|
"epoch": 0.18368067820558107,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998973771161324,
|
|
"loss": 6.4122,
|
|
"mean_token_accuracy": 0.13621948882937432,
|
|
"num_tokens": 3875233.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.395424509048462,
|
|
"epoch": 0.1841222182974214,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998964238931065,
|
|
"loss": 6.3969,
|
|
"mean_token_accuracy": 0.14365216121077537,
|
|
"num_tokens": 3885173.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.43842887878418,
|
|
"epoch": 0.18456375838926176,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998954662644876,
|
|
"loss": 6.3698,
|
|
"mean_token_accuracy": 0.141506065428257,
|
|
"num_tokens": 3894198.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.405653476715088,
|
|
"epoch": 0.1850052984811021,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998945042302943,
|
|
"loss": 6.362,
|
|
"mean_token_accuracy": 0.13782091364264487,
|
|
"num_tokens": 3904076.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.422827577590942,
|
|
"epoch": 0.18544683857294242,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998935377905457,
|
|
"loss": 6.4827,
|
|
"mean_token_accuracy": 0.13269177302718163,
|
|
"num_tokens": 3913204.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.533098840713501,
|
|
"epoch": 0.18588837866478275,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998925669452605,
|
|
"loss": 6.4243,
|
|
"mean_token_accuracy": 0.13815055713057517,
|
|
"num_tokens": 3922148.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.385688829421997,
|
|
"epoch": 0.1863299187566231,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998915916944579,
|
|
"loss": 6.402,
|
|
"mean_token_accuracy": 0.13988569304347037,
|
|
"num_tokens": 3931333.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.45911545753479,
|
|
"epoch": 0.18677145884846344,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998906120381568,
|
|
"loss": 6.3701,
|
|
"mean_token_accuracy": 0.14163922518491745,
|
|
"num_tokens": 3941061.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.4747344017028805,
|
|
"epoch": 0.18721299894030377,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998896279763766,
|
|
"loss": 6.4645,
|
|
"mean_token_accuracy": 0.13232587426900863,
|
|
"num_tokens": 3950075.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.432454586029053,
|
|
"epoch": 0.18765453903214413,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998886395091365,
|
|
"loss": 6.3139,
|
|
"mean_token_accuracy": 0.1374908208847046,
|
|
"num_tokens": 3958885.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.344161605834961,
|
|
"epoch": 0.18809607912398446,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998876466364559,
|
|
"loss": 6.4104,
|
|
"mean_token_accuracy": 0.13860961571335792,
|
|
"num_tokens": 3968218.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.387483358383179,
|
|
"epoch": 0.1885376192158248,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998866493583541,
|
|
"loss": 6.3306,
|
|
"mean_token_accuracy": 0.13824384585022925,
|
|
"num_tokens": 3977435.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.347888994216919,
|
|
"epoch": 0.18897915930766512,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998856476748509,
|
|
"loss": 6.3315,
|
|
"mean_token_accuracy": 0.14486501812934877,
|
|
"num_tokens": 3986608.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.364703226089477,
|
|
"epoch": 0.18942069939950548,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998846415859656,
|
|
"loss": 6.3417,
|
|
"mean_token_accuracy": 0.14277436435222626,
|
|
"num_tokens": 3996087.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.452169370651245,
|
|
"epoch": 0.1898622394913458,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998836310917182,
|
|
"loss": 6.3897,
|
|
"mean_token_accuracy": 0.13653551563620567,
|
|
"num_tokens": 4006257.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.4531981468200685,
|
|
"epoch": 0.19030377958318614,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998826161921282,
|
|
"loss": 6.4047,
|
|
"mean_token_accuracy": 0.14247702434659004,
|
|
"num_tokens": 4015904.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.370388221740723,
|
|
"epoch": 0.1907453196750265,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998815968872157,
|
|
"loss": 6.3914,
|
|
"mean_token_accuracy": 0.13624223321676254,
|
|
"num_tokens": 4025417.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.354130029678345,
|
|
"epoch": 0.19118685976686683,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998805731770007,
|
|
"loss": 6.2668,
|
|
"mean_token_accuracy": 0.15688675343990327,
|
|
"num_tokens": 4035181.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.40911750793457,
|
|
"epoch": 0.19162839985870717,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499879545061503,
|
|
"loss": 6.4414,
|
|
"mean_token_accuracy": 0.13603056818246842,
|
|
"num_tokens": 4045112.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.498990821838379,
|
|
"epoch": 0.1920699399505475,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998785125407432,
|
|
"loss": 6.5464,
|
|
"mean_token_accuracy": 0.12719694674015045,
|
|
"num_tokens": 4054566.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.520226097106933,
|
|
"epoch": 0.19251148004238786,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499877475614741,
|
|
"loss": 6.3688,
|
|
"mean_token_accuracy": 0.13931149691343309,
|
|
"num_tokens": 4063960.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.299141502380371,
|
|
"epoch": 0.1929530201342282,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998764342835169,
|
|
"loss": 6.3007,
|
|
"mean_token_accuracy": 0.14462162256240846,
|
|
"num_tokens": 4072620.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.3178962707519535,
|
|
"epoch": 0.19339456022606852,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998753885470915,
|
|
"loss": 6.2638,
|
|
"mean_token_accuracy": 0.142801184207201,
|
|
"num_tokens": 4081590.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.386137342453003,
|
|
"epoch": 0.19383610031790888,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998743384054851,
|
|
"loss": 6.4061,
|
|
"mean_token_accuracy": 0.13850954100489615,
|
|
"num_tokens": 4090758.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.348768806457519,
|
|
"epoch": 0.1942776404097492,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998732838587183,
|
|
"loss": 6.2249,
|
|
"mean_token_accuracy": 0.14862391501665115,
|
|
"num_tokens": 4099281.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.402739572525024,
|
|
"epoch": 0.19471918050158954,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998722249068118,
|
|
"loss": 6.3303,
|
|
"mean_token_accuracy": 0.14005536511540412,
|
|
"num_tokens": 4108953.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.359877395629883,
|
|
"epoch": 0.19516072059342987,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998711615497863,
|
|
"loss": 6.4579,
|
|
"mean_token_accuracy": 0.13361181691288948,
|
|
"num_tokens": 4118799.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.544803190231323,
|
|
"epoch": 0.19560226068527023,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998700937876626,
|
|
"loss": 6.4205,
|
|
"mean_token_accuracy": 0.13423945084214212,
|
|
"num_tokens": 4127862.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.3850291728973385,
|
|
"epoch": 0.19604380077711056,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998690216204615,
|
|
"loss": 6.495,
|
|
"mean_token_accuracy": 0.1222709484398365,
|
|
"num_tokens": 4139029.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.464286041259766,
|
|
"epoch": 0.1964853408689509,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998679450482043,
|
|
"loss": 6.2958,
|
|
"mean_token_accuracy": 0.14723266661167145,
|
|
"num_tokens": 4148257.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.36017689704895,
|
|
"epoch": 0.19692688096079125,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000499866864070912,
|
|
"loss": 6.2594,
|
|
"mean_token_accuracy": 0.13788010850548743,
|
|
"num_tokens": 4157626.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.3908546447753904,
|
|
"epoch": 0.19736842105263158,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998657786886056,
|
|
"loss": 6.4709,
|
|
"mean_token_accuracy": 0.13577495142817497,
|
|
"num_tokens": 4166804.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.486610317230225,
|
|
"epoch": 0.1978099611444719,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998646889013066,
|
|
"loss": 6.3604,
|
|
"mean_token_accuracy": 0.13759335353970528,
|
|
"num_tokens": 4175701.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.4614592552185055,
|
|
"epoch": 0.19825150123631224,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998635947090362,
|
|
"loss": 6.4333,
|
|
"mean_token_accuracy": 0.14182267859578132,
|
|
"num_tokens": 4184711.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.411881828308106,
|
|
"epoch": 0.1986930413281526,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004998624961118158,
|
|
"loss": 6.4015,
|
|
"mean_token_accuracy": 0.14113648906350135,
|
|
"num_tokens": 4193931.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.377731609344482,
|
|
"epoch": 0.19913458141999293,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499861393109667,
|
|
"loss": 6.2849,
|
|
"mean_token_accuracy": 0.14618429020047188,
|
|
"num_tokens": 4203000.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.252184343338013,
|
|
"epoch": 0.19957612151183327,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998602857026114,
|
|
"loss": 6.2994,
|
|
"mean_token_accuracy": 0.1432739280164242,
|
|
"num_tokens": 4211977.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.46929440498352,
|
|
"epoch": 0.20001766160367362,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998591738906708,
|
|
"loss": 6.3915,
|
|
"mean_token_accuracy": 0.14305510893464088,
|
|
"num_tokens": 4220375.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.426153373718262,
|
|
"epoch": 0.20045920169551396,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998580576738668,
|
|
"loss": 6.3733,
|
|
"mean_token_accuracy": 0.1404948763549328,
|
|
"num_tokens": 4230506.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.3839240074157715,
|
|
"epoch": 0.2009007417873543,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998569370522213,
|
|
"loss": 6.3415,
|
|
"mean_token_accuracy": 0.1391644887626171,
|
|
"num_tokens": 4240235.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.3975495338439945,
|
|
"epoch": 0.20134228187919462,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998558120257563,
|
|
"loss": 6.3999,
|
|
"mean_token_accuracy": 0.13654018118977546,
|
|
"num_tokens": 4249775.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.365513944625855,
|
|
"epoch": 0.20178382197103498,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004998546825944938,
|
|
"loss": 6.3373,
|
|
"mean_token_accuracy": 0.14069335907697678,
|
|
"num_tokens": 4258523.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.384157276153564,
|
|
"epoch": 0.2022253620628753,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000499853548758456,
|
|
"loss": 6.3589,
|
|
"mean_token_accuracy": 0.13782192021608353,
|
|
"num_tokens": 4267683.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.489559173583984,
|
|
"epoch": 0.20266690215471564,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.000499852410517665,
|
|
"loss": 6.4409,
|
|
"mean_token_accuracy": 0.13151715248823165,
|
|
"num_tokens": 4276903.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.439543437957764,
|
|
"epoch": 0.203108442246556,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004998512678721431,
|
|
"loss": 6.3807,
|
|
"mean_token_accuracy": 0.13557614907622337,
|
|
"num_tokens": 4287257.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.444064092636109,
|
|
"epoch": 0.20354998233839633,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499850120821913,
|
|
"loss": 6.4005,
|
|
"mean_token_accuracy": 0.1363210029900074,
|
|
"num_tokens": 4297345.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.469133949279785,
|
|
"epoch": 0.20399152243023666,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004998489693669967,
|
|
"loss": 6.3436,
|
|
"mean_token_accuracy": 0.135118205845356,
|
|
"num_tokens": 4306533.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.341489553451538,
|
|
"epoch": 0.204433062522077,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499847813507417,
|
|
"loss": 6.4077,
|
|
"mean_token_accuracy": 0.13763028532266616,
|
|
"num_tokens": 4316338.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.4129331588745115,
|
|
"epoch": 0.20487460261391735,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998466532431966,
|
|
"loss": 6.3616,
|
|
"mean_token_accuracy": 0.13560457453131675,
|
|
"num_tokens": 4326585.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.5451561450958256,
|
|
"epoch": 0.20531614270575768,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998454885743581,
|
|
"loss": 6.4974,
|
|
"mean_token_accuracy": 0.131976468116045,
|
|
"num_tokens": 4336490.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.331731176376342,
|
|
"epoch": 0.205757682797598,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998443195009242,
|
|
"loss": 6.3524,
|
|
"mean_token_accuracy": 0.1353374347090721,
|
|
"num_tokens": 4346264.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.46915283203125,
|
|
"epoch": 0.20619922288943837,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998431460229182,
|
|
"loss": 6.3484,
|
|
"mean_token_accuracy": 0.14326995760202407,
|
|
"num_tokens": 4355102.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.449292993545532,
|
|
"epoch": 0.2066407629812787,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004998419681403627,
|
|
"loss": 6.5183,
|
|
"mean_token_accuracy": 0.13123422861099243,
|
|
"num_tokens": 4365569.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.420946168899536,
|
|
"epoch": 0.20708230307311903,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998407858532809,
|
|
"loss": 6.3442,
|
|
"mean_token_accuracy": 0.14129015430808067,
|
|
"num_tokens": 4375437.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.4041321754455565,
|
|
"epoch": 0.20752384316495937,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499839599161696,
|
|
"loss": 6.3431,
|
|
"mean_token_accuracy": 0.1439853347837925,
|
|
"num_tokens": 4384420.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.3517293453216555,
|
|
"epoch": 0.20796538325679972,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004998384080656314,
|
|
"loss": 6.3093,
|
|
"mean_token_accuracy": 0.13698634803295134,
|
|
"num_tokens": 4393730.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.3013396739959715,
|
|
"epoch": 0.20840692334864006,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00049983721256511,
|
|
"loss": 6.2912,
|
|
"mean_token_accuracy": 0.14068662524223327,
|
|
"num_tokens": 4402731.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.36918888092041,
|
|
"epoch": 0.2088484634404804,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004998360126601556,
|
|
"loss": 6.3489,
|
|
"mean_token_accuracy": 0.14043711125850677,
|
|
"num_tokens": 4411606.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.387992668151855,
|
|
"epoch": 0.20929000353232075,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004998348083507916,
|
|
"loss": 6.4201,
|
|
"mean_token_accuracy": 0.13762734830379486,
|
|
"num_tokens": 4421685.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.478447484970093,
|
|
"epoch": 0.20973154362416108,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004998335996370416,
|
|
"loss": 6.3708,
|
|
"mean_token_accuracy": 0.14082587361335755,
|
|
"num_tokens": 4431765.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.374440622329712,
|
|
"epoch": 0.2101730837160014,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998323865189291,
|
|
"loss": 6.343,
|
|
"mean_token_accuracy": 0.13578818812966348,
|
|
"num_tokens": 4441191.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.384360408782959,
|
|
"epoch": 0.21061462380784174,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998311689964781,
|
|
"loss": 6.4306,
|
|
"mean_token_accuracy": 0.13119565919041634,
|
|
"num_tokens": 4450156.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.4847077369689945,
|
|
"epoch": 0.2110561638996821,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004998299470697125,
|
|
"loss": 6.4317,
|
|
"mean_token_accuracy": 0.1381568767130375,
|
|
"num_tokens": 4459466.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.431920385360717,
|
|
"epoch": 0.21149770399152243,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004998287207386559,
|
|
"loss": 6.4087,
|
|
"mean_token_accuracy": 0.13905522376298904,
|
|
"num_tokens": 4468539.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.486487150192261,
|
|
"epoch": 0.21193924408336276,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998274900033326,
|
|
"loss": 6.3309,
|
|
"mean_token_accuracy": 0.14359693378210067,
|
|
"num_tokens": 4477579.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.27841157913208,
|
|
"epoch": 0.21238078417520312,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998262548637667,
|
|
"loss": 6.2944,
|
|
"mean_token_accuracy": 0.14606404006481172,
|
|
"num_tokens": 4486800.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.3170582294464115,
|
|
"epoch": 0.21282232426704345,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004998250153199822,
|
|
"loss": 6.2406,
|
|
"mean_token_accuracy": 0.1487855888903141,
|
|
"num_tokens": 4495985.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.4847211837768555,
|
|
"epoch": 0.21326386435888378,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998237713720036,
|
|
"loss": 6.4147,
|
|
"mean_token_accuracy": 0.13529004976153375,
|
|
"num_tokens": 4504944.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.306296968460083,
|
|
"epoch": 0.2137054044507241,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998225230198552,
|
|
"loss": 6.3031,
|
|
"mean_token_accuracy": 0.14425254613161087,
|
|
"num_tokens": 4515402.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.379396724700928,
|
|
"epoch": 0.21414694454256447,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998212702635614,
|
|
"loss": 6.374,
|
|
"mean_token_accuracy": 0.13573372215032578,
|
|
"num_tokens": 4525009.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.499070882797241,
|
|
"epoch": 0.2145884846344048,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004998200131031469,
|
|
"loss": 6.4094,
|
|
"mean_token_accuracy": 0.13427471220493317,
|
|
"num_tokens": 4534460.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.376511430740356,
|
|
"epoch": 0.21503002472624513,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998187515386361,
|
|
"loss": 6.2374,
|
|
"mean_token_accuracy": 0.14696551114320755,
|
|
"num_tokens": 4543748.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.321905422210693,
|
|
"epoch": 0.2154715648180855,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998174855700538,
|
|
"loss": 6.3617,
|
|
"mean_token_accuracy": 0.14429828226566316,
|
|
"num_tokens": 4552722.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.440483331680298,
|
|
"epoch": 0.21591310490992582,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004998162151974248,
|
|
"loss": 6.2207,
|
|
"mean_token_accuracy": 0.14380936026573182,
|
|
"num_tokens": 4561607.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.3644684791564945,
|
|
"epoch": 0.21635464500176615,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499814940420774,
|
|
"loss": 6.5024,
|
|
"mean_token_accuracy": 0.1272777035832405,
|
|
"num_tokens": 4572524.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.4338010311126705,
|
|
"epoch": 0.21679618509360649,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998136612401266,
|
|
"loss": 6.3239,
|
|
"mean_token_accuracy": 0.14616527855396272,
|
|
"num_tokens": 4581601.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.408474111557007,
|
|
"epoch": 0.21723772518544684,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998123776555071,
|
|
"loss": 6.3758,
|
|
"mean_token_accuracy": 0.1353377342224121,
|
|
"num_tokens": 4591795.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.354497385025025,
|
|
"epoch": 0.21767926527728718,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998110896669412,
|
|
"loss": 6.3251,
|
|
"mean_token_accuracy": 0.13686212673783302,
|
|
"num_tokens": 4600745.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.451937007904053,
|
|
"epoch": 0.2181208053691275,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998097972744539,
|
|
"loss": 6.3817,
|
|
"mean_token_accuracy": 0.13510738238692283,
|
|
"num_tokens": 4610490.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.394930648803711,
|
|
"epoch": 0.21856234546096787,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998085004780705,
|
|
"loss": 6.3089,
|
|
"mean_token_accuracy": 0.14037252739071845,
|
|
"num_tokens": 4619511.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.379614734649659,
|
|
"epoch": 0.2190038855528082,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998071992778164,
|
|
"loss": 6.3428,
|
|
"mean_token_accuracy": 0.1402582421898842,
|
|
"num_tokens": 4628186.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.451162719726563,
|
|
"epoch": 0.21944542564464853,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499805893673717,
|
|
"loss": 6.378,
|
|
"mean_token_accuracy": 0.14208944439888,
|
|
"num_tokens": 4637431.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.312719869613647,
|
|
"epoch": 0.21988696573648886,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998045836657982,
|
|
"loss": 6.2251,
|
|
"mean_token_accuracy": 0.14331654608249664,
|
|
"num_tokens": 4646627.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.346300935745239,
|
|
"epoch": 0.22032850582832922,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004998032692540853,
|
|
"loss": 6.324,
|
|
"mean_token_accuracy": 0.13909852951765062,
|
|
"num_tokens": 4656095.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.4727942943573,
|
|
"epoch": 0.22077004592016955,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998019504386044,
|
|
"loss": 6.4001,
|
|
"mean_token_accuracy": 0.13648373931646346,
|
|
"num_tokens": 4665807.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.379480361938477,
|
|
"epoch": 0.22121158601200988,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004998006272193809,
|
|
"loss": 6.3575,
|
|
"mean_token_accuracy": 0.13852972015738488,
|
|
"num_tokens": 4674459.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.410311126708985,
|
|
"epoch": 0.22165312610385024,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997992995964412,
|
|
"loss": 6.4505,
|
|
"mean_token_accuracy": 0.13554090186953544,
|
|
"num_tokens": 4684063.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.3212048530578615,
|
|
"epoch": 0.22209466619569057,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004997979675698109,
|
|
"loss": 6.3377,
|
|
"mean_token_accuracy": 0.14127737581729888,
|
|
"num_tokens": 4692807.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.487754249572754,
|
|
"epoch": 0.2225362062875309,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997966311395164,
|
|
"loss": 6.2628,
|
|
"mean_token_accuracy": 0.14333414733409883,
|
|
"num_tokens": 4701100.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.231193733215332,
|
|
"epoch": 0.22297774637937123,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004997952903055836,
|
|
"loss": 6.3098,
|
|
"mean_token_accuracy": 0.1349740982055664,
|
|
"num_tokens": 4710697.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.37754340171814,
|
|
"epoch": 0.2234192864712116,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000499793945068039,
|
|
"loss": 6.2937,
|
|
"mean_token_accuracy": 0.13749002516269684,
|
|
"num_tokens": 4718745.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.354239130020142,
|
|
"epoch": 0.22386082656305192,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997925954269088,
|
|
"loss": 6.2648,
|
|
"mean_token_accuracy": 0.14231488481163979,
|
|
"num_tokens": 4728056.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.382005739212036,
|
|
"epoch": 0.22430236665489225,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004997912413822196,
|
|
"loss": 6.391,
|
|
"mean_token_accuracy": 0.1377481795847416,
|
|
"num_tokens": 4737605.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.34613995552063,
|
|
"epoch": 0.2247439067467326,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997898829339979,
|
|
"loss": 6.2206,
|
|
"mean_token_accuracy": 0.14988200217485428,
|
|
"num_tokens": 4746168.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.318027210235596,
|
|
"epoch": 0.22518544683857294,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00049978852008227,
|
|
"loss": 6.29,
|
|
"mean_token_accuracy": 0.142624107003212,
|
|
"num_tokens": 4755072.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.386806201934815,
|
|
"epoch": 0.22562698693041328,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499787152827063,
|
|
"loss": 6.3083,
|
|
"mean_token_accuracy": 0.1480213187634945,
|
|
"num_tokens": 4764580.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.287759494781494,
|
|
"epoch": 0.2260685270222536,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997857811684035,
|
|
"loss": 6.3079,
|
|
"mean_token_accuracy": 0.1506627842783928,
|
|
"num_tokens": 4774135.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.41878023147583,
|
|
"epoch": 0.22651006711409397,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004997844051063183,
|
|
"loss": 6.4043,
|
|
"mean_token_accuracy": 0.13596237674355507,
|
|
"num_tokens": 4784733.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.420801305770874,
|
|
"epoch": 0.2269516072059343,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997830246408346,
|
|
"loss": 6.3239,
|
|
"mean_token_accuracy": 0.14653001427650453,
|
|
"num_tokens": 4795327.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.26131682395935,
|
|
"epoch": 0.22739314729777463,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004997816397719791,
|
|
"loss": 6.3033,
|
|
"mean_token_accuracy": 0.1419690243899822,
|
|
"num_tokens": 4804314.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.447992181777954,
|
|
"epoch": 0.227834687389615,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997802504997792,
|
|
"loss": 6.3864,
|
|
"mean_token_accuracy": 0.1353736087679863,
|
|
"num_tokens": 4813637.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.362198352813721,
|
|
"epoch": 0.22827622748145532,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997788568242621,
|
|
"loss": 6.2733,
|
|
"mean_token_accuracy": 0.14258976951241492,
|
|
"num_tokens": 4823094.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.313487911224366,
|
|
"epoch": 0.22871776757329565,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499777458745455,
|
|
"loss": 6.2101,
|
|
"mean_token_accuracy": 0.14641790390014647,
|
|
"num_tokens": 4833199.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.383407735824585,
|
|
"epoch": 0.22915930766513598,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004997760562633853,
|
|
"loss": 6.3168,
|
|
"mean_token_accuracy": 0.1408907800912857,
|
|
"num_tokens": 4842970.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.429384851455689,
|
|
"epoch": 0.22960084775697634,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997746493780804,
|
|
"loss": 6.4179,
|
|
"mean_token_accuracy": 0.1343531347811222,
|
|
"num_tokens": 4852043.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.356952238082886,
|
|
"epoch": 0.23004238784881667,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499773238089568,
|
|
"loss": 6.2974,
|
|
"mean_token_accuracy": 0.13784752711653708,
|
|
"num_tokens": 4862232.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.3309001445770265,
|
|
"epoch": 0.230483927940657,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004997718223978758,
|
|
"loss": 6.2265,
|
|
"mean_token_accuracy": 0.14307404607534407,
|
|
"num_tokens": 4871186.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.393591213226318,
|
|
"epoch": 0.23092546803249736,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997704023030315,
|
|
"loss": 6.3176,
|
|
"mean_token_accuracy": 0.14954473525285722,
|
|
"num_tokens": 4879974.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.334340620040893,
|
|
"epoch": 0.2313670081243377,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004997689778050627,
|
|
"loss": 6.3876,
|
|
"mean_token_accuracy": 0.138017987459898,
|
|
"num_tokens": 4890300.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.35406002998352,
|
|
"epoch": 0.23180854821617802,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997675489039975,
|
|
"loss": 6.3527,
|
|
"mean_token_accuracy": 0.13665685877203942,
|
|
"num_tokens": 4900428.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.393978548049927,
|
|
"epoch": 0.23225008830801835,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004997661155998638,
|
|
"loss": 6.3461,
|
|
"mean_token_accuracy": 0.14447346180677414,
|
|
"num_tokens": 4910092.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.395442962646484,
|
|
"epoch": 0.2326916283998587,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004997646778926898,
|
|
"loss": 6.3456,
|
|
"mean_token_accuracy": 0.14186301603913307,
|
|
"num_tokens": 4919593.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.36322603225708,
|
|
"epoch": 0.23313316849169904,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004997632357825035,
|
|
"loss": 6.3172,
|
|
"mean_token_accuracy": 0.13682103008031846,
|
|
"num_tokens": 4929098.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.4403660774230955,
|
|
"epoch": 0.23357470858353938,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004997617892693333,
|
|
"loss": 6.3653,
|
|
"mean_token_accuracy": 0.13785530328750611,
|
|
"num_tokens": 4938265.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.4328492164611815,
|
|
"epoch": 0.23401624867537973,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004997603383532075,
|
|
"loss": 6.3177,
|
|
"mean_token_accuracy": 0.14054129794239997,
|
|
"num_tokens": 4946694.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.297847509384155,
|
|
"epoch": 0.23445778876722007,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004997588830341545,
|
|
"loss": 6.3275,
|
|
"mean_token_accuracy": 0.14105295538902282,
|
|
"num_tokens": 4955296.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.317044591903686,
|
|
"epoch": 0.2348993288590604,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004997574233122028,
|
|
"loss": 6.3017,
|
|
"mean_token_accuracy": 0.14537747204303741,
|
|
"num_tokens": 4964409.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.3555162906646725,
|
|
"epoch": 0.23534086895090076,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004997559591873809,
|
|
"loss": 6.3035,
|
|
"mean_token_accuracy": 0.14873416274785994,
|
|
"num_tokens": 4973449.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.351046800613403,
|
|
"epoch": 0.2357824090427411,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004997544906597178,
|
|
"loss": 6.3045,
|
|
"mean_token_accuracy": 0.14574557095766066,
|
|
"num_tokens": 4983057.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.3079445362091064,
|
|
"epoch": 0.23622394913458142,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004997530177292418,
|
|
"loss": 6.3526,
|
|
"mean_token_accuracy": 0.1371928870677948,
|
|
"num_tokens": 4991950.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.4892011165618895,
|
|
"epoch": 0.23666548922642175,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004997515403959823,
|
|
"loss": 6.3031,
|
|
"mean_token_accuracy": 0.14117597341537474,
|
|
"num_tokens": 5001042.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.349958276748657,
|
|
"epoch": 0.2371070293182621,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004997500586599677,
|
|
"loss": 6.2512,
|
|
"mean_token_accuracy": 0.14559754729270935,
|
|
"num_tokens": 5009827.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.331127786636353,
|
|
"epoch": 0.23754856941010244,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997485725212274,
|
|
"loss": 6.2914,
|
|
"mean_token_accuracy": 0.13917716667056085,
|
|
"num_tokens": 5018708.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.290257930755615,
|
|
"epoch": 0.23799010950194277,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004997470819797903,
|
|
"loss": 6.1657,
|
|
"mean_token_accuracy": 0.15060664638876914,
|
|
"num_tokens": 5027522.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.301162242889404,
|
|
"epoch": 0.23843164959378313,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004997455870356857,
|
|
"loss": 6.3071,
|
|
"mean_token_accuracy": 0.14116470664739608,
|
|
"num_tokens": 5035755.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.376118612289429,
|
|
"epoch": 0.23887318968562346,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004997440876889429,
|
|
"loss": 6.2543,
|
|
"mean_token_accuracy": 0.14213244915008544,
|
|
"num_tokens": 5045289.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.249507427215576,
|
|
"epoch": 0.2393147297774638,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004997425839395913,
|
|
"loss": 6.2774,
|
|
"mean_token_accuracy": 0.14211364090442657,
|
|
"num_tokens": 5053774.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.390804290771484,
|
|
"epoch": 0.23975626986930412,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004997410757876602,
|
|
"loss": 6.3637,
|
|
"mean_token_accuracy": 0.13094362914562224,
|
|
"num_tokens": 5062911.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.374802780151367,
|
|
"epoch": 0.24019780996114448,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997395632331793,
|
|
"loss": 6.231,
|
|
"mean_token_accuracy": 0.14750899523496627,
|
|
"num_tokens": 5072107.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.239001655578614,
|
|
"epoch": 0.2406393500529848,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004997380462761781,
|
|
"loss": 6.189,
|
|
"mean_token_accuracy": 0.14651150107383729,
|
|
"num_tokens": 5080588.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.313574028015137,
|
|
"epoch": 0.24108089014482514,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004997365249166864,
|
|
"loss": 6.3843,
|
|
"mean_token_accuracy": 0.14336365312337876,
|
|
"num_tokens": 5090262.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.42013373374939,
|
|
"epoch": 0.2415224302366655,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997349991547342,
|
|
"loss": 6.2793,
|
|
"mean_token_accuracy": 0.15069962069392204,
|
|
"num_tokens": 5099285.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.363212537765503,
|
|
"epoch": 0.24196397032850583,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997334689903509,
|
|
"loss": 6.337,
|
|
"mean_token_accuracy": 0.146900225430727,
|
|
"num_tokens": 5109115.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.39803113937378,
|
|
"epoch": 0.24240551042034617,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004997319344235668,
|
|
"loss": 6.3625,
|
|
"mean_token_accuracy": 0.14113707169890405,
|
|
"num_tokens": 5117977.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.412462043762207,
|
|
"epoch": 0.2428470505121865,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000499730395454412,
|
|
"loss": 6.3246,
|
|
"mean_token_accuracy": 0.14121332690119742,
|
|
"num_tokens": 5127457.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.294469976425171,
|
|
"epoch": 0.24328859060402686,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997288520829166,
|
|
"loss": 6.3746,
|
|
"mean_token_accuracy": 0.13444311991333963,
|
|
"num_tokens": 5137310.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.404769420623779,
|
|
"epoch": 0.2437301306958672,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004997273043091107,
|
|
"loss": 6.3024,
|
|
"mean_token_accuracy": 0.13945599272847176,
|
|
"num_tokens": 5146963.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.3221978664398195,
|
|
"epoch": 0.24417167078770752,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004997257521330248,
|
|
"loss": 6.285,
|
|
"mean_token_accuracy": 0.13930008858442305,
|
|
"num_tokens": 5155521.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.304354858398438,
|
|
"epoch": 0.24461321087954788,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004997241955546892,
|
|
"loss": 6.2707,
|
|
"mean_token_accuracy": 0.14256517514586448,
|
|
"num_tokens": 5165182.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.362063407897949,
|
|
"epoch": 0.2450547509713882,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997226345741343,
|
|
"loss": 6.2908,
|
|
"mean_token_accuracy": 0.13857515007257462,
|
|
"num_tokens": 5175511.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.305971288681031,
|
|
"epoch": 0.24549629106322854,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000499721069191391,
|
|
"loss": 6.2295,
|
|
"mean_token_accuracy": 0.14581285938620567,
|
|
"num_tokens": 5184772.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.251179599761963,
|
|
"epoch": 0.24593783115506887,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004997194994064896,
|
|
"loss": 6.3205,
|
|
"mean_token_accuracy": 0.14159369021654128,
|
|
"num_tokens": 5195136.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.401678276062012,
|
|
"epoch": 0.24637937124690923,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000499717925219461,
|
|
"loss": 6.2658,
|
|
"mean_token_accuracy": 0.15039479061961175,
|
|
"num_tokens": 5203163.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.363914871215821,
|
|
"epoch": 0.24682091133874956,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004997163466303362,
|
|
"loss": 6.342,
|
|
"mean_token_accuracy": 0.1374757319688797,
|
|
"num_tokens": 5213233.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.326372671127319,
|
|
"epoch": 0.2472624514305899,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499714763639146,
|
|
"loss": 6.2748,
|
|
"mean_token_accuracy": 0.13834284916520118,
|
|
"num_tokens": 5222940.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.359001636505127,
|
|
"epoch": 0.24770399152243025,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004997131762459211,
|
|
"loss": 6.2926,
|
|
"mean_token_accuracy": 0.1355063237249851,
|
|
"num_tokens": 5232263.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.353963899612427,
|
|
"epoch": 0.24814553161427058,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004997115844506932,
|
|
"loss": 6.2777,
|
|
"mean_token_accuracy": 0.13894380629062653,
|
|
"num_tokens": 5241536.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.347019195556641,
|
|
"epoch": 0.2485870717061109,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004997099882534929,
|
|
"loss": 6.3014,
|
|
"mean_token_accuracy": 0.13601062670350075,
|
|
"num_tokens": 5250702.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.308573961257935,
|
|
"epoch": 0.24902861179795124,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997083876543519,
|
|
"loss": 6.3152,
|
|
"mean_token_accuracy": 0.13795805871486663,
|
|
"num_tokens": 5259811.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.473266696929931,
|
|
"epoch": 0.2494701518897916,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997067826533014,
|
|
"loss": 6.3819,
|
|
"mean_token_accuracy": 0.1361972101032734,
|
|
"num_tokens": 5270518.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.389288711547851,
|
|
"epoch": 0.24991169198163193,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004997051732503726,
|
|
"loss": 6.2551,
|
|
"mean_token_accuracy": 0.13983014822006226,
|
|
"num_tokens": 5279538.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.26657543182373,
|
|
"epoch": 0.25035323207347226,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004997035594455975,
|
|
"loss": 6.3026,
|
|
"mean_token_accuracy": 0.13869107514619827,
|
|
"num_tokens": 5289633.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.390535449981689,
|
|
"epoch": 0.2507947721653126,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997019412390074,
|
|
"loss": 6.42,
|
|
"mean_token_accuracy": 0.13744667321443557,
|
|
"num_tokens": 5299148.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.3600469589233395,
|
|
"epoch": 0.2512363122571529,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000499700318630634,
|
|
"loss": 6.2602,
|
|
"mean_token_accuracy": 0.14515333026647567,
|
|
"num_tokens": 5309090.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.343839168548584,
|
|
"epoch": 0.2516778523489933,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004996986916205092,
|
|
"loss": 6.3523,
|
|
"mean_token_accuracy": 0.13558987081050872,
|
|
"num_tokens": 5318798.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.27102484703064,
|
|
"epoch": 0.25211939244083365,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004996970602086648,
|
|
"loss": 6.2258,
|
|
"mean_token_accuracy": 0.1445697531104088,
|
|
"num_tokens": 5327915.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.295015048980713,
|
|
"epoch": 0.252560932532674,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004996954243951327,
|
|
"loss": 6.2654,
|
|
"mean_token_accuracy": 0.14920969903469086,
|
|
"num_tokens": 5336970.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.284700727462768,
|
|
"epoch": 0.2530024726245143,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004996937841799451,
|
|
"loss": 6.2196,
|
|
"mean_token_accuracy": 0.1482589215040207,
|
|
"num_tokens": 5345167.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.241301822662353,
|
|
"epoch": 0.25344401271635464,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004996921395631342,
|
|
"loss": 6.2041,
|
|
"mean_token_accuracy": 0.14476508051156997,
|
|
"num_tokens": 5353399.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.302233171463013,
|
|
"epoch": 0.25388555280819497,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000499690490544732,
|
|
"loss": 6.3187,
|
|
"mean_token_accuracy": 0.1422203630208969,
|
|
"num_tokens": 5363224.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.388623285293579,
|
|
"epoch": 0.2543270929000353,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004996888371247707,
|
|
"loss": 6.3351,
|
|
"mean_token_accuracy": 0.1384458288550377,
|
|
"num_tokens": 5372274.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.4166820526123045,
|
|
"epoch": 0.2547686329918757,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000499687179303283,
|
|
"loss": 6.308,
|
|
"mean_token_accuracy": 0.14665373042225838,
|
|
"num_tokens": 5380240.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.302547883987427,
|
|
"epoch": 0.255210173083716,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004996855170803012,
|
|
"loss": 6.1651,
|
|
"mean_token_accuracy": 0.14814262390136718,
|
|
"num_tokens": 5389390.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.2304370403289795,
|
|
"epoch": 0.25565171317555635,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004996838504558581,
|
|
"loss": 6.332,
|
|
"mean_token_accuracy": 0.1434281162917614,
|
|
"num_tokens": 5399425.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.390418291091919,
|
|
"epoch": 0.2560932532673967,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000499682179429986,
|
|
"loss": 6.3432,
|
|
"mean_token_accuracy": 0.14031529799103737,
|
|
"num_tokens": 5408717.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.369663047790527,
|
|
"epoch": 0.256534793359237,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004996805040027178,
|
|
"loss": 6.2789,
|
|
"mean_token_accuracy": 0.13554130122065544,
|
|
"num_tokens": 5418475.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.373133182525635,
|
|
"epoch": 0.25697633345107734,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004996788241740863,
|
|
"loss": 6.3139,
|
|
"mean_token_accuracy": 0.14075277075171472,
|
|
"num_tokens": 5428403.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.349458980560303,
|
|
"epoch": 0.2574178735429177,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004996771399441243,
|
|
"loss": 6.372,
|
|
"mean_token_accuracy": 0.13378326818346978,
|
|
"num_tokens": 5437347.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.4478528022766115,
|
|
"epoch": 0.25785941363475806,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004996754513128652,
|
|
"loss": 6.2655,
|
|
"mean_token_accuracy": 0.14531978368759155,
|
|
"num_tokens": 5446804.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.286684846878051,
|
|
"epoch": 0.2583009537265984,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004996737582803416,
|
|
"loss": 6.2076,
|
|
"mean_token_accuracy": 0.14176183342933654,
|
|
"num_tokens": 5455888.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.301067447662353,
|
|
"epoch": 0.2587424938184387,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004996720608465868,
|
|
"loss": 6.2077,
|
|
"mean_token_accuracy": 0.14722970575094224,
|
|
"num_tokens": 5463977.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.3211047649383545,
|
|
"epoch": 0.25918403391027905,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004996703590116342,
|
|
"loss": 6.327,
|
|
"mean_token_accuracy": 0.13881488144397736,
|
|
"num_tokens": 5473780.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.309579610824585,
|
|
"epoch": 0.2596255740021194,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004996686527755171,
|
|
"loss": 6.1882,
|
|
"mean_token_accuracy": 0.14595898613333702,
|
|
"num_tokens": 5482151.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.318369293212891,
|
|
"epoch": 0.2600671140939597,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004996669421382687,
|
|
"loss": 6.2299,
|
|
"mean_token_accuracy": 0.1491067260503769,
|
|
"num_tokens": 5491103.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.297426509857178,
|
|
"epoch": 0.26050865418580005,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004996652270999228,
|
|
"loss": 6.2482,
|
|
"mean_token_accuracy": 0.14331730753183364,
|
|
"num_tokens": 5500367.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.3517374992370605,
|
|
"epoch": 0.26095019427764043,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004996635076605128,
|
|
"loss": 6.2829,
|
|
"mean_token_accuracy": 0.14498205482959747,
|
|
"num_tokens": 5509631.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.456418180465699,
|
|
"epoch": 0.26139173436948077,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004996617838200725,
|
|
"loss": 6.2799,
|
|
"mean_token_accuracy": 0.14098481461405754,
|
|
"num_tokens": 5518635.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.273197174072266,
|
|
"epoch": 0.2618332744613211,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004996600555786357,
|
|
"loss": 6.2366,
|
|
"mean_token_accuracy": 0.14240477085113526,
|
|
"num_tokens": 5527696.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.333998394012451,
|
|
"epoch": 0.26227481455316143,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004996583229362362,
|
|
"loss": 6.216,
|
|
"mean_token_accuracy": 0.14474834203720094,
|
|
"num_tokens": 5536632.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.4111855030059814,
|
|
"epoch": 0.26271635464500176,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004996565858929078,
|
|
"loss": 6.2995,
|
|
"mean_token_accuracy": 0.14190069884061812,
|
|
"num_tokens": 5545825.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.240679502487183,
|
|
"epoch": 0.2631578947368421,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004996548444486847,
|
|
"loss": 6.1819,
|
|
"mean_token_accuracy": 0.14833824932575226,
|
|
"num_tokens": 5555158.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.252728462219238,
|
|
"epoch": 0.2635994348286824,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004996530986036008,
|
|
"loss": 6.126,
|
|
"mean_token_accuracy": 0.14824561923742294,
|
|
"num_tokens": 5564218.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.236001491546631,
|
|
"epoch": 0.2640409749205228,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004996513483576907,
|
|
"loss": 6.2712,
|
|
"mean_token_accuracy": 0.14679816737771034,
|
|
"num_tokens": 5572760.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.370929002761841,
|
|
"epoch": 0.26448251501236314,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004996495937109884,
|
|
"loss": 6.3147,
|
|
"mean_token_accuracy": 0.14080894514918327,
|
|
"num_tokens": 5581660.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.323193359375,
|
|
"epoch": 0.26492405510420347,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004996478346635283,
|
|
"loss": 6.229,
|
|
"mean_token_accuracy": 0.14318683445453645,
|
|
"num_tokens": 5590664.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.26492405510420347,
|
|
"eval_entropy": 6.108612703278003,
|
|
"eval_loss": 6.312756538391113,
|
|
"eval_mean_token_accuracy": 0.14662449901759,
|
|
"eval_num_tokens": 5590664.0,
|
|
"eval_runtime": 26.935,
|
|
"eval_samples_per_second": 1311.12,
|
|
"eval_steps_per_second": 163.913,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 6.254260587692261,
|
|
"epoch": 0.2653655951960438,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004996460712153448,
|
|
"loss": 6.1098,
|
|
"mean_token_accuracy": 0.16003013849258424,
|
|
"num_tokens": 5598727.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 6.19307279586792,
|
|
"epoch": 0.26580713528788413,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004996443033664726,
|
|
"loss": 6.3173,
|
|
"mean_token_accuracy": 0.1360806442797184,
|
|
"num_tokens": 5608549.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 6.317127704620361,
|
|
"epoch": 0.26624867537972446,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004996425311169463,
|
|
"loss": 6.2454,
|
|
"mean_token_accuracy": 0.14779156744480132,
|
|
"num_tokens": 5617628.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 6.371944999694824,
|
|
"epoch": 0.2666902154715648,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004996407544668005,
|
|
"loss": 6.303,
|
|
"mean_token_accuracy": 0.1368146575987339,
|
|
"num_tokens": 5627182.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 6.376071310043335,
|
|
"epoch": 0.2671317555634052,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004996389734160701,
|
|
"loss": 6.323,
|
|
"mean_token_accuracy": 0.13930497989058493,
|
|
"num_tokens": 5636413.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 6.400035238265991,
|
|
"epoch": 0.2675732956552455,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00049963718796479,
|
|
"loss": 6.2654,
|
|
"mean_token_accuracy": 0.14247873574495315,
|
|
"num_tokens": 5646025.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 6.326315689086914,
|
|
"epoch": 0.26801483574708584,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996353981129952,
|
|
"loss": 6.2818,
|
|
"mean_token_accuracy": 0.1449798859655857,
|
|
"num_tokens": 5656577.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 6.399411296844482,
|
|
"epoch": 0.2684563758389262,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004996336038607206,
|
|
"loss": 6.2581,
|
|
"mean_token_accuracy": 0.14687425941228865,
|
|
"num_tokens": 5665163.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 6.332171678543091,
|
|
"epoch": 0.2688979159307665,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004996318052080015,
|
|
"loss": 6.2768,
|
|
"mean_token_accuracy": 0.14574099630117415,
|
|
"num_tokens": 5675196.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 6.325894498825074,
|
|
"epoch": 0.26933945602260684,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004996300021548731,
|
|
"loss": 6.2028,
|
|
"mean_token_accuracy": 0.14763407558202743,
|
|
"num_tokens": 5684361.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 6.266258382797242,
|
|
"epoch": 0.26978099611444717,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004996281947013707,
|
|
"loss": 6.1977,
|
|
"mean_token_accuracy": 0.14618466496467591,
|
|
"num_tokens": 5694187.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 6.300919008255005,
|
|
"epoch": 0.27022253620628756,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004996263828475298,
|
|
"loss": 6.2712,
|
|
"mean_token_accuracy": 0.13954370617866516,
|
|
"num_tokens": 5702858.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 6.261748504638672,
|
|
"epoch": 0.2706640762981279,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004996245665933857,
|
|
"loss": 6.1632,
|
|
"mean_token_accuracy": 0.14856553450226784,
|
|
"num_tokens": 5712727.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.303600072860718,
|
|
"epoch": 0.2711056163899682,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004996227459389741,
|
|
"loss": 6.2886,
|
|
"mean_token_accuracy": 0.14338717311620713,
|
|
"num_tokens": 5722904.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 6.386627197265625,
|
|
"epoch": 0.27154715648180855,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004996209208843307,
|
|
"loss": 6.3874,
|
|
"mean_token_accuracy": 0.14143950417637824,
|
|
"num_tokens": 5732228.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 6.375475549697876,
|
|
"epoch": 0.2719886965736489,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996190914294912,
|
|
"loss": 6.3109,
|
|
"mean_token_accuracy": 0.14234673753380775,
|
|
"num_tokens": 5743548.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 6.288537931442261,
|
|
"epoch": 0.2724302366654892,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004996172575744914,
|
|
"loss": 6.3338,
|
|
"mean_token_accuracy": 0.13253869488835335,
|
|
"num_tokens": 5754112.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 6.302958822250366,
|
|
"epoch": 0.27287177675732954,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004996154193193673,
|
|
"loss": 6.1664,
|
|
"mean_token_accuracy": 0.14899687618017196,
|
|
"num_tokens": 5763377.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 6.1695150375366214,
|
|
"epoch": 0.27331331684916993,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004996135766641549,
|
|
"loss": 6.1159,
|
|
"mean_token_accuracy": 0.15076552629470824,
|
|
"num_tokens": 5772000.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 6.356336355209351,
|
|
"epoch": 0.27375485694101026,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004996117296088903,
|
|
"loss": 6.2563,
|
|
"mean_token_accuracy": 0.14282927811145782,
|
|
"num_tokens": 5782192.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 6.394344520568848,
|
|
"epoch": 0.2741963970328506,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004996098781536095,
|
|
"loss": 6.2999,
|
|
"mean_token_accuracy": 0.14321804642677308,
|
|
"num_tokens": 5791163.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 6.244565391540528,
|
|
"epoch": 0.2746379371246909,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004996080222983492,
|
|
"loss": 6.3145,
|
|
"mean_token_accuracy": 0.13703466728329658,
|
|
"num_tokens": 5801815.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 6.4173187732696535,
|
|
"epoch": 0.27507947721653125,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004996061620431453,
|
|
"loss": 6.3207,
|
|
"mean_token_accuracy": 0.1415737859904766,
|
|
"num_tokens": 5811545.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 6.3702785015106205,
|
|
"epoch": 0.2755210173083716,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004996042973880344,
|
|
"loss": 6.3307,
|
|
"mean_token_accuracy": 0.1431344673037529,
|
|
"num_tokens": 5820285.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 6.2595337390899655,
|
|
"epoch": 0.2759625574002119,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004996024283330532,
|
|
"loss": 6.1762,
|
|
"mean_token_accuracy": 0.14116988331079483,
|
|
"num_tokens": 5829284.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 6.305311965942383,
|
|
"epoch": 0.2764040974920523,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000499600554878238,
|
|
"loss": 6.3521,
|
|
"mean_token_accuracy": 0.1364928737282753,
|
|
"num_tokens": 5838973.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 6.342598533630371,
|
|
"epoch": 0.27684563758389263,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004995986770236258,
|
|
"loss": 6.2177,
|
|
"mean_token_accuracy": 0.14314799010753632,
|
|
"num_tokens": 5847434.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 6.290801858901977,
|
|
"epoch": 0.27728717767573297,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004995967947692533,
|
|
"loss": 6.2193,
|
|
"mean_token_accuracy": 0.14620081037282945,
|
|
"num_tokens": 5856464.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 6.327192163467407,
|
|
"epoch": 0.2777287177675733,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004995949081151571,
|
|
"loss": 6.2846,
|
|
"mean_token_accuracy": 0.14579862579703332,
|
|
"num_tokens": 5865892.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 6.339615058898926,
|
|
"epoch": 0.2781702578594136,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004995930170613746,
|
|
"loss": 6.2622,
|
|
"mean_token_accuracy": 0.14785820320248605,
|
|
"num_tokens": 5874606.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 6.3258908748626705,
|
|
"epoch": 0.27861179795125396,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004995911216079425,
|
|
"loss": 6.2597,
|
|
"mean_token_accuracy": 0.1452340230345726,
|
|
"num_tokens": 5883853.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 6.370532512664795,
|
|
"epoch": 0.2790533380430943,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004995892217548981,
|
|
"loss": 6.2883,
|
|
"mean_token_accuracy": 0.1421412155032158,
|
|
"num_tokens": 5892841.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 6.340239238739014,
|
|
"epoch": 0.2794948781349347,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004995873175022786,
|
|
"loss": 6.259,
|
|
"mean_token_accuracy": 0.14697980433702468,
|
|
"num_tokens": 5901966.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 6.274954986572266,
|
|
"epoch": 0.279936418226775,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004995854088501213,
|
|
"loss": 6.1552,
|
|
"mean_token_accuracy": 0.14191541820764542,
|
|
"num_tokens": 5910003.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 6.269457006454468,
|
|
"epoch": 0.28037795831861534,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004995834957984634,
|
|
"loss": 6.3159,
|
|
"mean_token_accuracy": 0.1394389145076275,
|
|
"num_tokens": 5920307.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 6.303321027755738,
|
|
"epoch": 0.28081949841045567,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004995815783473428,
|
|
"loss": 6.1647,
|
|
"mean_token_accuracy": 0.15029042363166809,
|
|
"num_tokens": 5929875.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 6.301052713394165,
|
|
"epoch": 0.281261038502296,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004995796564967967,
|
|
"loss": 6.127,
|
|
"mean_token_accuracy": 0.1431355059146881,
|
|
"num_tokens": 5938570.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 6.2796125411987305,
|
|
"epoch": 0.28170257859413633,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004995777302468628,
|
|
"loss": 6.2874,
|
|
"mean_token_accuracy": 0.1460157573223114,
|
|
"num_tokens": 5947693.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 6.33156566619873,
|
|
"epoch": 0.28214411868597666,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004995757995975789,
|
|
"loss": 6.3641,
|
|
"mean_token_accuracy": 0.14592357650399207,
|
|
"num_tokens": 5957377.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 6.409634447097778,
|
|
"epoch": 0.28258565877781705,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004995738645489828,
|
|
"loss": 6.2884,
|
|
"mean_token_accuracy": 0.14403491765260695,
|
|
"num_tokens": 5966443.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 6.332985877990723,
|
|
"epoch": 0.2830271988696574,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004995719251011124,
|
|
"loss": 6.2072,
|
|
"mean_token_accuracy": 0.14735419005155564,
|
|
"num_tokens": 5975027.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 6.324332141876221,
|
|
"epoch": 0.2834687389614977,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004995699812540058,
|
|
"loss": 6.2752,
|
|
"mean_token_accuracy": 0.14320788607001306,
|
|
"num_tokens": 5983722.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 6.271279239654541,
|
|
"epoch": 0.28391027905333804,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000499568033007701,
|
|
"loss": 6.2811,
|
|
"mean_token_accuracy": 0.13799498602747917,
|
|
"num_tokens": 5993358.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 6.32847261428833,
|
|
"epoch": 0.2843518191451784,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004995660803622361,
|
|
"loss": 6.2185,
|
|
"mean_token_accuracy": 0.15176873803138732,
|
|
"num_tokens": 6002743.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 6.428246402740479,
|
|
"epoch": 0.2847933592370187,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004995641233176494,
|
|
"loss": 6.3779,
|
|
"mean_token_accuracy": 0.13898470029234886,
|
|
"num_tokens": 6013727.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 6.417748928070068,
|
|
"epoch": 0.28523489932885904,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004995621618739792,
|
|
"loss": 6.3063,
|
|
"mean_token_accuracy": 0.13999874591827394,
|
|
"num_tokens": 6023397.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 6.362044048309326,
|
|
"epoch": 0.2856764394206994,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000499560196031264,
|
|
"loss": 6.2001,
|
|
"mean_token_accuracy": 0.15036201179027558,
|
|
"num_tokens": 6032453.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 6.2208168506622314,
|
|
"epoch": 0.28611797951253976,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004995582257895423,
|
|
"loss": 6.1826,
|
|
"mean_token_accuracy": 0.13672572746872902,
|
|
"num_tokens": 6042441.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 6.303688001632691,
|
|
"epoch": 0.2865595196043801,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004995562511488528,
|
|
"loss": 6.1648,
|
|
"mean_token_accuracy": 0.1514339789748192,
|
|
"num_tokens": 6050881.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 6.293939399719238,
|
|
"epoch": 0.2870010596962204,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004995542721092337,
|
|
"loss": 6.2304,
|
|
"mean_token_accuracy": 0.14860680252313613,
|
|
"num_tokens": 6060804.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 6.365213298797608,
|
|
"epoch": 0.28744259978806075,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004995522886707244,
|
|
"loss": 6.3369,
|
|
"mean_token_accuracy": 0.13872155621647836,
|
|
"num_tokens": 6070774.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 6.407730340957642,
|
|
"epoch": 0.2878841398799011,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004995503008333634,
|
|
"loss": 6.3082,
|
|
"mean_token_accuracy": 0.1409797862172127,
|
|
"num_tokens": 6080158.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 6.329580640792846,
|
|
"epoch": 0.2883256799717414,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004995483085971897,
|
|
"loss": 6.2127,
|
|
"mean_token_accuracy": 0.15062418729066848,
|
|
"num_tokens": 6089183.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 6.3140839576721195,
|
|
"epoch": 0.2887672200635818,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004995463119622424,
|
|
"loss": 6.2869,
|
|
"mean_token_accuracy": 0.1393837496638298,
|
|
"num_tokens": 6098536.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 6.201459646224976,
|
|
"epoch": 0.28920876015542213,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004995443109285604,
|
|
"loss": 6.0704,
|
|
"mean_token_accuracy": 0.15581393390893936,
|
|
"num_tokens": 6107745.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 6.263937854766846,
|
|
"epoch": 0.28965030024726246,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004995423054961832,
|
|
"loss": 6.2581,
|
|
"mean_token_accuracy": 0.14954922050237657,
|
|
"num_tokens": 6117512.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 6.305516576766967,
|
|
"epoch": 0.2900918403391028,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00049954029566515,
|
|
"loss": 6.2557,
|
|
"mean_token_accuracy": 0.14468607753515245,
|
|
"num_tokens": 6126030.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 6.4128021717071535,
|
|
"epoch": 0.2905333804309431,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004995382814355,
|
|
"loss": 6.3,
|
|
"mean_token_accuracy": 0.13850856572389603,
|
|
"num_tokens": 6134888.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 6.3890117645263675,
|
|
"epoch": 0.29097492052278345,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004995362628072728,
|
|
"loss": 6.2668,
|
|
"mean_token_accuracy": 0.14920098334550858,
|
|
"num_tokens": 6144274.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 6.165565633773804,
|
|
"epoch": 0.2914164606146238,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004995342397805078,
|
|
"loss": 6.2744,
|
|
"mean_token_accuracy": 0.14215826392173767,
|
|
"num_tokens": 6153406.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 6.289848852157593,
|
|
"epoch": 0.29185800070646417,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004995322123552448,
|
|
"loss": 6.1934,
|
|
"mean_token_accuracy": 0.14832887351512908,
|
|
"num_tokens": 6162743.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 6.275933074951172,
|
|
"epoch": 0.2922995407983045,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004995301805315235,
|
|
"loss": 6.1805,
|
|
"mean_token_accuracy": 0.1520318605005741,
|
|
"num_tokens": 6171997.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 6.268936443328857,
|
|
"epoch": 0.29274108089014483,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004995281443093837,
|
|
"loss": 6.2017,
|
|
"mean_token_accuracy": 0.1493746504187584,
|
|
"num_tokens": 6181275.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 6.2795538902282715,
|
|
"epoch": 0.29318262098198516,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004995261036888652,
|
|
"loss": 6.2847,
|
|
"mean_token_accuracy": 0.14096189811825752,
|
|
"num_tokens": 6191640.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 6.350857257843018,
|
|
"epoch": 0.2936241610738255,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004995240586700081,
|
|
"loss": 6.2653,
|
|
"mean_token_accuracy": 0.14238337501883508,
|
|
"num_tokens": 6201508.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 6.261187982559204,
|
|
"epoch": 0.2940657011656658,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004995220092528522,
|
|
"loss": 6.1515,
|
|
"mean_token_accuracy": 0.15054052993655204,
|
|
"num_tokens": 6209902.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 6.294927644729614,
|
|
"epoch": 0.29450724125750616,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000499519955437438,
|
|
"loss": 6.308,
|
|
"mean_token_accuracy": 0.14006401896476744,
|
|
"num_tokens": 6219760.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 6.316092014312744,
|
|
"epoch": 0.29494878134934654,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004995178972238054,
|
|
"loss": 6.2726,
|
|
"mean_token_accuracy": 0.14333543106913565,
|
|
"num_tokens": 6228721.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 6.320749425888062,
|
|
"epoch": 0.2953903214411869,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000499515834611995,
|
|
"loss": 6.1222,
|
|
"mean_token_accuracy": 0.15580927431583405,
|
|
"num_tokens": 6237070.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 6.313472318649292,
|
|
"epoch": 0.2958318615330272,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004995137676020472,
|
|
"loss": 6.2513,
|
|
"mean_token_accuracy": 0.13897364661097528,
|
|
"num_tokens": 6245659.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 6.307816123962402,
|
|
"epoch": 0.29627340162486754,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004995116961940023,
|
|
"loss": 6.2262,
|
|
"mean_token_accuracy": 0.14813175648450852,
|
|
"num_tokens": 6255175.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 6.2639384269714355,
|
|
"epoch": 0.29671494171670787,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004995096203879009,
|
|
"loss": 6.2404,
|
|
"mean_token_accuracy": 0.13731699511408807,
|
|
"num_tokens": 6264962.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 6.2340796947479244,
|
|
"epoch": 0.2971564818085482,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004995075401837837,
|
|
"loss": 6.1452,
|
|
"mean_token_accuracy": 0.15479466691613197,
|
|
"num_tokens": 6273411.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 6.206551790237427,
|
|
"epoch": 0.29759802190038853,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004995054555816915,
|
|
"loss": 6.1274,
|
|
"mean_token_accuracy": 0.15238229930400848,
|
|
"num_tokens": 6282618.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 6.228631782531738,
|
|
"epoch": 0.2980395619922289,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004995033665816651,
|
|
"loss": 6.1255,
|
|
"mean_token_accuracy": 0.15363436192274094,
|
|
"num_tokens": 6292008.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 6.169542646408081,
|
|
"epoch": 0.29848110208406925,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004995012731837454,
|
|
"loss": 6.1025,
|
|
"mean_token_accuracy": 0.15055510327219962,
|
|
"num_tokens": 6301079.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 6.324261808395386,
|
|
"epoch": 0.2989226421759096,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004994991753879736,
|
|
"loss": 6.2718,
|
|
"mean_token_accuracy": 0.14163144826889038,
|
|
"num_tokens": 6310543.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 6.359718656539917,
|
|
"epoch": 0.2993641822677499,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004994970731943904,
|
|
"loss": 6.2171,
|
|
"mean_token_accuracy": 0.14785383343696595,
|
|
"num_tokens": 6320037.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 6.246334791183472,
|
|
"epoch": 0.29980572235959024,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004994949666030374,
|
|
"loss": 6.2478,
|
|
"mean_token_accuracy": 0.14385821670293808,
|
|
"num_tokens": 6328948.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 6.221922874450684,
|
|
"epoch": 0.3002472624514306,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004994928556139557,
|
|
"loss": 6.1036,
|
|
"mean_token_accuracy": 0.15099234580993653,
|
|
"num_tokens": 6337449.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 6.229247903823852,
|
|
"epoch": 0.3006888025432709,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004994907402271865,
|
|
"loss": 6.1396,
|
|
"mean_token_accuracy": 0.15253903567790986,
|
|
"num_tokens": 6346130.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 6.190823078155518,
|
|
"epoch": 0.3011303426351113,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004994886204427715,
|
|
"loss": 6.1814,
|
|
"mean_token_accuracy": 0.15078601539134978,
|
|
"num_tokens": 6354973.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 6.341151475906372,
|
|
"epoch": 0.3015718827269516,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004994864962607519,
|
|
"loss": 6.2574,
|
|
"mean_token_accuracy": 0.14179314076900482,
|
|
"num_tokens": 6364107.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 6.328457355499268,
|
|
"epoch": 0.30201342281879195,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004994843676811697,
|
|
"loss": 6.2059,
|
|
"mean_token_accuracy": 0.1432513862848282,
|
|
"num_tokens": 6372859.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 6.23663182258606,
|
|
"epoch": 0.3024549629106323,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004994822347040664,
|
|
"loss": 6.092,
|
|
"mean_token_accuracy": 0.15835918337106705,
|
|
"num_tokens": 6381818.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 6.300030136108399,
|
|
"epoch": 0.3028965030024726,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004994800973294837,
|
|
"loss": 6.2498,
|
|
"mean_token_accuracy": 0.14488281309604645,
|
|
"num_tokens": 6391460.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 6.328920793533325,
|
|
"epoch": 0.30333804309431295,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004994779555574636,
|
|
"loss": 6.2547,
|
|
"mean_token_accuracy": 0.14561234712600707,
|
|
"num_tokens": 6401461.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 6.293675470352173,
|
|
"epoch": 0.3037795831861533,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000499475809388048,
|
|
"loss": 6.1428,
|
|
"mean_token_accuracy": 0.1438477359712124,
|
|
"num_tokens": 6410435.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 6.337829685211181,
|
|
"epoch": 0.30422112327799367,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000499473658821279,
|
|
"loss": 6.3612,
|
|
"mean_token_accuracy": 0.1367957629263401,
|
|
"num_tokens": 6420710.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 6.429217433929443,
|
|
"epoch": 0.304662663369834,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004994715038571986,
|
|
"loss": 6.2124,
|
|
"mean_token_accuracy": 0.1464938424527645,
|
|
"num_tokens": 6429882.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 6.211455345153809,
|
|
"epoch": 0.30510420346167433,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004994693444958493,
|
|
"loss": 6.1677,
|
|
"mean_token_accuracy": 0.15407330840826033,
|
|
"num_tokens": 6439183.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 6.292701482772827,
|
|
"epoch": 0.30554574355351466,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000499467180737273,
|
|
"loss": 6.3449,
|
|
"mean_token_accuracy": 0.1406208023428917,
|
|
"num_tokens": 6448460.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 6.349296760559082,
|
|
"epoch": 0.305987283645355,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004994650125815124,
|
|
"loss": 6.2131,
|
|
"mean_token_accuracy": 0.14687474071979523,
|
|
"num_tokens": 6457687.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 6.28594217300415,
|
|
"epoch": 0.3064288237371953,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004994628400286097,
|
|
"loss": 6.1717,
|
|
"mean_token_accuracy": 0.148153455555439,
|
|
"num_tokens": 6467057.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 6.252876710891724,
|
|
"epoch": 0.30687036382903565,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004994606630786078,
|
|
"loss": 6.2493,
|
|
"mean_token_accuracy": 0.1461620330810547,
|
|
"num_tokens": 6477484.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 6.321864604949951,
|
|
"epoch": 0.30731190392087604,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004994584817315492,
|
|
"loss": 6.3043,
|
|
"mean_token_accuracy": 0.1443194717168808,
|
|
"num_tokens": 6488381.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 6.296575021743775,
|
|
"epoch": 0.30775344401271637,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004994562959874765,
|
|
"loss": 6.196,
|
|
"mean_token_accuracy": 0.14554316326975822,
|
|
"num_tokens": 6498279.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 6.269347381591797,
|
|
"epoch": 0.3081949841045567,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004994541058464326,
|
|
"loss": 6.2109,
|
|
"mean_token_accuracy": 0.14428319782018661,
|
|
"num_tokens": 6508008.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 6.34035325050354,
|
|
"epoch": 0.30863652419639703,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004994519113084605,
|
|
"loss": 6.2474,
|
|
"mean_token_accuracy": 0.14133610650897027,
|
|
"num_tokens": 6517263.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 6.349197673797607,
|
|
"epoch": 0.30907806428823736,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004994497123736029,
|
|
"loss": 6.3315,
|
|
"mean_token_accuracy": 0.13482841178774835,
|
|
"num_tokens": 6527682.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 6.293285512924195,
|
|
"epoch": 0.3095196043800777,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004994475090419034,
|
|
"loss": 6.1941,
|
|
"mean_token_accuracy": 0.14769349247217178,
|
|
"num_tokens": 6537143.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 6.316049528121948,
|
|
"epoch": 0.309961144471918,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004994453013134047,
|
|
"loss": 6.2011,
|
|
"mean_token_accuracy": 0.14517299979925155,
|
|
"num_tokens": 6546561.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 6.277545070648193,
|
|
"epoch": 0.3104026845637584,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004994430891881502,
|
|
"loss": 6.2015,
|
|
"mean_token_accuracy": 0.14352679401636123,
|
|
"num_tokens": 6555806.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 6.268626976013183,
|
|
"epoch": 0.31084422465559874,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004994408726661832,
|
|
"loss": 6.231,
|
|
"mean_token_accuracy": 0.1447139360010624,
|
|
"num_tokens": 6564836.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 6.2405225276947025,
|
|
"epoch": 0.3112857647474391,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004994386517475472,
|
|
"loss": 6.2323,
|
|
"mean_token_accuracy": 0.13839124515652657,
|
|
"num_tokens": 6574997.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 6.326260805130005,
|
|
"epoch": 0.3117273048392794,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004994364264322856,
|
|
"loss": 6.2421,
|
|
"mean_token_accuracy": 0.14486346989870072,
|
|
"num_tokens": 6584589.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 6.287415504455566,
|
|
"epoch": 0.31216884493111974,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004994341967204421,
|
|
"loss": 6.186,
|
|
"mean_token_accuracy": 0.15003243535757066,
|
|
"num_tokens": 6592898.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 6.322659063339233,
|
|
"epoch": 0.31261038502296007,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004994319626120603,
|
|
"loss": 6.1982,
|
|
"mean_token_accuracy": 0.15189156383275987,
|
|
"num_tokens": 6602454.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 6.218482780456543,
|
|
"epoch": 0.3130519251148004,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004994297241071841,
|
|
"loss": 6.2155,
|
|
"mean_token_accuracy": 0.1479742333292961,
|
|
"num_tokens": 6612454.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 6.29142951965332,
|
|
"epoch": 0.3134934652066408,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000499427481205857,
|
|
"loss": 6.1926,
|
|
"mean_token_accuracy": 0.15044232308864594,
|
|
"num_tokens": 6621286.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 6.223646450042724,
|
|
"epoch": 0.3139350052984811,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004994252339081234,
|
|
"loss": 6.1325,
|
|
"mean_token_accuracy": 0.15221345126628877,
|
|
"num_tokens": 6629684.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 6.260682678222656,
|
|
"epoch": 0.31437654539032145,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000499422982214027,
|
|
"loss": 6.2336,
|
|
"mean_token_accuracy": 0.15286535322666167,
|
|
"num_tokens": 6638836.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 6.343380880355835,
|
|
"epoch": 0.3148180854821618,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004994207261236121,
|
|
"loss": 6.1827,
|
|
"mean_token_accuracy": 0.14693615287542344,
|
|
"num_tokens": 6647337.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 6.189584636688233,
|
|
"epoch": 0.3152596255740021,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004994184656369227,
|
|
"loss": 6.1817,
|
|
"mean_token_accuracy": 0.14338988438248634,
|
|
"num_tokens": 6657246.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 6.359672164916992,
|
|
"epoch": 0.31570116566584244,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004994162007540033,
|
|
"loss": 6.3109,
|
|
"mean_token_accuracy": 0.13514265939593315,
|
|
"num_tokens": 6667981.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 6.32397427558899,
|
|
"epoch": 0.3161427057576828,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004994139314748981,
|
|
"loss": 6.16,
|
|
"mean_token_accuracy": 0.15298724174499512,
|
|
"num_tokens": 6677462.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 6.176218175888062,
|
|
"epoch": 0.31658424584952316,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004994116577996517,
|
|
"loss": 6.1994,
|
|
"mean_token_accuracy": 0.14874908104538917,
|
|
"num_tokens": 6687225.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 6.252984666824341,
|
|
"epoch": 0.3170257859413635,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004994093797283084,
|
|
"loss": 6.2788,
|
|
"mean_token_accuracy": 0.14002985283732414,
|
|
"num_tokens": 6696345.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 6.361448812484741,
|
|
"epoch": 0.3174673260332038,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004994070972609132,
|
|
"loss": 6.2544,
|
|
"mean_token_accuracy": 0.14232457354664801,
|
|
"num_tokens": 6706207.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 6.315224981307983,
|
|
"epoch": 0.31790886612504415,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004994048103975103,
|
|
"loss": 6.1593,
|
|
"mean_token_accuracy": 0.14630399346351625,
|
|
"num_tokens": 6714430.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 6.237560892105103,
|
|
"epoch": 0.3183504062168845,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000499402519138145,
|
|
"loss": 6.1883,
|
|
"mean_token_accuracy": 0.1458396703004837,
|
|
"num_tokens": 6724139.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 6.241400671005249,
|
|
"epoch": 0.3187919463087248,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004994002234828619,
|
|
"loss": 6.2346,
|
|
"mean_token_accuracy": 0.1450707234442234,
|
|
"num_tokens": 6733525.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 6.343650865554809,
|
|
"epoch": 0.31923348640056515,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000499397923431706,
|
|
"loss": 6.3247,
|
|
"mean_token_accuracy": 0.13921364694833754,
|
|
"num_tokens": 6743738.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 6.342299556732177,
|
|
"epoch": 0.31967502649240553,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004993956189847226,
|
|
"loss": 6.1986,
|
|
"mean_token_accuracy": 0.1489830307662487,
|
|
"num_tokens": 6752900.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 6.32194037437439,
|
|
"epoch": 0.32011656658424587,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004993933101419565,
|
|
"loss": 6.158,
|
|
"mean_token_accuracy": 0.1525537133216858,
|
|
"num_tokens": 6761776.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 6.306015205383301,
|
|
"epoch": 0.3205581066760862,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004993909969034531,
|
|
"loss": 6.3116,
|
|
"mean_token_accuracy": 0.14113244116306306,
|
|
"num_tokens": 6771543.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 6.283383131027222,
|
|
"epoch": 0.3209996467679265,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004993886792692576,
|
|
"loss": 6.1941,
|
|
"mean_token_accuracy": 0.1407588765025139,
|
|
"num_tokens": 6780010.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 6.345666599273682,
|
|
"epoch": 0.32144118685976686,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004993863572394156,
|
|
"loss": 6.2455,
|
|
"mean_token_accuracy": 0.1481287196278572,
|
|
"num_tokens": 6788830.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 6.319739246368409,
|
|
"epoch": 0.3218827269516072,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004993840308139724,
|
|
"loss": 6.2361,
|
|
"mean_token_accuracy": 0.14790267944335939,
|
|
"num_tokens": 6799121.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 6.272012615203858,
|
|
"epoch": 0.3223242670434475,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004993816999929738,
|
|
"loss": 6.1873,
|
|
"mean_token_accuracy": 0.1459096811711788,
|
|
"num_tokens": 6808519.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 6.246146488189697,
|
|
"epoch": 0.3227658071352879,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004993793647764651,
|
|
"loss": 6.2032,
|
|
"mean_token_accuracy": 0.15324788242578508,
|
|
"num_tokens": 6817583.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 6.358306646347046,
|
|
"epoch": 0.32320734722712824,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004993770251644923,
|
|
"loss": 6.2018,
|
|
"mean_token_accuracy": 0.14584973454475403,
|
|
"num_tokens": 6827732.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 6.219063949584961,
|
|
"epoch": 0.32364888731896857,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004993746811571013,
|
|
"loss": 6.1804,
|
|
"mean_token_accuracy": 0.14989982694387435,
|
|
"num_tokens": 6836903.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 6.157657623291016,
|
|
"epoch": 0.3240904274108089,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004993723327543379,
|
|
"loss": 6.184,
|
|
"mean_token_accuracy": 0.15377924591302872,
|
|
"num_tokens": 6845684.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 6.22325701713562,
|
|
"epoch": 0.32453196750264923,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000499369979956248,
|
|
"loss": 6.163,
|
|
"mean_token_accuracy": 0.14639684483408927,
|
|
"num_tokens": 6854650.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 6.313974905014038,
|
|
"epoch": 0.32497350759448956,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004993676227628779,
|
|
"loss": 6.182,
|
|
"mean_token_accuracy": 0.14079167023301126,
|
|
"num_tokens": 6864340.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 6.354143953323364,
|
|
"epoch": 0.3254150476863299,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004993652611742736,
|
|
"loss": 6.2106,
|
|
"mean_token_accuracy": 0.14864241406321527,
|
|
"num_tokens": 6873244.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 6.2044641971588135,
|
|
"epoch": 0.3258565877781703,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004993628951904815,
|
|
"loss": 6.0951,
|
|
"mean_token_accuracy": 0.15563804358243943,
|
|
"num_tokens": 6882392.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 6.283623170852661,
|
|
"epoch": 0.3262981278700106,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004993605248115479,
|
|
"loss": 6.3166,
|
|
"mean_token_accuracy": 0.1375298321247101,
|
|
"num_tokens": 6891515.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 6.39955735206604,
|
|
"epoch": 0.32673966796185094,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004993581500375191,
|
|
"loss": 6.2063,
|
|
"mean_token_accuracy": 0.14319797828793526,
|
|
"num_tokens": 6900104.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 6.301495885848999,
|
|
"epoch": 0.3271812080536913,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004993557708684417,
|
|
"loss": 6.3156,
|
|
"mean_token_accuracy": 0.1383724741637707,
|
|
"num_tokens": 6910443.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 6.2295175075531,
|
|
"epoch": 0.3276227481455316,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004993533873043625,
|
|
"loss": 6.1773,
|
|
"mean_token_accuracy": 0.1472519099712372,
|
|
"num_tokens": 6919882.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 6.3492731094360355,
|
|
"epoch": 0.32806428823737194,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000499350999345328,
|
|
"loss": 6.3019,
|
|
"mean_token_accuracy": 0.1388927437365055,
|
|
"num_tokens": 6929757.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 6.29475884437561,
|
|
"epoch": 0.32850582832921227,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000499348606991385,
|
|
"loss": 6.2597,
|
|
"mean_token_accuracy": 0.13804953098297118,
|
|
"num_tokens": 6938578.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 6.323968458175659,
|
|
"epoch": 0.32894736842105265,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004993462102425805,
|
|
"loss": 6.1738,
|
|
"mean_token_accuracy": 0.1445832960307598,
|
|
"num_tokens": 6947920.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 6.224078845977783,
|
|
"epoch": 0.329388908512893,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004993438090989612,
|
|
"loss": 6.1218,
|
|
"mean_token_accuracy": 0.1494213819503784,
|
|
"num_tokens": 6957291.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 6.270564126968384,
|
|
"epoch": 0.3298304486047333,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004993414035605743,
|
|
"loss": 6.1795,
|
|
"mean_token_accuracy": 0.15251390635967255,
|
|
"num_tokens": 6966504.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 6.331764554977417,
|
|
"epoch": 0.33027198869657365,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004993389936274669,
|
|
"loss": 6.213,
|
|
"mean_token_accuracy": 0.14998254030942917,
|
|
"num_tokens": 6976234.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 6.225750160217285,
|
|
"epoch": 0.330713528788414,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004993365792996862,
|
|
"loss": 6.2674,
|
|
"mean_token_accuracy": 0.1404741570353508,
|
|
"num_tokens": 6986372.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 6.320698499679565,
|
|
"epoch": 0.3311550688802543,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004993341605772795,
|
|
"loss": 6.1535,
|
|
"mean_token_accuracy": 0.1522038422524929,
|
|
"num_tokens": 6995553.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 6.248960161209107,
|
|
"epoch": 0.33159660897209464,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993317374602941,
|
|
"loss": 6.0784,
|
|
"mean_token_accuracy": 0.1559259220957756,
|
|
"num_tokens": 7005675.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 6.173632669448852,
|
|
"epoch": 0.33203814906393503,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004993293099487777,
|
|
"loss": 6.2065,
|
|
"mean_token_accuracy": 0.14199020266532897,
|
|
"num_tokens": 7014953.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 6.267611455917359,
|
|
"epoch": 0.33247968915577536,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004993268780427776,
|
|
"loss": 6.2142,
|
|
"mean_token_accuracy": 0.15134309455752373,
|
|
"num_tokens": 7025075.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 6.312801742553711,
|
|
"epoch": 0.3329212292476157,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004993244417423416,
|
|
"loss": 6.2068,
|
|
"mean_token_accuracy": 0.15050857216119767,
|
|
"num_tokens": 7034286.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 6.307934761047363,
|
|
"epoch": 0.333362769339456,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004993220010475174,
|
|
"loss": 6.2453,
|
|
"mean_token_accuracy": 0.14248408898711204,
|
|
"num_tokens": 7043957.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 6.289632654190063,
|
|
"epoch": 0.33380430943129635,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004993195559583526,
|
|
"loss": 6.1572,
|
|
"mean_token_accuracy": 0.1487005241215229,
|
|
"num_tokens": 7053170.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 6.1731133460998535,
|
|
"epoch": 0.3342458495231367,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004993171064748954,
|
|
"loss": 6.1612,
|
|
"mean_token_accuracy": 0.14813224822282792,
|
|
"num_tokens": 7062469.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 6.255552530288696,
|
|
"epoch": 0.334687389614977,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004993146525971937,
|
|
"loss": 6.1493,
|
|
"mean_token_accuracy": 0.15376724749803544,
|
|
"num_tokens": 7071463.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 6.3743010520935055,
|
|
"epoch": 0.3351289297068174,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004993121943252955,
|
|
"loss": 6.2374,
|
|
"mean_token_accuracy": 0.13975025340914726,
|
|
"num_tokens": 7081574.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 6.262507772445678,
|
|
"epoch": 0.33557046979865773,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004993097316592489,
|
|
"loss": 6.1487,
|
|
"mean_token_accuracy": 0.15553452372550963,
|
|
"num_tokens": 7090835.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 6.15237603187561,
|
|
"epoch": 0.33601200989049806,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004993072645991023,
|
|
"loss": 6.0825,
|
|
"mean_token_accuracy": 0.1396365225315094,
|
|
"num_tokens": 7100521.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 6.21912112236023,
|
|
"epoch": 0.3364535499823384,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000499304793144904,
|
|
"loss": 6.1712,
|
|
"mean_token_accuracy": 0.1433882623910904,
|
|
"num_tokens": 7109011.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 6.306987667083741,
|
|
"epoch": 0.3368950900741787,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004993023172967022,
|
|
"loss": 6.1968,
|
|
"mean_token_accuracy": 0.1458859533071518,
|
|
"num_tokens": 7119128.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 6.302616548538208,
|
|
"epoch": 0.33733663016601906,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004992998370545458,
|
|
"loss": 6.2696,
|
|
"mean_token_accuracy": 0.13797667175531386,
|
|
"num_tokens": 7128313.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 6.243565607070923,
|
|
"epoch": 0.3377781702578594,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004992973524184831,
|
|
"loss": 6.2332,
|
|
"mean_token_accuracy": 0.145349483191967,
|
|
"num_tokens": 7137567.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 6.308232927322388,
|
|
"epoch": 0.3382197103496998,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004992948633885627,
|
|
"loss": 6.2107,
|
|
"mean_token_accuracy": 0.147455532848835,
|
|
"num_tokens": 7147254.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 6.2316985607147215,
|
|
"epoch": 0.3386612504415401,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004992923699648335,
|
|
"loss": 6.1269,
|
|
"mean_token_accuracy": 0.15241755098104476,
|
|
"num_tokens": 7156215.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 6.3128533363342285,
|
|
"epoch": 0.33910279053338044,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004992898721473445,
|
|
"loss": 6.2145,
|
|
"mean_token_accuracy": 0.1414943240582943,
|
|
"num_tokens": 7165653.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 6.208751821517945,
|
|
"epoch": 0.33954433062522077,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004992873699361444,
|
|
"loss": 6.1056,
|
|
"mean_token_accuracy": 0.14766833633184434,
|
|
"num_tokens": 7174797.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 6.29413628578186,
|
|
"epoch": 0.3399858707170611,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004992848633312822,
|
|
"loss": 6.1408,
|
|
"mean_token_accuracy": 0.14888592660427094,
|
|
"num_tokens": 7184040.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 6.273240566253662,
|
|
"epoch": 0.34042741080890143,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004992823523328071,
|
|
"loss": 6.097,
|
|
"mean_token_accuracy": 0.15565756857395172,
|
|
"num_tokens": 7193533.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 6.19666600227356,
|
|
"epoch": 0.34086895090074176,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004992798369407684,
|
|
"loss": 6.1902,
|
|
"mean_token_accuracy": 0.14624166190624238,
|
|
"num_tokens": 7203355.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 6.274708843231201,
|
|
"epoch": 0.34131049099258215,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004992773171552152,
|
|
"loss": 6.1325,
|
|
"mean_token_accuracy": 0.14895608872175217,
|
|
"num_tokens": 7212569.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 6.172758293151856,
|
|
"epoch": 0.3417520310844225,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004992747929761968,
|
|
"loss": 6.1614,
|
|
"mean_token_accuracy": 0.15170100927352906,
|
|
"num_tokens": 7221886.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 6.239678812026978,
|
|
"epoch": 0.3421935711762628,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004992722644037628,
|
|
"loss": 6.2203,
|
|
"mean_token_accuracy": 0.14662540405988694,
|
|
"num_tokens": 7232065.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 6.307174253463745,
|
|
"epoch": 0.34263511126810314,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004992697314379628,
|
|
"loss": 6.1509,
|
|
"mean_token_accuracy": 0.1447463095188141,
|
|
"num_tokens": 7242287.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 6.272569704055786,
|
|
"epoch": 0.3430766513599435,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004992671940788462,
|
|
"loss": 6.1405,
|
|
"mean_token_accuracy": 0.14477290213108063,
|
|
"num_tokens": 7250638.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 6.187071228027344,
|
|
"epoch": 0.3435181914517838,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004992646523264628,
|
|
"loss": 6.1539,
|
|
"mean_token_accuracy": 0.15122336894273758,
|
|
"num_tokens": 7259526.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 6.216576433181762,
|
|
"epoch": 0.34395973154362414,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004992621061808625,
|
|
"loss": 6.1455,
|
|
"mean_token_accuracy": 0.1504262939095497,
|
|
"num_tokens": 7269260.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 6.225019454956055,
|
|
"epoch": 0.3444012716354645,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000499259555642095,
|
|
"loss": 6.167,
|
|
"mean_token_accuracy": 0.143419449031353,
|
|
"num_tokens": 7279061.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 6.263490152359009,
|
|
"epoch": 0.34484281172730485,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004992570007102104,
|
|
"loss": 6.15,
|
|
"mean_token_accuracy": 0.15289402306079863,
|
|
"num_tokens": 7289721.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 6.392903089523315,
|
|
"epoch": 0.3452843518191452,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004992544413852587,
|
|
"loss": 6.2987,
|
|
"mean_token_accuracy": 0.14017098546028137,
|
|
"num_tokens": 7299836.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 6.341606092453003,
|
|
"epoch": 0.3457258919109855,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00049925187766729,
|
|
"loss": 6.3001,
|
|
"mean_token_accuracy": 0.1420486383140087,
|
|
"num_tokens": 7309306.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 6.297093105316162,
|
|
"epoch": 0.34616743200282585,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004992493095563545,
|
|
"loss": 6.1999,
|
|
"mean_token_accuracy": 0.15256548225879668,
|
|
"num_tokens": 7318486.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 6.253756761550903,
|
|
"epoch": 0.3466089720946662,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004992467370525026,
|
|
"loss": 6.1648,
|
|
"mean_token_accuracy": 0.1465355783700943,
|
|
"num_tokens": 7327764.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 6.29128246307373,
|
|
"epoch": 0.3470505121865065,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004992441601557848,
|
|
"loss": 6.2269,
|
|
"mean_token_accuracy": 0.15001798868179322,
|
|
"num_tokens": 7337118.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 6.215613794326782,
|
|
"epoch": 0.3474920522783469,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004992415788662514,
|
|
"loss": 6.1704,
|
|
"mean_token_accuracy": 0.14473639652132989,
|
|
"num_tokens": 7345973.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 6.328490686416626,
|
|
"epoch": 0.34793359237018723,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004992389931839529,
|
|
"loss": 6.1743,
|
|
"mean_token_accuracy": 0.14794324338436127,
|
|
"num_tokens": 7355776.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 6.2720846176147464,
|
|
"epoch": 0.34837513246202756,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004992364031089401,
|
|
"loss": 6.1858,
|
|
"mean_token_accuracy": 0.1513002872467041,
|
|
"num_tokens": 7364820.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 6.277421283721924,
|
|
"epoch": 0.3488166725538679,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004992338086412636,
|
|
"loss": 6.2091,
|
|
"mean_token_accuracy": 0.14662266448140143,
|
|
"num_tokens": 7373881.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 6.260824489593506,
|
|
"epoch": 0.3492582126457082,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004992312097809744,
|
|
"loss": 6.1732,
|
|
"mean_token_accuracy": 0.15294966846704483,
|
|
"num_tokens": 7383095.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 6.289446401596069,
|
|
"epoch": 0.34969975273754855,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004992286065281234,
|
|
"loss": 6.1876,
|
|
"mean_token_accuracy": 0.14803554639220237,
|
|
"num_tokens": 7392702.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 6.307240962982178,
|
|
"epoch": 0.3501412928293889,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004992259988827614,
|
|
"loss": 6.3518,
|
|
"mean_token_accuracy": 0.13984315916895868,
|
|
"num_tokens": 7402560.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 6.256998872756958,
|
|
"epoch": 0.35058283292122927,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004992233868449397,
|
|
"loss": 6.1293,
|
|
"mean_token_accuracy": 0.15598249137401582,
|
|
"num_tokens": 7412375.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 6.326172494888306,
|
|
"epoch": 0.3510243730130696,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004992207704147093,
|
|
"loss": 6.1884,
|
|
"mean_token_accuracy": 0.14315188080072402,
|
|
"num_tokens": 7420734.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 6.247087144851685,
|
|
"epoch": 0.35146591310490993,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004992181495921216,
|
|
"loss": 6.1647,
|
|
"mean_token_accuracy": 0.14719347208738326,
|
|
"num_tokens": 7430156.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 6.216844654083252,
|
|
"epoch": 0.35190745319675026,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004992155243772277,
|
|
"loss": 6.1851,
|
|
"mean_token_accuracy": 0.1513088494539261,
|
|
"num_tokens": 7439189.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 6.258322238922119,
|
|
"epoch": 0.3523489932885906,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004992128947700795,
|
|
"loss": 6.1879,
|
|
"mean_token_accuracy": 0.14627946466207503,
|
|
"num_tokens": 7448768.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 6.253720235824585,
|
|
"epoch": 0.3527905333804309,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000499210260770728,
|
|
"loss": 6.1574,
|
|
"mean_token_accuracy": 0.14627916291356086,
|
|
"num_tokens": 7458468.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 6.266324186325074,
|
|
"epoch": 0.35323207347227126,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.000499207622379225,
|
|
"loss": 6.2229,
|
|
"mean_token_accuracy": 0.1418443389236927,
|
|
"num_tokens": 7467351.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 6.345872783660889,
|
|
"epoch": 0.35367361356411164,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004992049795956222,
|
|
"loss": 6.19,
|
|
"mean_token_accuracy": 0.1431963935494423,
|
|
"num_tokens": 7477116.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 6.257971954345703,
|
|
"epoch": 0.354115153655952,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004992023324199715,
|
|
"loss": 6.1043,
|
|
"mean_token_accuracy": 0.15152290165424348,
|
|
"num_tokens": 7485216.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 6.25113000869751,
|
|
"epoch": 0.3545566937477923,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004991996808523245,
|
|
"loss": 6.2547,
|
|
"mean_token_accuracy": 0.14295927956700324,
|
|
"num_tokens": 7495084.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 6.294170665740967,
|
|
"epoch": 0.35499823383963264,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004991970248927332,
|
|
"loss": 6.2849,
|
|
"mean_token_accuracy": 0.14390699565410614,
|
|
"num_tokens": 7503219.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 6.271115255355835,
|
|
"epoch": 0.35543977393147297,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004991943645412498,
|
|
"loss": 6.0751,
|
|
"mean_token_accuracy": 0.15546453595161439,
|
|
"num_tokens": 7511961.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 6.16305022239685,
|
|
"epoch": 0.3558813140233133,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004991916997979263,
|
|
"loss": 6.1843,
|
|
"mean_token_accuracy": 0.1484257772564888,
|
|
"num_tokens": 7521927.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 6.162647819519043,
|
|
"epoch": 0.35632285411515363,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004991890306628149,
|
|
"loss": 6.1326,
|
|
"mean_token_accuracy": 0.151800037920475,
|
|
"num_tokens": 7531093.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 6.230826377868652,
|
|
"epoch": 0.356764394206994,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004991863571359678,
|
|
"loss": 6.094,
|
|
"mean_token_accuracy": 0.14804090559482574,
|
|
"num_tokens": 7539813.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 6.34772834777832,
|
|
"epoch": 0.35720593429883435,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004991836792174376,
|
|
"loss": 6.2649,
|
|
"mean_token_accuracy": 0.1414028562605381,
|
|
"num_tokens": 7548954.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 6.269259119033814,
|
|
"epoch": 0.3576474743906747,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004991809969072765,
|
|
"loss": 6.1202,
|
|
"mean_token_accuracy": 0.14746632128953935,
|
|
"num_tokens": 7558275.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 6.181514644622803,
|
|
"epoch": 0.358089014482515,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004991783102055371,
|
|
"loss": 6.1689,
|
|
"mean_token_accuracy": 0.15268539562821387,
|
|
"num_tokens": 7567870.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 6.279887056350708,
|
|
"epoch": 0.35853055457435534,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004991756191122723,
|
|
"loss": 6.1269,
|
|
"mean_token_accuracy": 0.15328674614429474,
|
|
"num_tokens": 7577485.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 6.298182344436645,
|
|
"epoch": 0.3589720946661957,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004991729236275346,
|
|
"loss": 6.1762,
|
|
"mean_token_accuracy": 0.14742286801338195,
|
|
"num_tokens": 7587398.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 6.24832558631897,
|
|
"epoch": 0.359413634758036,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004991702237513768,
|
|
"loss": 6.1763,
|
|
"mean_token_accuracy": 0.1459968388080597,
|
|
"num_tokens": 7596310.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 6.258885526657105,
|
|
"epoch": 0.3598551748498764,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004991675194838517,
|
|
"loss": 6.1955,
|
|
"mean_token_accuracy": 0.138567902892828,
|
|
"num_tokens": 7606971.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 6.2136951923370365,
|
|
"epoch": 0.3602967149417167,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004991648108250125,
|
|
"loss": 6.175,
|
|
"mean_token_accuracy": 0.14450421258807183,
|
|
"num_tokens": 7616636.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 6.337588310241699,
|
|
"epoch": 0.36073825503355705,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000499162097774912,
|
|
"loss": 6.214,
|
|
"mean_token_accuracy": 0.14829875528812408,
|
|
"num_tokens": 7625128.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 6.297661161422729,
|
|
"epoch": 0.3611797951253974,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004991593803336037,
|
|
"loss": 6.1301,
|
|
"mean_token_accuracy": 0.1504852756857872,
|
|
"num_tokens": 7634224.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 6.2248612403869625,
|
|
"epoch": 0.3616213352172377,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004991566585011405,
|
|
"loss": 6.1054,
|
|
"mean_token_accuracy": 0.1508861094713211,
|
|
"num_tokens": 7643392.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 6.141217947006226,
|
|
"epoch": 0.36206287530907805,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004991539322775758,
|
|
"loss": 6.142,
|
|
"mean_token_accuracy": 0.1469010017812252,
|
|
"num_tokens": 7652491.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 6.402379751205444,
|
|
"epoch": 0.3625044154009184,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004991512016629632,
|
|
"loss": 6.3451,
|
|
"mean_token_accuracy": 0.13396419063210488,
|
|
"num_tokens": 7663192.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 6.351581001281739,
|
|
"epoch": 0.36294595549275877,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004991484666573558,
|
|
"loss": 6.1872,
|
|
"mean_token_accuracy": 0.14387465864419938,
|
|
"num_tokens": 7672801.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 6.290612125396729,
|
|
"epoch": 0.3633874955845991,
|
|
"grad_norm": 3.640625,
|
|
"learning_rate": 0.0004991457272608077,
|
|
"loss": 6.2029,
|
|
"mean_token_accuracy": 0.142944598197937,
|
|
"num_tokens": 7683013.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 6.285777425765991,
|
|
"epoch": 0.3638290356764394,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004991429834733721,
|
|
"loss": 6.2166,
|
|
"mean_token_accuracy": 0.14354896545410156,
|
|
"num_tokens": 7692760.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 6.293794918060303,
|
|
"epoch": 0.36427057576827976,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.000499140235295103,
|
|
"loss": 6.1902,
|
|
"mean_token_accuracy": 0.14732723981142043,
|
|
"num_tokens": 7702005.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 6.299161052703857,
|
|
"epoch": 0.3647121158601201,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004991374827260542,
|
|
"loss": 6.2069,
|
|
"mean_token_accuracy": 0.14357001036405564,
|
|
"num_tokens": 7711604.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 6.247972822189331,
|
|
"epoch": 0.3651536559519604,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004991347257662795,
|
|
"loss": 6.1049,
|
|
"mean_token_accuracy": 0.14599167481064795,
|
|
"num_tokens": 7720434.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 6.294910478591919,
|
|
"epoch": 0.36559519604380075,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.000499131964415833,
|
|
"loss": 6.166,
|
|
"mean_token_accuracy": 0.14839906394481658,
|
|
"num_tokens": 7730733.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 6.198695325851441,
|
|
"epoch": 0.36603673613564114,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004991291986747689,
|
|
"loss": 6.235,
|
|
"mean_token_accuracy": 0.14558938667178153,
|
|
"num_tokens": 7740394.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 6.325007724761963,
|
|
"epoch": 0.36647827622748147,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004991264285431412,
|
|
"loss": 6.1828,
|
|
"mean_token_accuracy": 0.150047105550766,
|
|
"num_tokens": 7748919.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 6.360399150848389,
|
|
"epoch": 0.3669198163193218,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004991236540210041,
|
|
"loss": 6.2051,
|
|
"mean_token_accuracy": 0.1464771181344986,
|
|
"num_tokens": 7758591.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 6.263759708404541,
|
|
"epoch": 0.36736135641116213,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004991208751084122,
|
|
"loss": 6.2409,
|
|
"mean_token_accuracy": 0.13913936614990235,
|
|
"num_tokens": 7768269.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 6.311656665802002,
|
|
"epoch": 0.36780289650300246,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004991180918054199,
|
|
"loss": 6.257,
|
|
"mean_token_accuracy": 0.14464529231190681,
|
|
"num_tokens": 7776980.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 6.337720155715942,
|
|
"epoch": 0.3682444365948428,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004991153041120815,
|
|
"loss": 6.1695,
|
|
"mean_token_accuracy": 0.1493624746799469,
|
|
"num_tokens": 7786664.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 6.2292993545532225,
|
|
"epoch": 0.3686859766866831,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004991125120284519,
|
|
"loss": 6.0267,
|
|
"mean_token_accuracy": 0.15732113569974898,
|
|
"num_tokens": 7794981.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 6.180199718475341,
|
|
"epoch": 0.3691275167785235,
|
|
"grad_norm": 6.78125,
|
|
"learning_rate": 0.0004991097155545856,
|
|
"loss": 6.1299,
|
|
"mean_token_accuracy": 0.15222777128219606,
|
|
"num_tokens": 7804850.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 6.182018852233886,
|
|
"epoch": 0.36956905687036384,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004991069146905374,
|
|
"loss": 6.1419,
|
|
"mean_token_accuracy": 0.15296721160411836,
|
|
"num_tokens": 7814117.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 6.265089225769043,
|
|
"epoch": 0.3700105969622042,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004991041094363621,
|
|
"loss": 6.1782,
|
|
"mean_token_accuracy": 0.15054446160793306,
|
|
"num_tokens": 7823384.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 6.2933553695678714,
|
|
"epoch": 0.3704521370540445,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004991012997921149,
|
|
"loss": 6.1724,
|
|
"mean_token_accuracy": 0.15083738043904305,
|
|
"num_tokens": 7834072.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 6.280925703048706,
|
|
"epoch": 0.37089367714588484,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004990984857578506,
|
|
"loss": 6.1744,
|
|
"mean_token_accuracy": 0.1427485764026642,
|
|
"num_tokens": 7843334.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 6.127236223220825,
|
|
"epoch": 0.37133521723772517,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004990956673336245,
|
|
"loss": 6.0968,
|
|
"mean_token_accuracy": 0.1535086452960968,
|
|
"num_tokens": 7853187.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 6.232405376434326,
|
|
"epoch": 0.3717767573295655,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004990928445194917,
|
|
"loss": 6.1824,
|
|
"mean_token_accuracy": 0.14675197005271912,
|
|
"num_tokens": 7862262.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 6.2625322341918945,
|
|
"epoch": 0.3722182974214059,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004990900173155074,
|
|
"loss": 6.1323,
|
|
"mean_token_accuracy": 0.15006745010614395,
|
|
"num_tokens": 7870725.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 6.220727872848511,
|
|
"epoch": 0.3726598375132462,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004990871857217273,
|
|
"loss": 6.0515,
|
|
"mean_token_accuracy": 0.15157599598169327,
|
|
"num_tokens": 7879492.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 6.237200546264648,
|
|
"epoch": 0.37310137760508655,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004990843497382066,
|
|
"loss": 6.1537,
|
|
"mean_token_accuracy": 0.14744771271944046,
|
|
"num_tokens": 7888710.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 6.243387746810913,
|
|
"epoch": 0.3735429176969269,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004990815093650009,
|
|
"loss": 6.1786,
|
|
"mean_token_accuracy": 0.1538126990199089,
|
|
"num_tokens": 7898313.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 6.194939756393433,
|
|
"epoch": 0.3739844577887672,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004990786646021659,
|
|
"loss": 6.1903,
|
|
"mean_token_accuracy": 0.14287389069795609,
|
|
"num_tokens": 7906726.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 6.255891227722168,
|
|
"epoch": 0.37442599788060754,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004990758154497573,
|
|
"loss": 6.1098,
|
|
"mean_token_accuracy": 0.15329550951719284,
|
|
"num_tokens": 7915554.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 6.313123893737793,
|
|
"epoch": 0.3748675379724479,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004990729619078309,
|
|
"loss": 6.2365,
|
|
"mean_token_accuracy": 0.14729351848363875,
|
|
"num_tokens": 7924732.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 6.307825803756714,
|
|
"epoch": 0.37530907806428826,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004990701039764427,
|
|
"loss": 6.1502,
|
|
"mean_token_accuracy": 0.1527288243174553,
|
|
"num_tokens": 7933808.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 6.24105749130249,
|
|
"epoch": 0.3757506181561286,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004990672416556485,
|
|
"loss": 6.1186,
|
|
"mean_token_accuracy": 0.15374407172203064,
|
|
"num_tokens": 7942558.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 6.174380731582642,
|
|
"epoch": 0.3761921582479689,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004990643749455045,
|
|
"loss": 6.2051,
|
|
"mean_token_accuracy": 0.14767509549856186,
|
|
"num_tokens": 7951951.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 6.311297607421875,
|
|
"epoch": 0.37663369833980925,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004990615038460667,
|
|
"loss": 6.1174,
|
|
"mean_token_accuracy": 0.15629696547985078,
|
|
"num_tokens": 7960543.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 6.212013912200928,
|
|
"epoch": 0.3770752384316496,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004990586283573916,
|
|
"loss": 6.1004,
|
|
"mean_token_accuracy": 0.15100028067827226,
|
|
"num_tokens": 7970273.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 6.24426040649414,
|
|
"epoch": 0.3775167785234899,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004990557484795355,
|
|
"loss": 6.1821,
|
|
"mean_token_accuracy": 0.15400006845593453,
|
|
"num_tokens": 7978888.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 6.259699487686158,
|
|
"epoch": 0.37795831861533025,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004990528642125545,
|
|
"loss": 6.1865,
|
|
"mean_token_accuracy": 0.1407089427113533,
|
|
"num_tokens": 7988843.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 6.279107713699341,
|
|
"epoch": 0.37839985870717063,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004990499755565055,
|
|
"loss": 6.1638,
|
|
"mean_token_accuracy": 0.151794371008873,
|
|
"num_tokens": 7998403.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 6.285480642318726,
|
|
"epoch": 0.37884139879901096,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004990470825114448,
|
|
"loss": 6.1885,
|
|
"mean_token_accuracy": 0.15127992779016494,
|
|
"num_tokens": 8007493.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 6.1836748123168945,
|
|
"epoch": 0.3792829388908513,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004990441850774292,
|
|
"loss": 6.1603,
|
|
"mean_token_accuracy": 0.15351675748825072,
|
|
"num_tokens": 8016399.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 6.262436246871948,
|
|
"epoch": 0.3797244789826916,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004990412832545155,
|
|
"loss": 6.1635,
|
|
"mean_token_accuracy": 0.14691063463687898,
|
|
"num_tokens": 8025891.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 6.238006687164306,
|
|
"epoch": 0.38016601907453196,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004990383770427603,
|
|
"loss": 6.0859,
|
|
"mean_token_accuracy": 0.1509350799024105,
|
|
"num_tokens": 8034733.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 6.230528879165649,
|
|
"epoch": 0.3806075591663723,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004990354664422209,
|
|
"loss": 6.1483,
|
|
"mean_token_accuracy": 0.1521308660507202,
|
|
"num_tokens": 8044443.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 6.138578844070435,
|
|
"epoch": 0.3810490992582126,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004990325514529541,
|
|
"loss": 6.1303,
|
|
"mean_token_accuracy": 0.16342166811227798,
|
|
"num_tokens": 8053920.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 6.3028443336486815,
|
|
"epoch": 0.381490639350053,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004990296320750169,
|
|
"loss": 6.1227,
|
|
"mean_token_accuracy": 0.15118969082832337,
|
|
"num_tokens": 8063455.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 6.22663893699646,
|
|
"epoch": 0.38193217944189334,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004990267083084667,
|
|
"loss": 6.1995,
|
|
"mean_token_accuracy": 0.1500270701944828,
|
|
"num_tokens": 8073353.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 6.255289125442505,
|
|
"epoch": 0.38237371953373367,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004990237801533607,
|
|
"loss": 6.2035,
|
|
"mean_token_accuracy": 0.15115233659744262,
|
|
"num_tokens": 8082164.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 6.303492021560669,
|
|
"epoch": 0.382815259625574,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004990208476097562,
|
|
"loss": 6.2161,
|
|
"mean_token_accuracy": 0.1453220874071121,
|
|
"num_tokens": 8090790.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 6.417842245101928,
|
|
"epoch": 0.38325679971741433,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004990179106777109,
|
|
"loss": 6.2292,
|
|
"mean_token_accuracy": 0.14599840193986893,
|
|
"num_tokens": 8100412.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 6.189248132705688,
|
|
"epoch": 0.38369833980925466,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004990149693572819,
|
|
"loss": 6.2178,
|
|
"mean_token_accuracy": 0.1462481401860714,
|
|
"num_tokens": 8110002.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 6.205133438110352,
|
|
"epoch": 0.384139879901095,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004990120236485271,
|
|
"loss": 6.1141,
|
|
"mean_token_accuracy": 0.1545722119510174,
|
|
"num_tokens": 8118898.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 6.2361159324646,
|
|
"epoch": 0.3845814199929354,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004990090735515043,
|
|
"loss": 6.1703,
|
|
"mean_token_accuracy": 0.1435256503522396,
|
|
"num_tokens": 8128207.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 6.186733150482178,
|
|
"epoch": 0.3850229600847757,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000499006119066271,
|
|
"loss": 6.1558,
|
|
"mean_token_accuracy": 0.14698365032672883,
|
|
"num_tokens": 8137317.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 6.266343832015991,
|
|
"epoch": 0.38546450017661604,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004990031601928854,
|
|
"loss": 6.1825,
|
|
"mean_token_accuracy": 0.1447221465408802,
|
|
"num_tokens": 8146519.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 6.168535375595093,
|
|
"epoch": 0.3859060402684564,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004990001969314051,
|
|
"loss": 6.2218,
|
|
"mean_token_accuracy": 0.145457149296999,
|
|
"num_tokens": 8155916.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 6.3184326171875,
|
|
"epoch": 0.3863475803602967,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004989972292818884,
|
|
"loss": 6.231,
|
|
"mean_token_accuracy": 0.14837146773934365,
|
|
"num_tokens": 8165251.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 6.2823505878448485,
|
|
"epoch": 0.38678912045213704,
|
|
"grad_norm": 5.40625,
|
|
"learning_rate": 0.0004989942572443934,
|
|
"loss": 6.2042,
|
|
"mean_token_accuracy": 0.14634532183408738,
|
|
"num_tokens": 8174761.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 6.271600246429443,
|
|
"epoch": 0.38723066054397737,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004989912808189784,
|
|
"loss": 6.1563,
|
|
"mean_token_accuracy": 0.15100886076688766,
|
|
"num_tokens": 8182980.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 6.3505312442779545,
|
|
"epoch": 0.38767220063581775,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004989883000057013,
|
|
"loss": 6.2051,
|
|
"mean_token_accuracy": 0.14624489918351175,
|
|
"num_tokens": 8193306.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 6.2322680950164795,
|
|
"epoch": 0.3881137407276581,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000498985314804621,
|
|
"loss": 6.0946,
|
|
"mean_token_accuracy": 0.15022510960698127,
|
|
"num_tokens": 8203446.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 6.238686370849609,
|
|
"epoch": 0.3885552808194984,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004989823252157958,
|
|
"loss": 6.1412,
|
|
"mean_token_accuracy": 0.1490713208913803,
|
|
"num_tokens": 8212414.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 6.13543381690979,
|
|
"epoch": 0.38899682091133875,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004989793312392841,
|
|
"loss": 6.0629,
|
|
"mean_token_accuracy": 0.15065995454788209,
|
|
"num_tokens": 8221509.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 6.232558631896973,
|
|
"epoch": 0.3894383610031791,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004989763328751448,
|
|
"loss": 6.1626,
|
|
"mean_token_accuracy": 0.14932333379983903,
|
|
"num_tokens": 8230017.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 6.253946590423584,
|
|
"epoch": 0.3898799010950194,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004989733301234365,
|
|
"loss": 6.1223,
|
|
"mean_token_accuracy": 0.15184631198644638,
|
|
"num_tokens": 8238853.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 6.283807992935181,
|
|
"epoch": 0.39032144118685974,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000498970322984218,
|
|
"loss": 6.2002,
|
|
"mean_token_accuracy": 0.14423604309558868,
|
|
"num_tokens": 8248112.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 6.273688220977784,
|
|
"epoch": 0.39076298127870013,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004989673114575483,
|
|
"loss": 6.1516,
|
|
"mean_token_accuracy": 0.14697378426790236,
|
|
"num_tokens": 8257166.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 6.248018789291382,
|
|
"epoch": 0.39120452137054046,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004989642955434863,
|
|
"loss": 6.1751,
|
|
"mean_token_accuracy": 0.14618921428918838,
|
|
"num_tokens": 8266229.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 6.263542175292969,
|
|
"epoch": 0.3916460614623808,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004989612752420912,
|
|
"loss": 6.1318,
|
|
"mean_token_accuracy": 0.147259022295475,
|
|
"num_tokens": 8275102.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 6.21520299911499,
|
|
"epoch": 0.3920876015542211,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000498958250553422,
|
|
"loss": 6.0509,
|
|
"mean_token_accuracy": 0.15448229461908342,
|
|
"num_tokens": 8283847.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 6.29284291267395,
|
|
"epoch": 0.39252914164606145,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004989552214775381,
|
|
"loss": 6.1753,
|
|
"mean_token_accuracy": 0.1464612901210785,
|
|
"num_tokens": 8292622.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 6.291398048400879,
|
|
"epoch": 0.3929706817379018,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004989521880144988,
|
|
"loss": 6.1034,
|
|
"mean_token_accuracy": 0.16104813367128373,
|
|
"num_tokens": 8301026.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 6.259631872177124,
|
|
"epoch": 0.3934122218297421,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004989491501643635,
|
|
"loss": 6.3562,
|
|
"mean_token_accuracy": 0.13695246875286102,
|
|
"num_tokens": 8310977.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 6.219717025756836,
|
|
"epoch": 0.3938537619215825,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004989461079271916,
|
|
"loss": 6.1221,
|
|
"mean_token_accuracy": 0.1505828931927681,
|
|
"num_tokens": 8319391.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 6.210220909118652,
|
|
"epoch": 0.39429530201342283,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004989430613030429,
|
|
"loss": 6.0801,
|
|
"mean_token_accuracy": 0.1500351071357727,
|
|
"num_tokens": 8328639.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 6.262903022766113,
|
|
"epoch": 0.39473684210526316,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.000498940010291977,
|
|
"loss": 6.1916,
|
|
"mean_token_accuracy": 0.1418144792318344,
|
|
"num_tokens": 8338190.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 6.208887529373169,
|
|
"epoch": 0.3951783821971035,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004989369548940536,
|
|
"loss": 6.1396,
|
|
"mean_token_accuracy": 0.14933243542909622,
|
|
"num_tokens": 8346874.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 6.2679730415344235,
|
|
"epoch": 0.3956199222889438,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004989338951093327,
|
|
"loss": 6.1072,
|
|
"mean_token_accuracy": 0.1559783160686493,
|
|
"num_tokens": 8356446.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 6.254531574249268,
|
|
"epoch": 0.39606146238078416,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004989308309378741,
|
|
"loss": 6.1142,
|
|
"mean_token_accuracy": 0.15238502025604247,
|
|
"num_tokens": 8365694.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 6.228513717651367,
|
|
"epoch": 0.3965030024726245,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004989277623797379,
|
|
"loss": 6.1785,
|
|
"mean_token_accuracy": 0.1451736718416214,
|
|
"num_tokens": 8374282.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 6.223094749450683,
|
|
"epoch": 0.3969445425644649,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004989246894349841,
|
|
"loss": 6.1571,
|
|
"mean_token_accuracy": 0.14543229341506958,
|
|
"num_tokens": 8383315.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 6.248504543304444,
|
|
"epoch": 0.3973860826563052,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004989216121036732,
|
|
"loss": 6.1193,
|
|
"mean_token_accuracy": 0.14976042211055757,
|
|
"num_tokens": 8392263.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 6.268833160400391,
|
|
"epoch": 0.39782762274814554,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004989185303858651,
|
|
"loss": 6.1598,
|
|
"mean_token_accuracy": 0.14398288130760192,
|
|
"num_tokens": 8400734.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 6.275659704208374,
|
|
"epoch": 0.39826916283998587,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004989154442816203,
|
|
"loss": 6.1967,
|
|
"mean_token_accuracy": 0.14542601853609086,
|
|
"num_tokens": 8410635.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 6.305443334579468,
|
|
"epoch": 0.3987107029318262,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004989123537909994,
|
|
"loss": 6.165,
|
|
"mean_token_accuracy": 0.14762203097343446,
|
|
"num_tokens": 8420111.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 6.190962457656861,
|
|
"epoch": 0.39915224302366653,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004989092589140629,
|
|
"loss": 6.1101,
|
|
"mean_token_accuracy": 0.14062744081020356,
|
|
"num_tokens": 8429459.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 6.277060890197754,
|
|
"epoch": 0.39959378311550686,
|
|
"grad_norm": 4.59375,
|
|
"learning_rate": 0.0004989061596508712,
|
|
"loss": 6.1288,
|
|
"mean_token_accuracy": 0.14999366477131842,
|
|
"num_tokens": 8438083.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 6.259339284896851,
|
|
"epoch": 0.40003532320734725,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004989030560014853,
|
|
"loss": 6.1662,
|
|
"mean_token_accuracy": 0.15049690380692482,
|
|
"num_tokens": 8447713.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 6.255221700668335,
|
|
"epoch": 0.4004768632991876,
|
|
"grad_norm": 5.75,
|
|
"learning_rate": 0.0004988999479659657,
|
|
"loss": 6.1189,
|
|
"mean_token_accuracy": 0.14965896531939507,
|
|
"num_tokens": 8457394.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 6.226453971862793,
|
|
"epoch": 0.4009184033910279,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004988968355443737,
|
|
"loss": 6.0989,
|
|
"mean_token_accuracy": 0.15315678864717483,
|
|
"num_tokens": 8467333.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 6.249733924865723,
|
|
"epoch": 0.40135994348286824,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004988937187367699,
|
|
"loss": 6.1927,
|
|
"mean_token_accuracy": 0.14078941121697425,
|
|
"num_tokens": 8477530.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 6.2826484680175785,
|
|
"epoch": 0.4018014835747086,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004988905975432154,
|
|
"loss": 6.2625,
|
|
"mean_token_accuracy": 0.14484824985265732,
|
|
"num_tokens": 8486861.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 6.243760204315185,
|
|
"epoch": 0.4022430236665489,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004988874719637715,
|
|
"loss": 6.1034,
|
|
"mean_token_accuracy": 0.15113344937562942,
|
|
"num_tokens": 8496541.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 6.19863486289978,
|
|
"epoch": 0.40268456375838924,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004988843419984994,
|
|
"loss": 6.1531,
|
|
"mean_token_accuracy": 0.1470022514462471,
|
|
"num_tokens": 8505667.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 6.358606481552124,
|
|
"epoch": 0.4031261038502296,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004988812076474604,
|
|
"loss": 6.1486,
|
|
"mean_token_accuracy": 0.14644313231110573,
|
|
"num_tokens": 8515133.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 6.305288457870484,
|
|
"epoch": 0.40356764394206995,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004988780689107158,
|
|
"loss": 6.1064,
|
|
"mean_token_accuracy": 0.15373924225568772,
|
|
"num_tokens": 8524797.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 6.173681545257568,
|
|
"epoch": 0.4040091840339103,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004988749257883271,
|
|
"loss": 6.1367,
|
|
"mean_token_accuracy": 0.14695328921079637,
|
|
"num_tokens": 8534667.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 6.227071952819824,
|
|
"epoch": 0.4044507241257506,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000498871778280356,
|
|
"loss": 6.1302,
|
|
"mean_token_accuracy": 0.15038311779499053,
|
|
"num_tokens": 8543874.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 6.192816591262817,
|
|
"epoch": 0.40489226421759095,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004988686263868641,
|
|
"loss": 6.1467,
|
|
"mean_token_accuracy": 0.14648784697055817,
|
|
"num_tokens": 8553620.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 6.25673189163208,
|
|
"epoch": 0.4053338043094313,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004988654701079131,
|
|
"loss": 6.2143,
|
|
"mean_token_accuracy": 0.14080783054232598,
|
|
"num_tokens": 8563857.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 6.334765005111694,
|
|
"epoch": 0.4057753444012716,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004988623094435649,
|
|
"loss": 6.2139,
|
|
"mean_token_accuracy": 0.14208807647228242,
|
|
"num_tokens": 8572677.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 6.229012393951416,
|
|
"epoch": 0.406216884493112,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004988591443938813,
|
|
"loss": 6.1269,
|
|
"mean_token_accuracy": 0.14795654267072678,
|
|
"num_tokens": 8581907.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 6.262136697769165,
|
|
"epoch": 0.4066584245849523,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004988559749589244,
|
|
"loss": 6.1629,
|
|
"mean_token_accuracy": 0.14598316252231597,
|
|
"num_tokens": 8591701.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 6.257154321670532,
|
|
"epoch": 0.40709996467679266,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004988528011387563,
|
|
"loss": 6.1899,
|
|
"mean_token_accuracy": 0.15008021965622903,
|
|
"num_tokens": 8601054.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 6.234865713119507,
|
|
"epoch": 0.407541504768633,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004988496229334392,
|
|
"loss": 6.1083,
|
|
"mean_token_accuracy": 0.15296214148402215,
|
|
"num_tokens": 8610346.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 6.223312854766846,
|
|
"epoch": 0.4079830448604733,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004988464403430352,
|
|
"loss": 6.1006,
|
|
"mean_token_accuracy": 0.1481364607810974,
|
|
"num_tokens": 8620823.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 6.2206339836120605,
|
|
"epoch": 0.40842458495231365,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004988432533676067,
|
|
"loss": 6.2553,
|
|
"mean_token_accuracy": 0.14241225197911261,
|
|
"num_tokens": 8630184.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 6.259246778488159,
|
|
"epoch": 0.408866125044154,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004988400620072163,
|
|
"loss": 6.2588,
|
|
"mean_token_accuracy": 0.1362864449620247,
|
|
"num_tokens": 8640064.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 6.3511247634887695,
|
|
"epoch": 0.40930766513599437,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004988368662619263,
|
|
"loss": 6.1484,
|
|
"mean_token_accuracy": 0.14784810915589333,
|
|
"num_tokens": 8650503.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 6.333515739440918,
|
|
"epoch": 0.4097492052278347,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004988336661317994,
|
|
"loss": 6.1629,
|
|
"mean_token_accuracy": 0.14861233532428741,
|
|
"num_tokens": 8659125.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 6.213559198379516,
|
|
"epoch": 0.41019074531967503,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004988304616168984,
|
|
"loss": 6.1769,
|
|
"mean_token_accuracy": 0.14591192007064818,
|
|
"num_tokens": 8668193.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 6.266979026794433,
|
|
"epoch": 0.41063228541151536,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004988272527172858,
|
|
"loss": 6.1308,
|
|
"mean_token_accuracy": 0.14889822229743005,
|
|
"num_tokens": 8677515.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 6.287114191055298,
|
|
"epoch": 0.4110738255033557,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004988240394330246,
|
|
"loss": 6.1746,
|
|
"mean_token_accuracy": 0.14187708795070647,
|
|
"num_tokens": 8687549.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 6.256554746627808,
|
|
"epoch": 0.411515365595196,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004988208217641778,
|
|
"loss": 6.1761,
|
|
"mean_token_accuracy": 0.14865077808499336,
|
|
"num_tokens": 8697371.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 6.30476655960083,
|
|
"epoch": 0.41195690568703636,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004988175997108086,
|
|
"loss": 6.1793,
|
|
"mean_token_accuracy": 0.1483299732208252,
|
|
"num_tokens": 8707193.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 6.268969869613647,
|
|
"epoch": 0.41239844577887674,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004988143732729797,
|
|
"loss": 6.1778,
|
|
"mean_token_accuracy": 0.1447226196527481,
|
|
"num_tokens": 8716052.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 6.170227193832398,
|
|
"epoch": 0.4128399858707171,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004988111424507546,
|
|
"loss": 6.1174,
|
|
"mean_token_accuracy": 0.15311618894338608,
|
|
"num_tokens": 8726140.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 6.254574155807495,
|
|
"epoch": 0.4132815259625574,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004988079072441964,
|
|
"loss": 6.1107,
|
|
"mean_token_accuracy": 0.15668862909078599,
|
|
"num_tokens": 8735299.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 6.258963775634766,
|
|
"epoch": 0.41372306605439774,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004988046676533687,
|
|
"loss": 6.179,
|
|
"mean_token_accuracy": 0.1478872299194336,
|
|
"num_tokens": 8744686.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 6.226867914199829,
|
|
"epoch": 0.41416460614623807,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004988014236783347,
|
|
"loss": 6.171,
|
|
"mean_token_accuracy": 0.15285128355026245,
|
|
"num_tokens": 8754942.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 6.317941951751709,
|
|
"epoch": 0.4146061462380784,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004987981753191582,
|
|
"loss": 6.1695,
|
|
"mean_token_accuracy": 0.14410044327378274,
|
|
"num_tokens": 8764054.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 6.133100175857544,
|
|
"epoch": 0.41504768632991873,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004987949225759027,
|
|
"loss": 6.0421,
|
|
"mean_token_accuracy": 0.15263513773679732,
|
|
"num_tokens": 8773050.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 6.275085163116455,
|
|
"epoch": 0.4154892264217591,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004987916654486321,
|
|
"loss": 6.1478,
|
|
"mean_token_accuracy": 0.1481424480676651,
|
|
"num_tokens": 8782476.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 6.360612583160401,
|
|
"epoch": 0.41593076651359945,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004987884039374099,
|
|
"loss": 6.215,
|
|
"mean_token_accuracy": 0.1436464659869671,
|
|
"num_tokens": 8791147.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 6.36751766204834,
|
|
"epoch": 0.4163723066054398,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004987851380423001,
|
|
"loss": 6.2116,
|
|
"mean_token_accuracy": 0.14959510266780854,
|
|
"num_tokens": 8801151.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 6.216678428649902,
|
|
"epoch": 0.4168138466972801,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004987818677633668,
|
|
"loss": 6.157,
|
|
"mean_token_accuracy": 0.14351932033896447,
|
|
"num_tokens": 8809587.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 6.13917121887207,
|
|
"epoch": 0.41725538678912044,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.000498778593100674,
|
|
"loss": 6.054,
|
|
"mean_token_accuracy": 0.1474153071641922,
|
|
"num_tokens": 8818168.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 6.221515893936157,
|
|
"epoch": 0.4176969268809608,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004987753140542857,
|
|
"loss": 6.1075,
|
|
"mean_token_accuracy": 0.15322076976299287,
|
|
"num_tokens": 8827477.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 6.230283880233765,
|
|
"epoch": 0.4181384669728011,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004987720306242664,
|
|
"loss": 6.0908,
|
|
"mean_token_accuracy": 0.15419567972421647,
|
|
"num_tokens": 8837067.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 6.259425640106201,
|
|
"epoch": 0.4185800070646415,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004987687428106803,
|
|
"loss": 6.1961,
|
|
"mean_token_accuracy": 0.15190616473555565,
|
|
"num_tokens": 8845790.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 6.233168458938598,
|
|
"epoch": 0.4190215471564818,
|
|
"grad_norm": 5.09375,
|
|
"learning_rate": 0.0004987654506135917,
|
|
"loss": 6.1166,
|
|
"mean_token_accuracy": 0.15246631503105162,
|
|
"num_tokens": 8855242.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 6.357547903060913,
|
|
"epoch": 0.41946308724832215,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004987621540330652,
|
|
"loss": 6.1807,
|
|
"mean_token_accuracy": 0.15104667320847512,
|
|
"num_tokens": 8864459.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 6.257883977890015,
|
|
"epoch": 0.4199046273401625,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004987588530691653,
|
|
"loss": 6.2325,
|
|
"mean_token_accuracy": 0.14518377780914307,
|
|
"num_tokens": 8875028.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 6.165983200073242,
|
|
"epoch": 0.4203461674320028,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004987555477219569,
|
|
"loss": 6.0833,
|
|
"mean_token_accuracy": 0.15509303510189057,
|
|
"num_tokens": 8883857.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 6.305104160308838,
|
|
"epoch": 0.42078770752384315,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004987522379915045,
|
|
"loss": 6.0764,
|
|
"mean_token_accuracy": 0.15581088662147521,
|
|
"num_tokens": 8893499.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 6.269616603851318,
|
|
"epoch": 0.4212292476156835,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000498748923877873,
|
|
"loss": 6.1035,
|
|
"mean_token_accuracy": 0.15332883447408677,
|
|
"num_tokens": 8903368.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 6.1651966094970705,
|
|
"epoch": 0.42167078770752386,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004987456053811273,
|
|
"loss": 6.1849,
|
|
"mean_token_accuracy": 0.1498742736876011,
|
|
"num_tokens": 8912701.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 6.17396912574768,
|
|
"epoch": 0.4221123277993642,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004987422825013325,
|
|
"loss": 6.1473,
|
|
"mean_token_accuracy": 0.14589054882526398,
|
|
"num_tokens": 8921962.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 6.349455690383911,
|
|
"epoch": 0.4225538678912045,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004987389552385536,
|
|
"loss": 6.1536,
|
|
"mean_token_accuracy": 0.14763372913002967,
|
|
"num_tokens": 8931923.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 6.243163013458252,
|
|
"epoch": 0.42299540798304486,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004987356235928558,
|
|
"loss": 6.1744,
|
|
"mean_token_accuracy": 0.14302204996347428,
|
|
"num_tokens": 8940403.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 6.256076335906982,
|
|
"epoch": 0.4234369480748852,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004987322875643044,
|
|
"loss": 6.0935,
|
|
"mean_token_accuracy": 0.1572992831468582,
|
|
"num_tokens": 8949377.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 6.306877994537354,
|
|
"epoch": 0.4238784881667255,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004987289471529647,
|
|
"loss": 6.2359,
|
|
"mean_token_accuracy": 0.145481688529253,
|
|
"num_tokens": 8958719.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 6.2402099609375,
|
|
"epoch": 0.42432002825856585,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004987256023589022,
|
|
"loss": 6.1936,
|
|
"mean_token_accuracy": 0.14106479585170745,
|
|
"num_tokens": 8968226.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 6.20019416809082,
|
|
"epoch": 0.42476156835040624,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004987222531821824,
|
|
"loss": 6.1456,
|
|
"mean_token_accuracy": 0.14612633734941483,
|
|
"num_tokens": 8976670.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 6.179481172561646,
|
|
"epoch": 0.42520310844224657,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004987188996228709,
|
|
"loss": 6.0789,
|
|
"mean_token_accuracy": 0.15591740757226943,
|
|
"num_tokens": 8986185.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 6.212154388427734,
|
|
"epoch": 0.4256446485340869,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004987155416810334,
|
|
"loss": 6.0864,
|
|
"mean_token_accuracy": 0.1552813544869423,
|
|
"num_tokens": 8995124.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 6.21709885597229,
|
|
"epoch": 0.42608618862592723,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004987121793567356,
|
|
"loss": 6.1716,
|
|
"mean_token_accuracy": 0.1470434084534645,
|
|
"num_tokens": 9004380.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 6.242340612411499,
|
|
"epoch": 0.42652772871776756,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004987088126500436,
|
|
"loss": 6.0855,
|
|
"mean_token_accuracy": 0.15288129597902297,
|
|
"num_tokens": 9013791.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 6.20204725265503,
|
|
"epoch": 0.4269692688096079,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000498705441561023,
|
|
"loss": 6.1038,
|
|
"mean_token_accuracy": 0.16311327815055848,
|
|
"num_tokens": 9023076.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 6.332134342193603,
|
|
"epoch": 0.4274108089014482,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004987020660897401,
|
|
"loss": 6.2081,
|
|
"mean_token_accuracy": 0.14697263911366462,
|
|
"num_tokens": 9032720.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 6.2755121231079105,
|
|
"epoch": 0.4278523489932886,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.000498698686236261,
|
|
"loss": 6.1613,
|
|
"mean_token_accuracy": 0.146524578332901,
|
|
"num_tokens": 9042652.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 6.2472004890441895,
|
|
"epoch": 0.42829388908512894,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004986953020006519,
|
|
"loss": 6.2262,
|
|
"mean_token_accuracy": 0.14156229123473169,
|
|
"num_tokens": 9052172.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 6.226924276351928,
|
|
"epoch": 0.4287354291769693,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004986919133829788,
|
|
"loss": 6.1085,
|
|
"mean_token_accuracy": 0.15182769894599915,
|
|
"num_tokens": 9061798.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 6.158733892440796,
|
|
"epoch": 0.4291769692688096,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004986885203833086,
|
|
"loss": 6.04,
|
|
"mean_token_accuracy": 0.15590932518243789,
|
|
"num_tokens": 9070429.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 6.165717315673828,
|
|
"epoch": 0.42961850936064994,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004986851230017075,
|
|
"loss": 6.1517,
|
|
"mean_token_accuracy": 0.15533166229724885,
|
|
"num_tokens": 9080200.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 6.206667804718018,
|
|
"epoch": 0.43006004945249027,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004986817212382419,
|
|
"loss": 6.1441,
|
|
"mean_token_accuracy": 0.14960070550441742,
|
|
"num_tokens": 9089555.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 6.226404857635498,
|
|
"epoch": 0.4305015895443306,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004986783150929786,
|
|
"loss": 6.1278,
|
|
"mean_token_accuracy": 0.14620326682925225,
|
|
"num_tokens": 9099091.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 6.274065351486206,
|
|
"epoch": 0.430943129636171,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004986749045659845,
|
|
"loss": 6.1929,
|
|
"mean_token_accuracy": 0.1484577551484108,
|
|
"num_tokens": 9109008.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 6.215702390670776,
|
|
"epoch": 0.4313846697280113,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004986714896573261,
|
|
"loss": 6.0642,
|
|
"mean_token_accuracy": 0.15413544476032257,
|
|
"num_tokens": 9117882.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 6.18838906288147,
|
|
"epoch": 0.43182620981985165,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004986680703670704,
|
|
"loss": 6.2156,
|
|
"mean_token_accuracy": 0.14986138939857482,
|
|
"num_tokens": 9126860.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 6.218597459793091,
|
|
"epoch": 0.432267749911692,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004986646466952845,
|
|
"loss": 6.1027,
|
|
"mean_token_accuracy": 0.15009103044867517,
|
|
"num_tokens": 9135819.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 6.20029296875,
|
|
"epoch": 0.4327092900035323,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004986612186420353,
|
|
"loss": 6.0957,
|
|
"mean_token_accuracy": 0.15253715515136718,
|
|
"num_tokens": 9145302.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 6.156060600280762,
|
|
"epoch": 0.43315083009537264,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004986577862073901,
|
|
"loss": 6.1599,
|
|
"mean_token_accuracy": 0.14464066177606583,
|
|
"num_tokens": 9154667.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 6.355712270736694,
|
|
"epoch": 0.43359237018721297,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004986543493914159,
|
|
"loss": 6.2065,
|
|
"mean_token_accuracy": 0.1452227145433426,
|
|
"num_tokens": 9164562.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 6.344915914535522,
|
|
"epoch": 0.43403391027905336,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004986509081941805,
|
|
"loss": 6.2122,
|
|
"mean_token_accuracy": 0.14627591297030448,
|
|
"num_tokens": 9174872.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 6.154640483856201,
|
|
"epoch": 0.4344754503708937,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004986474626157507,
|
|
"loss": 5.982,
|
|
"mean_token_accuracy": 0.16471818685531617,
|
|
"num_tokens": 9184322.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 6.106767034530639,
|
|
"epoch": 0.434916990462734,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004986440126561945,
|
|
"loss": 6.118,
|
|
"mean_token_accuracy": 0.14820999652147293,
|
|
"num_tokens": 9194450.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 6.2701087474823,
|
|
"epoch": 0.43535853055457435,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004986405583155792,
|
|
"loss": 6.1522,
|
|
"mean_token_accuracy": 0.1471060834825039,
|
|
"num_tokens": 9203658.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 6.234064769744873,
|
|
"epoch": 0.4358000706464147,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004986370995939725,
|
|
"loss": 6.1212,
|
|
"mean_token_accuracy": 0.15071560591459274,
|
|
"num_tokens": 9213609.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 6.175269746780396,
|
|
"epoch": 0.436241610738255,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004986336364914423,
|
|
"loss": 6.1706,
|
|
"mean_token_accuracy": 0.1434772104024887,
|
|
"num_tokens": 9222704.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 6.222776937484741,
|
|
"epoch": 0.43668315083009535,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004986301690080564,
|
|
"loss": 6.1661,
|
|
"mean_token_accuracy": 0.14416092187166213,
|
|
"num_tokens": 9231599.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 6.2662248611450195,
|
|
"epoch": 0.43712469092193573,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004986266971438826,
|
|
"loss": 6.1764,
|
|
"mean_token_accuracy": 0.14897412061691284,
|
|
"num_tokens": 9241886.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 6.277956199645996,
|
|
"epoch": 0.43756623101377606,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000498623220898989,
|
|
"loss": 6.1638,
|
|
"mean_token_accuracy": 0.1432771749794483,
|
|
"num_tokens": 9251085.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 6.278365135192871,
|
|
"epoch": 0.4380077711056164,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004986197402734436,
|
|
"loss": 6.1487,
|
|
"mean_token_accuracy": 0.1480664610862732,
|
|
"num_tokens": 9259601.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 6.258785533905029,
|
|
"epoch": 0.4384493111974567,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004986162552673148,
|
|
"loss": 6.1799,
|
|
"mean_token_accuracy": 0.15204193890094758,
|
|
"num_tokens": 9268935.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 6.276970481872558,
|
|
"epoch": 0.43889085128929706,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004986127658806706,
|
|
"loss": 6.1838,
|
|
"mean_token_accuracy": 0.14441031441092492,
|
|
"num_tokens": 9277647.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 6.257901382446289,
|
|
"epoch": 0.4393323913811374,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004986092721135796,
|
|
"loss": 6.1254,
|
|
"mean_token_accuracy": 0.1464274510741234,
|
|
"num_tokens": 9286610.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 6.224040937423706,
|
|
"epoch": 0.4397739314729777,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004986057739661101,
|
|
"loss": 6.2149,
|
|
"mean_token_accuracy": 0.14213823676109313,
|
|
"num_tokens": 9295946.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 6.199743700027466,
|
|
"epoch": 0.4402154715648181,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004986022714383307,
|
|
"loss": 6.1125,
|
|
"mean_token_accuracy": 0.1442783683538437,
|
|
"num_tokens": 9304903.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 6.1956946849823,
|
|
"epoch": 0.44065701165665844,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004985987645303099,
|
|
"loss": 6.0175,
|
|
"mean_token_accuracy": 0.15016455501317977,
|
|
"num_tokens": 9313606.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 6.185058498382569,
|
|
"epoch": 0.44109855174849877,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004985952532421164,
|
|
"loss": 6.1373,
|
|
"mean_token_accuracy": 0.14618215709924698,
|
|
"num_tokens": 9322815.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 6.249926280975342,
|
|
"epoch": 0.4415400918403391,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004985917375738193,
|
|
"loss": 6.0576,
|
|
"mean_token_accuracy": 0.15385938584804534,
|
|
"num_tokens": 9332630.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 6.112989044189453,
|
|
"epoch": 0.44198163193217943,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004985882175254871,
|
|
"loss": 6.1087,
|
|
"mean_token_accuracy": 0.14714636355638505,
|
|
"num_tokens": 9342216.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 6.237312364578247,
|
|
"epoch": 0.44242317202401976,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004985846930971887,
|
|
"loss": 6.147,
|
|
"mean_token_accuracy": 0.14364741295576094,
|
|
"num_tokens": 9352295.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 6.195395755767822,
|
|
"epoch": 0.4428647121158601,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004985811642889937,
|
|
"loss": 6.145,
|
|
"mean_token_accuracy": 0.14929724484682083,
|
|
"num_tokens": 9361462.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 6.209699726104736,
|
|
"epoch": 0.4433062522077005,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004985776311009705,
|
|
"loss": 6.0618,
|
|
"mean_token_accuracy": 0.14563873261213303,
|
|
"num_tokens": 9370379.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 6.244296598434448,
|
|
"epoch": 0.4437477922995408,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004985740935331888,
|
|
"loss": 6.1192,
|
|
"mean_token_accuracy": 0.1475251004099846,
|
|
"num_tokens": 9379255.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 6.226190853118896,
|
|
"epoch": 0.44418933239138114,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004985705515857177,
|
|
"loss": 6.0889,
|
|
"mean_token_accuracy": 0.15009573549032212,
|
|
"num_tokens": 9389313.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 6.096516418457031,
|
|
"epoch": 0.4446308724832215,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004985670052586268,
|
|
"loss": 5.8827,
|
|
"mean_token_accuracy": 0.16914348155260087,
|
|
"num_tokens": 9397778.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 6.196593523025513,
|
|
"epoch": 0.4450724125750618,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004985634545519853,
|
|
"loss": 6.1952,
|
|
"mean_token_accuracy": 0.1398940645158291,
|
|
"num_tokens": 9407831.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 6.167946147918701,
|
|
"epoch": 0.44551395266690214,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004985598994658629,
|
|
"loss": 6.0666,
|
|
"mean_token_accuracy": 0.1540227361023426,
|
|
"num_tokens": 9418458.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 6.179390811920166,
|
|
"epoch": 0.44595549275874247,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004985563400003291,
|
|
"loss": 5.9951,
|
|
"mean_token_accuracy": 0.16488620936870574,
|
|
"num_tokens": 9426911.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 6.27180323600769,
|
|
"epoch": 0.44639703285058285,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004985527761554539,
|
|
"loss": 6.1607,
|
|
"mean_token_accuracy": 0.14800687357783318,
|
|
"num_tokens": 9435896.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 6.298493957519531,
|
|
"epoch": 0.4468385729424232,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000498549207931307,
|
|
"loss": 6.181,
|
|
"mean_token_accuracy": 0.14514534771442414,
|
|
"num_tokens": 9445272.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 6.22353572845459,
|
|
"epoch": 0.4472801130342635,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004985456353279581,
|
|
"loss": 6.132,
|
|
"mean_token_accuracy": 0.14213817343115806,
|
|
"num_tokens": 9455377.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 6.2302265644073485,
|
|
"epoch": 0.44772165312610385,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004985420583454774,
|
|
"loss": 6.154,
|
|
"mean_token_accuracy": 0.15052020102739333,
|
|
"num_tokens": 9464918.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 6.2570312976837155,
|
|
"epoch": 0.4481631932179442,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004985384769839349,
|
|
"loss": 6.1742,
|
|
"mean_token_accuracy": 0.14404505118727684,
|
|
"num_tokens": 9473322.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 6.266055107116699,
|
|
"epoch": 0.4486047333097845,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004985348912434008,
|
|
"loss": 6.0661,
|
|
"mean_token_accuracy": 0.15727601945400238,
|
|
"num_tokens": 9482255.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 6.288808965682984,
|
|
"epoch": 0.44904627340162484,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004985313011239452,
|
|
"loss": 6.1165,
|
|
"mean_token_accuracy": 0.1513061538338661,
|
|
"num_tokens": 9491709.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 6.160472440719604,
|
|
"epoch": 0.4494878134934652,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004985277066256388,
|
|
"loss": 6.1041,
|
|
"mean_token_accuracy": 0.15101252347230912,
|
|
"num_tokens": 9500594.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 6.163977861404419,
|
|
"epoch": 0.44992935358530556,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004985241077485515,
|
|
"loss": 6.0951,
|
|
"mean_token_accuracy": 0.15175875127315522,
|
|
"num_tokens": 9509088.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 6.2438524723052975,
|
|
"epoch": 0.4503708936771459,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004985205044927541,
|
|
"loss": 6.0798,
|
|
"mean_token_accuracy": 0.15726079791784286,
|
|
"num_tokens": 9517776.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 6.192723655700684,
|
|
"epoch": 0.4508124337689862,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004985168968583173,
|
|
"loss": 6.146,
|
|
"mean_token_accuracy": 0.15224774926900864,
|
|
"num_tokens": 9527080.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 6.150369167327881,
|
|
"epoch": 0.45125397386082655,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004985132848453114,
|
|
"loss": 5.9983,
|
|
"mean_token_accuracy": 0.16127897500991822,
|
|
"num_tokens": 9536358.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 6.167308330535889,
|
|
"epoch": 0.4516955139526669,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004985096684538075,
|
|
"loss": 6.1038,
|
|
"mean_token_accuracy": 0.14964734613895417,
|
|
"num_tokens": 9545528.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 6.190183210372925,
|
|
"epoch": 0.4521370540445072,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004985060476838763,
|
|
"loss": 6.1315,
|
|
"mean_token_accuracy": 0.14921002686023713,
|
|
"num_tokens": 9554433.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 6.230302476882935,
|
|
"epoch": 0.4525785941363476,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004985024225355887,
|
|
"loss": 6.0682,
|
|
"mean_token_accuracy": 0.14985187724232674,
|
|
"num_tokens": 9563932.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 6.27160873413086,
|
|
"epoch": 0.45302013422818793,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004984987930090158,
|
|
"loss": 6.0615,
|
|
"mean_token_accuracy": 0.15488119423389435,
|
|
"num_tokens": 9572829.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 6.151999282836914,
|
|
"epoch": 0.45346167432002826,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004984951591042285,
|
|
"loss": 6.1005,
|
|
"mean_token_accuracy": 0.15698079913854598,
|
|
"num_tokens": 9583597.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 6.26218466758728,
|
|
"epoch": 0.4539032144118686,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004984915208212983,
|
|
"loss": 6.1823,
|
|
"mean_token_accuracy": 0.14492006301879884,
|
|
"num_tokens": 9593114.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 6.235624980926514,
|
|
"epoch": 0.4543447545037089,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004984878781602964,
|
|
"loss": 6.0829,
|
|
"mean_token_accuracy": 0.14600640833377837,
|
|
"num_tokens": 9601454.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 6.186273860931396,
|
|
"epoch": 0.45478629459554926,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004984842311212939,
|
|
"loss": 6.1448,
|
|
"mean_token_accuracy": 0.15090979114174843,
|
|
"num_tokens": 9611994.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 6.242185878753662,
|
|
"epoch": 0.4552278346873896,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004984805797043625,
|
|
"loss": 6.0986,
|
|
"mean_token_accuracy": 0.14918104112148284,
|
|
"num_tokens": 9621318.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 6.221137046813965,
|
|
"epoch": 0.45566937477923,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004984769239095736,
|
|
"loss": 6.0973,
|
|
"mean_token_accuracy": 0.15199169963598252,
|
|
"num_tokens": 9630270.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 6.247491025924683,
|
|
"epoch": 0.4561109148710703,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004984732637369989,
|
|
"loss": 6.1263,
|
|
"mean_token_accuracy": 0.1468114122748375,
|
|
"num_tokens": 9640391.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 6.236334943771363,
|
|
"epoch": 0.45655245496291064,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004984695991867099,
|
|
"loss": 6.1433,
|
|
"mean_token_accuracy": 0.1472519591450691,
|
|
"num_tokens": 9648827.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 6.168450736999512,
|
|
"epoch": 0.45699399505475097,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004984659302587788,
|
|
"loss": 6.0673,
|
|
"mean_token_accuracy": 0.14995986744761466,
|
|
"num_tokens": 9657940.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 6.161103534698486,
|
|
"epoch": 0.4574355351465913,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000498462256953277,
|
|
"loss": 6.1943,
|
|
"mean_token_accuracy": 0.14195918291807175,
|
|
"num_tokens": 9668296.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 6.272454166412354,
|
|
"epoch": 0.45787707523843163,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004984585792702767,
|
|
"loss": 6.1321,
|
|
"mean_token_accuracy": 0.1457594834268093,
|
|
"num_tokens": 9677914.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 6.276125431060791,
|
|
"epoch": 0.45831861533027196,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004984548972098501,
|
|
"loss": 6.2682,
|
|
"mean_token_accuracy": 0.13744014501571655,
|
|
"num_tokens": 9687339.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 6.200534772872925,
|
|
"epoch": 0.45876015542211235,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.000498451210772069,
|
|
"loss": 6.0492,
|
|
"mean_token_accuracy": 0.15557005926966666,
|
|
"num_tokens": 9696889.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 6.138857126235962,
|
|
"epoch": 0.4592016955139527,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004984475199570058,
|
|
"loss": 6.0119,
|
|
"mean_token_accuracy": 0.1522158980369568,
|
|
"num_tokens": 9705498.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 6.187509822845459,
|
|
"epoch": 0.459643235605793,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004984438247647329,
|
|
"loss": 6.0819,
|
|
"mean_token_accuracy": 0.14996571764349936,
|
|
"num_tokens": 9713936.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 6.235674858093262,
|
|
"epoch": 0.46008477569763334,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004984401251953223,
|
|
"loss": 6.139,
|
|
"mean_token_accuracy": 0.14663990586996078,
|
|
"num_tokens": 9723924.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 6.2642858028411865,
|
|
"epoch": 0.4605263157894737,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004984364212488469,
|
|
"loss": 6.1785,
|
|
"mean_token_accuracy": 0.14377184957265854,
|
|
"num_tokens": 9733427.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 6.205567359924316,
|
|
"epoch": 0.460967855881314,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004984327129253789,
|
|
"loss": 5.9885,
|
|
"mean_token_accuracy": 0.15839618146419526,
|
|
"num_tokens": 9742054.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 6.19922513961792,
|
|
"epoch": 0.46140939597315433,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004984290002249914,
|
|
"loss": 6.1593,
|
|
"mean_token_accuracy": 0.1428479090332985,
|
|
"num_tokens": 9752447.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 6.184007072448731,
|
|
"epoch": 0.4618509360649947,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004984252831477567,
|
|
"loss": 6.0063,
|
|
"mean_token_accuracy": 0.15819374471902847,
|
|
"num_tokens": 9760878.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 6.133184146881104,
|
|
"epoch": 0.46229247615683505,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004984215616937477,
|
|
"loss": 6.0676,
|
|
"mean_token_accuracy": 0.15267323404550553,
|
|
"num_tokens": 9770200.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 6.275788307189941,
|
|
"epoch": 0.4627340162486754,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004984178358630374,
|
|
"loss": 6.1659,
|
|
"mean_token_accuracy": 0.14913044422864913,
|
|
"num_tokens": 9780303.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 6.21355676651001,
|
|
"epoch": 0.4631755563405157,
|
|
"grad_norm": 3.859375,
|
|
"learning_rate": 0.0004984141056556989,
|
|
"loss": 6.062,
|
|
"mean_token_accuracy": 0.15438947528600694,
|
|
"num_tokens": 9790248.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 6.2150005340576175,
|
|
"epoch": 0.46361709643235605,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004984103710718051,
|
|
"loss": 6.1757,
|
|
"mean_token_accuracy": 0.14253960698843002,
|
|
"num_tokens": 9799345.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 6.234236717224121,
|
|
"epoch": 0.4640586365241964,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.000498406632111429,
|
|
"loss": 6.0315,
|
|
"mean_token_accuracy": 0.1504400633275509,
|
|
"num_tokens": 9808561.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 6.295517539978027,
|
|
"epoch": 0.4645001766160367,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004984028887746443,
|
|
"loss": 6.091,
|
|
"mean_token_accuracy": 0.15317275375127792,
|
|
"num_tokens": 9818324.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 6.0996545314788815,
|
|
"epoch": 0.4649417167078771,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004983991410615239,
|
|
"loss": 6.0616,
|
|
"mean_token_accuracy": 0.16138627082109452,
|
|
"num_tokens": 9827935.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 6.135337018966675,
|
|
"epoch": 0.4653832567997174,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004983953889721414,
|
|
"loss": 6.0966,
|
|
"mean_token_accuracy": 0.15333109125494956,
|
|
"num_tokens": 9837118.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 6.33495831489563,
|
|
"epoch": 0.46582479689155776,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004983916325065703,
|
|
"loss": 6.1469,
|
|
"mean_token_accuracy": 0.14710031673312188,
|
|
"num_tokens": 9846197.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 6.320817136764527,
|
|
"epoch": 0.4662663369833981,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004983878716648842,
|
|
"loss": 6.2274,
|
|
"mean_token_accuracy": 0.1372292719781399,
|
|
"num_tokens": 9856120.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 6.224937200546265,
|
|
"epoch": 0.4667078770752384,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004983841064471567,
|
|
"loss": 6.1598,
|
|
"mean_token_accuracy": 0.14868675619363786,
|
|
"num_tokens": 9865599.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 6.239090204238892,
|
|
"epoch": 0.46714941716707875,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004983803368534617,
|
|
"loss": 6.0918,
|
|
"mean_token_accuracy": 0.14730772823095323,
|
|
"num_tokens": 9876471.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 6.2774077415466305,
|
|
"epoch": 0.4675909572589191,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004983765628838728,
|
|
"loss": 6.1372,
|
|
"mean_token_accuracy": 0.14997045919299126,
|
|
"num_tokens": 9887680.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 6.305510187149048,
|
|
"epoch": 0.46803249735075947,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004983727845384641,
|
|
"loss": 6.2229,
|
|
"mean_token_accuracy": 0.13749768882989882,
|
|
"num_tokens": 9897366.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 6.251697826385498,
|
|
"epoch": 0.4684740374425998,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004983690018173096,
|
|
"loss": 6.17,
|
|
"mean_token_accuracy": 0.14041578024625778,
|
|
"num_tokens": 9907437.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 6.193480968475342,
|
|
"epoch": 0.46891557753444013,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004983652147204834,
|
|
"loss": 5.9589,
|
|
"mean_token_accuracy": 0.16042340472340583,
|
|
"num_tokens": 9915766.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 6.205143594741822,
|
|
"epoch": 0.46935711762628046,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004983614232480598,
|
|
"loss": 6.1733,
|
|
"mean_token_accuracy": 0.14470496103167535,
|
|
"num_tokens": 9925389.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 6.167950963973999,
|
|
"epoch": 0.4697986577181208,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004983576274001127,
|
|
"loss": 6.2229,
|
|
"mean_token_accuracy": 0.14586539566516876,
|
|
"num_tokens": 9935798.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 6.2063414573669435,
|
|
"epoch": 0.4702401978099611,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000498353827176717,
|
|
"loss": 6.0719,
|
|
"mean_token_accuracy": 0.15585483759641647,
|
|
"num_tokens": 9945579.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 6.267688894271851,
|
|
"epoch": 0.4706817379018015,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004983500225779466,
|
|
"loss": 6.0985,
|
|
"mean_token_accuracy": 0.1498646095395088,
|
|
"num_tokens": 9955248.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 6.230977582931518,
|
|
"epoch": 0.47112327799364184,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004983462136038764,
|
|
"loss": 6.0943,
|
|
"mean_token_accuracy": 0.1582035481929779,
|
|
"num_tokens": 9965078.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 6.220054006576538,
|
|
"epoch": 0.4715648180854822,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004983424002545809,
|
|
"loss": 6.0784,
|
|
"mean_token_accuracy": 0.1562138557434082,
|
|
"num_tokens": 9973932.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 6.264338159561158,
|
|
"epoch": 0.4720063581773225,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004983385825301348,
|
|
"loss": 6.1322,
|
|
"mean_token_accuracy": 0.14699085503816606,
|
|
"num_tokens": 9983315.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 6.2415910243988035,
|
|
"epoch": 0.47244789826916284,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004983347604306129,
|
|
"loss": 6.0708,
|
|
"mean_token_accuracy": 0.14864065274596214,
|
|
"num_tokens": 9992987.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 6.094457197189331,
|
|
"epoch": 0.47288943836100317,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004983309339560899,
|
|
"loss": 6.1439,
|
|
"mean_token_accuracy": 0.14318862557411194,
|
|
"num_tokens": 10002268.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 6.2612992286682125,
|
|
"epoch": 0.4733309784528435,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004983271031066412,
|
|
"loss": 6.1586,
|
|
"mean_token_accuracy": 0.14363493770360947,
|
|
"num_tokens": 10011772.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 6.305984926223755,
|
|
"epoch": 0.4737725185446839,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004983232678823414,
|
|
"loss": 6.141,
|
|
"mean_token_accuracy": 0.15256721675395965,
|
|
"num_tokens": 10021069.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 6.123571062088013,
|
|
"epoch": 0.4742140586365242,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004983194282832657,
|
|
"loss": 6.0592,
|
|
"mean_token_accuracy": 0.15314415395259856,
|
|
"num_tokens": 10029706.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 6.0487165451049805,
|
|
"epoch": 0.47465559872836455,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004983155843094895,
|
|
"loss": 6.0282,
|
|
"mean_token_accuracy": 0.1549852669239044,
|
|
"num_tokens": 10039633.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 6.2324432849884035,
|
|
"epoch": 0.4750971388202049,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004983117359610881,
|
|
"loss": 6.0862,
|
|
"mean_token_accuracy": 0.15131546556949615,
|
|
"num_tokens": 10048675.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 6.257778930664062,
|
|
"epoch": 0.4755386789120452,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004983078832381367,
|
|
"loss": 6.0631,
|
|
"mean_token_accuracy": 0.15427327901124954,
|
|
"num_tokens": 10057447.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 6.1880207538604735,
|
|
"epoch": 0.47598021900388554,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004983040261407109,
|
|
"loss": 6.1598,
|
|
"mean_token_accuracy": 0.14713627547025682,
|
|
"num_tokens": 10067020.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 6.261177015304566,
|
|
"epoch": 0.47642175909572587,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004983001646688863,
|
|
"loss": 6.1696,
|
|
"mean_token_accuracy": 0.14345274344086648,
|
|
"num_tokens": 10076466.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 6.160317230224609,
|
|
"epoch": 0.47686329918756626,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004982962988227383,
|
|
"loss": 6.0432,
|
|
"mean_token_accuracy": 0.15397232472896577,
|
|
"num_tokens": 10085384.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 6.20677080154419,
|
|
"epoch": 0.4773048392794066,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000498292428602343,
|
|
"loss": 6.1742,
|
|
"mean_token_accuracy": 0.1478663094341755,
|
|
"num_tokens": 10094015.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 6.2046802043914795,
|
|
"epoch": 0.4777463793712469,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004982885540077758,
|
|
"loss": 6.0629,
|
|
"mean_token_accuracy": 0.15281429886817932,
|
|
"num_tokens": 10103107.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 6.079674625396729,
|
|
"epoch": 0.47818791946308725,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004982846750391129,
|
|
"loss": 5.9917,
|
|
"mean_token_accuracy": 0.15909103006124498,
|
|
"num_tokens": 10112408.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 6.1567846775054935,
|
|
"epoch": 0.4786294595549276,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004982807916964303,
|
|
"loss": 6.0707,
|
|
"mean_token_accuracy": 0.14905139431357384,
|
|
"num_tokens": 10121605.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 6.115311241149902,
|
|
"epoch": 0.4790709996467679,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.000498276903979804,
|
|
"loss": 6.0543,
|
|
"mean_token_accuracy": 0.1517949789762497,
|
|
"num_tokens": 10130484.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 6.133319520950318,
|
|
"epoch": 0.47951253973860825,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00049827301188931,
|
|
"loss": 6.0355,
|
|
"mean_token_accuracy": 0.15710298717021942,
|
|
"num_tokens": 10140002.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 6.278661727905273,
|
|
"epoch": 0.47995407983044863,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004982691154250247,
|
|
"loss": 6.1998,
|
|
"mean_token_accuracy": 0.15036016926169396,
|
|
"num_tokens": 10150287.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 6.18853178024292,
|
|
"epoch": 0.48039561992228896,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004982652145870245,
|
|
"loss": 6.0384,
|
|
"mean_token_accuracy": 0.15560515448451043,
|
|
"num_tokens": 10160615.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 6.165748548507691,
|
|
"epoch": 0.4808371600141293,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004982613093753856,
|
|
"loss": 6.0834,
|
|
"mean_token_accuracy": 0.1541260801255703,
|
|
"num_tokens": 10170271.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 6.203157663345337,
|
|
"epoch": 0.4812787001059696,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004982573997901847,
|
|
"loss": 6.0805,
|
|
"mean_token_accuracy": 0.15566618293523787,
|
|
"num_tokens": 10179663.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 6.230932712554932,
|
|
"epoch": 0.48172024019780996,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004982534858314982,
|
|
"loss": 6.1355,
|
|
"mean_token_accuracy": 0.14900892227888107,
|
|
"num_tokens": 10188608.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 6.262550163269043,
|
|
"epoch": 0.4821617802896503,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004982495674994031,
|
|
"loss": 6.0865,
|
|
"mean_token_accuracy": 0.14918412119150162,
|
|
"num_tokens": 10198462.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 6.1284778118133545,
|
|
"epoch": 0.4826033203814906,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004982456447939758,
|
|
"loss": 6.0629,
|
|
"mean_token_accuracy": 0.15871936827898026,
|
|
"num_tokens": 10208362.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 6.189786338806153,
|
|
"epoch": 0.483044860473331,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004982417177152933,
|
|
"loss": 6.0889,
|
|
"mean_token_accuracy": 0.15344267934560776,
|
|
"num_tokens": 10217915.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 6.235037326812744,
|
|
"epoch": 0.48348640056517134,
|
|
"grad_norm": 5.09375,
|
|
"learning_rate": 0.0004982377862634325,
|
|
"loss": 6.131,
|
|
"mean_token_accuracy": 0.15101420134305954,
|
|
"num_tokens": 10226913.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 6.189169836044312,
|
|
"epoch": 0.48392794065701167,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004982338504384705,
|
|
"loss": 6.0879,
|
|
"mean_token_accuracy": 0.15291856229305267,
|
|
"num_tokens": 10236516.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 6.292510843276977,
|
|
"epoch": 0.484369480748852,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004982299102404843,
|
|
"loss": 6.1347,
|
|
"mean_token_accuracy": 0.15164220482110977,
|
|
"num_tokens": 10245492.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 6.15688533782959,
|
|
"epoch": 0.48481102084069233,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.000498225965669551,
|
|
"loss": 5.9841,
|
|
"mean_token_accuracy": 0.16536709070205688,
|
|
"num_tokens": 10254094.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 6.089360761642456,
|
|
"epoch": 0.48525256093253266,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004982220167257482,
|
|
"loss": 6.0383,
|
|
"mean_token_accuracy": 0.15727589279413223,
|
|
"num_tokens": 10263645.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 6.084077024459839,
|
|
"epoch": 0.485694101024373,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004982180634091529,
|
|
"loss": 6.0128,
|
|
"mean_token_accuracy": 0.1580739438533783,
|
|
"num_tokens": 10273416.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 6.23244342803955,
|
|
"epoch": 0.4861356411162134,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004982141057198427,
|
|
"loss": 6.1204,
|
|
"mean_token_accuracy": 0.15273454710841178,
|
|
"num_tokens": 10283194.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 6.240085029602051,
|
|
"epoch": 0.4865771812080537,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004982101436578952,
|
|
"loss": 6.1013,
|
|
"mean_token_accuracy": 0.14988823384046554,
|
|
"num_tokens": 10292188.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 6.161333322525024,
|
|
"epoch": 0.48701872129989404,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004982061772233878,
|
|
"loss": 6.0099,
|
|
"mean_token_accuracy": 0.16448492854833602,
|
|
"num_tokens": 10301539.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 6.117511987686157,
|
|
"epoch": 0.4874602613917344,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004982022064163984,
|
|
"loss": 6.0548,
|
|
"mean_token_accuracy": 0.15493491739034654,
|
|
"num_tokens": 10310379.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 6.296630859375,
|
|
"epoch": 0.4879018014835747,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004981982312370047,
|
|
"loss": 6.242,
|
|
"mean_token_accuracy": 0.13949622288346292,
|
|
"num_tokens": 10320622.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 6.197968816757202,
|
|
"epoch": 0.48834334157541504,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004981942516852847,
|
|
"loss": 6.0672,
|
|
"mean_token_accuracy": 0.1509483724832535,
|
|
"num_tokens": 10330525.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 6.176139831542969,
|
|
"epoch": 0.48878488166725537,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004981902677613161,
|
|
"loss": 6.0748,
|
|
"mean_token_accuracy": 0.15572689101099968,
|
|
"num_tokens": 10340288.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 6.263591957092285,
|
|
"epoch": 0.48922642175909575,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004981862794651771,
|
|
"loss": 6.1882,
|
|
"mean_token_accuracy": 0.14224747344851493,
|
|
"num_tokens": 10349836.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 6.236993360519409,
|
|
"epoch": 0.4896679618509361,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004981822867969459,
|
|
"loss": 6.1135,
|
|
"mean_token_accuracy": 0.14976053535938263,
|
|
"num_tokens": 10359481.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 6.228906965255737,
|
|
"epoch": 0.4901095019427764,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004981782897567006,
|
|
"loss": 6.068,
|
|
"mean_token_accuracy": 0.1566969633102417,
|
|
"num_tokens": 10369837.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 6.180895662307739,
|
|
"epoch": 0.49055104203461675,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004981742883445195,
|
|
"loss": 6.0438,
|
|
"mean_token_accuracy": 0.15206340700387955,
|
|
"num_tokens": 10379276.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 6.1696826934814455,
|
|
"epoch": 0.4909925821264571,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.000498170282560481,
|
|
"loss": 6.1867,
|
|
"mean_token_accuracy": 0.14743926301598548,
|
|
"num_tokens": 10388878.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 6.312894344329834,
|
|
"epoch": 0.4914341222182974,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004981662724046637,
|
|
"loss": 6.1512,
|
|
"mean_token_accuracy": 0.14519662261009217,
|
|
"num_tokens": 10399148.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 6.235131168365479,
|
|
"epoch": 0.49187566231013774,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000498162257877146,
|
|
"loss": 6.0919,
|
|
"mean_token_accuracy": 0.15135070234537124,
|
|
"num_tokens": 10409002.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 6.129899597167968,
|
|
"epoch": 0.4923172024019781,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004981582389780065,
|
|
"loss": 6.1344,
|
|
"mean_token_accuracy": 0.1505287192761898,
|
|
"num_tokens": 10418083.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 6.293564653396606,
|
|
"epoch": 0.49275874249381846,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004981542157073241,
|
|
"loss": 6.1486,
|
|
"mean_token_accuracy": 0.14746079742908477,
|
|
"num_tokens": 10428134.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 6.274387216567993,
|
|
"epoch": 0.4932002825856588,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004981501880651775,
|
|
"loss": 6.132,
|
|
"mean_token_accuracy": 0.14803507775068284,
|
|
"num_tokens": 10437436.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 6.2339592456817625,
|
|
"epoch": 0.4936418226774991,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004981461560516457,
|
|
"loss": 6.0992,
|
|
"mean_token_accuracy": 0.14704242050647737,
|
|
"num_tokens": 10446176.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 6.229759883880615,
|
|
"epoch": 0.49408336276933945,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004981421196668075,
|
|
"loss": 6.243,
|
|
"mean_token_accuracy": 0.14259758442640305,
|
|
"num_tokens": 10455953.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 6.307909250259399,
|
|
"epoch": 0.4945249028611798,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004981380789107422,
|
|
"loss": 6.0736,
|
|
"mean_token_accuracy": 0.15389894247055053,
|
|
"num_tokens": 10465129.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 6.122000789642334,
|
|
"epoch": 0.4949664429530201,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004981340337835287,
|
|
"loss": 6.0793,
|
|
"mean_token_accuracy": 0.1542934447526932,
|
|
"num_tokens": 10474376.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 6.166776704788208,
|
|
"epoch": 0.4954079830448605,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004981299842852464,
|
|
"loss": 6.1663,
|
|
"mean_token_accuracy": 0.1488489493727684,
|
|
"num_tokens": 10484849.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 6.202208805084228,
|
|
"epoch": 0.49584952313670083,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004981259304159747,
|
|
"loss": 6.0273,
|
|
"mean_token_accuracy": 0.15956118404865266,
|
|
"num_tokens": 10493950.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 6.168651723861695,
|
|
"epoch": 0.49629106322854116,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004981218721757929,
|
|
"loss": 5.9799,
|
|
"mean_token_accuracy": 0.1569823607802391,
|
|
"num_tokens": 10502890.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 6.119230270385742,
|
|
"epoch": 0.4967326033203815,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004981178095647805,
|
|
"loss": 5.9866,
|
|
"mean_token_accuracy": 0.15033361464738845,
|
|
"num_tokens": 10511702.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 6.212582731246949,
|
|
"epoch": 0.4971741434122218,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004981137425830171,
|
|
"loss": 6.0833,
|
|
"mean_token_accuracy": 0.146825347840786,
|
|
"num_tokens": 10520212.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 6.213112783432007,
|
|
"epoch": 0.49761568350406216,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004981096712305825,
|
|
"loss": 6.0966,
|
|
"mean_token_accuracy": 0.1567651391029358,
|
|
"num_tokens": 10529652.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 6.214666318893433,
|
|
"epoch": 0.4980572235959025,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004981055955075561,
|
|
"loss": 6.1651,
|
|
"mean_token_accuracy": 0.14563403353095056,
|
|
"num_tokens": 10537980.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 6.205415534973144,
|
|
"epoch": 0.4984987636877429,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004981015154140181,
|
|
"loss": 6.0204,
|
|
"mean_token_accuracy": 0.15574650317430497,
|
|
"num_tokens": 10546854.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 6.154613637924195,
|
|
"epoch": 0.4989403037795832,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004980974309500483,
|
|
"loss": 6.0621,
|
|
"mean_token_accuracy": 0.15574722364544868,
|
|
"num_tokens": 10555691.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 6.17102541923523,
|
|
"epoch": 0.49938184387142354,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004980933421157267,
|
|
"loss": 6.1159,
|
|
"mean_token_accuracy": 0.14486125558614732,
|
|
"num_tokens": 10564750.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 6.234163522720337,
|
|
"epoch": 0.49982338396326387,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004980892489111334,
|
|
"loss": 6.152,
|
|
"mean_token_accuracy": 0.14877569377422334,
|
|
"num_tokens": 10573515.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 6.125738573074341,
|
|
"epoch": 0.5002649240551043,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004980851513363486,
|
|
"loss": 6.0233,
|
|
"mean_token_accuracy": 0.15632108598947525,
|
|
"num_tokens": 10582730.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 6.051721811294556,
|
|
"epoch": 0.5007064641469445,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004980810493914526,
|
|
"loss": 5.9253,
|
|
"mean_token_accuracy": 0.1711601883172989,
|
|
"num_tokens": 10591267.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 6.154175090789795,
|
|
"epoch": 0.5011480042387849,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004980769430765256,
|
|
"loss": 6.04,
|
|
"mean_token_accuracy": 0.1528927817940712,
|
|
"num_tokens": 10599776.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 6.192328596115113,
|
|
"epoch": 0.5015895443306252,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004980728323916484,
|
|
"loss": 6.033,
|
|
"mean_token_accuracy": 0.1478010207414627,
|
|
"num_tokens": 10609670.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 6.142802715301514,
|
|
"epoch": 0.5020310844224656,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004980687173369009,
|
|
"loss": 5.9971,
|
|
"mean_token_accuracy": 0.15713515877723694,
|
|
"num_tokens": 10619032.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 6.176899385452271,
|
|
"epoch": 0.5024726245143059,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004980645979123644,
|
|
"loss": 6.0839,
|
|
"mean_token_accuracy": 0.14918567463755608,
|
|
"num_tokens": 10628851.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 6.220816135406494,
|
|
"epoch": 0.5029141646061462,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004980604741181192,
|
|
"loss": 6.0664,
|
|
"mean_token_accuracy": 0.1565829783678055,
|
|
"num_tokens": 10638335.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 6.225756311416626,
|
|
"epoch": 0.5033557046979866,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004980563459542461,
|
|
"loss": 6.1504,
|
|
"mean_token_accuracy": 0.15053488165140153,
|
|
"num_tokens": 10648450.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 6.272598075866699,
|
|
"epoch": 0.5037972447898269,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004980522134208261,
|
|
"loss": 6.168,
|
|
"mean_token_accuracy": 0.14580240920186044,
|
|
"num_tokens": 10658700.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 6.281301689147949,
|
|
"epoch": 0.5042387848816673,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004980480765179401,
|
|
"loss": 6.183,
|
|
"mean_token_accuracy": 0.14910355508327483,
|
|
"num_tokens": 10667952.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 6.137789487838745,
|
|
"epoch": 0.5046803249735076,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004980439352456692,
|
|
"loss": 6.0103,
|
|
"mean_token_accuracy": 0.1529277339577675,
|
|
"num_tokens": 10677228.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 6.194245338439941,
|
|
"epoch": 0.505121865065348,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004980397896040944,
|
|
"loss": 6.0869,
|
|
"mean_token_accuracy": 0.15276115983724595,
|
|
"num_tokens": 10686183.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 6.287981605529785,
|
|
"epoch": 0.5055634051571882,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004980356395932969,
|
|
"loss": 6.1249,
|
|
"mean_token_accuracy": 0.15401637256145478,
|
|
"num_tokens": 10695293.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 6.208388042449951,
|
|
"epoch": 0.5060049452490286,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004980314852133581,
|
|
"loss": 6.0737,
|
|
"mean_token_accuracy": 0.155954746901989,
|
|
"num_tokens": 10704853.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 6.1891162395477295,
|
|
"epoch": 0.506446485340869,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004980273264643594,
|
|
"loss": 6.0797,
|
|
"mean_token_accuracy": 0.14783507138490676,
|
|
"num_tokens": 10714307.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 6.068199825286865,
|
|
"epoch": 0.5068880254327093,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004980231633463822,
|
|
"loss": 5.9478,
|
|
"mean_token_accuracy": 0.14717553332448005,
|
|
"num_tokens": 10723513.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 6.131747579574585,
|
|
"epoch": 0.5073295655245497,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004980189958595081,
|
|
"loss": 6.1132,
|
|
"mean_token_accuracy": 0.15128831416368485,
|
|
"num_tokens": 10732809.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 6.229391098022461,
|
|
"epoch": 0.5077711056163899,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004980148240038186,
|
|
"loss": 6.1388,
|
|
"mean_token_accuracy": 0.15277309194207192,
|
|
"num_tokens": 10742960.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 6.311017084121704,
|
|
"epoch": 0.5082126457082303,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004980106477793957,
|
|
"loss": 6.2002,
|
|
"mean_token_accuracy": 0.15205241590738297,
|
|
"num_tokens": 10752835.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 6.192711448669433,
|
|
"epoch": 0.5086541858000706,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004980064671863209,
|
|
"loss": 6.0765,
|
|
"mean_token_accuracy": 0.1547958582639694,
|
|
"num_tokens": 10762139.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 6.211809253692627,
|
|
"epoch": 0.509095725891911,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004980022822246763,
|
|
"loss": 6.1501,
|
|
"mean_token_accuracy": 0.14922941774129866,
|
|
"num_tokens": 10771961.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 6.349077844619751,
|
|
"epoch": 0.5095372659837514,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004979980928945439,
|
|
"loss": 6.1847,
|
|
"mean_token_accuracy": 0.1427362911403179,
|
|
"num_tokens": 10780163.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 6.252031850814819,
|
|
"epoch": 0.5099788060755917,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004979938991960056,
|
|
"loss": 6.1567,
|
|
"mean_token_accuracy": 0.1454293832182884,
|
|
"num_tokens": 10788339.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 6.193761348724365,
|
|
"epoch": 0.510420346167432,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004979897011291436,
|
|
"loss": 6.1412,
|
|
"mean_token_accuracy": 0.1439156413078308,
|
|
"num_tokens": 10797315.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 6.285819005966187,
|
|
"epoch": 0.5108618862592723,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004979854986940402,
|
|
"loss": 6.0717,
|
|
"mean_token_accuracy": 0.14682874381542205,
|
|
"num_tokens": 10806864.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 6.234613418579102,
|
|
"epoch": 0.5113034263511127,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004979812918907777,
|
|
"loss": 6.0984,
|
|
"mean_token_accuracy": 0.15000496208667755,
|
|
"num_tokens": 10816417.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 6.24019980430603,
|
|
"epoch": 0.511744966442953,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004979770807194385,
|
|
"loss": 6.1482,
|
|
"mean_token_accuracy": 0.1514828845858574,
|
|
"num_tokens": 10825692.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 6.236111831665039,
|
|
"epoch": 0.5121865065347934,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004979728651801051,
|
|
"loss": 6.1403,
|
|
"mean_token_accuracy": 0.1545632392168045,
|
|
"num_tokens": 10834652.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 6.167957305908203,
|
|
"epoch": 0.5126280466266337,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004979686452728602,
|
|
"loss": 6.1464,
|
|
"mean_token_accuracy": 0.14476050958037376,
|
|
"num_tokens": 10844491.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 6.158088731765747,
|
|
"epoch": 0.513069586718474,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004979644209977863,
|
|
"loss": 6.0836,
|
|
"mean_token_accuracy": 0.1580489918589592,
|
|
"num_tokens": 10853948.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 6.193817520141602,
|
|
"epoch": 0.5135111268103144,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004979601923549661,
|
|
"loss": 6.0705,
|
|
"mean_token_accuracy": 0.15333878844976426,
|
|
"num_tokens": 10861745.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 6.259048175811768,
|
|
"epoch": 0.5139526669021547,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004979559593444826,
|
|
"loss": 6.1645,
|
|
"mean_token_accuracy": 0.1452197715640068,
|
|
"num_tokens": 10871239.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 6.205961465835571,
|
|
"epoch": 0.5143942069939951,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004979517219664187,
|
|
"loss": 6.0248,
|
|
"mean_token_accuracy": 0.15704307109117507,
|
|
"num_tokens": 10880883.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 6.200279664993286,
|
|
"epoch": 0.5148357470858353,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004979474802208572,
|
|
"loss": 6.0787,
|
|
"mean_token_accuracy": 0.15447696894407273,
|
|
"num_tokens": 10890002.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 6.135254621505737,
|
|
"epoch": 0.5152772871776757,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004979432341078816,
|
|
"loss": 6.0187,
|
|
"mean_token_accuracy": 0.14993426129221915,
|
|
"num_tokens": 10898299.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 6.215742015838623,
|
|
"epoch": 0.5157188272695161,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004979389836275746,
|
|
"loss": 6.2195,
|
|
"mean_token_accuracy": 0.14315202385187148,
|
|
"num_tokens": 10907918.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 6.2449322700500485,
|
|
"epoch": 0.5161603673613564,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004979347287800198,
|
|
"loss": 6.089,
|
|
"mean_token_accuracy": 0.15006405860185623,
|
|
"num_tokens": 10917318.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 6.182945251464844,
|
|
"epoch": 0.5166019074531968,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004979304695653005,
|
|
"loss": 6.0404,
|
|
"mean_token_accuracy": 0.1500822015106678,
|
|
"num_tokens": 10926338.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 6.164806938171386,
|
|
"epoch": 0.5170434475450371,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004979262059835001,
|
|
"loss": 6.0823,
|
|
"mean_token_accuracy": 0.15123574808239937,
|
|
"num_tokens": 10935244.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 6.243174409866333,
|
|
"epoch": 0.5174849876368774,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004979219380347021,
|
|
"loss": 6.0969,
|
|
"mean_token_accuracy": 0.15276483595371246,
|
|
"num_tokens": 10943764.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 6.290911149978638,
|
|
"epoch": 0.5179265277287177,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004979176657189901,
|
|
"loss": 6.0856,
|
|
"mean_token_accuracy": 0.1533655822277069,
|
|
"num_tokens": 10952580.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 6.23861780166626,
|
|
"epoch": 0.5183680678205581,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004979133890364477,
|
|
"loss": 6.1112,
|
|
"mean_token_accuracy": 0.15561173781752585,
|
|
"num_tokens": 10961745.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 6.081136846542359,
|
|
"epoch": 0.5188096079123985,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.000497909107987159,
|
|
"loss": 6.0203,
|
|
"mean_token_accuracy": 0.1529902383685112,
|
|
"num_tokens": 10971018.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 6.202692270278931,
|
|
"epoch": 0.5192511480042388,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004979048225712074,
|
|
"loss": 6.0744,
|
|
"mean_token_accuracy": 0.1534593366086483,
|
|
"num_tokens": 10980070.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 6.22016716003418,
|
|
"epoch": 0.5196926880960792,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004979005327886772,
|
|
"loss": 6.0273,
|
|
"mean_token_accuracy": 0.1515096217393875,
|
|
"num_tokens": 10989090.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 6.23254246711731,
|
|
"epoch": 0.5201342281879194,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004978962386396525,
|
|
"loss": 6.0883,
|
|
"mean_token_accuracy": 0.15314121246337892,
|
|
"num_tokens": 10998652.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 6.148999738693237,
|
|
"epoch": 0.5205757682797598,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004978919401242171,
|
|
"loss": 5.9882,
|
|
"mean_token_accuracy": 0.15903434306383132,
|
|
"num_tokens": 11006323.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 6.012803792953491,
|
|
"epoch": 0.5210173083716001,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004978876372424553,
|
|
"loss": 5.9238,
|
|
"mean_token_accuracy": 0.164156411588192,
|
|
"num_tokens": 11015054.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 6.143123817443848,
|
|
"epoch": 0.5214588484634405,
|
|
"grad_norm": 5.1875,
|
|
"learning_rate": 0.0004978833299944515,
|
|
"loss": 6.1265,
|
|
"mean_token_accuracy": 0.14407195448875426,
|
|
"num_tokens": 11025787.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 6.360718059539795,
|
|
"epoch": 0.5219003885552809,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004978790183802901,
|
|
"loss": 6.2388,
|
|
"mean_token_accuracy": 0.1436489887535572,
|
|
"num_tokens": 11036091.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 6.328134918212891,
|
|
"epoch": 0.5223419286471211,
|
|
"grad_norm": 3.859375,
|
|
"learning_rate": 0.0004978747024000554,
|
|
"loss": 6.1939,
|
|
"mean_token_accuracy": 0.1392632395029068,
|
|
"num_tokens": 11046442.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 6.268065500259399,
|
|
"epoch": 0.5227834687389615,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004978703820538321,
|
|
"loss": 6.2112,
|
|
"mean_token_accuracy": 0.14451470226049423,
|
|
"num_tokens": 11056907.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 6.211714887619019,
|
|
"epoch": 0.5232250088308018,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004978660573417048,
|
|
"loss": 6.0584,
|
|
"mean_token_accuracy": 0.15640886425971984,
|
|
"num_tokens": 11065298.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 6.202786159515381,
|
|
"epoch": 0.5236665489226422,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.000497861728263758,
|
|
"loss": 6.0566,
|
|
"mean_token_accuracy": 0.15214993953704833,
|
|
"num_tokens": 11074509.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 6.189145088195801,
|
|
"epoch": 0.5241080890144825,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004978573948200769,
|
|
"loss": 6.0983,
|
|
"mean_token_accuracy": 0.15263655185699462,
|
|
"num_tokens": 11082433.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 6.122281789779663,
|
|
"epoch": 0.5245496291063229,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004978530570107461,
|
|
"loss": 6.0632,
|
|
"mean_token_accuracy": 0.15261141806840897,
|
|
"num_tokens": 11090838.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 6.231547832489014,
|
|
"epoch": 0.5249911691981632,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004978487148358506,
|
|
"loss": 6.0673,
|
|
"mean_token_accuracy": 0.1546216756105423,
|
|
"num_tokens": 11100048.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 6.150852632522583,
|
|
"epoch": 0.5254327092900035,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004978443682954756,
|
|
"loss": 6.0743,
|
|
"mean_token_accuracy": 0.1524834528565407,
|
|
"num_tokens": 11109871.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 6.17802734375,
|
|
"epoch": 0.5258742493818439,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004978400173897061,
|
|
"loss": 6.0653,
|
|
"mean_token_accuracy": 0.14837429970502852,
|
|
"num_tokens": 11119450.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 6.265403985977173,
|
|
"epoch": 0.5263157894736842,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004978356621186275,
|
|
"loss": 6.007,
|
|
"mean_token_accuracy": 0.16124734580516814,
|
|
"num_tokens": 11128321.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 6.202954912185669,
|
|
"epoch": 0.5267573295655246,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004978313024823249,
|
|
"loss": 6.0737,
|
|
"mean_token_accuracy": 0.15226287469267846,
|
|
"num_tokens": 11138657.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 6.148827409744262,
|
|
"epoch": 0.5271988696573648,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.0004978269384808839,
|
|
"loss": 6.0597,
|
|
"mean_token_accuracy": 0.1582752376794815,
|
|
"num_tokens": 11147704.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 6.209830904006958,
|
|
"epoch": 0.5276404097492052,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004978225701143898,
|
|
"loss": 6.1387,
|
|
"mean_token_accuracy": 0.14596268758177758,
|
|
"num_tokens": 11156979.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 6.260457229614258,
|
|
"epoch": 0.5280819498410456,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004978181973829284,
|
|
"loss": 6.0266,
|
|
"mean_token_accuracy": 0.15336811989545823,
|
|
"num_tokens": 11165539.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 6.3307692527771,
|
|
"epoch": 0.5285234899328859,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004978138202865851,
|
|
"loss": 6.1168,
|
|
"mean_token_accuracy": 0.14098541140556337,
|
|
"num_tokens": 11175911.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 6.204238653182983,
|
|
"epoch": 0.5289650300247263,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004978094388254459,
|
|
"loss": 6.1287,
|
|
"mean_token_accuracy": 0.14792783409357071,
|
|
"num_tokens": 11185365.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 6.221013116836548,
|
|
"epoch": 0.5294065701165666,
|
|
"grad_norm": 5.125,
|
|
"learning_rate": 0.0004978050529995965,
|
|
"loss": 6.0366,
|
|
"mean_token_accuracy": 0.1510949432849884,
|
|
"num_tokens": 11195318.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 6.264184522628784,
|
|
"epoch": 0.5298481102084069,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004978006628091228,
|
|
"loss": 6.1571,
|
|
"mean_token_accuracy": 0.14806697890162468,
|
|
"num_tokens": 11205246.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5298481102084069,
|
|
"eval_entropy": 6.074740511752741,
|
|
"eval_loss": 6.123631954193115,
|
|
"eval_mean_token_accuracy": 0.1567293423705229,
|
|
"eval_num_tokens": 11205246.0,
|
|
"eval_runtime": 26.285,
|
|
"eval_samples_per_second": 1343.541,
|
|
"eval_steps_per_second": 167.966,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 6.261495876312256,
|
|
"epoch": 0.5302896503002472,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004977962682541108,
|
|
"loss": 6.1245,
|
|
"mean_token_accuracy": 0.14799828678369523,
|
|
"num_tokens": 11215183.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 6.234362173080444,
|
|
"epoch": 0.5307311903920876,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004977918693346467,
|
|
"loss": 6.0681,
|
|
"mean_token_accuracy": 0.14836506694555282,
|
|
"num_tokens": 11224127.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 6.2427223205566404,
|
|
"epoch": 0.531172730483928,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004977874660508165,
|
|
"loss": 6.1051,
|
|
"mean_token_accuracy": 0.15863558948040007,
|
|
"num_tokens": 11233014.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 6.267404651641845,
|
|
"epoch": 0.5316142705757683,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004977830584027065,
|
|
"loss": 6.1116,
|
|
"mean_token_accuracy": 0.15553241968154907,
|
|
"num_tokens": 11242251.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 6.252231168746948,
|
|
"epoch": 0.5320558106676087,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004977786463904033,
|
|
"loss": 6.1432,
|
|
"mean_token_accuracy": 0.14830528125166892,
|
|
"num_tokens": 11251947.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 6.1382335186004635,
|
|
"epoch": 0.5324973507594489,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004977742300139929,
|
|
"loss": 6.1673,
|
|
"mean_token_accuracy": 0.148697080463171,
|
|
"num_tokens": 11261125.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 6.280923986434937,
|
|
"epoch": 0.5329388908512893,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004977698092735621,
|
|
"loss": 6.068,
|
|
"mean_token_accuracy": 0.15308852344751359,
|
|
"num_tokens": 11270334.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 6.235616731643677,
|
|
"epoch": 0.5333804309431296,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004977653841691975,
|
|
"loss": 6.06,
|
|
"mean_token_accuracy": 0.15150801390409468,
|
|
"num_tokens": 11280497.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 6.170658874511719,
|
|
"epoch": 0.53382197103497,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004977609547009857,
|
|
"loss": 5.9952,
|
|
"mean_token_accuracy": 0.15689463764429093,
|
|
"num_tokens": 11288636.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 6.238555002212524,
|
|
"epoch": 0.5342635111268104,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004977565208690134,
|
|
"loss": 6.1211,
|
|
"mean_token_accuracy": 0.15063835978507994,
|
|
"num_tokens": 11297519.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 6.268319177627563,
|
|
"epoch": 0.5347050512186506,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004977520826733677,
|
|
"loss": 6.0851,
|
|
"mean_token_accuracy": 0.15677888840436935,
|
|
"num_tokens": 11306280.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 6.24368577003479,
|
|
"epoch": 0.535146591310491,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004977476401141353,
|
|
"loss": 6.071,
|
|
"mean_token_accuracy": 0.14682250916957856,
|
|
"num_tokens": 11315366.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 6.185540246963501,
|
|
"epoch": 0.5355881314023313,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004977431931914032,
|
|
"loss": 6.0787,
|
|
"mean_token_accuracy": 0.14786505848169326,
|
|
"num_tokens": 11324664.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 6.199446153640747,
|
|
"epoch": 0.5360296714941717,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004977387419052586,
|
|
"loss": 6.0797,
|
|
"mean_token_accuracy": 0.1473124697804451,
|
|
"num_tokens": 11334118.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 6.347864866256714,
|
|
"epoch": 0.536471211586012,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.000497734286255789,
|
|
"loss": 6.175,
|
|
"mean_token_accuracy": 0.14238944202661513,
|
|
"num_tokens": 11342684.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 6.262286758422851,
|
|
"epoch": 0.5369127516778524,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004977298262430813,
|
|
"loss": 6.1101,
|
|
"mean_token_accuracy": 0.1559641495347023,
|
|
"num_tokens": 11351298.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 6.177248239517212,
|
|
"epoch": 0.5373542917696927,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004977253618672229,
|
|
"loss": 6.048,
|
|
"mean_token_accuracy": 0.15297479629516603,
|
|
"num_tokens": 11360264.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 6.191631174087524,
|
|
"epoch": 0.537795831861533,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004977208931283013,
|
|
"loss": 6.0225,
|
|
"mean_token_accuracy": 0.15780718624591827,
|
|
"num_tokens": 11369815.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 6.261722660064697,
|
|
"epoch": 0.5382373719533734,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004977164200264042,
|
|
"loss": 6.1168,
|
|
"mean_token_accuracy": 0.14988852441310882,
|
|
"num_tokens": 11379131.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 6.200402641296387,
|
|
"epoch": 0.5386789120452137,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.0004977119425616191,
|
|
"loss": 5.9978,
|
|
"mean_token_accuracy": 0.15366772264242173,
|
|
"num_tokens": 11387692.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 6.184014987945557,
|
|
"epoch": 0.5391204521370541,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004977074607340336,
|
|
"loss": 6.0627,
|
|
"mean_token_accuracy": 0.15367623716592788,
|
|
"num_tokens": 11396278.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 6.098484373092651,
|
|
"epoch": 0.5395619922288943,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004977029745437357,
|
|
"loss": 6.0075,
|
|
"mean_token_accuracy": 0.16174166202545165,
|
|
"num_tokens": 11404790.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 6.2133594989776615,
|
|
"epoch": 0.5400035323207347,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000497698483990813,
|
|
"loss": 6.0825,
|
|
"mean_token_accuracy": 0.14521845802664757,
|
|
"num_tokens": 11414614.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 6.2395154476165775,
|
|
"epoch": 0.5404450724125751,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004976939890753539,
|
|
"loss": 6.1112,
|
|
"mean_token_accuracy": 0.1490165799856186,
|
|
"num_tokens": 11423696.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 6.1709897994995115,
|
|
"epoch": 0.5408866125044154,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.000497689489797446,
|
|
"loss": 6.0606,
|
|
"mean_token_accuracy": 0.1530643433332443,
|
|
"num_tokens": 11432669.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 6.204414415359497,
|
|
"epoch": 0.5413281525962558,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004976849861571778,
|
|
"loss": 6.1017,
|
|
"mean_token_accuracy": 0.15045553892850877,
|
|
"num_tokens": 11442132.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 6.218031549453736,
|
|
"epoch": 0.541769692688096,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004976804781546373,
|
|
"loss": 6.0728,
|
|
"mean_token_accuracy": 0.14818092808127403,
|
|
"num_tokens": 11451821.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 6.208802270889282,
|
|
"epoch": 0.5422112327799364,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004976759657899129,
|
|
"loss": 6.0682,
|
|
"mean_token_accuracy": 0.15299722403287888,
|
|
"num_tokens": 11460242.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 6.111813926696778,
|
|
"epoch": 0.5426527728717767,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.000497671449063093,
|
|
"loss": 6.08,
|
|
"mean_token_accuracy": 0.1515306919813156,
|
|
"num_tokens": 11469588.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 6.246411895751953,
|
|
"epoch": 0.5430943129636171,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.000497666927974266,
|
|
"loss": 6.1593,
|
|
"mean_token_accuracy": 0.14249540939927102,
|
|
"num_tokens": 11480401.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 6.300544309616089,
|
|
"epoch": 0.5435358530554575,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004976624025235205,
|
|
"loss": 6.0559,
|
|
"mean_token_accuracy": 0.14820022881031036,
|
|
"num_tokens": 11489117.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 6.183306360244751,
|
|
"epoch": 0.5439773931472978,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004976578727109453,
|
|
"loss": 6.0201,
|
|
"mean_token_accuracy": 0.15444311127066612,
|
|
"num_tokens": 11497612.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 6.119126510620117,
|
|
"epoch": 0.5444189332391381,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004976533385366289,
|
|
"loss": 6.1239,
|
|
"mean_token_accuracy": 0.14944978952407836,
|
|
"num_tokens": 11507024.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 6.167967653274536,
|
|
"epoch": 0.5448604733309784,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004976488000006602,
|
|
"loss": 6.0558,
|
|
"mean_token_accuracy": 0.15538153201341628,
|
|
"num_tokens": 11516873.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 6.2573628425598145,
|
|
"epoch": 0.5453020134228188,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004976442571031282,
|
|
"loss": 6.1195,
|
|
"mean_token_accuracy": 0.1560243234038353,
|
|
"num_tokens": 11526128.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 6.223786067962647,
|
|
"epoch": 0.5457435535146591,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004976397098441218,
|
|
"loss": 6.1373,
|
|
"mean_token_accuracy": 0.15402478873729705,
|
|
"num_tokens": 11535030.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 6.111001682281494,
|
|
"epoch": 0.5461850936064995,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004976351582237301,
|
|
"loss": 6.0279,
|
|
"mean_token_accuracy": 0.1489868089556694,
|
|
"num_tokens": 11543113.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 6.244951248168945,
|
|
"epoch": 0.5466266336983399,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004976306022420423,
|
|
"loss": 6.0814,
|
|
"mean_token_accuracy": 0.14897802099585533,
|
|
"num_tokens": 11552744.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 6.2333760261535645,
|
|
"epoch": 0.5470681737901801,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004976260418991476,
|
|
"loss": 6.0815,
|
|
"mean_token_accuracy": 0.15112528651952745,
|
|
"num_tokens": 11561274.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 6.188093137741089,
|
|
"epoch": 0.5475097138820205,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004976214771951354,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.15548378378152847,
|
|
"num_tokens": 11570485.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 6.247988700866699,
|
|
"epoch": 0.5479512539738608,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004976169081300949,
|
|
"loss": 6.1145,
|
|
"mean_token_accuracy": 0.14788752794265747,
|
|
"num_tokens": 11579380.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 6.229219913482666,
|
|
"epoch": 0.5483927940657012,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004976123347041159,
|
|
"loss": 6.0947,
|
|
"mean_token_accuracy": 0.1510343536734581,
|
|
"num_tokens": 11588686.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 6.136067247390747,
|
|
"epoch": 0.5488343341575415,
|
|
"grad_norm": 7.28125,
|
|
"learning_rate": 0.0004976077569172879,
|
|
"loss": 6.0207,
|
|
"mean_token_accuracy": 0.15724413692951203,
|
|
"num_tokens": 11598547.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 6.204976606369018,
|
|
"epoch": 0.5492758742493818,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004976031747697006,
|
|
"loss": 6.0959,
|
|
"mean_token_accuracy": 0.15085032731294631,
|
|
"num_tokens": 11608407.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 6.1893705368042,
|
|
"epoch": 0.5497174143412222,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004975985882614435,
|
|
"loss": 6.0526,
|
|
"mean_token_accuracy": 0.15429275631904601,
|
|
"num_tokens": 11618641.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 6.2130521774292,
|
|
"epoch": 0.5501589544330625,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004975939973926068,
|
|
"loss": 6.1113,
|
|
"mean_token_accuracy": 0.14406439512968064,
|
|
"num_tokens": 11627082.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 6.180857801437378,
|
|
"epoch": 0.5506004945249029,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004975894021632803,
|
|
"loss": 6.0049,
|
|
"mean_token_accuracy": 0.1561313599348068,
|
|
"num_tokens": 11636045.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 6.171938514709472,
|
|
"epoch": 0.5510420346167432,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000497584802573554,
|
|
"loss": 6.09,
|
|
"mean_token_accuracy": 0.1516232445836067,
|
|
"num_tokens": 11646516.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 6.1169013500213625,
|
|
"epoch": 0.5514835747085836,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.000497580198623518,
|
|
"loss": 6.0152,
|
|
"mean_token_accuracy": 0.15931856781244277,
|
|
"num_tokens": 11655512.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 6.179685831069946,
|
|
"epoch": 0.5519251148004238,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004975755903132623,
|
|
"loss": 6.1158,
|
|
"mean_token_accuracy": 0.15324108451604843,
|
|
"num_tokens": 11665641.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 6.242779970169067,
|
|
"epoch": 0.5523666548922642,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004975709776428776,
|
|
"loss": 6.0864,
|
|
"mean_token_accuracy": 0.14270863980054854,
|
|
"num_tokens": 11674585.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 6.1917078495025635,
|
|
"epoch": 0.5528081949841046,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.000497566360612454,
|
|
"loss": 5.9814,
|
|
"mean_token_accuracy": 0.16099566966295242,
|
|
"num_tokens": 11683498.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 6.150371551513672,
|
|
"epoch": 0.5532497350759449,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.000497561739222082,
|
|
"loss": 6.0133,
|
|
"mean_token_accuracy": 0.15729362815618514,
|
|
"num_tokens": 11692663.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 6.237178993225098,
|
|
"epoch": 0.5536912751677853,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004975571134718521,
|
|
"loss": 6.1624,
|
|
"mean_token_accuracy": 0.14940599352121353,
|
|
"num_tokens": 11701906.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 6.188458633422852,
|
|
"epoch": 0.5541328152596255,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004975524833618548,
|
|
"loss": 6.0612,
|
|
"mean_token_accuracy": 0.15533912926912308,
|
|
"num_tokens": 11710932.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 6.136988687515259,
|
|
"epoch": 0.5545743553514659,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.000497547848892181,
|
|
"loss": 6.0925,
|
|
"mean_token_accuracy": 0.15054061263799667,
|
|
"num_tokens": 11719953.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 6.216779804229736,
|
|
"epoch": 0.5550158954433062,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004975432100629215,
|
|
"loss": 5.9751,
|
|
"mean_token_accuracy": 0.15986845195293425,
|
|
"num_tokens": 11728706.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 6.262577915191651,
|
|
"epoch": 0.5554574355351466,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.000497538566874167,
|
|
"loss": 6.1512,
|
|
"mean_token_accuracy": 0.14726722687482835,
|
|
"num_tokens": 11738537.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 6.1831403255462645,
|
|
"epoch": 0.555898975626987,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004975339193260084,
|
|
"loss": 5.9988,
|
|
"mean_token_accuracy": 0.15619935542345048,
|
|
"num_tokens": 11747503.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 6.209629535675049,
|
|
"epoch": 0.5563405157188273,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004975292674185371,
|
|
"loss": 6.0719,
|
|
"mean_token_accuracy": 0.15479969680309297,
|
|
"num_tokens": 11756501.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 6.174160957336426,
|
|
"epoch": 0.5567820558106676,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004975246111518439,
|
|
"loss": 6.0483,
|
|
"mean_token_accuracy": 0.1491239570081234,
|
|
"num_tokens": 11765483.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 6.230826044082642,
|
|
"epoch": 0.5572235959025079,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004975199505260202,
|
|
"loss": 6.1862,
|
|
"mean_token_accuracy": 0.14385148659348487,
|
|
"num_tokens": 11774941.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 6.284946060180664,
|
|
"epoch": 0.5576651359943483,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004975152855411571,
|
|
"loss": 6.1552,
|
|
"mean_token_accuracy": 0.1457800880074501,
|
|
"num_tokens": 11785080.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 6.319910860061645,
|
|
"epoch": 0.5581066760861886,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004975106161973462,
|
|
"loss": 6.0255,
|
|
"mean_token_accuracy": 0.15467681735754013,
|
|
"num_tokens": 11793933.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 6.182535457611084,
|
|
"epoch": 0.558548216178029,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000497505942494679,
|
|
"loss": 6.0675,
|
|
"mean_token_accuracy": 0.14724954590201378,
|
|
"num_tokens": 11803592.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 6.128745031356812,
|
|
"epoch": 0.5589897562698694,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004975012644332467,
|
|
"loss": 5.9718,
|
|
"mean_token_accuracy": 0.15875890329480172,
|
|
"num_tokens": 11812397.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 6.2402550220489506,
|
|
"epoch": 0.5594312963617096,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004974965820131413,
|
|
"loss": 6.1241,
|
|
"mean_token_accuracy": 0.1507368728518486,
|
|
"num_tokens": 11821734.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 6.170193338394165,
|
|
"epoch": 0.55987283645355,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004974918952344544,
|
|
"loss": 6.0176,
|
|
"mean_token_accuracy": 0.1553915947675705,
|
|
"num_tokens": 11832107.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 6.16438479423523,
|
|
"epoch": 0.5603143765453903,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004974872040972777,
|
|
"loss": 6.0291,
|
|
"mean_token_accuracy": 0.15436061918735505,
|
|
"num_tokens": 11841983.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 6.111740016937256,
|
|
"epoch": 0.5607559166372307,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004974825086017033,
|
|
"loss": 6.0285,
|
|
"mean_token_accuracy": 0.15739574581384658,
|
|
"num_tokens": 11851836.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 6.1818804264068605,
|
|
"epoch": 0.561197456729071,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.000497477808747823,
|
|
"loss": 6.0737,
|
|
"mean_token_accuracy": 0.15442853420972824,
|
|
"num_tokens": 11861109.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 6.214493465423584,
|
|
"epoch": 0.5616389968209113,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004974731045357292,
|
|
"loss": 6.1666,
|
|
"mean_token_accuracy": 0.1480507642030716,
|
|
"num_tokens": 11871015.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 6.224303102493286,
|
|
"epoch": 0.5620805369127517,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.0004974683959655136,
|
|
"loss": 6.0559,
|
|
"mean_token_accuracy": 0.15506404340267183,
|
|
"num_tokens": 11881306.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 6.2358441829681395,
|
|
"epoch": 0.562522077004592,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004974636830372686,
|
|
"loss": 5.9684,
|
|
"mean_token_accuracy": 0.1575288876891136,
|
|
"num_tokens": 11890251.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 6.170713281631469,
|
|
"epoch": 0.5629636170964324,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004974589657510866,
|
|
"loss": 6.0966,
|
|
"mean_token_accuracy": 0.1509570896625519,
|
|
"num_tokens": 11899662.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 6.143237447738647,
|
|
"epoch": 0.5634051571882727,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004974542441070601,
|
|
"loss": 6.0628,
|
|
"mean_token_accuracy": 0.15524649620056152,
|
|
"num_tokens": 11908699.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 6.159485769271851,
|
|
"epoch": 0.563846697280113,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004974495181052814,
|
|
"loss": 6.0416,
|
|
"mean_token_accuracy": 0.15841482132673262,
|
|
"num_tokens": 11916637.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 6.245145463943482,
|
|
"epoch": 0.5642882373719533,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004974447877458433,
|
|
"loss": 6.1138,
|
|
"mean_token_accuracy": 0.15061435103416443,
|
|
"num_tokens": 11926063.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 6.221379137039184,
|
|
"epoch": 0.5647297774637937,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004974400530288381,
|
|
"loss": 5.9968,
|
|
"mean_token_accuracy": 0.15577640980482102,
|
|
"num_tokens": 11934861.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 6.233156442642212,
|
|
"epoch": 0.5651713175556341,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004974353139543589,
|
|
"loss": 6.0984,
|
|
"mean_token_accuracy": 0.15241503417491914,
|
|
"num_tokens": 11944403.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 6.242249774932861,
|
|
"epoch": 0.5656128576474744,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004974305705224983,
|
|
"loss": 6.192,
|
|
"mean_token_accuracy": 0.15282924622297286,
|
|
"num_tokens": 11953306.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 6.240070533752442,
|
|
"epoch": 0.5660543977393148,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004974258227333493,
|
|
"loss": 6.0747,
|
|
"mean_token_accuracy": 0.1487444445490837,
|
|
"num_tokens": 11962727.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 6.250161600112915,
|
|
"epoch": 0.566495937831155,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004974210705870052,
|
|
"loss": 6.2021,
|
|
"mean_token_accuracy": 0.14626676738262176,
|
|
"num_tokens": 11972375.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 6.143079137802124,
|
|
"epoch": 0.5669374779229954,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004974163140835586,
|
|
"loss": 5.9903,
|
|
"mean_token_accuracy": 0.15524720996618271,
|
|
"num_tokens": 11981989.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 6.185615587234497,
|
|
"epoch": 0.5673790180148357,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004974115532231029,
|
|
"loss": 6.0347,
|
|
"mean_token_accuracy": 0.1525355249643326,
|
|
"num_tokens": 11990865.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 6.183894205093384,
|
|
"epoch": 0.5678205581066761,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004974067880057315,
|
|
"loss": 6.0403,
|
|
"mean_token_accuracy": 0.15843118131160736,
|
|
"num_tokens": 12000697.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 6.191749143600464,
|
|
"epoch": 0.5682620981985165,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004974020184315375,
|
|
"loss": 6.112,
|
|
"mean_token_accuracy": 0.15010613352060317,
|
|
"num_tokens": 12010560.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 6.25274658203125,
|
|
"epoch": 0.5687036382903567,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.0004973972445006144,
|
|
"loss": 6.1426,
|
|
"mean_token_accuracy": 0.15021998137235643,
|
|
"num_tokens": 12020760.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 6.1001549243927,
|
|
"epoch": 0.5691451783821971,
|
|
"grad_norm": 3.640625,
|
|
"learning_rate": 0.0004973924662130559,
|
|
"loss": 5.9806,
|
|
"mean_token_accuracy": 0.15531480312347412,
|
|
"num_tokens": 12030467.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 6.1398577213287355,
|
|
"epoch": 0.5695867184740374,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004973876835689554,
|
|
"loss": 6.0788,
|
|
"mean_token_accuracy": 0.1474594548344612,
|
|
"num_tokens": 12039897.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 6.215720844268799,
|
|
"epoch": 0.5700282585658778,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004973828965684066,
|
|
"loss": 6.102,
|
|
"mean_token_accuracy": 0.14926670640707015,
|
|
"num_tokens": 12048997.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 6.244099140167236,
|
|
"epoch": 0.5704697986577181,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004973781052115035,
|
|
"loss": 6.0028,
|
|
"mean_token_accuracy": 0.15570057332515716,
|
|
"num_tokens": 12057493.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 6.127003002166748,
|
|
"epoch": 0.5709113387495585,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004973733094983396,
|
|
"loss": 6.0991,
|
|
"mean_token_accuracy": 0.1567182257771492,
|
|
"num_tokens": 12066329.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 6.141180372238159,
|
|
"epoch": 0.5713528788413988,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004973685094290092,
|
|
"loss": 6.102,
|
|
"mean_token_accuracy": 0.15247246474027634,
|
|
"num_tokens": 12076022.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 6.237234592437744,
|
|
"epoch": 0.5717944189332391,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.000497363705003606,
|
|
"loss": 6.0739,
|
|
"mean_token_accuracy": 0.14747185185551642,
|
|
"num_tokens": 12085750.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 6.275226354598999,
|
|
"epoch": 0.5722359590250795,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004973588962222244,
|
|
"loss": 6.0831,
|
|
"mean_token_accuracy": 0.1538494572043419,
|
|
"num_tokens": 12094935.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 6.150537633895874,
|
|
"epoch": 0.5726774991169198,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004973540830849585,
|
|
"loss": 6.022,
|
|
"mean_token_accuracy": 0.15123365074396133,
|
|
"num_tokens": 12104970.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 6.1925688743591305,
|
|
"epoch": 0.5731190392087602,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004973492655919025,
|
|
"loss": 6.1351,
|
|
"mean_token_accuracy": 0.14966658353805543,
|
|
"num_tokens": 12116195.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 6.265226793289185,
|
|
"epoch": 0.5735605793006004,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004973444437431508,
|
|
"loss": 6.0662,
|
|
"mean_token_accuracy": 0.15317095220088958,
|
|
"num_tokens": 12125485.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 6.144006729125977,
|
|
"epoch": 0.5740021193924408,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004973396175387981,
|
|
"loss": 6.0788,
|
|
"mean_token_accuracy": 0.15357084721326827,
|
|
"num_tokens": 12135474.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 6.165819597244263,
|
|
"epoch": 0.5744436594842812,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004973347869789385,
|
|
"loss": 6.1009,
|
|
"mean_token_accuracy": 0.1501133732497692,
|
|
"num_tokens": 12144945.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 6.256242799758911,
|
|
"epoch": 0.5748851995761215,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004973299520636671,
|
|
"loss": 6.0569,
|
|
"mean_token_accuracy": 0.15410331934690474,
|
|
"num_tokens": 12154893.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 6.225384521484375,
|
|
"epoch": 0.5753267396679619,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004973251127930782,
|
|
"loss": 6.1315,
|
|
"mean_token_accuracy": 0.14763701856136321,
|
|
"num_tokens": 12164047.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 6.24685001373291,
|
|
"epoch": 0.5757682797598022,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004973202691672669,
|
|
"loss": 6.1279,
|
|
"mean_token_accuracy": 0.1465580239892006,
|
|
"num_tokens": 12172965.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 6.203349494934082,
|
|
"epoch": 0.5762098198516425,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004973154211863279,
|
|
"loss": 6.1462,
|
|
"mean_token_accuracy": 0.1492430865764618,
|
|
"num_tokens": 12183534.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 6.190635442733765,
|
|
"epoch": 0.5766513599434828,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004973105688503563,
|
|
"loss": 6.0962,
|
|
"mean_token_accuracy": 0.15006413906812668,
|
|
"num_tokens": 12194370.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 6.201846075057984,
|
|
"epoch": 0.5770929000353232,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.000497305712159447,
|
|
"loss": 6.0899,
|
|
"mean_token_accuracy": 0.15036289542913436,
|
|
"num_tokens": 12203765.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 6.2407386779785154,
|
|
"epoch": 0.5775344401271636,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004973008511136954,
|
|
"loss": 6.0436,
|
|
"mean_token_accuracy": 0.15642048344016074,
|
|
"num_tokens": 12212889.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 6.228720664978027,
|
|
"epoch": 0.5779759802190039,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004972959857131963,
|
|
"loss": 6.0991,
|
|
"mean_token_accuracy": 0.1515391692519188,
|
|
"num_tokens": 12222055.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 6.237844610214234,
|
|
"epoch": 0.5784175203108443,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004972911159580454,
|
|
"loss": 6.1281,
|
|
"mean_token_accuracy": 0.15056926906108856,
|
|
"num_tokens": 12232092.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 6.21602201461792,
|
|
"epoch": 0.5788590604026845,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000497286241848338,
|
|
"loss": 6.1419,
|
|
"mean_token_accuracy": 0.14570123925805092,
|
|
"num_tokens": 12241411.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 6.213965797424317,
|
|
"epoch": 0.5793006004945249,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004972813633841696,
|
|
"loss": 6.0186,
|
|
"mean_token_accuracy": 0.15196094810962676,
|
|
"num_tokens": 12249735.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 6.210372972488403,
|
|
"epoch": 0.5797421405863652,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004972764805656355,
|
|
"loss": 6.0338,
|
|
"mean_token_accuracy": 0.15679688304662703,
|
|
"num_tokens": 12259132.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 6.1579570293426515,
|
|
"epoch": 0.5801836806782056,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004972715933928318,
|
|
"loss": 6.1017,
|
|
"mean_token_accuracy": 0.1559670940041542,
|
|
"num_tokens": 12269401.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 6.211545133590699,
|
|
"epoch": 0.580625220770046,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004972667018658539,
|
|
"loss": 6.1179,
|
|
"mean_token_accuracy": 0.14414386153221131,
|
|
"num_tokens": 12279163.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 6.173906469345093,
|
|
"epoch": 0.5810667608618862,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004972618059847976,
|
|
"loss": 5.9978,
|
|
"mean_token_accuracy": 0.15999294966459274,
|
|
"num_tokens": 12287942.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 6.2115003108978275,
|
|
"epoch": 0.5815083009537266,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004972569057497591,
|
|
"loss": 6.0068,
|
|
"mean_token_accuracy": 0.15378794223070144,
|
|
"num_tokens": 12296717.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 6.207294654846192,
|
|
"epoch": 0.5819498410455669,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004972520011608341,
|
|
"loss": 5.9907,
|
|
"mean_token_accuracy": 0.16442489475011826,
|
|
"num_tokens": 12305983.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 6.11067795753479,
|
|
"epoch": 0.5823913811374073,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 0.0004972470922181189,
|
|
"loss": 6.064,
|
|
"mean_token_accuracy": 0.1454851284623146,
|
|
"num_tokens": 12315338.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 6.159762525558472,
|
|
"epoch": 0.5828329212292476,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004972421789217094,
|
|
"loss": 6.1611,
|
|
"mean_token_accuracy": 0.14217343926429749,
|
|
"num_tokens": 12324828.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 6.256775808334351,
|
|
"epoch": 0.583274461321088,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 0.0004972372612717022,
|
|
"loss": 6.025,
|
|
"mean_token_accuracy": 0.1642207235097885,
|
|
"num_tokens": 12332844.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 6.231286430358887,
|
|
"epoch": 0.5837160014129283,
|
|
"grad_norm": 4.9375,
|
|
"learning_rate": 0.0004972323392681934,
|
|
"loss": 6.0346,
|
|
"mean_token_accuracy": 0.15260550677776336,
|
|
"num_tokens": 12342062.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 6.233716201782227,
|
|
"epoch": 0.5841575415047686,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004972274129112794,
|
|
"loss": 6.128,
|
|
"mean_token_accuracy": 0.14080557674169542,
|
|
"num_tokens": 12352071.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 6.3159643650054935,
|
|
"epoch": 0.584599081596609,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004972224822010567,
|
|
"loss": 6.2045,
|
|
"mean_token_accuracy": 0.14211712777614594,
|
|
"num_tokens": 12362025.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 6.222633790969849,
|
|
"epoch": 0.5850406216884493,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004972175471376222,
|
|
"loss": 6.2029,
|
|
"mean_token_accuracy": 0.1442934051156044,
|
|
"num_tokens": 12371547.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 6.262058734893799,
|
|
"epoch": 0.5854821617802897,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004972126077210722,
|
|
"loss": 6.0817,
|
|
"mean_token_accuracy": 0.15001257061958312,
|
|
"num_tokens": 12381385.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 6.322567796707153,
|
|
"epoch": 0.5859237018721299,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004972076639515035,
|
|
"loss": 6.1214,
|
|
"mean_token_accuracy": 0.15077711939811705,
|
|
"num_tokens": 12391302.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 6.136204528808594,
|
|
"epoch": 0.5863652419639703,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004972027158290131,
|
|
"loss": 6.038,
|
|
"mean_token_accuracy": 0.15844113975763321,
|
|
"num_tokens": 12400388.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 6.101259660720825,
|
|
"epoch": 0.5868067820558107,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.000497197763353698,
|
|
"loss": 6.1047,
|
|
"mean_token_accuracy": 0.1440892532467842,
|
|
"num_tokens": 12409695.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 6.210428762435913,
|
|
"epoch": 0.587248322147651,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.000497192806525655,
|
|
"loss": 5.956,
|
|
"mean_token_accuracy": 0.1615053281188011,
|
|
"num_tokens": 12418728.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 6.184083366394043,
|
|
"epoch": 0.5876898622394914,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004971878453449811,
|
|
"loss": 6.1403,
|
|
"mean_token_accuracy": 0.15096160173416137,
|
|
"num_tokens": 12428072.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 6.221541213989258,
|
|
"epoch": 0.5881314023313317,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.000497182879811774,
|
|
"loss": 6.0572,
|
|
"mean_token_accuracy": 0.159123557806015,
|
|
"num_tokens": 12436624.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 6.16471152305603,
|
|
"epoch": 0.588572942423172,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004971779099261304,
|
|
"loss": 6.0573,
|
|
"mean_token_accuracy": 0.14437438026070595,
|
|
"num_tokens": 12446370.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 6.233976030349732,
|
|
"epoch": 0.5890144825150123,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.000497172935688148,
|
|
"loss": 6.114,
|
|
"mean_token_accuracy": 0.15265168845653534,
|
|
"num_tokens": 12456705.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 6.233513212203979,
|
|
"epoch": 0.5894560226068527,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004971679570979242,
|
|
"loss": 6.1202,
|
|
"mean_token_accuracy": 0.15143783241510392,
|
|
"num_tokens": 12466150.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 6.15090160369873,
|
|
"epoch": 0.5898975626986931,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004971629741555565,
|
|
"loss": 5.9865,
|
|
"mean_token_accuracy": 0.1553258329629898,
|
|
"num_tokens": 12475051.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 6.15589075088501,
|
|
"epoch": 0.5903391027905334,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004971579868611423,
|
|
"loss": 6.0754,
|
|
"mean_token_accuracy": 0.1528732568025589,
|
|
"num_tokens": 12485427.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 6.150468969345093,
|
|
"epoch": 0.5907806428823738,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004971529952147797,
|
|
"loss": 6.0171,
|
|
"mean_token_accuracy": 0.15561191588640214,
|
|
"num_tokens": 12494489.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 6.251090431213379,
|
|
"epoch": 0.591222182974214,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.000497147999216566,
|
|
"loss": 6.0594,
|
|
"mean_token_accuracy": 0.15239985883235932,
|
|
"num_tokens": 12503656.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 6.278953886032104,
|
|
"epoch": 0.5916637230660544,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004971429988665996,
|
|
"loss": 6.0904,
|
|
"mean_token_accuracy": 0.14635108262300492,
|
|
"num_tokens": 12512940.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 6.216693925857544,
|
|
"epoch": 0.5921052631578947,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000497137994164978,
|
|
"loss": 6.049,
|
|
"mean_token_accuracy": 0.15235408991575242,
|
|
"num_tokens": 12523186.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 6.208224725723267,
|
|
"epoch": 0.5925468032497351,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004971329851117996,
|
|
"loss": 6.0792,
|
|
"mean_token_accuracy": 0.14888448268175125,
|
|
"num_tokens": 12533018.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 6.291949510574341,
|
|
"epoch": 0.5929883433415755,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004971279717071622,
|
|
"loss": 6.1424,
|
|
"mean_token_accuracy": 0.15083410516381263,
|
|
"num_tokens": 12542889.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 6.280454683303833,
|
|
"epoch": 0.5934298834334157,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004971229539511643,
|
|
"loss": 6.1197,
|
|
"mean_token_accuracy": 0.14412906095385553,
|
|
"num_tokens": 12553625.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 6.154693746566773,
|
|
"epoch": 0.5938714235252561,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.000497117931843904,
|
|
"loss": 6.0614,
|
|
"mean_token_accuracy": 0.1494505375623703,
|
|
"num_tokens": 12563012.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 6.299040460586548,
|
|
"epoch": 0.5943129636170964,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004971129053854797,
|
|
"loss": 6.19,
|
|
"mean_token_accuracy": 0.14032588005065919,
|
|
"num_tokens": 12572892.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 6.226144170761108,
|
|
"epoch": 0.5947545037089368,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00049710787457599,
|
|
"loss": 6.005,
|
|
"mean_token_accuracy": 0.1601989150047302,
|
|
"num_tokens": 12581550.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 6.205187177658081,
|
|
"epoch": 0.5951960438007771,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004971028394155332,
|
|
"loss": 6.1132,
|
|
"mean_token_accuracy": 0.15160066187381743,
|
|
"num_tokens": 12590599.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 6.233553647994995,
|
|
"epoch": 0.5956375838926175,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004970977999042082,
|
|
"loss": 6.0533,
|
|
"mean_token_accuracy": 0.15343946889042853,
|
|
"num_tokens": 12599497.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 6.162289619445801,
|
|
"epoch": 0.5960791239844578,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004970927560421137,
|
|
"loss": 6.1035,
|
|
"mean_token_accuracy": 0.1528333231806755,
|
|
"num_tokens": 12608273.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 6.151650285720825,
|
|
"epoch": 0.5965206640762981,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004970877078293483,
|
|
"loss": 5.9908,
|
|
"mean_token_accuracy": 0.1540530242025852,
|
|
"num_tokens": 12617287.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 6.2019072532653805,
|
|
"epoch": 0.5969622041681385,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004970826552660111,
|
|
"loss": 6.0679,
|
|
"mean_token_accuracy": 0.15437413454055787,
|
|
"num_tokens": 12626874.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 6.175334405899048,
|
|
"epoch": 0.5974037442599788,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004970775983522009,
|
|
"loss": 6.1008,
|
|
"mean_token_accuracy": 0.15122495591640472,
|
|
"num_tokens": 12635218.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 6.212725591659546,
|
|
"epoch": 0.5978452843518192,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004970725370880168,
|
|
"loss": 6.0673,
|
|
"mean_token_accuracy": 0.15267443880438805,
|
|
"num_tokens": 12644395.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 6.247377157211304,
|
|
"epoch": 0.5982868244436594,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004970674714735581,
|
|
"loss": 6.1117,
|
|
"mean_token_accuracy": 0.15235370993614197,
|
|
"num_tokens": 12654540.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 6.217602729797363,
|
|
"epoch": 0.5987283645354998,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004970624015089239,
|
|
"loss": 5.965,
|
|
"mean_token_accuracy": 0.1598532095551491,
|
|
"num_tokens": 12663546.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 6.069162797927857,
|
|
"epoch": 0.5991699046273402,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004970573271942135,
|
|
"loss": 6.0505,
|
|
"mean_token_accuracy": 0.15797914415597916,
|
|
"num_tokens": 12672353.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 6.119115257263184,
|
|
"epoch": 0.5996114447191805,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004970522485295265,
|
|
"loss": 5.9604,
|
|
"mean_token_accuracy": 0.1626288414001465,
|
|
"num_tokens": 12680833.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 6.2099771976470945,
|
|
"epoch": 0.6000529848110209,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004970471655149621,
|
|
"loss": 5.931,
|
|
"mean_token_accuracy": 0.15862324982881545,
|
|
"num_tokens": 12690033.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 6.035942649841308,
|
|
"epoch": 0.6004945249028611,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00049704207815062,
|
|
"loss": 6.0148,
|
|
"mean_token_accuracy": 0.16100204288959502,
|
|
"num_tokens": 12700127.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 6.246385383605957,
|
|
"epoch": 0.6009360649947015,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004970369864366,
|
|
"loss": 6.0568,
|
|
"mean_token_accuracy": 0.1493418201804161,
|
|
"num_tokens": 12709803.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 6.23317322731018,
|
|
"epoch": 0.6013776050865418,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004970318903730017,
|
|
"loss": 6.0184,
|
|
"mean_token_accuracy": 0.15744948983192444,
|
|
"num_tokens": 12718876.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 6.226846408843994,
|
|
"epoch": 0.6018191451783822,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004970267899599249,
|
|
"loss": 6.1384,
|
|
"mean_token_accuracy": 0.15181976407766343,
|
|
"num_tokens": 12728745.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 6.207247638702393,
|
|
"epoch": 0.6022606852702226,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004970216851974695,
|
|
"loss": 6.1304,
|
|
"mean_token_accuracy": 0.1460263289511204,
|
|
"num_tokens": 12738764.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 6.148588848114014,
|
|
"epoch": 0.6027022253620629,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004970165760857356,
|
|
"loss": 6.0685,
|
|
"mean_token_accuracy": 0.14464377611875534,
|
|
"num_tokens": 12747888.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 6.315575790405274,
|
|
"epoch": 0.6031437654539032,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004970114626248232,
|
|
"loss": 6.0977,
|
|
"mean_token_accuracy": 0.14810532927513123,
|
|
"num_tokens": 12757763.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 6.293575620651245,
|
|
"epoch": 0.6035853055457435,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.0004970063448148326,
|
|
"loss": 6.1372,
|
|
"mean_token_accuracy": 0.14629552736878396,
|
|
"num_tokens": 12767924.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 6.260718154907226,
|
|
"epoch": 0.6040268456375839,
|
|
"grad_norm": 5.90625,
|
|
"learning_rate": 0.0004970012226558639,
|
|
"loss": 6.1513,
|
|
"mean_token_accuracy": 0.14904167130589485,
|
|
"num_tokens": 12777140.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 6.217737531661987,
|
|
"epoch": 0.6044683857294242,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004969960961480176,
|
|
"loss": 6.1159,
|
|
"mean_token_accuracy": 0.15016963630914687,
|
|
"num_tokens": 12786731.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 6.2195882320404055,
|
|
"epoch": 0.6049099258212646,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004969909652913939,
|
|
"loss": 6.0566,
|
|
"mean_token_accuracy": 0.15309870839118958,
|
|
"num_tokens": 12796839.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 6.253087329864502,
|
|
"epoch": 0.605351465913105,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004969858300860935,
|
|
"loss": 6.1138,
|
|
"mean_token_accuracy": 0.15200683176517488,
|
|
"num_tokens": 12805944.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 6.224487781524658,
|
|
"epoch": 0.6057930060049452,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 0.0004969806905322169,
|
|
"loss": 6.0726,
|
|
"mean_token_accuracy": 0.15439479649066926,
|
|
"num_tokens": 12814692.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 6.1771105289459225,
|
|
"epoch": 0.6062345460967856,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004969755466298649,
|
|
"loss": 6.0233,
|
|
"mean_token_accuracy": 0.1491582840681076,
|
|
"num_tokens": 12824506.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 6.228961563110351,
|
|
"epoch": 0.6066760861886259,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004969703983791382,
|
|
"loss": 6.0964,
|
|
"mean_token_accuracy": 0.15290898382663726,
|
|
"num_tokens": 12835157.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 6.189265441894531,
|
|
"epoch": 0.6071176262804663,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004969652457801376,
|
|
"loss": 6.0108,
|
|
"mean_token_accuracy": 0.1485551714897156,
|
|
"num_tokens": 12844281.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 6.2684972286224365,
|
|
"epoch": 0.6075591663723066,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004969600888329641,
|
|
"loss": 6.0707,
|
|
"mean_token_accuracy": 0.1507108047604561,
|
|
"num_tokens": 12854486.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 6.215403413772583,
|
|
"epoch": 0.608000706464147,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004969549275377186,
|
|
"loss": 6.0526,
|
|
"mean_token_accuracy": 0.15018294453620912,
|
|
"num_tokens": 12863574.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 6.19040732383728,
|
|
"epoch": 0.6084422465559873,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004969497618945024,
|
|
"loss": 6.0325,
|
|
"mean_token_accuracy": 0.15197444781661035,
|
|
"num_tokens": 12872450.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 6.17571005821228,
|
|
"epoch": 0.6088837866478276,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004969445919034165,
|
|
"loss": 5.9714,
|
|
"mean_token_accuracy": 0.16512659937143326,
|
|
"num_tokens": 12881299.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 6.0891955375671385,
|
|
"epoch": 0.609325326739668,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004969394175645623,
|
|
"loss": 5.9488,
|
|
"mean_token_accuracy": 0.15983871519565582,
|
|
"num_tokens": 12889943.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 6.0837867736816404,
|
|
"epoch": 0.6097668668315083,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004969342388780411,
|
|
"loss": 6.0627,
|
|
"mean_token_accuracy": 0.15418387949466705,
|
|
"num_tokens": 12899497.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 6.157145881652832,
|
|
"epoch": 0.6102084069233487,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004969290558439546,
|
|
"loss": 6.0392,
|
|
"mean_token_accuracy": 0.15607356578111647,
|
|
"num_tokens": 12908677.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 6.222147655487061,
|
|
"epoch": 0.6106499470151889,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004969238684624038,
|
|
"loss": 6.155,
|
|
"mean_token_accuracy": 0.14163556098937988,
|
|
"num_tokens": 12918468.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 6.208994007110595,
|
|
"epoch": 0.6110914871070293,
|
|
"grad_norm": 4.75,
|
|
"learning_rate": 0.0004969186767334908,
|
|
"loss": 6.0333,
|
|
"mean_token_accuracy": 0.15937585681676864,
|
|
"num_tokens": 12928527.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 6.227367925643921,
|
|
"epoch": 0.6115330271988697,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004969134806573172,
|
|
"loss": 5.9931,
|
|
"mean_token_accuracy": 0.1560715138912201,
|
|
"num_tokens": 12937021.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 6.0965118408203125,
|
|
"epoch": 0.61197456729071,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004969082802339846,
|
|
"loss": 5.9683,
|
|
"mean_token_accuracy": 0.1567614756524563,
|
|
"num_tokens": 12945570.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 6.151629972457886,
|
|
"epoch": 0.6124161073825504,
|
|
"grad_norm": 3.984375,
|
|
"learning_rate": 0.000496903075463595,
|
|
"loss": 6.0941,
|
|
"mean_token_accuracy": 0.14968045204877853,
|
|
"num_tokens": 12954594.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 6.1665760517120365,
|
|
"epoch": 0.6128576474743906,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004968978663462504,
|
|
"loss": 6.0703,
|
|
"mean_token_accuracy": 0.15526689887046813,
|
|
"num_tokens": 12963328.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 6.171751880645752,
|
|
"epoch": 0.613299187566231,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004968926528820529,
|
|
"loss": 6.0662,
|
|
"mean_token_accuracy": 0.15428778827190398,
|
|
"num_tokens": 12972806.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 6.232146310806274,
|
|
"epoch": 0.6137407276580713,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004968874350711044,
|
|
"loss": 6.0649,
|
|
"mean_token_accuracy": 0.1464855320751667,
|
|
"num_tokens": 12981940.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 6.231241750717163,
|
|
"epoch": 0.6141822677499117,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004968822129135072,
|
|
"loss": 6.0182,
|
|
"mean_token_accuracy": 0.15274877846240997,
|
|
"num_tokens": 12990501.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 6.256838703155518,
|
|
"epoch": 0.6146238078417521,
|
|
"grad_norm": 4.25,
|
|
"learning_rate": 0.0004968769864093637,
|
|
"loss": 6.0867,
|
|
"mean_token_accuracy": 0.14663174301385878,
|
|
"num_tokens": 12999734.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 6.219386291503906,
|
|
"epoch": 0.6150653479335924,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004968717555587762,
|
|
"loss": 6.1369,
|
|
"mean_token_accuracy": 0.14457945972681047,
|
|
"num_tokens": 13009323.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 6.275314235687256,
|
|
"epoch": 0.6155068880254327,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004968665203618472,
|
|
"loss": 6.1536,
|
|
"mean_token_accuracy": 0.15292704552412034,
|
|
"num_tokens": 13018136.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 6.254905414581299,
|
|
"epoch": 0.615948428117273,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.0004968612808186793,
|
|
"loss": 6.1091,
|
|
"mean_token_accuracy": 0.15201055482029915,
|
|
"num_tokens": 13026494.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 6.192426538467407,
|
|
"epoch": 0.6163899682091134,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004968560369293751,
|
|
"loss": 6.1093,
|
|
"mean_token_accuracy": 0.15276225358247758,
|
|
"num_tokens": 13036548.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 6.232642126083374,
|
|
"epoch": 0.6168315083009537,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.0004968507886940372,
|
|
"loss": 6.1121,
|
|
"mean_token_accuracy": 0.15091473534703254,
|
|
"num_tokens": 13045653.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 6.289934301376343,
|
|
"epoch": 0.6172730483927941,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004968455361127686,
|
|
"loss": 6.1739,
|
|
"mean_token_accuracy": 0.14828065782785416,
|
|
"num_tokens": 13056204.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 6.243044137954712,
|
|
"epoch": 0.6177145884846345,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004968402791856721,
|
|
"loss": 6.1285,
|
|
"mean_token_accuracy": 0.15255769044160844,
|
|
"num_tokens": 13067215.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 6.24944486618042,
|
|
"epoch": 0.6181561285764747,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004968350179128507,
|
|
"loss": 6.0627,
|
|
"mean_token_accuracy": 0.15274736136198044,
|
|
"num_tokens": 13076824.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 6.172572994232178,
|
|
"epoch": 0.6185976686683151,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004968297522944075,
|
|
"loss": 6.0354,
|
|
"mean_token_accuracy": 0.15531302243471146,
|
|
"num_tokens": 13086205.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 6.105914640426636,
|
|
"epoch": 0.6190392087601554,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004968244823304455,
|
|
"loss": 6.0018,
|
|
"mean_token_accuracy": 0.15155387222766875,
|
|
"num_tokens": 13096381.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 6.20639476776123,
|
|
"epoch": 0.6194807488519958,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004968192080210683,
|
|
"loss": 6.0391,
|
|
"mean_token_accuracy": 0.1583210527896881,
|
|
"num_tokens": 13106533.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 6.117431354522705,
|
|
"epoch": 0.619922288943836,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.0004968139293663787,
|
|
"loss": 6.0547,
|
|
"mean_token_accuracy": 0.15728403776884078,
|
|
"num_tokens": 13116605.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 6.140177392959595,
|
|
"epoch": 0.6203638290356764,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004968086463664806,
|
|
"loss": 6.0207,
|
|
"mean_token_accuracy": 0.15957427769899368,
|
|
"num_tokens": 13125316.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 6.286570930480957,
|
|
"epoch": 0.6208053691275168,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.000496803359021477,
|
|
"loss": 6.1795,
|
|
"mean_token_accuracy": 0.15137581676244735,
|
|
"num_tokens": 13135595.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 6.3050120830535885,
|
|
"epoch": 0.6212469092193571,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004967980673314719,
|
|
"loss": 6.1225,
|
|
"mean_token_accuracy": 0.15151166468858718,
|
|
"num_tokens": 13144395.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 6.1149821281433105,
|
|
"epoch": 0.6216884493111975,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004967927712965688,
|
|
"loss": 6.0612,
|
|
"mean_token_accuracy": 0.15384516268968582,
|
|
"num_tokens": 13153906.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 6.1296850681304935,
|
|
"epoch": 0.6221299894030378,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004967874709168714,
|
|
"loss": 6.0122,
|
|
"mean_token_accuracy": 0.1552685961127281,
|
|
"num_tokens": 13163840.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 6.168993759155273,
|
|
"epoch": 0.6225715294948782,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004967821661924837,
|
|
"loss": 6.038,
|
|
"mean_token_accuracy": 0.15430732667446137,
|
|
"num_tokens": 13173224.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 6.19411449432373,
|
|
"epoch": 0.6230130695867184,
|
|
"grad_norm": 6.875,
|
|
"learning_rate": 0.0004967768571235094,
|
|
"loss": 6.0777,
|
|
"mean_token_accuracy": 0.1492239847779274,
|
|
"num_tokens": 13182664.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 6.154684066772461,
|
|
"epoch": 0.6234546096785588,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004967715437100526,
|
|
"loss": 5.9867,
|
|
"mean_token_accuracy": 0.1553950473666191,
|
|
"num_tokens": 13191076.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 6.296986627578735,
|
|
"epoch": 0.6238961497703992,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004967662259522174,
|
|
"loss": 6.1738,
|
|
"mean_token_accuracy": 0.14851178973913193,
|
|
"num_tokens": 13201075.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 6.217172002792358,
|
|
"epoch": 0.6243376898622395,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000496760903850108,
|
|
"loss": 6.1084,
|
|
"mean_token_accuracy": 0.15260327011346816,
|
|
"num_tokens": 13210602.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 6.235305547714233,
|
|
"epoch": 0.6247792299540799,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004967555774038286,
|
|
"loss": 6.0738,
|
|
"mean_token_accuracy": 0.15017012655735015,
|
|
"num_tokens": 13219601.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 6.2360265254974365,
|
|
"epoch": 0.6252207700459201,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004967502466134836,
|
|
"loss": 6.1494,
|
|
"mean_token_accuracy": 0.15250493586063385,
|
|
"num_tokens": 13230675.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 6.27086296081543,
|
|
"epoch": 0.6256623101377605,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004967449114791773,
|
|
"loss": 6.0931,
|
|
"mean_token_accuracy": 0.15382839292287825,
|
|
"num_tokens": 13240349.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 6.238660764694214,
|
|
"epoch": 0.6261038502296008,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004967395720010143,
|
|
"loss": 6.1546,
|
|
"mean_token_accuracy": 0.14545532166957856,
|
|
"num_tokens": 13249867.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 6.212581157684326,
|
|
"epoch": 0.6265453903214412,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004967342281790992,
|
|
"loss": 6.0925,
|
|
"mean_token_accuracy": 0.15382098108530046,
|
|
"num_tokens": 13259143.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 6.256375122070312,
|
|
"epoch": 0.6269869304132816,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004967288800135368,
|
|
"loss": 6.0149,
|
|
"mean_token_accuracy": 0.149423186480999,
|
|
"num_tokens": 13268673.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 6.232032728195191,
|
|
"epoch": 0.6274284705051218,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004967235275044315,
|
|
"loss": 6.0383,
|
|
"mean_token_accuracy": 0.1562743902206421,
|
|
"num_tokens": 13278035.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 6.261171579360962,
|
|
"epoch": 0.6278700105969622,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004967181706518886,
|
|
"loss": 6.1578,
|
|
"mean_token_accuracy": 0.14218074977397918,
|
|
"num_tokens": 13286950.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 6.111796236038208,
|
|
"epoch": 0.6283115506888025,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004967128094560128,
|
|
"loss": 6.0202,
|
|
"mean_token_accuracy": 0.16301421150565149,
|
|
"num_tokens": 13296425.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 6.250481128692627,
|
|
"epoch": 0.6287530907806429,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004967074439169092,
|
|
"loss": 6.1432,
|
|
"mean_token_accuracy": 0.14082750529050828,
|
|
"num_tokens": 13306094.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 6.209989309310913,
|
|
"epoch": 0.6291946308724832,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004967020740346827,
|
|
"loss": 6.0726,
|
|
"mean_token_accuracy": 0.1573947176337242,
|
|
"num_tokens": 13315181.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 6.201513481140137,
|
|
"epoch": 0.6296361709643236,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004966966998094387,
|
|
"loss": 5.9838,
|
|
"mean_token_accuracy": 0.15726577639579772,
|
|
"num_tokens": 13324108.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 6.2309064865112305,
|
|
"epoch": 0.630077711056164,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004966913212412825,
|
|
"loss": 6.0686,
|
|
"mean_token_accuracy": 0.15295007675886155,
|
|
"num_tokens": 13333101.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 6.212774181365967,
|
|
"epoch": 0.6305192511480042,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004966859383303194,
|
|
"loss": 6.0015,
|
|
"mean_token_accuracy": 0.1559315010905266,
|
|
"num_tokens": 13341804.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 6.160013818740845,
|
|
"epoch": 0.6309607912398446,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004966805510766549,
|
|
"loss": 6.0336,
|
|
"mean_token_accuracy": 0.15144553557038307,
|
|
"num_tokens": 13350911.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 6.2372581481933596,
|
|
"epoch": 0.6314023313316849,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004966751594803944,
|
|
"loss": 6.0261,
|
|
"mean_token_accuracy": 0.15334241688251496,
|
|
"num_tokens": 13360657.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 6.166117763519287,
|
|
"epoch": 0.6318438714235253,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004966697635416437,
|
|
"loss": 5.9945,
|
|
"mean_token_accuracy": 0.1584376350045204,
|
|
"num_tokens": 13370462.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 6.263478851318359,
|
|
"epoch": 0.6322854115153655,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004966643632605082,
|
|
"loss": 6.1045,
|
|
"mean_token_accuracy": 0.14802244305610657,
|
|
"num_tokens": 13379446.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 6.201040315628052,
|
|
"epoch": 0.6327269516072059,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.000496658958637094,
|
|
"loss": 6.1054,
|
|
"mean_token_accuracy": 0.1525284618139267,
|
|
"num_tokens": 13389238.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 6.1420855045318605,
|
|
"epoch": 0.6331684916990463,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.000496653549671507,
|
|
"loss": 6.1154,
|
|
"mean_token_accuracy": 0.14715484976768495,
|
|
"num_tokens": 13398613.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 6.264933013916016,
|
|
"epoch": 0.6336100317908866,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004966481363638529,
|
|
"loss": 6.0982,
|
|
"mean_token_accuracy": 0.15162092745304107,
|
|
"num_tokens": 13407600.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 6.142405271530151,
|
|
"epoch": 0.634051571882727,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004966427187142378,
|
|
"loss": 5.9838,
|
|
"mean_token_accuracy": 0.1597929358482361,
|
|
"num_tokens": 13415974.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 6.245382308959961,
|
|
"epoch": 0.6344931119745673,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004966372967227681,
|
|
"loss": 6.0112,
|
|
"mean_token_accuracy": 0.15867528319358826,
|
|
"num_tokens": 13425628.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 6.155143213272095,
|
|
"epoch": 0.6349346520664076,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004966318703895496,
|
|
"loss": 6.0202,
|
|
"mean_token_accuracy": 0.16059588491916657,
|
|
"num_tokens": 13435573.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 6.180757522583008,
|
|
"epoch": 0.6353761921582479,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004966264397146888,
|
|
"loss": 5.9861,
|
|
"mean_token_accuracy": 0.155886735022068,
|
|
"num_tokens": 13443969.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 6.26367564201355,
|
|
"epoch": 0.6358177322500883,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004966210046982921,
|
|
"loss": 6.0873,
|
|
"mean_token_accuracy": 0.14780050665140151,
|
|
"num_tokens": 13452823.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 6.246481275558471,
|
|
"epoch": 0.6362592723419287,
|
|
"grad_norm": 6.5625,
|
|
"learning_rate": 0.0004966155653404661,
|
|
"loss": 6.0847,
|
|
"mean_token_accuracy": 0.15006960928440094,
|
|
"num_tokens": 13461090.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 6.266584396362305,
|
|
"epoch": 0.636700812433769,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004966101216413172,
|
|
"loss": 6.0998,
|
|
"mean_token_accuracy": 0.143781378865242,
|
|
"num_tokens": 13471425.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 6.295030927658081,
|
|
"epoch": 0.6371423525256094,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004966046736009519,
|
|
"loss": 6.1334,
|
|
"mean_token_accuracy": 0.1519760623574257,
|
|
"num_tokens": 13479755.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 6.20279541015625,
|
|
"epoch": 0.6375838926174496,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.0004965992212194772,
|
|
"loss": 6.0216,
|
|
"mean_token_accuracy": 0.15963679254055024,
|
|
"num_tokens": 13488854.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 6.139471006393433,
|
|
"epoch": 0.63802543270929,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004965937644969998,
|
|
"loss": 6.0855,
|
|
"mean_token_accuracy": 0.1470048598945141,
|
|
"num_tokens": 13497987.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 6.185364294052124,
|
|
"epoch": 0.6384669728011303,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004965883034336266,
|
|
"loss": 6.1126,
|
|
"mean_token_accuracy": 0.15082333609461784,
|
|
"num_tokens": 13506960.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 6.267209434509278,
|
|
"epoch": 0.6389085128929707,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004965828380294645,
|
|
"loss": 6.0478,
|
|
"mean_token_accuracy": 0.16055953800678252,
|
|
"num_tokens": 13515907.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 6.232587671279907,
|
|
"epoch": 0.6393500529848111,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004965773682846207,
|
|
"loss": 6.1523,
|
|
"mean_token_accuracy": 0.15573379397392273,
|
|
"num_tokens": 13524876.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 6.185802936553955,
|
|
"epoch": 0.6397915930766513,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004965718941992021,
|
|
"loss": 6.0312,
|
|
"mean_token_accuracy": 0.15648015439510346,
|
|
"num_tokens": 13532891.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 6.307486963272095,
|
|
"epoch": 0.6402331331684917,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004965664157733162,
|
|
"loss": 6.1176,
|
|
"mean_token_accuracy": 0.15312286764383315,
|
|
"num_tokens": 13542409.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 6.226913166046143,
|
|
"epoch": 0.640674673260332,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004965609330070703,
|
|
"loss": 6.0814,
|
|
"mean_token_accuracy": 0.1505043089389801,
|
|
"num_tokens": 13551947.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 6.246300411224365,
|
|
"epoch": 0.6411162133521724,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004965554459005717,
|
|
"loss": 6.1256,
|
|
"mean_token_accuracy": 0.15032473504543303,
|
|
"num_tokens": 13560812.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 6.283781480789185,
|
|
"epoch": 0.6415577534440127,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004965499544539278,
|
|
"loss": 6.1123,
|
|
"mean_token_accuracy": 0.14852680265903473,
|
|
"num_tokens": 13570197.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 6.1979292869567875,
|
|
"epoch": 0.641999293535853,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004965444586672463,
|
|
"loss": 6.0288,
|
|
"mean_token_accuracy": 0.15019979029893876,
|
|
"num_tokens": 13579614.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 6.203632497787476,
|
|
"epoch": 0.6424408336276934,
|
|
"grad_norm": 4.0,
|
|
"learning_rate": 0.000496538958540635,
|
|
"loss": 6.0889,
|
|
"mean_token_accuracy": 0.15143698453903198,
|
|
"num_tokens": 13589511.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 6.26300163269043,
|
|
"epoch": 0.6428823737195337,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004965334540742015,
|
|
"loss": 6.0463,
|
|
"mean_token_accuracy": 0.1591418817639351,
|
|
"num_tokens": 13597718.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 6.192359066009521,
|
|
"epoch": 0.6433239138113741,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004965279452680535,
|
|
"loss": 6.1226,
|
|
"mean_token_accuracy": 0.1504811927676201,
|
|
"num_tokens": 13607599.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 6.262105798721313,
|
|
"epoch": 0.6437654539032144,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004965224321222991,
|
|
"loss": 6.1584,
|
|
"mean_token_accuracy": 0.1500078409910202,
|
|
"num_tokens": 13616513.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 6.173467588424683,
|
|
"epoch": 0.6442069939950548,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004965169146370462,
|
|
"loss": 6.0219,
|
|
"mean_token_accuracy": 0.15918111354112624,
|
|
"num_tokens": 13625505.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 6.249496698379517,
|
|
"epoch": 0.644648534086895,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004965113928124031,
|
|
"loss": 6.1037,
|
|
"mean_token_accuracy": 0.15476782619953156,
|
|
"num_tokens": 13635340.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 6.183323574066162,
|
|
"epoch": 0.6450900741787354,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004965058666484775,
|
|
"loss": 6.0321,
|
|
"mean_token_accuracy": 0.1503544792532921,
|
|
"num_tokens": 13644886.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 6.183138990402222,
|
|
"epoch": 0.6455316142705758,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004965003361453782,
|
|
"loss": 6.0759,
|
|
"mean_token_accuracy": 0.1546678811311722,
|
|
"num_tokens": 13654093.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 6.262458944320679,
|
|
"epoch": 0.6459731543624161,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004964948013032132,
|
|
"loss": 6.1199,
|
|
"mean_token_accuracy": 0.14781120419502258,
|
|
"num_tokens": 13663095.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 6.282963609695434,
|
|
"epoch": 0.6464146944542565,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000496489262122091,
|
|
"loss": 6.1553,
|
|
"mean_token_accuracy": 0.14864987134933472,
|
|
"num_tokens": 13673624.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 6.259463548660278,
|
|
"epoch": 0.6468562345460968,
|
|
"grad_norm": 7.4375,
|
|
"learning_rate": 0.0004964837186021201,
|
|
"loss": 6.0348,
|
|
"mean_token_accuracy": 0.15352552831172944,
|
|
"num_tokens": 13683145.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 6.175587797164917,
|
|
"epoch": 0.6472977746379371,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.0004964781707434093,
|
|
"loss": 6.0329,
|
|
"mean_token_accuracy": 0.15152520984411239,
|
|
"num_tokens": 13691963.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 6.037362384796142,
|
|
"epoch": 0.6477393147297774,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004964726185460669,
|
|
"loss": 5.9579,
|
|
"mean_token_accuracy": 0.1579597070813179,
|
|
"num_tokens": 13700926.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 6.1612313747406,
|
|
"epoch": 0.6481808548216178,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004964670620102019,
|
|
"loss": 6.1494,
|
|
"mean_token_accuracy": 0.14145292192697526,
|
|
"num_tokens": 13709824.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 6.25114688873291,
|
|
"epoch": 0.6486223949134582,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004964615011359231,
|
|
"loss": 6.0579,
|
|
"mean_token_accuracy": 0.151515481621027,
|
|
"num_tokens": 13718789.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 6.252131652832031,
|
|
"epoch": 0.6490639350052985,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004964559359233395,
|
|
"loss": 6.0618,
|
|
"mean_token_accuracy": 0.15075841844081878,
|
|
"num_tokens": 13728180.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 6.1781408309936525,
|
|
"epoch": 0.6495054750971389,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004964503663725601,
|
|
"loss": 6.167,
|
|
"mean_token_accuracy": 0.14491574019193648,
|
|
"num_tokens": 13737819.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 6.216016721725464,
|
|
"epoch": 0.6499470151889791,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004964447924836938,
|
|
"loss": 6.1369,
|
|
"mean_token_accuracy": 0.149229533970356,
|
|
"num_tokens": 13747519.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 6.343541479110717,
|
|
"epoch": 0.6503885552808195,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.0004964392142568501,
|
|
"loss": 6.1307,
|
|
"mean_token_accuracy": 0.14465169459581376,
|
|
"num_tokens": 13757821.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 6.229691362380981,
|
|
"epoch": 0.6508300953726598,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004964336316921381,
|
|
"loss": 5.9414,
|
|
"mean_token_accuracy": 0.15893535315990448,
|
|
"num_tokens": 13766560.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 6.181404256820679,
|
|
"epoch": 0.6512716354645002,
|
|
"grad_norm": 3.53125,
|
|
"learning_rate": 0.0004964280447896672,
|
|
"loss": 5.9699,
|
|
"mean_token_accuracy": 0.1556891031563282,
|
|
"num_tokens": 13775560.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 6.093255043029785,
|
|
"epoch": 0.6517131755563406,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004964224535495468,
|
|
"loss": 6.0828,
|
|
"mean_token_accuracy": 0.14826790988445282,
|
|
"num_tokens": 13784391.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 6.163384532928466,
|
|
"epoch": 0.6521547156481808,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004964168579718864,
|
|
"loss": 6.047,
|
|
"mean_token_accuracy": 0.15087808892130852,
|
|
"num_tokens": 13794008.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 6.277848768234253,
|
|
"epoch": 0.6525962557400212,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004964112580567959,
|
|
"loss": 6.0799,
|
|
"mean_token_accuracy": 0.14790103286504747,
|
|
"num_tokens": 13804321.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 6.251108884811401,
|
|
"epoch": 0.6530377958318615,
|
|
"grad_norm": 10.625,
|
|
"learning_rate": 0.0004964056538043845,
|
|
"loss": 6.0947,
|
|
"mean_token_accuracy": 0.1505176082253456,
|
|
"num_tokens": 13813492.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 6.119813537597656,
|
|
"epoch": 0.6534793359237019,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004964000452147624,
|
|
"loss": 6.07,
|
|
"mean_token_accuracy": 0.1533577561378479,
|
|
"num_tokens": 13822471.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 6.178601408004761,
|
|
"epoch": 0.6539208760155422,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004963944322880394,
|
|
"loss": 6.1343,
|
|
"mean_token_accuracy": 0.14370774999260902,
|
|
"num_tokens": 13832789.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 6.242937612533569,
|
|
"epoch": 0.6543624161073825,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004963888150243253,
|
|
"loss": 6.1002,
|
|
"mean_token_accuracy": 0.14843902736902237,
|
|
"num_tokens": 13842230.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 6.277557611465454,
|
|
"epoch": 0.6548039561992229,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004963831934237302,
|
|
"loss": 6.0289,
|
|
"mean_token_accuracy": 0.15670600831508635,
|
|
"num_tokens": 13851542.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 6.187560272216797,
|
|
"epoch": 0.6552454962910632,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004963775674863643,
|
|
"loss": 6.0288,
|
|
"mean_token_accuracy": 0.1488627851009369,
|
|
"num_tokens": 13860753.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 6.172817325592041,
|
|
"epoch": 0.6556870363829036,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004963719372123378,
|
|
"loss": 6.0395,
|
|
"mean_token_accuracy": 0.15519573241472245,
|
|
"num_tokens": 13870133.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 6.218771266937256,
|
|
"epoch": 0.6561285764747439,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004963663026017609,
|
|
"loss": 6.1058,
|
|
"mean_token_accuracy": 0.15374775975942612,
|
|
"num_tokens": 13879086.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 6.224050903320313,
|
|
"epoch": 0.6565701165665843,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004963606636547441,
|
|
"loss": 6.0514,
|
|
"mean_token_accuracy": 0.1545367494225502,
|
|
"num_tokens": 13888706.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 6.183874034881592,
|
|
"epoch": 0.6570116566584245,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004963550203713976,
|
|
"loss": 6.0948,
|
|
"mean_token_accuracy": 0.15013214200735092,
|
|
"num_tokens": 13897455.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 6.207463502883911,
|
|
"epoch": 0.6574531967502649,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004963493727518323,
|
|
"loss": 6.0951,
|
|
"mean_token_accuracy": 0.15092161446809768,
|
|
"num_tokens": 13907697.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 6.19521541595459,
|
|
"epoch": 0.6578947368421053,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004963437207961585,
|
|
"loss": 6.1067,
|
|
"mean_token_accuracy": 0.15172283574938775,
|
|
"num_tokens": 13917124.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 6.222240877151489,
|
|
"epoch": 0.6583362769339456,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004963380645044874,
|
|
"loss": 6.0407,
|
|
"mean_token_accuracy": 0.15824299454689025,
|
|
"num_tokens": 13926434.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 6.138532924652099,
|
|
"epoch": 0.658777817025786,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004963324038769292,
|
|
"loss": 6.0144,
|
|
"mean_token_accuracy": 0.1565467596054077,
|
|
"num_tokens": 13934883.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 6.204624605178833,
|
|
"epoch": 0.6592193571176262,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004963267389135953,
|
|
"loss": 6.0827,
|
|
"mean_token_accuracy": 0.15051436573266982,
|
|
"num_tokens": 13944514.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 6.168144702911377,
|
|
"epoch": 0.6596608972094666,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004963210696145964,
|
|
"loss": 6.0078,
|
|
"mean_token_accuracy": 0.1553253263235092,
|
|
"num_tokens": 13953434.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 6.130171871185302,
|
|
"epoch": 0.6601024373013069,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004963153959800436,
|
|
"loss": 6.0286,
|
|
"mean_token_accuracy": 0.16009896844625474,
|
|
"num_tokens": 13962493.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 6.192154836654663,
|
|
"epoch": 0.6605439773931473,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000496309718010048,
|
|
"loss": 6.0678,
|
|
"mean_token_accuracy": 0.15374763309955597,
|
|
"num_tokens": 13971193.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 6.266092729568482,
|
|
"epoch": 0.6609855174849877,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004963040357047209,
|
|
"loss": 6.1029,
|
|
"mean_token_accuracy": 0.1511322468519211,
|
|
"num_tokens": 13981829.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 6.223195028305054,
|
|
"epoch": 0.661427057576828,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004962983490641737,
|
|
"loss": 6.035,
|
|
"mean_token_accuracy": 0.15042887330055238,
|
|
"num_tokens": 13990262.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 6.1686547756195065,
|
|
"epoch": 0.6618685976686683,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004962926580885177,
|
|
"loss": 6.0737,
|
|
"mean_token_accuracy": 0.1577219158411026,
|
|
"num_tokens": 14000100.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 6.214493942260742,
|
|
"epoch": 0.6623101377605086,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004962869627778642,
|
|
"loss": 6.1151,
|
|
"mean_token_accuracy": 0.15706808865070343,
|
|
"num_tokens": 14009330.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 6.23420147895813,
|
|
"epoch": 0.662751677852349,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004962812631323252,
|
|
"loss": 6.0684,
|
|
"mean_token_accuracy": 0.15241270512342453,
|
|
"num_tokens": 14018109.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 6.213022470474243,
|
|
"epoch": 0.6631932179441893,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.000496275559152012,
|
|
"loss": 5.9906,
|
|
"mean_token_accuracy": 0.15551604926586152,
|
|
"num_tokens": 14027318.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 6.2161946296691895,
|
|
"epoch": 0.6636347580360297,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004962698508370365,
|
|
"loss": 6.1051,
|
|
"mean_token_accuracy": 0.15343084782361985,
|
|
"num_tokens": 14037061.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 6.179489421844482,
|
|
"epoch": 0.6640762981278701,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004962641381875103,
|
|
"loss": 6.0699,
|
|
"mean_token_accuracy": 0.14859853237867354,
|
|
"num_tokens": 14046008.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 6.203066730499268,
|
|
"epoch": 0.6645178382197103,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004962584212035456,
|
|
"loss": 6.0769,
|
|
"mean_token_accuracy": 0.14658914059400557,
|
|
"num_tokens": 14054535.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 6.205629682540893,
|
|
"epoch": 0.6649593783115507,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004962526998852543,
|
|
"loss": 6.0521,
|
|
"mean_token_accuracy": 0.1541662707924843,
|
|
"num_tokens": 14063680.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 6.24108362197876,
|
|
"epoch": 0.665400918403391,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004962469742327483,
|
|
"loss": 6.0845,
|
|
"mean_token_accuracy": 0.1557173639535904,
|
|
"num_tokens": 14072206.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 6.241954326629639,
|
|
"epoch": 0.6658424584952314,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00049624124424614,
|
|
"loss": 6.0976,
|
|
"mean_token_accuracy": 0.15491850823163986,
|
|
"num_tokens": 14081943.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 6.207191371917725,
|
|
"epoch": 0.6662839985870717,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004962355099255415,
|
|
"loss": 6.0566,
|
|
"mean_token_accuracy": 0.1543470561504364,
|
|
"num_tokens": 14091695.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 6.092154788970947,
|
|
"epoch": 0.666725538678912,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004962297712710653,
|
|
"loss": 5.9816,
|
|
"mean_token_accuracy": 0.15961627513170243,
|
|
"num_tokens": 14100811.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 6.1884294033050535,
|
|
"epoch": 0.6671670787707524,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004962240282828236,
|
|
"loss": 6.1548,
|
|
"mean_token_accuracy": 0.14150830507278442,
|
|
"num_tokens": 14109818.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 6.2431878566741945,
|
|
"epoch": 0.6676086188625927,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.000496218280960929,
|
|
"loss": 6.0784,
|
|
"mean_token_accuracy": 0.15114578008651733,
|
|
"num_tokens": 14119811.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 6.316728115081787,
|
|
"epoch": 0.6680501589544331,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004962125293054941,
|
|
"loss": 6.0431,
|
|
"mean_token_accuracy": 0.1584528237581253,
|
|
"num_tokens": 14128963.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 6.191557216644287,
|
|
"epoch": 0.6684916990462734,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004962067733166317,
|
|
"loss": 6.0948,
|
|
"mean_token_accuracy": 0.14102213308215142,
|
|
"num_tokens": 14138532.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 6.112533760070801,
|
|
"epoch": 0.6689332391381138,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004962010129944542,
|
|
"loss": 6.0604,
|
|
"mean_token_accuracy": 0.15434442609548568,
|
|
"num_tokens": 14148107.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 6.277549076080322,
|
|
"epoch": 0.669374779229954,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.0004961952483390747,
|
|
"loss": 6.1156,
|
|
"mean_token_accuracy": 0.1456269219517708,
|
|
"num_tokens": 14158823.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 6.2724374294281,
|
|
"epoch": 0.6698163193217944,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004961894793506062,
|
|
"loss": 6.0665,
|
|
"mean_token_accuracy": 0.15882535129785538,
|
|
"num_tokens": 14168147.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 6.207061910629273,
|
|
"epoch": 0.6702578594136348,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004961837060291615,
|
|
"loss": 6.0889,
|
|
"mean_token_accuracy": 0.15001036822795868,
|
|
"num_tokens": 14177123.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 6.213112258911133,
|
|
"epoch": 0.6706993995054751,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004961779283748538,
|
|
"loss": 6.0762,
|
|
"mean_token_accuracy": 0.14930718392133713,
|
|
"num_tokens": 14186614.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 6.258604288101196,
|
|
"epoch": 0.6711409395973155,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004961721463877963,
|
|
"loss": 6.0879,
|
|
"mean_token_accuracy": 0.147329892963171,
|
|
"num_tokens": 14195310.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 6.242795372009278,
|
|
"epoch": 0.6715824796891557,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004961663600681023,
|
|
"loss": 6.0477,
|
|
"mean_token_accuracy": 0.14992639869451524,
|
|
"num_tokens": 14204321.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 6.1641522407531735,
|
|
"epoch": 0.6720240197809961,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000496160569415885,
|
|
"loss": 6.0743,
|
|
"mean_token_accuracy": 0.14891463667154312,
|
|
"num_tokens": 14213615.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 6.224883890151977,
|
|
"epoch": 0.6724655598728364,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004961547744312579,
|
|
"loss": 5.9574,
|
|
"mean_token_accuracy": 0.15733491480350495,
|
|
"num_tokens": 14222715.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 6.1939027309417725,
|
|
"epoch": 0.6729070999646768,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004961489751143346,
|
|
"loss": 6.0857,
|
|
"mean_token_accuracy": 0.1541801318526268,
|
|
"num_tokens": 14232117.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 6.13014850616455,
|
|
"epoch": 0.6733486400565172,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004961431714652287,
|
|
"loss": 5.9731,
|
|
"mean_token_accuracy": 0.16042798459529878,
|
|
"num_tokens": 14240606.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 6.220015954971314,
|
|
"epoch": 0.6737901801483575,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004961373634840538,
|
|
"loss": 6.073,
|
|
"mean_token_accuracy": 0.14794691205024718,
|
|
"num_tokens": 14249844.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 6.200179195404052,
|
|
"epoch": 0.6742317202401978,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004961315511709237,
|
|
"loss": 6.0879,
|
|
"mean_token_accuracy": 0.15268362164497376,
|
|
"num_tokens": 14259231.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 6.250634336471558,
|
|
"epoch": 0.6746732603320381,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004961257345259524,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.15392789170145987,
|
|
"num_tokens": 14268508.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 6.212841749191284,
|
|
"epoch": 0.6751148004238785,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.0004961199135492535,
|
|
"loss": 6.0158,
|
|
"mean_token_accuracy": 0.1586117058992386,
|
|
"num_tokens": 14278057.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 6.137183141708374,
|
|
"epoch": 0.6755563405157188,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004961140882409414,
|
|
"loss": 6.1053,
|
|
"mean_token_accuracy": 0.14983683377504348,
|
|
"num_tokens": 14287225.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 6.176516056060791,
|
|
"epoch": 0.6759978806075592,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00049610825860113,
|
|
"loss": 6.0602,
|
|
"mean_token_accuracy": 0.15462789237499236,
|
|
"num_tokens": 14296529.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 6.218318700790405,
|
|
"epoch": 0.6764394206993996,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004961024246299336,
|
|
"loss": 5.9889,
|
|
"mean_token_accuracy": 0.15721210241317748,
|
|
"num_tokens": 14305675.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 6.232691097259521,
|
|
"epoch": 0.6768809607912398,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004960965863274665,
|
|
"loss": 5.9634,
|
|
"mean_token_accuracy": 0.15535827577114106,
|
|
"num_tokens": 14313632.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 6.118216848373413,
|
|
"epoch": 0.6773225008830802,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.000496090743693843,
|
|
"loss": 6.0886,
|
|
"mean_token_accuracy": 0.15240846276283265,
|
|
"num_tokens": 14323353.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 6.241943311691284,
|
|
"epoch": 0.6777640409749205,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004960848967291775,
|
|
"loss": 6.064,
|
|
"mean_token_accuracy": 0.1510762870311737,
|
|
"num_tokens": 14331953.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 6.291945219039917,
|
|
"epoch": 0.6782055810667609,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004960790454335846,
|
|
"loss": 6.1253,
|
|
"mean_token_accuracy": 0.1440570555627346,
|
|
"num_tokens": 14342456.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 6.166342258453369,
|
|
"epoch": 0.6786471211586012,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.000496073189807179,
|
|
"loss": 5.9019,
|
|
"mean_token_accuracy": 0.1624265655875206,
|
|
"num_tokens": 14351013.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 6.187205171585083,
|
|
"epoch": 0.6790886612504415,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004960673298500753,
|
|
"loss": 6.18,
|
|
"mean_token_accuracy": 0.14918676763772964,
|
|
"num_tokens": 14360887.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 6.226143932342529,
|
|
"epoch": 0.6795302013422819,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004960614655623883,
|
|
"loss": 6.0989,
|
|
"mean_token_accuracy": 0.148998162150383,
|
|
"num_tokens": 14370510.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 6.229071617126465,
|
|
"epoch": 0.6799717414341222,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.000496055596944233,
|
|
"loss": 6.0895,
|
|
"mean_token_accuracy": 0.1563186064362526,
|
|
"num_tokens": 14379315.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 6.21696834564209,
|
|
"epoch": 0.6804132815259626,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004960497239957243,
|
|
"loss": 6.0804,
|
|
"mean_token_accuracy": 0.14839715361595154,
|
|
"num_tokens": 14388537.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 6.247610473632813,
|
|
"epoch": 0.6808548216178029,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004960438467169772,
|
|
"loss": 6.1075,
|
|
"mean_token_accuracy": 0.14529118984937667,
|
|
"num_tokens": 14398347.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 6.288898611068726,
|
|
"epoch": 0.6812963617096433,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004960379651081068,
|
|
"loss": 6.0266,
|
|
"mean_token_accuracy": 0.1562356874346733,
|
|
"num_tokens": 14407304.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 6.2475076675415036,
|
|
"epoch": 0.6817379018014835,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004960320791692283,
|
|
"loss": 6.0411,
|
|
"mean_token_accuracy": 0.15162470787763596,
|
|
"num_tokens": 14416641.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 6.248139762878418,
|
|
"epoch": 0.6821794418933239,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004960261889004572,
|
|
"loss": 6.1653,
|
|
"mean_token_accuracy": 0.14672458916902542,
|
|
"num_tokens": 14426095.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 6.227323007583618,
|
|
"epoch": 0.6826209819851643,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004960202943019088,
|
|
"loss": 6.0558,
|
|
"mean_token_accuracy": 0.15345034152269363,
|
|
"num_tokens": 14434563.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 6.118875980377197,
|
|
"epoch": 0.6830625220770046,
|
|
"grad_norm": 4.3125,
|
|
"learning_rate": 0.0004960143953736984,
|
|
"loss": 5.9894,
|
|
"mean_token_accuracy": 0.15708500742912293,
|
|
"num_tokens": 14444319.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 6.229998683929443,
|
|
"epoch": 0.683504062168845,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004960084921159419,
|
|
"loss": 6.0232,
|
|
"mean_token_accuracy": 0.15335571765899658,
|
|
"num_tokens": 14453381.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 6.130149507522583,
|
|
"epoch": 0.6839456022606852,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004960025845287546,
|
|
"loss": 6.0223,
|
|
"mean_token_accuracy": 0.15564830154180526,
|
|
"num_tokens": 14462660.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 6.125526428222656,
|
|
"epoch": 0.6843871423525256,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004959966726122523,
|
|
"loss": 5.9577,
|
|
"mean_token_accuracy": 0.16211079359054564,
|
|
"num_tokens": 14471820.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 6.218053960800171,
|
|
"epoch": 0.6848286824443659,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.000495990756366551,
|
|
"loss": 6.1168,
|
|
"mean_token_accuracy": 0.1515028163790703,
|
|
"num_tokens": 14481663.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 6.257606124877929,
|
|
"epoch": 0.6852702225362063,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004959848357917664,
|
|
"loss": 6.1271,
|
|
"mean_token_accuracy": 0.147647662460804,
|
|
"num_tokens": 14491515.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 6.142368125915527,
|
|
"epoch": 0.6857117626280467,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004959789108880145,
|
|
"loss": 5.9671,
|
|
"mean_token_accuracy": 0.14912231415510177,
|
|
"num_tokens": 14500852.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 6.136193132400512,
|
|
"epoch": 0.686153302719887,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004959729816554115,
|
|
"loss": 6.0328,
|
|
"mean_token_accuracy": 0.15739069730043412,
|
|
"num_tokens": 14509771.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 6.211749124526977,
|
|
"epoch": 0.6865948428117273,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004959670480940734,
|
|
"loss": 6.0121,
|
|
"mean_token_accuracy": 0.16098477467894554,
|
|
"num_tokens": 14519377.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 6.21663122177124,
|
|
"epoch": 0.6870363829035676,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.0004959611102041165,
|
|
"loss": 6.0525,
|
|
"mean_token_accuracy": 0.15086856484413147,
|
|
"num_tokens": 14528998.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 6.172790050506592,
|
|
"epoch": 0.687477922995408,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004959551679856571,
|
|
"loss": 6.0792,
|
|
"mean_token_accuracy": 0.15509206503629686,
|
|
"num_tokens": 14538153.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 6.196965932846069,
|
|
"epoch": 0.6879194630872483,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004959492214388117,
|
|
"loss": 6.0166,
|
|
"mean_token_accuracy": 0.1575303018093109,
|
|
"num_tokens": 14547631.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 6.256254625320435,
|
|
"epoch": 0.6883610031790887,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004959432705636968,
|
|
"loss": 5.9797,
|
|
"mean_token_accuracy": 0.15786290168762207,
|
|
"num_tokens": 14557685.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 6.231467437744141,
|
|
"epoch": 0.688802543270929,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004959373153604287,
|
|
"loss": 6.0993,
|
|
"mean_token_accuracy": 0.15257465690374375,
|
|
"num_tokens": 14567360.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 6.125985431671142,
|
|
"epoch": 0.6892440833627693,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004959313558291243,
|
|
"loss": 6.0254,
|
|
"mean_token_accuracy": 0.15141796320676804,
|
|
"num_tokens": 14576916.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 6.101062536239624,
|
|
"epoch": 0.6896856234546097,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004959253919699004,
|
|
"loss": 5.9499,
|
|
"mean_token_accuracy": 0.16243618130683898,
|
|
"num_tokens": 14586716.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 6.2262571334838865,
|
|
"epoch": 0.69012716354645,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004959194237828735,
|
|
"loss": 5.9998,
|
|
"mean_token_accuracy": 0.153834930062294,
|
|
"num_tokens": 14595690.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 6.181614828109741,
|
|
"epoch": 0.6905687036382904,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004959134512681609,
|
|
"loss": 6.0546,
|
|
"mean_token_accuracy": 0.14944540560245514,
|
|
"num_tokens": 14605481.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 6.180599164962769,
|
|
"epoch": 0.6910102437301306,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004959074744258794,
|
|
"loss": 6.116,
|
|
"mean_token_accuracy": 0.15085441544651984,
|
|
"num_tokens": 14615242.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 6.201753234863281,
|
|
"epoch": 0.691451783821971,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004959014932561461,
|
|
"loss": 5.9454,
|
|
"mean_token_accuracy": 0.16299830228090287,
|
|
"num_tokens": 14624343.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 6.127270126342774,
|
|
"epoch": 0.6918933239138114,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004958955077590782,
|
|
"loss": 5.9414,
|
|
"mean_token_accuracy": 0.16462224572896958,
|
|
"num_tokens": 14633014.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 6.168978500366211,
|
|
"epoch": 0.6923348640056517,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004958895179347929,
|
|
"loss": 6.0763,
|
|
"mean_token_accuracy": 0.1522584706544876,
|
|
"num_tokens": 14642796.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 6.25012173652649,
|
|
"epoch": 0.6927764040974921,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004958835237834075,
|
|
"loss": 6.1059,
|
|
"mean_token_accuracy": 0.14263201132416725,
|
|
"num_tokens": 14652388.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 6.271516036987305,
|
|
"epoch": 0.6932179441893324,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004958775253050396,
|
|
"loss": 6.0596,
|
|
"mean_token_accuracy": 0.15313490480184555,
|
|
"num_tokens": 14661219.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 6.182176208496093,
|
|
"epoch": 0.6936594842811727,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004958715224998066,
|
|
"loss": 6.0727,
|
|
"mean_token_accuracy": 0.15574069023132325,
|
|
"num_tokens": 14670878.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 6.181418514251709,
|
|
"epoch": 0.694101024373013,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004958655153678261,
|
|
"loss": 6.0899,
|
|
"mean_token_accuracy": 0.1497741535305977,
|
|
"num_tokens": 14680893.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 6.235378074645996,
|
|
"epoch": 0.6945425644648534,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004958595039092156,
|
|
"loss": 6.0022,
|
|
"mean_token_accuracy": 0.15413426607847214,
|
|
"num_tokens": 14689249.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 6.23575348854065,
|
|
"epoch": 0.6949841045566938,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004958534881240932,
|
|
"loss": 6.0297,
|
|
"mean_token_accuracy": 0.15611442476511,
|
|
"num_tokens": 14698724.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 6.180769920349121,
|
|
"epoch": 0.6954256446485341,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004958474680125766,
|
|
"loss": 5.9864,
|
|
"mean_token_accuracy": 0.15255807638168334,
|
|
"num_tokens": 14707756.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 6.145475435256958,
|
|
"epoch": 0.6958671847403745,
|
|
"grad_norm": 5.15625,
|
|
"learning_rate": 0.0004958414435747837,
|
|
"loss": 6.027,
|
|
"mean_token_accuracy": 0.1529964953660965,
|
|
"num_tokens": 14717416.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 6.201198482513428,
|
|
"epoch": 0.6963087248322147,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004958354148108324,
|
|
"loss": 6.0707,
|
|
"mean_token_accuracy": 0.16048150211572648,
|
|
"num_tokens": 14727321.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 6.18621597290039,
|
|
"epoch": 0.6967502649240551,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.000495829381720841,
|
|
"loss": 5.9491,
|
|
"mean_token_accuracy": 0.166436567902565,
|
|
"num_tokens": 14736298.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 6.208941507339477,
|
|
"epoch": 0.6971918050158954,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004958233443049275,
|
|
"loss": 6.0093,
|
|
"mean_token_accuracy": 0.14525908082723618,
|
|
"num_tokens": 14745893.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 6.208337497711182,
|
|
"epoch": 0.6976333451077358,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004958173025632103,
|
|
"loss": 6.0529,
|
|
"mean_token_accuracy": 0.14887382239103317,
|
|
"num_tokens": 14755277.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 6.2192895889282225,
|
|
"epoch": 0.6980748851995762,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004958112564958079,
|
|
"loss": 6.1697,
|
|
"mean_token_accuracy": 0.14462502300739288,
|
|
"num_tokens": 14764369.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 6.16321964263916,
|
|
"epoch": 0.6985164252914164,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004958052061028385,
|
|
"loss": 6.0086,
|
|
"mean_token_accuracy": 0.16280398070812224,
|
|
"num_tokens": 14772970.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 6.204917478561401,
|
|
"epoch": 0.6989579653832568,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004957991513844205,
|
|
"loss": 6.0686,
|
|
"mean_token_accuracy": 0.15557245910167694,
|
|
"num_tokens": 14782862.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 6.263249015808105,
|
|
"epoch": 0.6993995054750971,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004957930923406729,
|
|
"loss": 6.0712,
|
|
"mean_token_accuracy": 0.15803339332342148,
|
|
"num_tokens": 14792042.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 6.223450803756714,
|
|
"epoch": 0.6998410455669375,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004957870289717142,
|
|
"loss": 6.0063,
|
|
"mean_token_accuracy": 0.1534290134906769,
|
|
"num_tokens": 14801032.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 6.15586667060852,
|
|
"epoch": 0.7002825856587778,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004957809612776631,
|
|
"loss": 6.0196,
|
|
"mean_token_accuracy": 0.1556229293346405,
|
|
"num_tokens": 14810594.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 6.19131817817688,
|
|
"epoch": 0.7007241257506182,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004957748892586384,
|
|
"loss": 6.1236,
|
|
"mean_token_accuracy": 0.14985551685094833,
|
|
"num_tokens": 14820570.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 6.108098936080933,
|
|
"epoch": 0.7011656658424585,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004957688129147594,
|
|
"loss": 5.9444,
|
|
"mean_token_accuracy": 0.16571446657180786,
|
|
"num_tokens": 14830078.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 6.1342144966125485,
|
|
"epoch": 0.7016072059342988,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004957627322461448,
|
|
"loss": 6.0137,
|
|
"mean_token_accuracy": 0.15698135048151016,
|
|
"num_tokens": 14839974.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 6.232937955856324,
|
|
"epoch": 0.7020487460261392,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004957566472529139,
|
|
"loss": 6.1025,
|
|
"mean_token_accuracy": 0.14428324848413468,
|
|
"num_tokens": 14849551.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 6.2377479553222654,
|
|
"epoch": 0.7024902861179795,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004957505579351858,
|
|
"loss": 6.0336,
|
|
"mean_token_accuracy": 0.1549524500966072,
|
|
"num_tokens": 14859011.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 6.175362968444825,
|
|
"epoch": 0.7029318262098199,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004957444642930798,
|
|
"loss": 5.9942,
|
|
"mean_token_accuracy": 0.15593235790729523,
|
|
"num_tokens": 14867948.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 6.191630506515503,
|
|
"epoch": 0.7033733663016601,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004957383663267152,
|
|
"loss": 6.051,
|
|
"mean_token_accuracy": 0.15497976690530776,
|
|
"num_tokens": 14877233.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 6.204564094543457,
|
|
"epoch": 0.7038149063935005,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004957322640362118,
|
|
"loss": 6.069,
|
|
"mean_token_accuracy": 0.14801982194185256,
|
|
"num_tokens": 14887439.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 6.322771501541138,
|
|
"epoch": 0.7042564464853409,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004957261574216887,
|
|
"loss": 6.1465,
|
|
"mean_token_accuracy": 0.14907680749893187,
|
|
"num_tokens": 14897064.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 6.244523668289185,
|
|
"epoch": 0.7046979865771812,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004957200464832656,
|
|
"loss": 6.1031,
|
|
"mean_token_accuracy": 0.14721770584583282,
|
|
"num_tokens": 14907054.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 6.220310115814209,
|
|
"epoch": 0.7051395266690216,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004957139312210626,
|
|
"loss": 6.0558,
|
|
"mean_token_accuracy": 0.15061642229557037,
|
|
"num_tokens": 14916969.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 6.189560461044311,
|
|
"epoch": 0.7055810667608619,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.000495707811635199,
|
|
"loss": 6.0849,
|
|
"mean_token_accuracy": 0.1534519761800766,
|
|
"num_tokens": 14926404.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 6.195728206634522,
|
|
"epoch": 0.7060226068527022,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004957016877257949,
|
|
"loss": 6.0637,
|
|
"mean_token_accuracy": 0.14685604795813562,
|
|
"num_tokens": 14935693.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 6.2307899475097654,
|
|
"epoch": 0.7064641469445425,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004956955594929704,
|
|
"loss": 6.01,
|
|
"mean_token_accuracy": 0.15188159197568893,
|
|
"num_tokens": 14945147.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 6.178026580810547,
|
|
"epoch": 0.7069056870363829,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004956894269368454,
|
|
"loss": 6.0336,
|
|
"mean_token_accuracy": 0.15496408343315124,
|
|
"num_tokens": 14954022.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 6.117526531219482,
|
|
"epoch": 0.7073472271282233,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004956832900575399,
|
|
"loss": 6.0382,
|
|
"mean_token_accuracy": 0.15371241867542268,
|
|
"num_tokens": 14962977.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 6.195847368240356,
|
|
"epoch": 0.7077887672200636,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004956771488551742,
|
|
"loss": 6.0909,
|
|
"mean_token_accuracy": 0.14825759455561638,
|
|
"num_tokens": 14973420.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 6.267194128036499,
|
|
"epoch": 0.708230307311904,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004956710033298689,
|
|
"loss": 6.035,
|
|
"mean_token_accuracy": 0.15323473662137985,
|
|
"num_tokens": 14981762.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 6.320011281967163,
|
|
"epoch": 0.7086718474037442,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000495664853481744,
|
|
"loss": 6.1254,
|
|
"mean_token_accuracy": 0.1446717455983162,
|
|
"num_tokens": 14991449.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 6.248271751403808,
|
|
"epoch": 0.7091133874955846,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004956586993109201,
|
|
"loss": 6.0381,
|
|
"mean_token_accuracy": 0.15330882221460343,
|
|
"num_tokens": 15000802.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 6.082692623138428,
|
|
"epoch": 0.7095549275874249,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.0004956525408175179,
|
|
"loss": 6.0586,
|
|
"mean_token_accuracy": 0.15180643945932387,
|
|
"num_tokens": 15010580.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 6.142378139495849,
|
|
"epoch": 0.7099964676792653,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004956463780016578,
|
|
"loss": 6.0869,
|
|
"mean_token_accuracy": 0.14902941286563873,
|
|
"num_tokens": 15020059.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 6.221126222610474,
|
|
"epoch": 0.7104380077711057,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004956402108634607,
|
|
"loss": 6.0477,
|
|
"mean_token_accuracy": 0.152384951710701,
|
|
"num_tokens": 15030268.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 6.179953908920288,
|
|
"epoch": 0.7108795478629459,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004956340394030473,
|
|
"loss": 6.0078,
|
|
"mean_token_accuracy": 0.1581128403544426,
|
|
"num_tokens": 15038865.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 6.272174596786499,
|
|
"epoch": 0.7113210879547863,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004956278636205386,
|
|
"loss": 6.1555,
|
|
"mean_token_accuracy": 0.14396643489599228,
|
|
"num_tokens": 15048427.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 6.2368580341339115,
|
|
"epoch": 0.7117626280466266,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004956216835160556,
|
|
"loss": 6.0152,
|
|
"mean_token_accuracy": 0.16587988734245301,
|
|
"num_tokens": 15057366.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 6.218137741088867,
|
|
"epoch": 0.712204168138467,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.0004956154990897191,
|
|
"loss": 6.0775,
|
|
"mean_token_accuracy": 0.14875958263874053,
|
|
"num_tokens": 15067098.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 6.218372488021851,
|
|
"epoch": 0.7126457082303073,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004956093103416505,
|
|
"loss": 6.062,
|
|
"mean_token_accuracy": 0.15535494238138198,
|
|
"num_tokens": 15075734.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 6.20798077583313,
|
|
"epoch": 0.7130872483221476,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004956031172719711,
|
|
"loss": 6.1019,
|
|
"mean_token_accuracy": 0.15078829303383828,
|
|
"num_tokens": 15084625.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 6.084878635406494,
|
|
"epoch": 0.713528788413988,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004955969198808021,
|
|
"loss": 5.9352,
|
|
"mean_token_accuracy": 0.16838667690753936,
|
|
"num_tokens": 15093256.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 6.141441059112549,
|
|
"epoch": 0.7139703285058283,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004955907181682648,
|
|
"loss": 5.9937,
|
|
"mean_token_accuracy": 0.15782455503940582,
|
|
"num_tokens": 15103175.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 6.172451734542847,
|
|
"epoch": 0.7144118685976687,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004955845121344809,
|
|
"loss": 6.0842,
|
|
"mean_token_accuracy": 0.154188871383667,
|
|
"num_tokens": 15112789.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 6.190401649475097,
|
|
"epoch": 0.714853408689509,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004955783017795717,
|
|
"loss": 6.1132,
|
|
"mean_token_accuracy": 0.15388823449611663,
|
|
"num_tokens": 15121869.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 6.15615177154541,
|
|
"epoch": 0.7152949487813494,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000495572087103659,
|
|
"loss": 5.9973,
|
|
"mean_token_accuracy": 0.15638259947299957,
|
|
"num_tokens": 15131441.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 6.16906967163086,
|
|
"epoch": 0.7157364888731896,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004955658681068647,
|
|
"loss": 6.0608,
|
|
"mean_token_accuracy": 0.1528923600912094,
|
|
"num_tokens": 15140641.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 6.263287353515625,
|
|
"epoch": 0.71617802896503,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004955596447893105,
|
|
"loss": 6.0468,
|
|
"mean_token_accuracy": 0.1551143765449524,
|
|
"num_tokens": 15150073.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 6.11682391166687,
|
|
"epoch": 0.7166195690568704,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004955534171511181,
|
|
"loss": 5.8063,
|
|
"mean_token_accuracy": 0.17062758654356003,
|
|
"num_tokens": 15159879.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 6.120118474960327,
|
|
"epoch": 0.7170611091487107,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00049554718519241,
|
|
"loss": 6.0203,
|
|
"mean_token_accuracy": 0.15730814039707183,
|
|
"num_tokens": 15168316.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 6.1357043266296385,
|
|
"epoch": 0.7175026492405511,
|
|
"grad_norm": 5.46875,
|
|
"learning_rate": 0.0004955409489133078,
|
|
"loss": 6.0343,
|
|
"mean_token_accuracy": 0.1505425527691841,
|
|
"num_tokens": 15176700.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 6.227250671386718,
|
|
"epoch": 0.7179441893323913,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004955347083139338,
|
|
"loss": 6.0417,
|
|
"mean_token_accuracy": 0.1585338830947876,
|
|
"num_tokens": 15185997.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 6.14000449180603,
|
|
"epoch": 0.7183857294242317,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004955284633944104,
|
|
"loss": 6.0411,
|
|
"mean_token_accuracy": 0.15232947319746018,
|
|
"num_tokens": 15195341.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 6.185124254226684,
|
|
"epoch": 0.718827269516072,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004955222141548597,
|
|
"loss": 6.0902,
|
|
"mean_token_accuracy": 0.15339289903640746,
|
|
"num_tokens": 15205501.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 6.161205530166626,
|
|
"epoch": 0.7192688096079124,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004955159605954043,
|
|
"loss": 6.0393,
|
|
"mean_token_accuracy": 0.15205711349844933,
|
|
"num_tokens": 15214778.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 6.311834096908569,
|
|
"epoch": 0.7197103496997528,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004955097027161666,
|
|
"loss": 6.0639,
|
|
"mean_token_accuracy": 0.15708200111985207,
|
|
"num_tokens": 15224201.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 6.216530847549438,
|
|
"epoch": 0.7201518897915931,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004955034405172693,
|
|
"loss": 6.0027,
|
|
"mean_token_accuracy": 0.16143639236688614,
|
|
"num_tokens": 15233472.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 6.148335742950439,
|
|
"epoch": 0.7205934298834334,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.000495497173998835,
|
|
"loss": 6.0696,
|
|
"mean_token_accuracy": 0.15243514031171798,
|
|
"num_tokens": 15242323.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 6.167079496383667,
|
|
"epoch": 0.7210349699752737,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004954909031609864,
|
|
"loss": 6.0843,
|
|
"mean_token_accuracy": 0.14983757585287094,
|
|
"num_tokens": 15252952.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 6.204553461074829,
|
|
"epoch": 0.7214765100671141,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004954846280038465,
|
|
"loss": 6.0603,
|
|
"mean_token_accuracy": 0.1506972149014473,
|
|
"num_tokens": 15261815.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 6.255751132965088,
|
|
"epoch": 0.7219180501589544,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004954783485275381,
|
|
"loss": 6.1082,
|
|
"mean_token_accuracy": 0.15254272818565368,
|
|
"num_tokens": 15271026.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 6.19788007736206,
|
|
"epoch": 0.7223595902507948,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004954720647321843,
|
|
"loss": 5.9651,
|
|
"mean_token_accuracy": 0.1562256060540676,
|
|
"num_tokens": 15279795.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 6.155232620239258,
|
|
"epoch": 0.7228011303426352,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004954657766179081,
|
|
"loss": 6.0821,
|
|
"mean_token_accuracy": 0.15056323632597923,
|
|
"num_tokens": 15289113.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 6.194340467453003,
|
|
"epoch": 0.7232426704344754,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004954594841848327,
|
|
"loss": 5.9395,
|
|
"mean_token_accuracy": 0.16234055683016776,
|
|
"num_tokens": 15298271.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 6.262794113159179,
|
|
"epoch": 0.7236842105263158,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004954531874330814,
|
|
"loss": 6.0269,
|
|
"mean_token_accuracy": 0.15222135111689566,
|
|
"num_tokens": 15307677.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 6.061808633804321,
|
|
"epoch": 0.7241257506181561,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004954468863627774,
|
|
"loss": 6.0352,
|
|
"mean_token_accuracy": 0.1541186660528183,
|
|
"num_tokens": 15316637.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 6.157130289077759,
|
|
"epoch": 0.7245672907099965,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004954405809740445,
|
|
"loss": 6.0196,
|
|
"mean_token_accuracy": 0.15551941692829133,
|
|
"num_tokens": 15325221.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 6.266123628616333,
|
|
"epoch": 0.7250088308018368,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004954342712670058,
|
|
"loss": 6.0362,
|
|
"mean_token_accuracy": 0.1526273787021637,
|
|
"num_tokens": 15335877.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 6.191796398162841,
|
|
"epoch": 0.7254503708936771,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004954279572417852,
|
|
"loss": 6.0759,
|
|
"mean_token_accuracy": 0.1485827647149563,
|
|
"num_tokens": 15345096.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 6.133485746383667,
|
|
"epoch": 0.7258919109855175,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004954216388985063,
|
|
"loss": 5.9009,
|
|
"mean_token_accuracy": 0.16367556452751159,
|
|
"num_tokens": 15353785.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 6.198287105560302,
|
|
"epoch": 0.7263334510773578,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004954153162372928,
|
|
"loss": 5.9914,
|
|
"mean_token_accuracy": 0.15659495443105698,
|
|
"num_tokens": 15362761.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 6.200320911407471,
|
|
"epoch": 0.7267749911691982,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004954089892582686,
|
|
"loss": 6.0033,
|
|
"mean_token_accuracy": 0.14984651207923888,
|
|
"num_tokens": 15371951.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 6.1897303581237795,
|
|
"epoch": 0.7272165312610385,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004954026579615577,
|
|
"loss": 6.0632,
|
|
"mean_token_accuracy": 0.1566293716430664,
|
|
"num_tokens": 15380277.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 6.193405818939209,
|
|
"epoch": 0.7276580713528789,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004953963223472841,
|
|
"loss": 6.062,
|
|
"mean_token_accuracy": 0.15038451701402664,
|
|
"num_tokens": 15390951.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 6.28805890083313,
|
|
"epoch": 0.7280996114447191,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004953899824155718,
|
|
"loss": 6.0329,
|
|
"mean_token_accuracy": 0.15698810070753097,
|
|
"num_tokens": 15399394.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 6.1586767673492435,
|
|
"epoch": 0.7285411515365595,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004953836381665452,
|
|
"loss": 5.9735,
|
|
"mean_token_accuracy": 0.1548301711678505,
|
|
"num_tokens": 15408644.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 6.174379491806031,
|
|
"epoch": 0.7289826916283999,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004953772896003284,
|
|
"loss": 6.0737,
|
|
"mean_token_accuracy": 0.15424104779958725,
|
|
"num_tokens": 15417398.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 6.245291805267334,
|
|
"epoch": 0.7294242317202402,
|
|
"grad_norm": 3.90625,
|
|
"learning_rate": 0.0004953709367170458,
|
|
"loss": 6.1137,
|
|
"mean_token_accuracy": 0.1443786732852459,
|
|
"num_tokens": 15426532.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 6.244936513900757,
|
|
"epoch": 0.7298657718120806,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.000495364579516822,
|
|
"loss": 6.095,
|
|
"mean_token_accuracy": 0.14691477119922638,
|
|
"num_tokens": 15436371.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 6.3124534606933596,
|
|
"epoch": 0.7303073119039208,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004953582179997813,
|
|
"loss": 6.1494,
|
|
"mean_token_accuracy": 0.14667709469795226,
|
|
"num_tokens": 15446600.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 6.254750108718872,
|
|
"epoch": 0.7307488519957612,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004953518521660484,
|
|
"loss": 5.9877,
|
|
"mean_token_accuracy": 0.1541195407509804,
|
|
"num_tokens": 15455547.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 6.181308889389038,
|
|
"epoch": 0.7311903920876015,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004953454820157481,
|
|
"loss": 6.0464,
|
|
"mean_token_accuracy": 0.15462103337049485,
|
|
"num_tokens": 15464543.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 6.208321475982666,
|
|
"epoch": 0.7316319321794419,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004953391075490051,
|
|
"loss": 6.1598,
|
|
"mean_token_accuracy": 0.1457721471786499,
|
|
"num_tokens": 15473626.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 6.221294593811035,
|
|
"epoch": 0.7320734722712823,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004953327287659444,
|
|
"loss": 6.0933,
|
|
"mean_token_accuracy": 0.1486469939351082,
|
|
"num_tokens": 15484164.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 6.314439582824707,
|
|
"epoch": 0.7325150123631226,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004953263456666907,
|
|
"loss": 6.102,
|
|
"mean_token_accuracy": 0.14443486854434012,
|
|
"num_tokens": 15493718.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 6.220274448394775,
|
|
"epoch": 0.7329565524549629,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004953199582513693,
|
|
"loss": 6.0242,
|
|
"mean_token_accuracy": 0.15442363172769547,
|
|
"num_tokens": 15503339.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 6.215155076980591,
|
|
"epoch": 0.7333980925468032,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004953135665201052,
|
|
"loss": 6.006,
|
|
"mean_token_accuracy": 0.1588119901716709,
|
|
"num_tokens": 15513314.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 6.217810535430909,
|
|
"epoch": 0.7338396326386436,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004953071704730237,
|
|
"loss": 6.0986,
|
|
"mean_token_accuracy": 0.14826320856809616,
|
|
"num_tokens": 15522943.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 6.1630918979644775,
|
|
"epoch": 0.7342811727304839,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004953007701102499,
|
|
"loss": 6.0575,
|
|
"mean_token_accuracy": 0.1495142787694931,
|
|
"num_tokens": 15531975.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 6.1869665622711185,
|
|
"epoch": 0.7347227128223243,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 0.0004952943654319094,
|
|
"loss": 5.9788,
|
|
"mean_token_accuracy": 0.15272131115198134,
|
|
"num_tokens": 15541139.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 6.212423419952392,
|
|
"epoch": 0.7351642529141647,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004952879564381276,
|
|
"loss": 6.0591,
|
|
"mean_token_accuracy": 0.15568502247333527,
|
|
"num_tokens": 15550604.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 6.161788749694824,
|
|
"epoch": 0.7356057930060049,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004952815431290298,
|
|
"loss": 5.9785,
|
|
"mean_token_accuracy": 0.15971437096595764,
|
|
"num_tokens": 15558995.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 6.235270690917969,
|
|
"epoch": 0.7360473330978453,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.000495275125504742,
|
|
"loss": 6.0522,
|
|
"mean_token_accuracy": 0.15424182116985322,
|
|
"num_tokens": 15568229.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 6.141129970550537,
|
|
"epoch": 0.7364888731896856,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004952687035653899,
|
|
"loss": 5.9708,
|
|
"mean_token_accuracy": 0.15418651700019836,
|
|
"num_tokens": 15577042.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 6.1271415710449215,
|
|
"epoch": 0.736930413281526,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004952622773110989,
|
|
"loss": 5.9139,
|
|
"mean_token_accuracy": 0.16094250828027726,
|
|
"num_tokens": 15585825.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 6.182744836807251,
|
|
"epoch": 0.7373719533733663,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004952558467419953,
|
|
"loss": 5.9343,
|
|
"mean_token_accuracy": 0.15798150151968002,
|
|
"num_tokens": 15595486.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 6.092209577560425,
|
|
"epoch": 0.7378134934652066,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.000495249411858205,
|
|
"loss": 5.9585,
|
|
"mean_token_accuracy": 0.14684529975056648,
|
|
"num_tokens": 15605312.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 6.1702048778533936,
|
|
"epoch": 0.738255033557047,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 0.0004952429726598538,
|
|
"loss": 5.9953,
|
|
"mean_token_accuracy": 0.15861203223466874,
|
|
"num_tokens": 15615185.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 6.253500270843506,
|
|
"epoch": 0.7386965736488873,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004952365291470682,
|
|
"loss": 6.0975,
|
|
"mean_token_accuracy": 0.153415647149086,
|
|
"num_tokens": 15625259.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 6.236084794998169,
|
|
"epoch": 0.7391381137407277,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004952300813199742,
|
|
"loss": 6.0742,
|
|
"mean_token_accuracy": 0.15204451978206635,
|
|
"num_tokens": 15635040.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 6.262276887893677,
|
|
"epoch": 0.739579653832568,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004952236291786981,
|
|
"loss": 6.0712,
|
|
"mean_token_accuracy": 0.15011000037193298,
|
|
"num_tokens": 15644996.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 6.096345233917236,
|
|
"epoch": 0.7400211939244083,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004952171727233665,
|
|
"loss": 6.0005,
|
|
"mean_token_accuracy": 0.1511855512857437,
|
|
"num_tokens": 15654598.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 6.156092548370362,
|
|
"epoch": 0.7404627340162486,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004952107119541055,
|
|
"loss": 6.0067,
|
|
"mean_token_accuracy": 0.1565088838338852,
|
|
"num_tokens": 15664213.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 6.1887593269348145,
|
|
"epoch": 0.740904274108089,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004952042468710421,
|
|
"loss": 6.0605,
|
|
"mean_token_accuracy": 0.1537364087998867,
|
|
"num_tokens": 15673595.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 6.240141248703003,
|
|
"epoch": 0.7413458141999294,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004951977774743027,
|
|
"loss": 6.1115,
|
|
"mean_token_accuracy": 0.14618029668927193,
|
|
"num_tokens": 15682753.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 6.133825016021729,
|
|
"epoch": 0.7417873542917697,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004951913037640139,
|
|
"loss": 5.9389,
|
|
"mean_token_accuracy": 0.16434774845838546,
|
|
"num_tokens": 15691508.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 6.120059823989868,
|
|
"epoch": 0.7422288943836101,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004951848257403029,
|
|
"loss": 5.9389,
|
|
"mean_token_accuracy": 0.15547937601804734,
|
|
"num_tokens": 15701110.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 6.063517713546753,
|
|
"epoch": 0.7426704344754503,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004951783434032963,
|
|
"loss": 5.8822,
|
|
"mean_token_accuracy": 0.16648623794317247,
|
|
"num_tokens": 15710565.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 6.129230642318726,
|
|
"epoch": 0.7431119745672907,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004951718567531211,
|
|
"loss": 6.0531,
|
|
"mean_token_accuracy": 0.14975019171833992,
|
|
"num_tokens": 15718364.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 6.169689178466797,
|
|
"epoch": 0.743553514659131,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004951653657899045,
|
|
"loss": 6.1328,
|
|
"mean_token_accuracy": 0.14661180898547171,
|
|
"num_tokens": 15729127.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 6.192731428146362,
|
|
"epoch": 0.7439950547509714,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004951588705137737,
|
|
"loss": 6.1017,
|
|
"mean_token_accuracy": 0.1482056498527527,
|
|
"num_tokens": 15738491.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 6.24168210029602,
|
|
"epoch": 0.7444365948428118,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004951523709248557,
|
|
"loss": 5.9737,
|
|
"mean_token_accuracy": 0.15786256790161132,
|
|
"num_tokens": 15748346.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 6.125617933273316,
|
|
"epoch": 0.744878134934652,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000495145867023278,
|
|
"loss": 6.0018,
|
|
"mean_token_accuracy": 0.1626955583691597,
|
|
"num_tokens": 15757242.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 6.2744465351104735,
|
|
"epoch": 0.7453196750264924,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.000495139358809168,
|
|
"loss": 6.0348,
|
|
"mean_token_accuracy": 0.15362615138292313,
|
|
"num_tokens": 15767236.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 6.171437835693359,
|
|
"epoch": 0.7457612151183327,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004951328462826532,
|
|
"loss": 6.0764,
|
|
"mean_token_accuracy": 0.14767611175775527,
|
|
"num_tokens": 15776977.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 6.1203724384307865,
|
|
"epoch": 0.7462027552101731,
|
|
"grad_norm": 13.5625,
|
|
"learning_rate": 0.0004951263294438611,
|
|
"loss": 5.9988,
|
|
"mean_token_accuracy": 0.1552292600274086,
|
|
"num_tokens": 15787333.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 6.117383146286011,
|
|
"epoch": 0.7466442953020134,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004951198082929194,
|
|
"loss": 5.8902,
|
|
"mean_token_accuracy": 0.1694972649216652,
|
|
"num_tokens": 15794773.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 6.115877676010132,
|
|
"epoch": 0.7470858353938538,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004951132828299558,
|
|
"loss": 5.994,
|
|
"mean_token_accuracy": 0.16377333998680116,
|
|
"num_tokens": 15803803.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 6.182858276367187,
|
|
"epoch": 0.7475273754856941,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004951067530550982,
|
|
"loss": 6.0366,
|
|
"mean_token_accuracy": 0.15338488817214965,
|
|
"num_tokens": 15814021.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 6.186029148101807,
|
|
"epoch": 0.7479689155775344,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004951002189684745,
|
|
"loss": 6.0211,
|
|
"mean_token_accuracy": 0.14898501634597777,
|
|
"num_tokens": 15822974.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 6.1186785221099855,
|
|
"epoch": 0.7484104556693748,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004950936805702127,
|
|
"loss": 5.9307,
|
|
"mean_token_accuracy": 0.16209083497524263,
|
|
"num_tokens": 15832202.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 6.187338018417359,
|
|
"epoch": 0.7488519957612151,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.0004950871378604409,
|
|
"loss": 6.033,
|
|
"mean_token_accuracy": 0.15920102149248122,
|
|
"num_tokens": 15841223.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 6.17196831703186,
|
|
"epoch": 0.7492935358530555,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004950805908392872,
|
|
"loss": 5.9752,
|
|
"mean_token_accuracy": 0.1617097333073616,
|
|
"num_tokens": 15850260.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 6.116999387741089,
|
|
"epoch": 0.7497350759448957,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004950740395068799,
|
|
"loss": 6.0575,
|
|
"mean_token_accuracy": 0.15411865711212158,
|
|
"num_tokens": 15859780.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 6.143398094177246,
|
|
"epoch": 0.7501766160367361,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004950674838633473,
|
|
"loss": 5.9971,
|
|
"mean_token_accuracy": 0.15415159314870835,
|
|
"num_tokens": 15868331.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 6.169262361526489,
|
|
"epoch": 0.7506181561285765,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004950609239088178,
|
|
"loss": 6.0497,
|
|
"mean_token_accuracy": 0.14991126954555511,
|
|
"num_tokens": 15877359.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 6.193778324127197,
|
|
"epoch": 0.7510596962204168,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004950543596434201,
|
|
"loss": 5.9772,
|
|
"mean_token_accuracy": 0.16402651369571686,
|
|
"num_tokens": 15886976.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 6.131670570373535,
|
|
"epoch": 0.7515012363122572,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004950477910672825,
|
|
"loss": 6.0348,
|
|
"mean_token_accuracy": 0.15271446779370307,
|
|
"num_tokens": 15896139.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 6.180541944503784,
|
|
"epoch": 0.7519427764040975,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.000495041218180534,
|
|
"loss": 6.0177,
|
|
"mean_token_accuracy": 0.16259529143571855,
|
|
"num_tokens": 15904672.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 6.059027624130249,
|
|
"epoch": 0.7523843164959378,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000495034640983303,
|
|
"loss": 5.8731,
|
|
"mean_token_accuracy": 0.16886622160673143,
|
|
"num_tokens": 15912716.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 6.12007884979248,
|
|
"epoch": 0.7528258565877781,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004950280594757186,
|
|
"loss": 5.9946,
|
|
"mean_token_accuracy": 0.15706919729709626,
|
|
"num_tokens": 15921974.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 6.191877841949463,
|
|
"epoch": 0.7532673966796185,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004950214736579097,
|
|
"loss": 5.9961,
|
|
"mean_token_accuracy": 0.1594957433640957,
|
|
"num_tokens": 15930859.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 6.105285406112671,
|
|
"epoch": 0.7537089367714589,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004950148835300051,
|
|
"loss": 5.933,
|
|
"mean_token_accuracy": 0.15683687925338746,
|
|
"num_tokens": 15940052.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 6.158630323410034,
|
|
"epoch": 0.7541504768632992,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004950082890921341,
|
|
"loss": 5.998,
|
|
"mean_token_accuracy": 0.15748081728816032,
|
|
"num_tokens": 15948422.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 6.182331562042236,
|
|
"epoch": 0.7545920169551396,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004950016903444261,
|
|
"loss": 6.0974,
|
|
"mean_token_accuracy": 0.15164448618888854,
|
|
"num_tokens": 15957433.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 6.238806486129761,
|
|
"epoch": 0.7550335570469798,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004949950872870099,
|
|
"loss": 6.0159,
|
|
"mean_token_accuracy": 0.15430637300014496,
|
|
"num_tokens": 15966542.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 6.178037452697754,
|
|
"epoch": 0.7554750971388202,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000494988479920015,
|
|
"loss": 6.1505,
|
|
"mean_token_accuracy": 0.1452166497707367,
|
|
"num_tokens": 15977067.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 6.255996131896973,
|
|
"epoch": 0.7559166372306605,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.000494981868243571,
|
|
"loss": 6.0632,
|
|
"mean_token_accuracy": 0.15499598830938338,
|
|
"num_tokens": 15986502.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 6.271188640594483,
|
|
"epoch": 0.7563581773225009,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004949752522578073,
|
|
"loss": 6.1111,
|
|
"mean_token_accuracy": 0.15028804168105125,
|
|
"num_tokens": 15996788.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 6.170350408554077,
|
|
"epoch": 0.7567997174143413,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004949686319628535,
|
|
"loss": 6.0201,
|
|
"mean_token_accuracy": 0.15122852921485902,
|
|
"num_tokens": 16007212.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 6.107031393051147,
|
|
"epoch": 0.7572412575061815,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004949620073588394,
|
|
"loss": 6.0547,
|
|
"mean_token_accuracy": 0.15020963698625564,
|
|
"num_tokens": 16017000.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 6.2585564136505125,
|
|
"epoch": 0.7576827975980219,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004949553784458945,
|
|
"loss": 6.1396,
|
|
"mean_token_accuracy": 0.14561762511730195,
|
|
"num_tokens": 16026647.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 6.2295958518981935,
|
|
"epoch": 0.7581243376898622,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004949487452241489,
|
|
"loss": 5.8828,
|
|
"mean_token_accuracy": 0.16303810477256775,
|
|
"num_tokens": 16034773.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 6.237812662124634,
|
|
"epoch": 0.7585658777817026,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004949421076937325,
|
|
"loss": 6.0022,
|
|
"mean_token_accuracy": 0.15621815025806426,
|
|
"num_tokens": 16043787.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 6.059094953536987,
|
|
"epoch": 0.7590074178735429,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004949354658547753,
|
|
"loss": 5.9761,
|
|
"mean_token_accuracy": 0.16451401114463807,
|
|
"num_tokens": 16053130.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 6.142942190170288,
|
|
"epoch": 0.7594489579653833,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004949288197074074,
|
|
"loss": 6.1217,
|
|
"mean_token_accuracy": 0.1474703349173069,
|
|
"num_tokens": 16062529.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 6.1555428981781,
|
|
"epoch": 0.7598904980572236,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004949221692517589,
|
|
"loss": 5.9824,
|
|
"mean_token_accuracy": 0.14887360334396363,
|
|
"num_tokens": 16071932.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 6.282268905639649,
|
|
"epoch": 0.7603320381490639,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004949155144879602,
|
|
"loss": 5.9612,
|
|
"mean_token_accuracy": 0.15913195461034774,
|
|
"num_tokens": 16081077.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 6.123275375366211,
|
|
"epoch": 0.7607735782409043,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004949088554161417,
|
|
"loss": 5.8976,
|
|
"mean_token_accuracy": 0.16462857276201248,
|
|
"num_tokens": 16089725.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 6.1253915309906,
|
|
"epoch": 0.7612151183327446,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004949021920364339,
|
|
"loss": 6.0818,
|
|
"mean_token_accuracy": 0.1539457008242607,
|
|
"num_tokens": 16099362.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 6.263493871688842,
|
|
"epoch": 0.761656658424585,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004948955243489671,
|
|
"loss": 6.1044,
|
|
"mean_token_accuracy": 0.15207269489765168,
|
|
"num_tokens": 16108746.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 6.254348278045654,
|
|
"epoch": 0.7620981985164252,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004948888523538721,
|
|
"loss": 6.2109,
|
|
"mean_token_accuracy": 0.1440314069390297,
|
|
"num_tokens": 16118902.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 6.151745843887329,
|
|
"epoch": 0.7625397386082656,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004948821760512795,
|
|
"loss": 5.9669,
|
|
"mean_token_accuracy": 0.1618361622095108,
|
|
"num_tokens": 16127781.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 6.161589670181274,
|
|
"epoch": 0.762981278700106,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004948754954413201,
|
|
"loss": 5.9428,
|
|
"mean_token_accuracy": 0.1669818416237831,
|
|
"num_tokens": 16136004.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 6.114984655380249,
|
|
"epoch": 0.7634228187919463,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004948688105241248,
|
|
"loss": 5.9832,
|
|
"mean_token_accuracy": 0.16015140414237977,
|
|
"num_tokens": 16145023.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 6.139699029922485,
|
|
"epoch": 0.7638643588837867,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004948621212998246,
|
|
"loss": 6.0611,
|
|
"mean_token_accuracy": 0.15055262818932533,
|
|
"num_tokens": 16154242.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 6.218677186965943,
|
|
"epoch": 0.764305898975627,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004948554277685505,
|
|
"loss": 6.0142,
|
|
"mean_token_accuracy": 0.14951191693544388,
|
|
"num_tokens": 16163252.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 6.244760608673095,
|
|
"epoch": 0.7647474390674673,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004948487299304335,
|
|
"loss": 5.9431,
|
|
"mean_token_accuracy": 0.15852085798978804,
|
|
"num_tokens": 16171363.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 6.172284317016602,
|
|
"epoch": 0.7651889791593076,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.000494842027785605,
|
|
"loss": 6.1235,
|
|
"mean_token_accuracy": 0.15257852524518967,
|
|
"num_tokens": 16181234.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 6.188773202896118,
|
|
"epoch": 0.765630519251148,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004948353213341961,
|
|
"loss": 6.0368,
|
|
"mean_token_accuracy": 0.1514037013053894,
|
|
"num_tokens": 16189420.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 6.278617191314697,
|
|
"epoch": 0.7660720593429884,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004948286105763385,
|
|
"loss": 6.2021,
|
|
"mean_token_accuracy": 0.14024263024330139,
|
|
"num_tokens": 16199202.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 6.261602783203125,
|
|
"epoch": 0.7665135994348287,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004948218955121632,
|
|
"loss": 6.033,
|
|
"mean_token_accuracy": 0.15275065898895263,
|
|
"num_tokens": 16208481.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 6.184469747543335,
|
|
"epoch": 0.766955139526669,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004948151761418021,
|
|
"loss": 6.0913,
|
|
"mean_token_accuracy": 0.15930637568235398,
|
|
"num_tokens": 16217282.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 6.13504114151001,
|
|
"epoch": 0.7673966796185093,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004948084524653868,
|
|
"loss": 5.9651,
|
|
"mean_token_accuracy": 0.15824726969003677,
|
|
"num_tokens": 16226567.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 6.193227529525757,
|
|
"epoch": 0.7678382197103497,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004948017244830489,
|
|
"loss": 6.1761,
|
|
"mean_token_accuracy": 0.14736137688159942,
|
|
"num_tokens": 16236255.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 6.180487108230591,
|
|
"epoch": 0.76827975980219,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004947949921949201,
|
|
"loss": 5.9276,
|
|
"mean_token_accuracy": 0.16612430810928344,
|
|
"num_tokens": 16244838.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 6.048501920700073,
|
|
"epoch": 0.7687212998940304,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004947882556011325,
|
|
"loss": 5.864,
|
|
"mean_token_accuracy": 0.16519371271133423,
|
|
"num_tokens": 16254101.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 6.045390367507935,
|
|
"epoch": 0.7691628399858708,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000494781514701818,
|
|
"loss": 5.9404,
|
|
"mean_token_accuracy": 0.1638119101524353,
|
|
"num_tokens": 16263496.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 6.197959566116333,
|
|
"epoch": 0.769604380077711,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004947747694971085,
|
|
"loss": 6.018,
|
|
"mean_token_accuracy": 0.15746343284845352,
|
|
"num_tokens": 16271884.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 6.186513757705688,
|
|
"epoch": 0.7700459201695514,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004947680199871363,
|
|
"loss": 5.9421,
|
|
"mean_token_accuracy": 0.16937040835618972,
|
|
"num_tokens": 16281197.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 6.087084770202637,
|
|
"epoch": 0.7704874602613917,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004947612661720336,
|
|
"loss": 6.0195,
|
|
"mean_token_accuracy": 0.1552564576268196,
|
|
"num_tokens": 16289908.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 6.107022476196289,
|
|
"epoch": 0.7709290003532321,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004947545080519327,
|
|
"loss": 6.0016,
|
|
"mean_token_accuracy": 0.15504290387034417,
|
|
"num_tokens": 16299237.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 6.244728994369507,
|
|
"epoch": 0.7713705404450724,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.000494747745626966,
|
|
"loss": 6.0161,
|
|
"mean_token_accuracy": 0.1612411007285118,
|
|
"num_tokens": 16308175.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 6.150093460083008,
|
|
"epoch": 0.7718120805369127,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004947409788972659,
|
|
"loss": 5.9777,
|
|
"mean_token_accuracy": 0.1611553907394409,
|
|
"num_tokens": 16317121.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 6.105035400390625,
|
|
"epoch": 0.7722536206287531,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004947342078629649,
|
|
"loss": 5.9399,
|
|
"mean_token_accuracy": 0.15897390842437745,
|
|
"num_tokens": 16325764.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 6.109813976287842,
|
|
"epoch": 0.7726951607205934,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004947274325241959,
|
|
"loss": 5.9563,
|
|
"mean_token_accuracy": 0.15956080257892608,
|
|
"num_tokens": 16333823.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 6.125399732589722,
|
|
"epoch": 0.7731367008124338,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004947206528810913,
|
|
"loss": 5.9579,
|
|
"mean_token_accuracy": 0.16569003760814666,
|
|
"num_tokens": 16341918.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 6.074509716033935,
|
|
"epoch": 0.7735782409042741,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004947138689337843,
|
|
"loss": 6.0194,
|
|
"mean_token_accuracy": 0.15725950747728348,
|
|
"num_tokens": 16351904.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 6.157044219970703,
|
|
"epoch": 0.7740197809961145,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004947070806824074,
|
|
"loss": 6.0175,
|
|
"mean_token_accuracy": 0.15132663100957872,
|
|
"num_tokens": 16360921.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 6.202144718170166,
|
|
"epoch": 0.7744613210879547,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004947002881270937,
|
|
"loss": 6.0581,
|
|
"mean_token_accuracy": 0.14726337194442748,
|
|
"num_tokens": 16370929.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 6.24249849319458,
|
|
"epoch": 0.7749028611797951,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.0004946934912679764,
|
|
"loss": 6.0456,
|
|
"mean_token_accuracy": 0.1561698243021965,
|
|
"num_tokens": 16380099.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 6.2365148067474365,
|
|
"epoch": 0.7753444012716355,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004946866901051885,
|
|
"loss": 6.0564,
|
|
"mean_token_accuracy": 0.15523979514837266,
|
|
"num_tokens": 16389109.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 6.14391942024231,
|
|
"epoch": 0.7757859413634758,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004946798846388634,
|
|
"loss": 6.1027,
|
|
"mean_token_accuracy": 0.15341169089078904,
|
|
"num_tokens": 16398601.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 6.095554780960083,
|
|
"epoch": 0.7762274814553162,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004946730748691342,
|
|
"loss": 5.9552,
|
|
"mean_token_accuracy": 0.16528091281652452,
|
|
"num_tokens": 16406950.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 6.209650373458862,
|
|
"epoch": 0.7766690215471564,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004946662607961344,
|
|
"loss": 5.9834,
|
|
"mean_token_accuracy": 0.1604272246360779,
|
|
"num_tokens": 16414680.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 6.168493175506592,
|
|
"epoch": 0.7771105616389968,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004946594424199976,
|
|
"loss": 6.0461,
|
|
"mean_token_accuracy": 0.1582956314086914,
|
|
"num_tokens": 16424060.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 6.140843391418457,
|
|
"epoch": 0.7775521017308371,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004946526197408571,
|
|
"loss": 6.0426,
|
|
"mean_token_accuracy": 0.15482948273420333,
|
|
"num_tokens": 16433691.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 6.209283351898193,
|
|
"epoch": 0.7779936418226775,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004946457927588467,
|
|
"loss": 6.0597,
|
|
"mean_token_accuracy": 0.15235007852315902,
|
|
"num_tokens": 16443234.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 6.144260358810425,
|
|
"epoch": 0.7784351819145179,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004946389614741002,
|
|
"loss": 6.0082,
|
|
"mean_token_accuracy": 0.16013663113117219,
|
|
"num_tokens": 16452084.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 6.145121288299561,
|
|
"epoch": 0.7788767220063582,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004946321258867513,
|
|
"loss": 5.9754,
|
|
"mean_token_accuracy": 0.1602022811770439,
|
|
"num_tokens": 16460135.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 6.144701051712036,
|
|
"epoch": 0.7793182620981985,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000494625285996934,
|
|
"loss": 6.1058,
|
|
"mean_token_accuracy": 0.15144651457667352,
|
|
"num_tokens": 16469919.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 6.140231657028198,
|
|
"epoch": 0.7797598021900388,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004946184418047823,
|
|
"loss": 6.022,
|
|
"mean_token_accuracy": 0.15065136328339576,
|
|
"num_tokens": 16478473.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 6.235374116897583,
|
|
"epoch": 0.7802013422818792,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004946115933104301,
|
|
"loss": 6.0279,
|
|
"mean_token_accuracy": 0.1558874547481537,
|
|
"num_tokens": 16486878.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 6.199049854278565,
|
|
"epoch": 0.7806428823737195,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004946047405140119,
|
|
"loss": 6.0759,
|
|
"mean_token_accuracy": 0.1492841623723507,
|
|
"num_tokens": 16496798.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 6.202003431320191,
|
|
"epoch": 0.7810844224655599,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004945978834156616,
|
|
"loss": 5.994,
|
|
"mean_token_accuracy": 0.16024575084447862,
|
|
"num_tokens": 16506508.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 6.0723021030426025,
|
|
"epoch": 0.7815259625574003,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004945910220155136,
|
|
"loss": 5.9722,
|
|
"mean_token_accuracy": 0.1620054602622986,
|
|
"num_tokens": 16514979.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 6.188809442520141,
|
|
"epoch": 0.7819675026492405,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004945841563137025,
|
|
"loss": 6.0436,
|
|
"mean_token_accuracy": 0.15457658618688583,
|
|
"num_tokens": 16524654.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 6.233149766921997,
|
|
"epoch": 0.7824090427410809,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004945772863103626,
|
|
"loss": 6.1173,
|
|
"mean_token_accuracy": 0.1509366050362587,
|
|
"num_tokens": 16534486.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 6.245261812210083,
|
|
"epoch": 0.7828505828329212,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004945704120056286,
|
|
"loss": 6.0401,
|
|
"mean_token_accuracy": 0.16267454922199248,
|
|
"num_tokens": 16543718.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 6.09795355796814,
|
|
"epoch": 0.7832921229247616,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000494563533399635,
|
|
"loss": 5.9766,
|
|
"mean_token_accuracy": 0.1589898332953453,
|
|
"num_tokens": 16553159.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 6.214016628265381,
|
|
"epoch": 0.7837336630166019,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.0004945566504925167,
|
|
"loss": 6.0601,
|
|
"mean_token_accuracy": 0.15150932148098945,
|
|
"num_tokens": 16562398.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 6.241987991333008,
|
|
"epoch": 0.7841752031084422,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004945497632844084,
|
|
"loss": 5.9994,
|
|
"mean_token_accuracy": 0.1608886316418648,
|
|
"num_tokens": 16571530.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 6.15855860710144,
|
|
"epoch": 0.7846167432002826,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004945428717754453,
|
|
"loss": 6.0128,
|
|
"mean_token_accuracy": 0.1525505930185318,
|
|
"num_tokens": 16581074.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 6.088472747802735,
|
|
"epoch": 0.7850582832921229,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000494535975965762,
|
|
"loss": 5.8857,
|
|
"mean_token_accuracy": 0.16745850592851638,
|
|
"num_tokens": 16589574.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 6.060295724868775,
|
|
"epoch": 0.7854998233839633,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004945290758554939,
|
|
"loss": 5.967,
|
|
"mean_token_accuracy": 0.16401208192110062,
|
|
"num_tokens": 16599623.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 6.118352174758911,
|
|
"epoch": 0.7859413634758036,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.000494522171444776,
|
|
"loss": 6.0456,
|
|
"mean_token_accuracy": 0.14564495235681535,
|
|
"num_tokens": 16608559.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 6.165759563446045,
|
|
"epoch": 0.786382903567644,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004945152627337437,
|
|
"loss": 5.9585,
|
|
"mean_token_accuracy": 0.16287342160940171,
|
|
"num_tokens": 16617148.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 6.087662029266357,
|
|
"epoch": 0.7868244436594842,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004945083497225321,
|
|
"loss": 5.9767,
|
|
"mean_token_accuracy": 0.16042562276124955,
|
|
"num_tokens": 16626405.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 6.153976058959961,
|
|
"epoch": 0.7872659837513246,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004945014324112769,
|
|
"loss": 6.0194,
|
|
"mean_token_accuracy": 0.15582138448953628,
|
|
"num_tokens": 16635116.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 6.114471054077148,
|
|
"epoch": 0.787707523843165,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004944945108001134,
|
|
"loss": 5.9926,
|
|
"mean_token_accuracy": 0.1544615477323532,
|
|
"num_tokens": 16644381.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 6.18104887008667,
|
|
"epoch": 0.7881490639350053,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004944875848891773,
|
|
"loss": 6.0524,
|
|
"mean_token_accuracy": 0.15410684943199157,
|
|
"num_tokens": 16654275.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 6.228330326080322,
|
|
"epoch": 0.7885906040268457,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004944806546786042,
|
|
"loss": 6.0999,
|
|
"mean_token_accuracy": 0.14967502653598785,
|
|
"num_tokens": 16663484.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 6.175157356262207,
|
|
"epoch": 0.7890321441186859,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00049447372016853,
|
|
"loss": 6.0366,
|
|
"mean_token_accuracy": 0.15706061720848083,
|
|
"num_tokens": 16672490.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 6.1683669090271,
|
|
"epoch": 0.7894736842105263,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004944667813590904,
|
|
"loss": 6.0157,
|
|
"mean_token_accuracy": 0.15035513937473297,
|
|
"num_tokens": 16681242.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 6.104328966140747,
|
|
"epoch": 0.7899152243023666,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004944598382504214,
|
|
"loss": 5.9353,
|
|
"mean_token_accuracy": 0.15881823003292084,
|
|
"num_tokens": 16690359.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 6.171369123458862,
|
|
"epoch": 0.790356764394207,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004944528908426589,
|
|
"loss": 6.0449,
|
|
"mean_token_accuracy": 0.16055190712213516,
|
|
"num_tokens": 16700774.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 6.287743616104126,
|
|
"epoch": 0.7907983044860474,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004944459391359391,
|
|
"loss": 6.1122,
|
|
"mean_token_accuracy": 0.15050581097602844,
|
|
"num_tokens": 16710513.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 6.176932334899902,
|
|
"epoch": 0.7912398445778877,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004944389831303982,
|
|
"loss": 6.0271,
|
|
"mean_token_accuracy": 0.1555835410952568,
|
|
"num_tokens": 16720785.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 6.202974414825439,
|
|
"epoch": 0.791681384669728,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004944320228261723,
|
|
"loss": 6.0091,
|
|
"mean_token_accuracy": 0.1591140389442444,
|
|
"num_tokens": 16729083.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 6.150328063964844,
|
|
"epoch": 0.7921229247615683,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.000494425058223398,
|
|
"loss": 6.0207,
|
|
"mean_token_accuracy": 0.1523827463388443,
|
|
"num_tokens": 16738313.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 6.1048441410064695,
|
|
"epoch": 0.7925644648534087,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004944180893222117,
|
|
"loss": 5.9611,
|
|
"mean_token_accuracy": 0.16035664975643157,
|
|
"num_tokens": 16747191.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 6.144352149963379,
|
|
"epoch": 0.793006004945249,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004944111161227496,
|
|
"loss": 6.0032,
|
|
"mean_token_accuracy": 0.15728989839553834,
|
|
"num_tokens": 16755921.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 6.203505754470825,
|
|
"epoch": 0.7934475450370894,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.0004944041386251486,
|
|
"loss": 6.144,
|
|
"mean_token_accuracy": 0.1521465003490448,
|
|
"num_tokens": 16765394.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 6.20770001411438,
|
|
"epoch": 0.7938890851289298,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004943971568295454,
|
|
"loss": 6.0234,
|
|
"mean_token_accuracy": 0.16135077625513078,
|
|
"num_tokens": 16774824.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 6.168958568572998,
|
|
"epoch": 0.79433062522077,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004943901707360765,
|
|
"loss": 6.1627,
|
|
"mean_token_accuracy": 0.14651539474725722,
|
|
"num_tokens": 16783945.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 6.158242082595825,
|
|
"epoch": 0.7947721653126104,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000494383180344879,
|
|
"loss": 5.9415,
|
|
"mean_token_accuracy": 0.1593190088868141,
|
|
"num_tokens": 16792618.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.7947721653126104,
|
|
"eval_entropy": 5.975076497208627,
|
|
"eval_loss": 6.048604488372803,
|
|
"eval_mean_token_accuracy": 0.16088079484720164,
|
|
"eval_num_tokens": 16792618.0,
|
|
"eval_runtime": 26.2413,
|
|
"eval_samples_per_second": 1345.781,
|
|
"eval_steps_per_second": 168.246,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 6.16330132484436,
|
|
"epoch": 0.7952137054044507,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004943761856560898,
|
|
"loss": 6.0054,
|
|
"mean_token_accuracy": 0.16190404444932938,
|
|
"num_tokens": 16801210.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 6.19029974937439,
|
|
"epoch": 0.7956552454962911,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.000494369186669846,
|
|
"loss": 6.0443,
|
|
"mean_token_accuracy": 0.16017620116472245,
|
|
"num_tokens": 16810371.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 6.174519681930542,
|
|
"epoch": 0.7960967855881314,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004943621833862844,
|
|
"loss": 5.9585,
|
|
"mean_token_accuracy": 0.15855027139186859,
|
|
"num_tokens": 16818886.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 6.178792524337768,
|
|
"epoch": 0.7965383256799717,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004943551758055425,
|
|
"loss": 6.0172,
|
|
"mean_token_accuracy": 0.1579152137041092,
|
|
"num_tokens": 16827705.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 6.2442505836486815,
|
|
"epoch": 0.7969798657718121,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004943481639277574,
|
|
"loss": 6.0142,
|
|
"mean_token_accuracy": 0.15518439263105394,
|
|
"num_tokens": 16836313.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 6.213355827331543,
|
|
"epoch": 0.7974214058636524,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.0004943411477530665,
|
|
"loss": 6.0734,
|
|
"mean_token_accuracy": 0.14613794684410095,
|
|
"num_tokens": 16845016.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 6.18611102104187,
|
|
"epoch": 0.7978629459554928,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004943341272816073,
|
|
"loss": 5.9978,
|
|
"mean_token_accuracy": 0.1506240576505661,
|
|
"num_tokens": 16854025.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 6.2279809474945065,
|
|
"epoch": 0.7983044860473331,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004943271025135173,
|
|
"loss": 5.9687,
|
|
"mean_token_accuracy": 0.16130097955465317,
|
|
"num_tokens": 16862859.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 6.198914575576782,
|
|
"epoch": 0.7987460261391734,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004943200734489341,
|
|
"loss": 6.0707,
|
|
"mean_token_accuracy": 0.15602338537573815,
|
|
"num_tokens": 16872226.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 6.120191383361816,
|
|
"epoch": 0.7991875662310137,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004943130400879953,
|
|
"loss": 5.949,
|
|
"mean_token_accuracy": 0.16058978736400603,
|
|
"num_tokens": 16881977.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 6.167643356323242,
|
|
"epoch": 0.7996291063228541,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004943060024308389,
|
|
"loss": 6.0691,
|
|
"mean_token_accuracy": 0.14636371284723282,
|
|
"num_tokens": 16891656.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 6.198838472366333,
|
|
"epoch": 0.8000706464146945,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004942989604776026,
|
|
"loss": 5.9387,
|
|
"mean_token_accuracy": 0.1607286438345909,
|
|
"num_tokens": 16900944.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 6.1139894962310795,
|
|
"epoch": 0.8005121865065348,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004942919142284244,
|
|
"loss": 5.9587,
|
|
"mean_token_accuracy": 0.1589059628546238,
|
|
"num_tokens": 16910154.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 6.167115831375122,
|
|
"epoch": 0.8009537265983752,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004942848636834423,
|
|
"loss": 6.088,
|
|
"mean_token_accuracy": 0.15294271409511567,
|
|
"num_tokens": 16919694.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 6.1631608486175535,
|
|
"epoch": 0.8013952666902154,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004942778088427944,
|
|
"loss": 6.0452,
|
|
"mean_token_accuracy": 0.15437108725309373,
|
|
"num_tokens": 16928530.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 6.217332363128662,
|
|
"epoch": 0.8018368067820558,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.000494270749706619,
|
|
"loss": 6.0569,
|
|
"mean_token_accuracy": 0.1532064601778984,
|
|
"num_tokens": 16938614.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 6.273269748687744,
|
|
"epoch": 0.8022783468738961,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004942636862750544,
|
|
"loss": 6.0024,
|
|
"mean_token_accuracy": 0.1548839457333088,
|
|
"num_tokens": 16947655.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 6.263075590133667,
|
|
"epoch": 0.8027198869657365,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004942566185482387,
|
|
"loss": 6.1003,
|
|
"mean_token_accuracy": 0.15037893801927565,
|
|
"num_tokens": 16957101.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 6.146580791473388,
|
|
"epoch": 0.8031614270575769,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004942495465263106,
|
|
"loss": 6.109,
|
|
"mean_token_accuracy": 0.14742673188447952,
|
|
"num_tokens": 16966421.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 6.202206945419311,
|
|
"epoch": 0.8036029671494171,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004942424702094085,
|
|
"loss": 6.0191,
|
|
"mean_token_accuracy": 0.15906717628240585,
|
|
"num_tokens": 16975656.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 6.178380012512207,
|
|
"epoch": 0.8040445072412575,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004942353895976713,
|
|
"loss": 6.0599,
|
|
"mean_token_accuracy": 0.15076268017292022,
|
|
"num_tokens": 16984409.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 6.16157898902893,
|
|
"epoch": 0.8044860473330978,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004942283046912374,
|
|
"loss": 5.9762,
|
|
"mean_token_accuracy": 0.14847689867019653,
|
|
"num_tokens": 16992728.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 6.166329860687256,
|
|
"epoch": 0.8049275874249382,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004942212154902456,
|
|
"loss": 5.8957,
|
|
"mean_token_accuracy": 0.1641251653432846,
|
|
"num_tokens": 17001616.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 6.1823100566864015,
|
|
"epoch": 0.8053691275167785,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.000494214121994835,
|
|
"loss": 6.049,
|
|
"mean_token_accuracy": 0.15651159435510636,
|
|
"num_tokens": 17010655.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 6.135058641433716,
|
|
"epoch": 0.8058106676086189,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004942070242051444,
|
|
"loss": 6.0237,
|
|
"mean_token_accuracy": 0.1511933371424675,
|
|
"num_tokens": 17019819.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 6.190236616134643,
|
|
"epoch": 0.8062522077004592,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004941999221213129,
|
|
"loss": 6.0379,
|
|
"mean_token_accuracy": 0.15519107580184938,
|
|
"num_tokens": 17029218.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 6.196532678604126,
|
|
"epoch": 0.8066937477922995,
|
|
"grad_norm": 4.5625,
|
|
"learning_rate": 0.0004941928157434796,
|
|
"loss": 5.9583,
|
|
"mean_token_accuracy": 0.15509601384401323,
|
|
"num_tokens": 17037880.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 6.095403337478638,
|
|
"epoch": 0.8071352878841399,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004941857050717836,
|
|
"loss": 6.0598,
|
|
"mean_token_accuracy": 0.15429162681102754,
|
|
"num_tokens": 17047934.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 6.279002666473389,
|
|
"epoch": 0.8075768279759802,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004941785901063642,
|
|
"loss": 6.1084,
|
|
"mean_token_accuracy": 0.14977463185787201,
|
|
"num_tokens": 17057258.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 6.214845800399781,
|
|
"epoch": 0.8080183680678206,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004941714708473611,
|
|
"loss": 6.0519,
|
|
"mean_token_accuracy": 0.15372628569602967,
|
|
"num_tokens": 17066387.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 6.08232626914978,
|
|
"epoch": 0.8084599081596608,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004941643472949134,
|
|
"loss": 5.9797,
|
|
"mean_token_accuracy": 0.15843379348516465,
|
|
"num_tokens": 17075952.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 6.0682563304901125,
|
|
"epoch": 0.8089014482515012,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004941572194491608,
|
|
"loss": 5.8706,
|
|
"mean_token_accuracy": 0.16113847345113755,
|
|
"num_tokens": 17084209.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 6.09498815536499,
|
|
"epoch": 0.8093429883433416,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.000494150087310243,
|
|
"loss": 6.0974,
|
|
"mean_token_accuracy": 0.15568703263998032,
|
|
"num_tokens": 17093395.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 6.211379718780518,
|
|
"epoch": 0.8097845284351819,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004941429508782995,
|
|
"loss": 5.9763,
|
|
"mean_token_accuracy": 0.15933869704604148,
|
|
"num_tokens": 17102646.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 6.223939275741577,
|
|
"epoch": 0.8102260685270223,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004941358101534703,
|
|
"loss": 5.9914,
|
|
"mean_token_accuracy": 0.1557866096496582,
|
|
"num_tokens": 17111530.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 6.101489305496216,
|
|
"epoch": 0.8106676086188626,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004941286651358952,
|
|
"loss": 5.9333,
|
|
"mean_token_accuracy": 0.1631128028035164,
|
|
"num_tokens": 17119659.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.9786371231079105,
|
|
"epoch": 0.8111091487107029,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004941215158257142,
|
|
"loss": 5.9632,
|
|
"mean_token_accuracy": 0.1578883334994316,
|
|
"num_tokens": 17127931.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 6.224986839294433,
|
|
"epoch": 0.8115506888025432,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004941143622230672,
|
|
"loss": 6.0128,
|
|
"mean_token_accuracy": 0.15638066306710244,
|
|
"num_tokens": 17137374.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 6.306176853179932,
|
|
"epoch": 0.8119922288943836,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 0.0004941072043280946,
|
|
"loss": 6.0675,
|
|
"mean_token_accuracy": 0.14437773153185846,
|
|
"num_tokens": 17147257.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 6.164927577972412,
|
|
"epoch": 0.812433768986224,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004941000421409365,
|
|
"loss": 5.9507,
|
|
"mean_token_accuracy": 0.15665391683578492,
|
|
"num_tokens": 17156233.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 6.225679111480713,
|
|
"epoch": 0.8128753090780643,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004940928756617331,
|
|
"loss": 6.1359,
|
|
"mean_token_accuracy": 0.14476195946335793,
|
|
"num_tokens": 17166364.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 6.20369143486023,
|
|
"epoch": 0.8133168491699047,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004940857048906248,
|
|
"loss": 6.0208,
|
|
"mean_token_accuracy": 0.15950246453285216,
|
|
"num_tokens": 17175853.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 6.222797155380249,
|
|
"epoch": 0.8137583892617449,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004940785298277523,
|
|
"loss": 6.1214,
|
|
"mean_token_accuracy": 0.14765160977840425,
|
|
"num_tokens": 17187849.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 6.20315260887146,
|
|
"epoch": 0.8141999293535853,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.000494071350473256,
|
|
"loss": 5.986,
|
|
"mean_token_accuracy": 0.15655021518468856,
|
|
"num_tokens": 17196646.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 6.183213424682617,
|
|
"epoch": 0.8146414694454256,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004940641668272765,
|
|
"loss": 6.1141,
|
|
"mean_token_accuracy": 0.15241051316261292,
|
|
"num_tokens": 17205919.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 6.197967433929444,
|
|
"epoch": 0.815083009537266,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004940569788899544,
|
|
"loss": 6.0825,
|
|
"mean_token_accuracy": 0.15468350201845169,
|
|
"num_tokens": 17215085.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 6.15929069519043,
|
|
"epoch": 0.8155245496291064,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.0004940497866614309,
|
|
"loss": 6.056,
|
|
"mean_token_accuracy": 0.14778956323862075,
|
|
"num_tokens": 17223633.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 6.147996044158935,
|
|
"epoch": 0.8159660897209466,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004940425901418465,
|
|
"loss": 5.9745,
|
|
"mean_token_accuracy": 0.15986088961362838,
|
|
"num_tokens": 17232915.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 6.181144189834595,
|
|
"epoch": 0.816407629812787,
|
|
"grad_norm": 3.984375,
|
|
"learning_rate": 0.0004940353893313423,
|
|
"loss": 6.1006,
|
|
"mean_token_accuracy": 0.1512872740626335,
|
|
"num_tokens": 17242392.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 6.270976161956787,
|
|
"epoch": 0.8168491699046273,
|
|
"grad_norm": 5.71875,
|
|
"learning_rate": 0.0004940281842300596,
|
|
"loss": 6.1767,
|
|
"mean_token_accuracy": 0.14558177962899208,
|
|
"num_tokens": 17252259.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 6.290340375900269,
|
|
"epoch": 0.8172907099964677,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004940209748381392,
|
|
"loss": 6.0376,
|
|
"mean_token_accuracy": 0.14993744641542434,
|
|
"num_tokens": 17261584.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 6.1955766677856445,
|
|
"epoch": 0.817732250088308,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.0004940137611557225,
|
|
"loss": 5.9871,
|
|
"mean_token_accuracy": 0.1564241111278534,
|
|
"num_tokens": 17270901.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 6.110502481460571,
|
|
"epoch": 0.8181737901801484,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004940065431829508,
|
|
"loss": 6.0165,
|
|
"mean_token_accuracy": 0.1528618276119232,
|
|
"num_tokens": 17280024.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 6.171491527557373,
|
|
"epoch": 0.8186153302719887,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004939993209199654,
|
|
"loss": 6.0735,
|
|
"mean_token_accuracy": 0.15109170973300934,
|
|
"num_tokens": 17290131.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 6.316831159591675,
|
|
"epoch": 0.819056870363829,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004939920943669079,
|
|
"loss": 6.0763,
|
|
"mean_token_accuracy": 0.149622143805027,
|
|
"num_tokens": 17299453.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 6.217446279525757,
|
|
"epoch": 0.8194984104556694,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004939848635239198,
|
|
"loss": 6.0406,
|
|
"mean_token_accuracy": 0.1519092798233032,
|
|
"num_tokens": 17309344.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 6.164099025726318,
|
|
"epoch": 0.8199399505475097,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004939776283911429,
|
|
"loss": 5.9662,
|
|
"mean_token_accuracy": 0.1645274356007576,
|
|
"num_tokens": 17318636.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 6.105147838592529,
|
|
"epoch": 0.8203814906393501,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004939703889687186,
|
|
"loss": 6.0213,
|
|
"mean_token_accuracy": 0.15480365753173828,
|
|
"num_tokens": 17328146.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 6.14805326461792,
|
|
"epoch": 0.8208230307311903,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004939631452567891,
|
|
"loss": 6.0843,
|
|
"mean_token_accuracy": 0.15634123831987382,
|
|
"num_tokens": 17338542.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 6.275281000137329,
|
|
"epoch": 0.8212645708230307,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.000493955897255496,
|
|
"loss": 6.04,
|
|
"mean_token_accuracy": 0.15544226467609407,
|
|
"num_tokens": 17347577.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 6.2426682472229,
|
|
"epoch": 0.8217061109148711,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004939486449649814,
|
|
"loss": 6.0423,
|
|
"mean_token_accuracy": 0.15123710185289382,
|
|
"num_tokens": 17356554.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 6.186700057983399,
|
|
"epoch": 0.8221476510067114,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004939413883853873,
|
|
"loss": 6.0493,
|
|
"mean_token_accuracy": 0.15451455116271973,
|
|
"num_tokens": 17366432.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 6.191228437423706,
|
|
"epoch": 0.8225891910985518,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.000493934127516856,
|
|
"loss": 6.018,
|
|
"mean_token_accuracy": 0.15782462805509567,
|
|
"num_tokens": 17376556.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 6.176034069061279,
|
|
"epoch": 0.823030731190392,
|
|
"grad_norm": 3.65625,
|
|
"learning_rate": 0.0004939268623595297,
|
|
"loss": 6.0829,
|
|
"mean_token_accuracy": 0.15094019025564193,
|
|
"num_tokens": 17385382.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 6.195343017578125,
|
|
"epoch": 0.8234722712822324,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004939195929135506,
|
|
"loss": 5.9479,
|
|
"mean_token_accuracy": 0.1533026024699211,
|
|
"num_tokens": 17393229.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 6.169883394241333,
|
|
"epoch": 0.8239138113740727,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004939123191790612,
|
|
"loss": 5.9319,
|
|
"mean_token_accuracy": 0.14991182833909988,
|
|
"num_tokens": 17402439.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 6.150929021835327,
|
|
"epoch": 0.8243553514659131,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004939050411562041,
|
|
"loss": 6.0917,
|
|
"mean_token_accuracy": 0.14788064062595369,
|
|
"num_tokens": 17412349.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 6.054622459411621,
|
|
"epoch": 0.8247968915577535,
|
|
"grad_norm": 3.953125,
|
|
"learning_rate": 0.0004938977588451216,
|
|
"loss": 5.8675,
|
|
"mean_token_accuracy": 0.1703634589910507,
|
|
"num_tokens": 17420842.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 6.145426797866821,
|
|
"epoch": 0.8252384316495938,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004938904722459565,
|
|
"loss": 5.94,
|
|
"mean_token_accuracy": 0.1631227657198906,
|
|
"num_tokens": 17429877.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 6.153570747375488,
|
|
"epoch": 0.8256799717414341,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004938831813588515,
|
|
"loss": 6.0604,
|
|
"mean_token_accuracy": 0.15108452886343002,
|
|
"num_tokens": 17439508.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 6.1563780307769775,
|
|
"epoch": 0.8261215118332744,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004938758861839495,
|
|
"loss": 5.9997,
|
|
"mean_token_accuracy": 0.15649935901165007,
|
|
"num_tokens": 17449004.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 6.141077184677124,
|
|
"epoch": 0.8265630519251148,
|
|
"grad_norm": 4.25,
|
|
"learning_rate": 0.0004938685867213934,
|
|
"loss": 6.0038,
|
|
"mean_token_accuracy": 0.1581357717514038,
|
|
"num_tokens": 17458462.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 6.223224925994873,
|
|
"epoch": 0.8270045920169551,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004938612829713262,
|
|
"loss": 6.0288,
|
|
"mean_token_accuracy": 0.15867939889431,
|
|
"num_tokens": 17466808.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 6.172831058502197,
|
|
"epoch": 0.8274461321087955,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004938539749338909,
|
|
"loss": 6.0742,
|
|
"mean_token_accuracy": 0.1540021702647209,
|
|
"num_tokens": 17476441.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 6.1683203220367435,
|
|
"epoch": 0.8278876722006359,
|
|
"grad_norm": 6.1875,
|
|
"learning_rate": 0.0004938466626092308,
|
|
"loss": 6.0027,
|
|
"mean_token_accuracy": 0.16268929094076157,
|
|
"num_tokens": 17485393.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 6.125380802154541,
|
|
"epoch": 0.8283292122924761,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000493839345997489,
|
|
"loss": 6.0305,
|
|
"mean_token_accuracy": 0.15758230686187744,
|
|
"num_tokens": 17494904.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 6.257401657104492,
|
|
"epoch": 0.8287707523843165,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004938320250988087,
|
|
"loss": 6.0235,
|
|
"mean_token_accuracy": 0.15207177996635438,
|
|
"num_tokens": 17505137.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 6.20851697921753,
|
|
"epoch": 0.8292122924761568,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004938246999133337,
|
|
"loss": 6.0834,
|
|
"mean_token_accuracy": 0.155420882999897,
|
|
"num_tokens": 17514039.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 6.104730176925659,
|
|
"epoch": 0.8296538325679972,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004938173704412071,
|
|
"loss": 5.9529,
|
|
"mean_token_accuracy": 0.163827283680439,
|
|
"num_tokens": 17522423.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 6.13248643875122,
|
|
"epoch": 0.8300953726598375,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004938100366825728,
|
|
"loss": 5.9137,
|
|
"mean_token_accuracy": 0.16646003127098083,
|
|
"num_tokens": 17531958.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 6.148837900161743,
|
|
"epoch": 0.8305369127516778,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004938026986375742,
|
|
"loss": 6.0062,
|
|
"mean_token_accuracy": 0.16234309375286102,
|
|
"num_tokens": 17540905.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 6.1506743907928465,
|
|
"epoch": 0.8309784528435182,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004937953563063553,
|
|
"loss": 6.0534,
|
|
"mean_token_accuracy": 0.1501004308462143,
|
|
"num_tokens": 17551007.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 6.153183650970459,
|
|
"epoch": 0.8314199929353585,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004937880096890598,
|
|
"loss": 5.8739,
|
|
"mean_token_accuracy": 0.16787810176610946,
|
|
"num_tokens": 17559403.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 6.184926891326905,
|
|
"epoch": 0.8318615330271989,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004937806587858315,
|
|
"loss": 6.0475,
|
|
"mean_token_accuracy": 0.15986477732658386,
|
|
"num_tokens": 17569191.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 6.258034801483154,
|
|
"epoch": 0.8323030731190392,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004937733035968147,
|
|
"loss": 6.0953,
|
|
"mean_token_accuracy": 0.14976078867912293,
|
|
"num_tokens": 17578538.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 6.188538408279419,
|
|
"epoch": 0.8327446132108796,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004937659441221531,
|
|
"loss": 5.9661,
|
|
"mean_token_accuracy": 0.15306929647922515,
|
|
"num_tokens": 17587344.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 6.130722427368164,
|
|
"epoch": 0.8331861533027198,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004937585803619912,
|
|
"loss": 5.9615,
|
|
"mean_token_accuracy": 0.1581699386239052,
|
|
"num_tokens": 17596033.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 6.176023197174072,
|
|
"epoch": 0.8336276933945602,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004937512123164731,
|
|
"loss": 5.9247,
|
|
"mean_token_accuracy": 0.1648713991045952,
|
|
"num_tokens": 17605860.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 6.164800596237183,
|
|
"epoch": 0.8340692334864006,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004937438399857431,
|
|
"loss": 6.0333,
|
|
"mean_token_accuracy": 0.15173615366220475,
|
|
"num_tokens": 17615819.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 6.1563958644866945,
|
|
"epoch": 0.8345107735782409,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004937364633699459,
|
|
"loss": 6.0285,
|
|
"mean_token_accuracy": 0.15544223189353942,
|
|
"num_tokens": 17625478.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 6.206226634979248,
|
|
"epoch": 0.8349523136700813,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004937290824692255,
|
|
"loss": 5.9959,
|
|
"mean_token_accuracy": 0.1604430839419365,
|
|
"num_tokens": 17635329.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 6.0999308109283445,
|
|
"epoch": 0.8353938537619215,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004937216972837269,
|
|
"loss": 5.9751,
|
|
"mean_token_accuracy": 0.15586129426956177,
|
|
"num_tokens": 17644129.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 6.07632360458374,
|
|
"epoch": 0.8358353938537619,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004937143078135946,
|
|
"loss": 5.94,
|
|
"mean_token_accuracy": 0.16034181118011476,
|
|
"num_tokens": 17652836.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 6.203134632110595,
|
|
"epoch": 0.8362769339456022,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004937069140589735,
|
|
"loss": 5.969,
|
|
"mean_token_accuracy": 0.15560818165540696,
|
|
"num_tokens": 17661222.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 6.170781993865967,
|
|
"epoch": 0.8367184740374426,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004936995160200083,
|
|
"loss": 5.9338,
|
|
"mean_token_accuracy": 0.1625818833708763,
|
|
"num_tokens": 17669637.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 6.180658292770386,
|
|
"epoch": 0.837160014129283,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004936921136968439,
|
|
"loss": 6.1231,
|
|
"mean_token_accuracy": 0.1459084391593933,
|
|
"num_tokens": 17678589.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 6.209010219573974,
|
|
"epoch": 0.8376015542211233,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004936847070896254,
|
|
"loss": 6.0875,
|
|
"mean_token_accuracy": 0.15022720098495485,
|
|
"num_tokens": 17689129.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 6.264245510101318,
|
|
"epoch": 0.8380430943129636,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004936772961984979,
|
|
"loss": 6.0895,
|
|
"mean_token_accuracy": 0.15328721404075624,
|
|
"num_tokens": 17698864.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 6.217590379714966,
|
|
"epoch": 0.8384846344048039,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004936698810236065,
|
|
"loss": 6.1524,
|
|
"mean_token_accuracy": 0.14972497373819352,
|
|
"num_tokens": 17707900.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 6.180559921264648,
|
|
"epoch": 0.8389261744966443,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004936624615650964,
|
|
"loss": 5.985,
|
|
"mean_token_accuracy": 0.1569998010993004,
|
|
"num_tokens": 17716983.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 6.2115813255310055,
|
|
"epoch": 0.8393677145884846,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004936550378231133,
|
|
"loss": 5.9936,
|
|
"mean_token_accuracy": 0.1554318845272064,
|
|
"num_tokens": 17726503.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 6.199985313415527,
|
|
"epoch": 0.839809254680325,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004936476097978023,
|
|
"loss": 6.0589,
|
|
"mean_token_accuracy": 0.15271791815757751,
|
|
"num_tokens": 17735708.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 6.238025188446045,
|
|
"epoch": 0.8402507947721654,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004936401774893088,
|
|
"loss": 6.0111,
|
|
"mean_token_accuracy": 0.15702128112316133,
|
|
"num_tokens": 17745169.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 6.28457989692688,
|
|
"epoch": 0.8406923348640056,
|
|
"grad_norm": 4.4375,
|
|
"learning_rate": 0.0004936327408977786,
|
|
"loss": 6.1275,
|
|
"mean_token_accuracy": 0.14965770095586778,
|
|
"num_tokens": 17755630.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 6.213114309310913,
|
|
"epoch": 0.841133874955846,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.0004936253000233574,
|
|
"loss": 6.0052,
|
|
"mean_token_accuracy": 0.1566065639257431,
|
|
"num_tokens": 17764469.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 6.128476524353028,
|
|
"epoch": 0.8415754150476863,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004936178548661909,
|
|
"loss": 6.0905,
|
|
"mean_token_accuracy": 0.14764439612627028,
|
|
"num_tokens": 17774977.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 6.143621635437012,
|
|
"epoch": 0.8420169551395267,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.000493610405426425,
|
|
"loss": 6.0011,
|
|
"mean_token_accuracy": 0.1499892368912697,
|
|
"num_tokens": 17784250.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 6.20766806602478,
|
|
"epoch": 0.842458495231367,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004936029517042056,
|
|
"loss": 6.0459,
|
|
"mean_token_accuracy": 0.15633412301540375,
|
|
"num_tokens": 17793858.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 6.276909065246582,
|
|
"epoch": 0.8429000353232073,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004935954936996787,
|
|
"loss": 6.1303,
|
|
"mean_token_accuracy": 0.14823518842458724,
|
|
"num_tokens": 17804330.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 6.184249591827393,
|
|
"epoch": 0.8433415754150477,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004935880314129903,
|
|
"loss": 6.0214,
|
|
"mean_token_accuracy": 0.15660575330257415,
|
|
"num_tokens": 17813750.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 6.1108362674713135,
|
|
"epoch": 0.843783115506888,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004935805648442868,
|
|
"loss": 5.981,
|
|
"mean_token_accuracy": 0.15835636854171753,
|
|
"num_tokens": 17823537.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 6.182886791229248,
|
|
"epoch": 0.8442246555987284,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004935730939937143,
|
|
"loss": 5.9993,
|
|
"mean_token_accuracy": 0.15982471406459808,
|
|
"num_tokens": 17833298.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 6.243503379821777,
|
|
"epoch": 0.8446661956905687,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004935656188614192,
|
|
"loss": 5.924,
|
|
"mean_token_accuracy": 0.16516816467046738,
|
|
"num_tokens": 17842339.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 6.193902778625488,
|
|
"epoch": 0.845107735782409,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004935581394475479,
|
|
"loss": 6.1125,
|
|
"mean_token_accuracy": 0.1564135506749153,
|
|
"num_tokens": 17851827.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 6.080324697494507,
|
|
"epoch": 0.8455492758742493,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004935506557522469,
|
|
"loss": 5.9882,
|
|
"mean_token_accuracy": 0.15881171822547913,
|
|
"num_tokens": 17860788.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 6.200874280929566,
|
|
"epoch": 0.8459908159660897,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.000493543167775663,
|
|
"loss": 5.9783,
|
|
"mean_token_accuracy": 0.15974099338054656,
|
|
"num_tokens": 17869849.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 6.23571743965149,
|
|
"epoch": 0.8464323560579301,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004935356755179426,
|
|
"loss": 5.993,
|
|
"mean_token_accuracy": 0.15421488881111145,
|
|
"num_tokens": 17879431.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 6.252764511108398,
|
|
"epoch": 0.8468738961497704,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004935281789792326,
|
|
"loss": 6.1044,
|
|
"mean_token_accuracy": 0.15210022479295732,
|
|
"num_tokens": 17888599.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 6.190015029907227,
|
|
"epoch": 0.8473154362416108,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004935206781596799,
|
|
"loss": 5.9982,
|
|
"mean_token_accuracy": 0.1624806120991707,
|
|
"num_tokens": 17898662.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 6.2146673679351805,
|
|
"epoch": 0.847756976333451,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004935131730594315,
|
|
"loss": 6.0349,
|
|
"mean_token_accuracy": 0.15563121289014817,
|
|
"num_tokens": 17907810.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 6.178008794784546,
|
|
"epoch": 0.8481985164252914,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004935056636786342,
|
|
"loss": 6.0042,
|
|
"mean_token_accuracy": 0.15478068590164185,
|
|
"num_tokens": 17917611.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 6.188114881515503,
|
|
"epoch": 0.8486400565171317,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004934981500174353,
|
|
"loss": 6.0329,
|
|
"mean_token_accuracy": 0.15326831638813018,
|
|
"num_tokens": 17926076.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 6.1936304569244385,
|
|
"epoch": 0.8490815966089721,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004934906320759818,
|
|
"loss": 6.0451,
|
|
"mean_token_accuracy": 0.1524820163846016,
|
|
"num_tokens": 17935521.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 6.2309952735900875,
|
|
"epoch": 0.8495231367008125,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004934831098544211,
|
|
"loss": 6.0237,
|
|
"mean_token_accuracy": 0.15770833045244217,
|
|
"num_tokens": 17944849.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 6.235608005523682,
|
|
"epoch": 0.8499646767926528,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004934755833529007,
|
|
"loss": 5.9992,
|
|
"mean_token_accuracy": 0.1565394029021263,
|
|
"num_tokens": 17953988.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 6.154301691055298,
|
|
"epoch": 0.8504062168844931,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004934680525715677,
|
|
"loss": 5.9896,
|
|
"mean_token_accuracy": 0.15951733887195588,
|
|
"num_tokens": 17963319.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 6.129526615142822,
|
|
"epoch": 0.8508477569763334,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004934605175105698,
|
|
"loss": 5.9604,
|
|
"mean_token_accuracy": 0.16619348227977754,
|
|
"num_tokens": 17972054.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 6.212171268463135,
|
|
"epoch": 0.8512892970681738,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004934529781700546,
|
|
"loss": 6.0995,
|
|
"mean_token_accuracy": 0.15235573276877404,
|
|
"num_tokens": 17981630.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 6.247295379638672,
|
|
"epoch": 0.8517308371600141,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004934454345501698,
|
|
"loss": 6.045,
|
|
"mean_token_accuracy": 0.1502332419157028,
|
|
"num_tokens": 17990987.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 6.117348384857178,
|
|
"epoch": 0.8521723772518545,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004934378866510633,
|
|
"loss": 5.9442,
|
|
"mean_token_accuracy": 0.1672571614384651,
|
|
"num_tokens": 17999284.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 6.1755430698394775,
|
|
"epoch": 0.8526139173436948,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004934303344728828,
|
|
"loss": 5.9889,
|
|
"mean_token_accuracy": 0.15463931411504744,
|
|
"num_tokens": 18008670.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 6.129124164581299,
|
|
"epoch": 0.8530554574355351,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004934227780157761,
|
|
"loss": 5.9668,
|
|
"mean_token_accuracy": 0.15953436493873596,
|
|
"num_tokens": 18018374.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 6.236544036865235,
|
|
"epoch": 0.8534969975273755,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004934152172798916,
|
|
"loss": 6.0639,
|
|
"mean_token_accuracy": 0.15600237548351287,
|
|
"num_tokens": 18026943.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 6.235983610153198,
|
|
"epoch": 0.8539385376192158,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004934076522653772,
|
|
"loss": 6.0029,
|
|
"mean_token_accuracy": 0.15417421311140062,
|
|
"num_tokens": 18036270.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 6.143337106704712,
|
|
"epoch": 0.8543800777110562,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.000493400082972381,
|
|
"loss": 5.9936,
|
|
"mean_token_accuracy": 0.1586397185921669,
|
|
"num_tokens": 18045611.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 6.150987148284912,
|
|
"epoch": 0.8548216178028964,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004933925094010516,
|
|
"loss": 6.0247,
|
|
"mean_token_accuracy": 0.15174849480390548,
|
|
"num_tokens": 18055152.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 6.204892015457153,
|
|
"epoch": 0.8552631578947368,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004933849315515369,
|
|
"loss": 6.0152,
|
|
"mean_token_accuracy": 0.14948640912771224,
|
|
"num_tokens": 18064376.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 6.090399599075317,
|
|
"epoch": 0.8557046979865772,
|
|
"grad_norm": 4.25,
|
|
"learning_rate": 0.0004933773494239857,
|
|
"loss": 5.94,
|
|
"mean_token_accuracy": 0.16883918195962905,
|
|
"num_tokens": 18073569.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 6.110611486434936,
|
|
"epoch": 0.8561462380784175,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004933697630185464,
|
|
"loss": 5.9969,
|
|
"mean_token_accuracy": 0.1602720320224762,
|
|
"num_tokens": 18083264.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 6.22624568939209,
|
|
"epoch": 0.8565877781702579,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004933621723353677,
|
|
"loss": 5.9994,
|
|
"mean_token_accuracy": 0.15230705291032792,
|
|
"num_tokens": 18093151.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 6.208186960220337,
|
|
"epoch": 0.8570293182620982,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.000493354577374598,
|
|
"loss": 5.9289,
|
|
"mean_token_accuracy": 0.16737866401672363,
|
|
"num_tokens": 18102087.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 6.187351655960083,
|
|
"epoch": 0.8574708583539385,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004933469781363865,
|
|
"loss": 6.0346,
|
|
"mean_token_accuracy": 0.15789082199335097,
|
|
"num_tokens": 18111854.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 6.136016178131103,
|
|
"epoch": 0.8579123984457788,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004933393746208819,
|
|
"loss": 6.0629,
|
|
"mean_token_accuracy": 0.15245209634304047,
|
|
"num_tokens": 18120520.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 6.211365509033203,
|
|
"epoch": 0.8583539385376192,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004933317668282331,
|
|
"loss": 6.1116,
|
|
"mean_token_accuracy": 0.1523909091949463,
|
|
"num_tokens": 18130557.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 6.193790864944458,
|
|
"epoch": 0.8587954786294596,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004933241547585891,
|
|
"loss": 5.9211,
|
|
"mean_token_accuracy": 0.16193769872188568,
|
|
"num_tokens": 18139199.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 6.155925941467285,
|
|
"epoch": 0.8592370187212999,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004933165384120991,
|
|
"loss": 5.9702,
|
|
"mean_token_accuracy": 0.16056935489177704,
|
|
"num_tokens": 18150039.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 6.1194170951843265,
|
|
"epoch": 0.8596785588131403,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.0004933089177889124,
|
|
"loss": 5.9771,
|
|
"mean_token_accuracy": 0.15308154970407487,
|
|
"num_tokens": 18159451.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 6.193133115768433,
|
|
"epoch": 0.8601200989049805,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004933012928891781,
|
|
"loss": 6.073,
|
|
"mean_token_accuracy": 0.1550351247191429,
|
|
"num_tokens": 18169896.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 6.174573802947998,
|
|
"epoch": 0.8605616389968209,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004932936637130456,
|
|
"loss": 5.9386,
|
|
"mean_token_accuracy": 0.16603296995162964,
|
|
"num_tokens": 18177764.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 6.169020938873291,
|
|
"epoch": 0.8610031790886612,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004932860302606644,
|
|
"loss": 6.0167,
|
|
"mean_token_accuracy": 0.15849282890558242,
|
|
"num_tokens": 18186940.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 6.194835758209228,
|
|
"epoch": 0.8614447191805016,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004932783925321838,
|
|
"loss": 5.8995,
|
|
"mean_token_accuracy": 0.16262447088956833,
|
|
"num_tokens": 18195374.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 6.117531776428223,
|
|
"epoch": 0.861886259272342,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000493270750527754,
|
|
"loss": 6.0212,
|
|
"mean_token_accuracy": 0.15546985268592833,
|
|
"num_tokens": 18204779.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 6.091239595413208,
|
|
"epoch": 0.8623277993641822,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004932631042475241,
|
|
"loss": 5.9414,
|
|
"mean_token_accuracy": 0.16219218373298644,
|
|
"num_tokens": 18214099.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 6.16319899559021,
|
|
"epoch": 0.8627693394560226,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.0004932554536916441,
|
|
"loss": 6.0175,
|
|
"mean_token_accuracy": 0.15754653364419938,
|
|
"num_tokens": 18223190.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 6.178204345703125,
|
|
"epoch": 0.8632108795478629,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.000493247798860264,
|
|
"loss": 5.9915,
|
|
"mean_token_accuracy": 0.1578979194164276,
|
|
"num_tokens": 18232380.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 6.176240873336792,
|
|
"epoch": 0.8636524196397033,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.0004932401397535337,
|
|
"loss": 6.0937,
|
|
"mean_token_accuracy": 0.15338415801525115,
|
|
"num_tokens": 18242621.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 6.2324787139892575,
|
|
"epoch": 0.8640939597315436,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.000493232476371603,
|
|
"loss": 6.1318,
|
|
"mean_token_accuracy": 0.15454535335302352,
|
|
"num_tokens": 18253183.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 6.208017826080322,
|
|
"epoch": 0.864535499823384,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004932248087146223,
|
|
"loss": 5.9138,
|
|
"mean_token_accuracy": 0.15757145136594772,
|
|
"num_tokens": 18261967.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 6.152089548110962,
|
|
"epoch": 0.8649770399152243,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.0004932171367827417,
|
|
"loss": 6.0224,
|
|
"mean_token_accuracy": 0.15886688679456712,
|
|
"num_tokens": 18270902.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 6.119718074798584,
|
|
"epoch": 0.8654185800070646,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004932094605761115,
|
|
"loss": 6.0116,
|
|
"mean_token_accuracy": 0.15925500839948653,
|
|
"num_tokens": 18279387.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 6.106378841400146,
|
|
"epoch": 0.865860120098905,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004932017800948821,
|
|
"loss": 5.8453,
|
|
"mean_token_accuracy": 0.16939669251441955,
|
|
"num_tokens": 18288363.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 6.334258270263672,
|
|
"epoch": 0.8663016601907453,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004931940953392038,
|
|
"loss": 6.1468,
|
|
"mean_token_accuracy": 0.14759631007909774,
|
|
"num_tokens": 18297398.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 6.31011815071106,
|
|
"epoch": 0.8667432002825857,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004931864063092274,
|
|
"loss": 6.0036,
|
|
"mean_token_accuracy": 0.1502399615943432,
|
|
"num_tokens": 18306230.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 6.187512826919556,
|
|
"epoch": 0.8671847403744259,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004931787130051034,
|
|
"loss": 6.1044,
|
|
"mean_token_accuracy": 0.16098907440900803,
|
|
"num_tokens": 18316395.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 6.212162637710572,
|
|
"epoch": 0.8676262804662663,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004931710154269824,
|
|
"loss": 6.0132,
|
|
"mean_token_accuracy": 0.16348406225442885,
|
|
"num_tokens": 18326020.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 6.163374042510986,
|
|
"epoch": 0.8680678205581067,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004931633135750154,
|
|
"loss": 6.0028,
|
|
"mean_token_accuracy": 0.15662624835968017,
|
|
"num_tokens": 18335320.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 6.153064966201782,
|
|
"epoch": 0.868509360649947,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004931556074493531,
|
|
"loss": 6.0605,
|
|
"mean_token_accuracy": 0.15074578672647476,
|
|
"num_tokens": 18345137.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 6.156153726577759,
|
|
"epoch": 0.8689509007417874,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004931478970501465,
|
|
"loss": 6.0596,
|
|
"mean_token_accuracy": 0.15259919315576553,
|
|
"num_tokens": 18354289.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 6.29138593673706,
|
|
"epoch": 0.8693924408336277,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004931401823775466,
|
|
"loss": 6.135,
|
|
"mean_token_accuracy": 0.14294005930423737,
|
|
"num_tokens": 18363701.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 6.255833435058594,
|
|
"epoch": 0.869833980925468,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004931324634317047,
|
|
"loss": 6.0139,
|
|
"mean_token_accuracy": 0.15377718731760978,
|
|
"num_tokens": 18373336.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 6.233364200592041,
|
|
"epoch": 0.8702755210173083,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004931247402127719,
|
|
"loss": 6.0086,
|
|
"mean_token_accuracy": 0.1552053853869438,
|
|
"num_tokens": 18383233.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 6.228805875778198,
|
|
"epoch": 0.8707170611091487,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004931170127208995,
|
|
"loss": 6.0661,
|
|
"mean_token_accuracy": 0.15398486107587814,
|
|
"num_tokens": 18393214.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 6.146592283248902,
|
|
"epoch": 0.8711586012009891,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.0004931092809562388,
|
|
"loss": 5.946,
|
|
"mean_token_accuracy": 0.1565675213932991,
|
|
"num_tokens": 18401773.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 6.112184190750122,
|
|
"epoch": 0.8716001412928294,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004931015449189414,
|
|
"loss": 5.9951,
|
|
"mean_token_accuracy": 0.15512312427163125,
|
|
"num_tokens": 18411748.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 6.177978467941284,
|
|
"epoch": 0.8720416813846698,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004930938046091587,
|
|
"loss": 6.0476,
|
|
"mean_token_accuracy": 0.15289223715662956,
|
|
"num_tokens": 18421399.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 6.1912150382995605,
|
|
"epoch": 0.87248322147651,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004930860600270425,
|
|
"loss": 6.048,
|
|
"mean_token_accuracy": 0.15060875192284584,
|
|
"num_tokens": 18430052.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 6.186047840118408,
|
|
"epoch": 0.8729247615683504,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004930783111727443,
|
|
"loss": 5.8845,
|
|
"mean_token_accuracy": 0.16470766216516494,
|
|
"num_tokens": 18438268.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 6.079912853240967,
|
|
"epoch": 0.8733663016601907,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.000493070558046416,
|
|
"loss": 6.0036,
|
|
"mean_token_accuracy": 0.15994871109724046,
|
|
"num_tokens": 18446964.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 6.154115200042725,
|
|
"epoch": 0.8738078417520311,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004930628006482097,
|
|
"loss": 5.9974,
|
|
"mean_token_accuracy": 0.15065375491976737,
|
|
"num_tokens": 18455701.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 6.197438716888428,
|
|
"epoch": 0.8742493818438715,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004930550389782769,
|
|
"loss": 5.9724,
|
|
"mean_token_accuracy": 0.15478905737400056,
|
|
"num_tokens": 18465635.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 6.170751237869263,
|
|
"epoch": 0.8746909219357117,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004930472730367701,
|
|
"loss": 5.9129,
|
|
"mean_token_accuracy": 0.15688419491052627,
|
|
"num_tokens": 18474833.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 6.145848369598388,
|
|
"epoch": 0.8751324620275521,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004930395028238412,
|
|
"loss": 5.9868,
|
|
"mean_token_accuracy": 0.15899734795093537,
|
|
"num_tokens": 18482987.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 6.132942628860474,
|
|
"epoch": 0.8755740021193924,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004930317283396423,
|
|
"loss": 5.9045,
|
|
"mean_token_accuracy": 0.1640846237540245,
|
|
"num_tokens": 18491274.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 6.167538642883301,
|
|
"epoch": 0.8760155422112328,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.000493023949584326,
|
|
"loss": 6.0527,
|
|
"mean_token_accuracy": 0.15335492864251138,
|
|
"num_tokens": 18500811.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 6.064701843261719,
|
|
"epoch": 0.8764570823030731,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.0004930161665580445,
|
|
"loss": 5.8384,
|
|
"mean_token_accuracy": 0.17185902297496797,
|
|
"num_tokens": 18509475.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 6.170683908462524,
|
|
"epoch": 0.8768986223949135,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004930083792609502,
|
|
"loss": 5.9832,
|
|
"mean_token_accuracy": 0.1548695906996727,
|
|
"num_tokens": 18519410.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.974826192855835,
|
|
"epoch": 0.8773401624867538,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004930005876931958,
|
|
"loss": 5.8249,
|
|
"mean_token_accuracy": 0.17380041480064393,
|
|
"num_tokens": 18529194.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 6.168081188201905,
|
|
"epoch": 0.8777817025785941,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004929927918549339,
|
|
"loss": 6.0463,
|
|
"mean_token_accuracy": 0.14996799752116202,
|
|
"num_tokens": 18539166.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 6.2125404357910154,
|
|
"epoch": 0.8782232426704345,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004929849917463171,
|
|
"loss": 5.9887,
|
|
"mean_token_accuracy": 0.16084574833512305,
|
|
"num_tokens": 18548166.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 6.147589111328125,
|
|
"epoch": 0.8786647827622748,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004929771873674984,
|
|
"loss": 5.985,
|
|
"mean_token_accuracy": 0.1554001420736313,
|
|
"num_tokens": 18557041.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 6.150298070907593,
|
|
"epoch": 0.8791063228541152,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004929693787186305,
|
|
"loss": 6.0116,
|
|
"mean_token_accuracy": 0.15107946917414666,
|
|
"num_tokens": 18566461.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 6.1634551048278805,
|
|
"epoch": 0.8795478629459554,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004929615657998664,
|
|
"loss": 5.9419,
|
|
"mean_token_accuracy": 0.1572975307703018,
|
|
"num_tokens": 18576334.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 6.205463933944702,
|
|
"epoch": 0.8799894030377958,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004929537486113593,
|
|
"loss": 5.9623,
|
|
"mean_token_accuracy": 0.1574566476047039,
|
|
"num_tokens": 18584882.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 6.226665925979614,
|
|
"epoch": 0.8804309431296362,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004929459271532621,
|
|
"loss": 6.0103,
|
|
"mean_token_accuracy": 0.1574738770723343,
|
|
"num_tokens": 18593669.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 6.148843240737915,
|
|
"epoch": 0.8808724832214765,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004929381014257282,
|
|
"loss": 6.0501,
|
|
"mean_token_accuracy": 0.1535251572728157,
|
|
"num_tokens": 18603357.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 6.149325132369995,
|
|
"epoch": 0.8813140233133169,
|
|
"grad_norm": 5.28125,
|
|
"learning_rate": 0.0004929302714289107,
|
|
"loss": 5.9397,
|
|
"mean_token_accuracy": 0.1659372180700302,
|
|
"num_tokens": 18611856.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 6.14805383682251,
|
|
"epoch": 0.8817555634051572,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004929224371629634,
|
|
"loss": 6.0145,
|
|
"mean_token_accuracy": 0.1571170061826706,
|
|
"num_tokens": 18620500.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 6.111777973175049,
|
|
"epoch": 0.8821971034969975,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004929145986280394,
|
|
"loss": 5.9444,
|
|
"mean_token_accuracy": 0.16665309220552443,
|
|
"num_tokens": 18628836.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 6.169977283477783,
|
|
"epoch": 0.8826386435888378,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004929067558242922,
|
|
"loss": 5.8904,
|
|
"mean_token_accuracy": 0.16612378358840943,
|
|
"num_tokens": 18636831.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 6.173154354095459,
|
|
"epoch": 0.8830801836806782,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004928989087518758,
|
|
"loss": 6.0369,
|
|
"mean_token_accuracy": 0.1609070673584938,
|
|
"num_tokens": 18646327.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 6.114136409759522,
|
|
"epoch": 0.8835217237725186,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004928910574109435,
|
|
"loss": 6.0673,
|
|
"mean_token_accuracy": 0.15682611614465714,
|
|
"num_tokens": 18656125.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 6.20459623336792,
|
|
"epoch": 0.8839632638643589,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004928832018016495,
|
|
"loss": 6.0328,
|
|
"mean_token_accuracy": 0.15780654102563857,
|
|
"num_tokens": 18665853.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 6.258661460876465,
|
|
"epoch": 0.8844048039561992,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004928753419241472,
|
|
"loss": 6.0983,
|
|
"mean_token_accuracy": 0.15185749977827073,
|
|
"num_tokens": 18676674.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 6.1970985412597654,
|
|
"epoch": 0.8848463440480395,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004928674777785912,
|
|
"loss": 5.9439,
|
|
"mean_token_accuracy": 0.16666018813848496,
|
|
"num_tokens": 18685535.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 6.1253903865814205,
|
|
"epoch": 0.8852878841398799,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004928596093651351,
|
|
"loss": 5.9636,
|
|
"mean_token_accuracy": 0.15550997406244277,
|
|
"num_tokens": 18694186.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 6.115320158004761,
|
|
"epoch": 0.8857294242317202,
|
|
"grad_norm": 4.875,
|
|
"learning_rate": 0.000492851736683933,
|
|
"loss": 5.9543,
|
|
"mean_token_accuracy": 0.1645532190799713,
|
|
"num_tokens": 18703061.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 6.151181602478028,
|
|
"epoch": 0.8861709643235606,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004928438597351395,
|
|
"loss": 5.9118,
|
|
"mean_token_accuracy": 0.16242409944534303,
|
|
"num_tokens": 18712466.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 6.182442283630371,
|
|
"epoch": 0.886612504415401,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004928359785189086,
|
|
"loss": 6.0178,
|
|
"mean_token_accuracy": 0.15392802581191062,
|
|
"num_tokens": 18721522.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 6.12618727684021,
|
|
"epoch": 0.8870540445072412,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004928280930353948,
|
|
"loss": 5.9416,
|
|
"mean_token_accuracy": 0.15530440360307693,
|
|
"num_tokens": 18730488.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 6.158182525634766,
|
|
"epoch": 0.8874955845990816,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004928202032847525,
|
|
"loss": 5.8864,
|
|
"mean_token_accuracy": 0.16544022411108017,
|
|
"num_tokens": 18740318.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 6.146950149536133,
|
|
"epoch": 0.8879371246909219,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004928123092671362,
|
|
"loss": 5.9917,
|
|
"mean_token_accuracy": 0.15361434519290923,
|
|
"num_tokens": 18748731.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 6.050906038284301,
|
|
"epoch": 0.8883786647827623,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004928044109827008,
|
|
"loss": 5.9194,
|
|
"mean_token_accuracy": 0.16573346555233,
|
|
"num_tokens": 18757847.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 6.267030811309814,
|
|
"epoch": 0.8888202048746026,
|
|
"grad_norm": 5.59375,
|
|
"learning_rate": 0.0004927965084316007,
|
|
"loss": 6.0377,
|
|
"mean_token_accuracy": 0.1447622910141945,
|
|
"num_tokens": 18767429.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 6.183168506622314,
|
|
"epoch": 0.889261744966443,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.000492788601613991,
|
|
"loss": 5.9443,
|
|
"mean_token_accuracy": 0.1628161758184433,
|
|
"num_tokens": 18776652.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 6.131083583831787,
|
|
"epoch": 0.8897032850582833,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.0004927806905300265,
|
|
"loss": 5.9772,
|
|
"mean_token_accuracy": 0.15684217661619188,
|
|
"num_tokens": 18785687.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 6.125252103805542,
|
|
"epoch": 0.8901448251501236,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.000492772775179862,
|
|
"loss": 6.0162,
|
|
"mean_token_accuracy": 0.15839558988809585,
|
|
"num_tokens": 18794924.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 6.181124544143676,
|
|
"epoch": 0.890586365241964,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004927648555636528,
|
|
"loss": 5.8787,
|
|
"mean_token_accuracy": 0.1720139965415001,
|
|
"num_tokens": 18803359.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 6.148335695266724,
|
|
"epoch": 0.8910279053338043,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004927569316815539,
|
|
"loss": 6.1219,
|
|
"mean_token_accuracy": 0.14714574366807937,
|
|
"num_tokens": 18813496.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 6.149403619766235,
|
|
"epoch": 0.8914694454256447,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004927490035337205,
|
|
"loss": 5.9629,
|
|
"mean_token_accuracy": 0.16067009270191193,
|
|
"num_tokens": 18823274.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 6.1795487880706785,
|
|
"epoch": 0.8919109855174849,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.000492741071120308,
|
|
"loss": 5.9607,
|
|
"mean_token_accuracy": 0.16393790245056153,
|
|
"num_tokens": 18832436.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 6.214590406417846,
|
|
"epoch": 0.8923525256093253,
|
|
"grad_norm": 3.796875,
|
|
"learning_rate": 0.0004927331344414717,
|
|
"loss": 6.0233,
|
|
"mean_token_accuracy": 0.15794878751039504,
|
|
"num_tokens": 18841923.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 6.201234197616577,
|
|
"epoch": 0.8927940657011657,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004927251934973672,
|
|
"loss": 6.0736,
|
|
"mean_token_accuracy": 0.15925167202949525,
|
|
"num_tokens": 18850957.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 6.264265060424805,
|
|
"epoch": 0.893235605793006,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004927172482881499,
|
|
"loss": 6.0676,
|
|
"mean_token_accuracy": 0.15099077001214029,
|
|
"num_tokens": 18859622.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 6.223895263671875,
|
|
"epoch": 0.8936771458848464,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004927092988139755,
|
|
"loss": 6.0428,
|
|
"mean_token_accuracy": 0.15183982253074646,
|
|
"num_tokens": 18868555.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 6.211693000793457,
|
|
"epoch": 0.8941186859766866,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004927013450749999,
|
|
"loss": 6.019,
|
|
"mean_token_accuracy": 0.15297604501247405,
|
|
"num_tokens": 18877445.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 6.171515369415284,
|
|
"epoch": 0.894560226068527,
|
|
"grad_norm": 7.59375,
|
|
"learning_rate": 0.0004926933870713787,
|
|
"loss": 5.9209,
|
|
"mean_token_accuracy": 0.15988947749137877,
|
|
"num_tokens": 18886386.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 6.149491453170777,
|
|
"epoch": 0.8950017661603673,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004926854248032678,
|
|
"loss": 6.0348,
|
|
"mean_token_accuracy": 0.15640042424201966,
|
|
"num_tokens": 18895016.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 6.085942983627319,
|
|
"epoch": 0.8954433062522077,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004926774582708234,
|
|
"loss": 5.8979,
|
|
"mean_token_accuracy": 0.16461617052555083,
|
|
"num_tokens": 18904126.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 6.114335441589356,
|
|
"epoch": 0.8958848463440481,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004926694874742012,
|
|
"loss": 5.9586,
|
|
"mean_token_accuracy": 0.1573253482580185,
|
|
"num_tokens": 18913064.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 6.165401983261108,
|
|
"epoch": 0.8963263864358884,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004926615124135577,
|
|
"loss": 6.0607,
|
|
"mean_token_accuracy": 0.1534641534090042,
|
|
"num_tokens": 18921189.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 6.199530220031738,
|
|
"epoch": 0.8967679265277287,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004926535330890488,
|
|
"loss": 5.974,
|
|
"mean_token_accuracy": 0.159789377450943,
|
|
"num_tokens": 18930818.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 6.257216835021973,
|
|
"epoch": 0.897209466619569,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004926455495008311,
|
|
"loss": 5.9908,
|
|
"mean_token_accuracy": 0.15595454275608062,
|
|
"num_tokens": 18940376.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 6.172543859481811,
|
|
"epoch": 0.8976510067114094,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004926375616490608,
|
|
"loss": 6.0041,
|
|
"mean_token_accuracy": 0.16691479980945587,
|
|
"num_tokens": 18949418.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 6.140330648422241,
|
|
"epoch": 0.8980925468032497,
|
|
"grad_norm": 7.15625,
|
|
"learning_rate": 0.0004926295695338945,
|
|
"loss": 5.9703,
|
|
"mean_token_accuracy": 0.1607614979147911,
|
|
"num_tokens": 18959315.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 6.1289197444915775,
|
|
"epoch": 0.8985340868950901,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004926215731554887,
|
|
"loss": 5.8859,
|
|
"mean_token_accuracy": 0.16685865074396133,
|
|
"num_tokens": 18968336.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 6.141733074188233,
|
|
"epoch": 0.8989756269869305,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000492613572514,
|
|
"loss": 5.958,
|
|
"mean_token_accuracy": 0.1616265818476677,
|
|
"num_tokens": 18977123.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 6.176858758926391,
|
|
"epoch": 0.8994171670787707,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004926055676095851,
|
|
"loss": 6.0825,
|
|
"mean_token_accuracy": 0.1572777435183525,
|
|
"num_tokens": 18986150.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 6.252068185806275,
|
|
"epoch": 0.8998587071706111,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004925975584424012,
|
|
"loss": 6.0836,
|
|
"mean_token_accuracy": 0.15544864535331726,
|
|
"num_tokens": 18996010.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 6.203353500366211,
|
|
"epoch": 0.9003002472624514,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004925895450126046,
|
|
"loss": 6.0569,
|
|
"mean_token_accuracy": 0.14781340956687927,
|
|
"num_tokens": 19005100.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 6.158134269714355,
|
|
"epoch": 0.9007417873542918,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004925815273203526,
|
|
"loss": 5.9553,
|
|
"mean_token_accuracy": 0.16117661744356154,
|
|
"num_tokens": 19013844.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 6.237428331375122,
|
|
"epoch": 0.901183327446132,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004925735053658022,
|
|
"loss": 6.101,
|
|
"mean_token_accuracy": 0.1538894847035408,
|
|
"num_tokens": 19024218.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 6.201617336273193,
|
|
"epoch": 0.9016248675379724,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004925654791491106,
|
|
"loss": 6.0243,
|
|
"mean_token_accuracy": 0.1535754010081291,
|
|
"num_tokens": 19034725.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 6.197865295410156,
|
|
"epoch": 0.9020664076298128,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004925574486704351,
|
|
"loss": 6.0435,
|
|
"mean_token_accuracy": 0.1501529857516289,
|
|
"num_tokens": 19044597.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 6.275617885589599,
|
|
"epoch": 0.9025079477216531,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004925494139299329,
|
|
"loss": 6.176,
|
|
"mean_token_accuracy": 0.14526568949222565,
|
|
"num_tokens": 19055124.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 6.176630258560181,
|
|
"epoch": 0.9029494878134935,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004925413749277613,
|
|
"loss": 5.9432,
|
|
"mean_token_accuracy": 0.15719038546085357,
|
|
"num_tokens": 19064516.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 6.128312587738037,
|
|
"epoch": 0.9033910279053338,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004925333316640779,
|
|
"loss": 5.9976,
|
|
"mean_token_accuracy": 0.161532860994339,
|
|
"num_tokens": 19072926.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 6.2058759212493895,
|
|
"epoch": 0.9038325679971742,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004925252841390403,
|
|
"loss": 6.0408,
|
|
"mean_token_accuracy": 0.1520572617650032,
|
|
"num_tokens": 19082313.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 6.148319673538208,
|
|
"epoch": 0.9042741080890144,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004925172323528061,
|
|
"loss": 5.9824,
|
|
"mean_token_accuracy": 0.1626274913549423,
|
|
"num_tokens": 19091891.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 6.185559797286987,
|
|
"epoch": 0.9047156481808548,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.000492509176305533,
|
|
"loss": 5.9893,
|
|
"mean_token_accuracy": 0.15698708444833756,
|
|
"num_tokens": 19100311.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 6.193223094940185,
|
|
"epoch": 0.9051571882726952,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004925011159973788,
|
|
"loss": 6.0128,
|
|
"mean_token_accuracy": 0.1560434177517891,
|
|
"num_tokens": 19110463.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 6.235753107070923,
|
|
"epoch": 0.9055987283645355,
|
|
"grad_norm": 5.3125,
|
|
"learning_rate": 0.0004924930514285015,
|
|
"loss": 5.9917,
|
|
"mean_token_accuracy": 0.1641075938940048,
|
|
"num_tokens": 19120723.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 6.142373132705688,
|
|
"epoch": 0.9060402684563759,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000492484982599059,
|
|
"loss": 6.007,
|
|
"mean_token_accuracy": 0.15472819954156875,
|
|
"num_tokens": 19130259.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 6.232355165481567,
|
|
"epoch": 0.9064818085482161,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004924769095092094,
|
|
"loss": 6.0484,
|
|
"mean_token_accuracy": 0.15291386246681213,
|
|
"num_tokens": 19140256.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 6.187994813919067,
|
|
"epoch": 0.9069233486400565,
|
|
"grad_norm": 4.75,
|
|
"learning_rate": 0.0004924688321591109,
|
|
"loss": 6.0521,
|
|
"mean_token_accuracy": 0.15677061378955842,
|
|
"num_tokens": 19149165.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 6.072564315795899,
|
|
"epoch": 0.9073648887318968,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004924607505489215,
|
|
"loss": 5.9736,
|
|
"mean_token_accuracy": 0.1617050975561142,
|
|
"num_tokens": 19159254.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 6.197022867202759,
|
|
"epoch": 0.9078064288237372,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004924526646787998,
|
|
"loss": 6.0264,
|
|
"mean_token_accuracy": 0.15401589646935462,
|
|
"num_tokens": 19168166.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 6.284684085845948,
|
|
"epoch": 0.9082479689155776,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.000492444574548904,
|
|
"loss": 5.9976,
|
|
"mean_token_accuracy": 0.15589857399463652,
|
|
"num_tokens": 19176887.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 6.12396273612976,
|
|
"epoch": 0.9086895090074179,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004924364801593927,
|
|
"loss": 5.9254,
|
|
"mean_token_accuracy": 0.1621394783258438,
|
|
"num_tokens": 19185510.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 6.0319455623626705,
|
|
"epoch": 0.9091310490992582,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004924283815104243,
|
|
"loss": 5.9667,
|
|
"mean_token_accuracy": 0.16688053756952287,
|
|
"num_tokens": 19195459.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 6.176657485961914,
|
|
"epoch": 0.9095725891910985,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004924202786021578,
|
|
"loss": 5.989,
|
|
"mean_token_accuracy": 0.15756237059831618,
|
|
"num_tokens": 19204590.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 6.190572357177734,
|
|
"epoch": 0.9100141292829389,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004924121714347515,
|
|
"loss": 5.9534,
|
|
"mean_token_accuracy": 0.15884590595960618,
|
|
"num_tokens": 19213302.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 6.197195100784302,
|
|
"epoch": 0.9104556693747792,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004924040600083644,
|
|
"loss": 6.0684,
|
|
"mean_token_accuracy": 0.154947692155838,
|
|
"num_tokens": 19223172.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 6.18108868598938,
|
|
"epoch": 0.9108972094666196,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004923959443231554,
|
|
"loss": 5.9656,
|
|
"mean_token_accuracy": 0.15735325068235398,
|
|
"num_tokens": 19232234.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 6.096418237686157,
|
|
"epoch": 0.91133874955846,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004923878243792836,
|
|
"loss": 5.9418,
|
|
"mean_token_accuracy": 0.1593674212694168,
|
|
"num_tokens": 19241070.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 6.177568054199218,
|
|
"epoch": 0.9117802896503002,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004923797001769079,
|
|
"loss": 6.0312,
|
|
"mean_token_accuracy": 0.16176247596740723,
|
|
"num_tokens": 19251094.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 6.284003639221192,
|
|
"epoch": 0.9122218297421406,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004923715717161875,
|
|
"loss": 6.1177,
|
|
"mean_token_accuracy": 0.1512012779712677,
|
|
"num_tokens": 19260588.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 6.246473407745361,
|
|
"epoch": 0.9126633698339809,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004923634389972817,
|
|
"loss": 6.1614,
|
|
"mean_token_accuracy": 0.14666686132550238,
|
|
"num_tokens": 19270687.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 6.129995346069336,
|
|
"epoch": 0.9131049099258213,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004923553020203497,
|
|
"loss": 5.9474,
|
|
"mean_token_accuracy": 0.16146068274974823,
|
|
"num_tokens": 19278739.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 6.315760231018066,
|
|
"epoch": 0.9135464500176615,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004923471607855511,
|
|
"loss": 6.1081,
|
|
"mean_token_accuracy": 0.14812798649072648,
|
|
"num_tokens": 19289184.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 6.219142246246338,
|
|
"epoch": 0.9139879901095019,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.000492339015293045,
|
|
"loss": 5.9659,
|
|
"mean_token_accuracy": 0.1682812362909317,
|
|
"num_tokens": 19298390.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 6.11060905456543,
|
|
"epoch": 0.9144295302013423,
|
|
"grad_norm": 6.90625,
|
|
"learning_rate": 0.0004923308655429913,
|
|
"loss": 5.9021,
|
|
"mean_token_accuracy": 0.16550161987543105,
|
|
"num_tokens": 19307227.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 6.1038957118988035,
|
|
"epoch": 0.9148710702931826,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004923227115355495,
|
|
"loss": 5.9588,
|
|
"mean_token_accuracy": 0.15407850295305253,
|
|
"num_tokens": 19317701.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 6.190516138076783,
|
|
"epoch": 0.915312610385023,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004923145532708794,
|
|
"loss": 6.0538,
|
|
"mean_token_accuracy": 0.15957052856683732,
|
|
"num_tokens": 19326983.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 6.193438386917114,
|
|
"epoch": 0.9157541504768633,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004923063907491408,
|
|
"loss": 6.0553,
|
|
"mean_token_accuracy": 0.15762412548065186,
|
|
"num_tokens": 19337157.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 6.217849206924439,
|
|
"epoch": 0.9161956905687036,
|
|
"grad_norm": 4.375,
|
|
"learning_rate": 0.0004922982239704936,
|
|
"loss": 6.1498,
|
|
"mean_token_accuracy": 0.15656513199210167,
|
|
"num_tokens": 19346845.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 6.305586433410644,
|
|
"epoch": 0.9166372306605439,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004922900529350978,
|
|
"loss": 6.027,
|
|
"mean_token_accuracy": 0.15455891340970992,
|
|
"num_tokens": 19356905.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 6.249670124053955,
|
|
"epoch": 0.9170787707523843,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.0004922818776431134,
|
|
"loss": 6.012,
|
|
"mean_token_accuracy": 0.1489650472998619,
|
|
"num_tokens": 19366595.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 6.233332109451294,
|
|
"epoch": 0.9175203108442247,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004922736980947005,
|
|
"loss": 6.0644,
|
|
"mean_token_accuracy": 0.15061762630939485,
|
|
"num_tokens": 19377213.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 6.136075878143311,
|
|
"epoch": 0.917961850936065,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004922655142900196,
|
|
"loss": 5.9352,
|
|
"mean_token_accuracy": 0.1552181825041771,
|
|
"num_tokens": 19385510.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 6.085175561904907,
|
|
"epoch": 0.9184033910279054,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004922573262292308,
|
|
"loss": 5.9464,
|
|
"mean_token_accuracy": 0.1548845037817955,
|
|
"num_tokens": 19394505.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 6.119608592987061,
|
|
"epoch": 0.9188449311197456,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004922491339124945,
|
|
"loss": 5.8446,
|
|
"mean_token_accuracy": 0.16599608659744264,
|
|
"num_tokens": 19403140.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 6.160563516616821,
|
|
"epoch": 0.919286471211586,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004922409373399713,
|
|
"loss": 6.0634,
|
|
"mean_token_accuracy": 0.15320063084363938,
|
|
"num_tokens": 19412709.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 6.123647928237915,
|
|
"epoch": 0.9197280113034263,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004922327365118216,
|
|
"loss": 5.8959,
|
|
"mean_token_accuracy": 0.1659088060259819,
|
|
"num_tokens": 19422442.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 6.180219507217407,
|
|
"epoch": 0.9201695513952667,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004922245314282062,
|
|
"loss": 6.0409,
|
|
"mean_token_accuracy": 0.15570426285266875,
|
|
"num_tokens": 19432153.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 6.168195962905884,
|
|
"epoch": 0.9206110914871071,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004922163220892858,
|
|
"loss": 5.8333,
|
|
"mean_token_accuracy": 0.17357273697853087,
|
|
"num_tokens": 19440811.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 6.117291784286499,
|
|
"epoch": 0.9210526315789473,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.000492208108495221,
|
|
"loss": 6.0344,
|
|
"mean_token_accuracy": 0.15521479845046998,
|
|
"num_tokens": 19451330.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 6.094224691390991,
|
|
"epoch": 0.9214941716707877,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.000492199890646173,
|
|
"loss": 5.8815,
|
|
"mean_token_accuracy": 0.16824816912412643,
|
|
"num_tokens": 19459689.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 6.163274574279785,
|
|
"epoch": 0.921935711762628,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004921916685423028,
|
|
"loss": 5.943,
|
|
"mean_token_accuracy": 0.16071141958236695,
|
|
"num_tokens": 19468110.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 6.167320251464844,
|
|
"epoch": 0.9223772518544684,
|
|
"grad_norm": 4.40625,
|
|
"learning_rate": 0.0004921834421837711,
|
|
"loss": 5.9947,
|
|
"mean_token_accuracy": 0.15582612305879592,
|
|
"num_tokens": 19477190.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 6.2047117233276365,
|
|
"epoch": 0.9228187919463087,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004921752115707394,
|
|
"loss": 6.0946,
|
|
"mean_token_accuracy": 0.15232176333665848,
|
|
"num_tokens": 19485757.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 6.197108173370362,
|
|
"epoch": 0.9232603320381491,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004921669767033688,
|
|
"loss": 6.0333,
|
|
"mean_token_accuracy": 0.1551002785563469,
|
|
"num_tokens": 19494846.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 6.180310535430908,
|
|
"epoch": 0.9237018721299894,
|
|
"grad_norm": 9.0625,
|
|
"learning_rate": 0.0004921587375818207,
|
|
"loss": 6.0293,
|
|
"mean_token_accuracy": 0.15100041329860686,
|
|
"num_tokens": 19504307.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 6.214234972000122,
|
|
"epoch": 0.9241434122218297,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004921504942062564,
|
|
"loss": 5.9805,
|
|
"mean_token_accuracy": 0.15465851426124572,
|
|
"num_tokens": 19512741.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 6.100347805023193,
|
|
"epoch": 0.9245849523136701,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004921422465768374,
|
|
"loss": 5.8617,
|
|
"mean_token_accuracy": 0.16154198795557023,
|
|
"num_tokens": 19521823.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 6.15104398727417,
|
|
"epoch": 0.9250264924055104,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004921339946937253,
|
|
"loss": 6.0634,
|
|
"mean_token_accuracy": 0.15580296963453294,
|
|
"num_tokens": 19531048.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 6.199530696868896,
|
|
"epoch": 0.9254680324973508,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004921257385570818,
|
|
"loss": 6.0152,
|
|
"mean_token_accuracy": 0.15597717314958573,
|
|
"num_tokens": 19539543.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 6.238590097427368,
|
|
"epoch": 0.925909572589191,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004921174781670685,
|
|
"loss": 6.1305,
|
|
"mean_token_accuracy": 0.15179005190730094,
|
|
"num_tokens": 19549242.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 6.275363397598267,
|
|
"epoch": 0.9263511126810314,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004921092135238473,
|
|
"loss": 6.0273,
|
|
"mean_token_accuracy": 0.14577364027500153,
|
|
"num_tokens": 19558259.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 6.22588005065918,
|
|
"epoch": 0.9267926527728718,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00049210094462758,
|
|
"loss": 6.0251,
|
|
"mean_token_accuracy": 0.16097075939178468,
|
|
"num_tokens": 19567327.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 6.193928194046021,
|
|
"epoch": 0.9272341928647121,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004920926714784288,
|
|
"loss": 6.0363,
|
|
"mean_token_accuracy": 0.15664020031690598,
|
|
"num_tokens": 19576696.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 6.151621580123901,
|
|
"epoch": 0.9276757329565525,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004920843940765555,
|
|
"loss": 5.9212,
|
|
"mean_token_accuracy": 0.16299362182617189,
|
|
"num_tokens": 19585708.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 6.2330797672271725,
|
|
"epoch": 0.9281172730483928,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004920761124221224,
|
|
"loss": 6.0814,
|
|
"mean_token_accuracy": 0.16604722887277604,
|
|
"num_tokens": 19595199.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 6.218397569656372,
|
|
"epoch": 0.9285588131402331,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004920678265152919,
|
|
"loss": 6.0204,
|
|
"mean_token_accuracy": 0.14686674624681473,
|
|
"num_tokens": 19604781.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 6.154498529434204,
|
|
"epoch": 0.9290003532320734,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000492059536356226,
|
|
"loss": 5.9744,
|
|
"mean_token_accuracy": 0.16245217323303224,
|
|
"num_tokens": 19614203.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 6.171329021453857,
|
|
"epoch": 0.9294418933239138,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004920512419450872,
|
|
"loss": 5.9991,
|
|
"mean_token_accuracy": 0.15724168121814727,
|
|
"num_tokens": 19623664.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 6.220635652542114,
|
|
"epoch": 0.9298834334157542,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.000492042943282038,
|
|
"loss": 5.9778,
|
|
"mean_token_accuracy": 0.15525819957256318,
|
|
"num_tokens": 19632960.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 6.1476593017578125,
|
|
"epoch": 0.9303249735075945,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.000492034640367241,
|
|
"loss": 6.0964,
|
|
"mean_token_accuracy": 0.1484966441988945,
|
|
"num_tokens": 19643087.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 6.23501410484314,
|
|
"epoch": 0.9307665135994349,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.000492026333200859,
|
|
"loss": 6.0565,
|
|
"mean_token_accuracy": 0.15510230362415314,
|
|
"num_tokens": 19653015.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 6.26780948638916,
|
|
"epoch": 0.9312080536912751,
|
|
"grad_norm": 3.859375,
|
|
"learning_rate": 0.0004920180217830543,
|
|
"loss": 6.0616,
|
|
"mean_token_accuracy": 0.1520492762327194,
|
|
"num_tokens": 19661569.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 6.125591278076172,
|
|
"epoch": 0.9316495937831155,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00049200970611399,
|
|
"loss": 5.8859,
|
|
"mean_token_accuracy": 0.16664395481348038,
|
|
"num_tokens": 19669559.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 6.075623226165772,
|
|
"epoch": 0.9320911338749558,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004920013861938291,
|
|
"loss": 5.9133,
|
|
"mean_token_accuracy": 0.167872416973114,
|
|
"num_tokens": 19678766.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 6.12970929145813,
|
|
"epoch": 0.9325326739667962,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004919930620227345,
|
|
"loss": 6.0406,
|
|
"mean_token_accuracy": 0.1478048160672188,
|
|
"num_tokens": 19688422.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 6.293255186080932,
|
|
"epoch": 0.9329742140586366,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004919847336008692,
|
|
"loss": 6.078,
|
|
"mean_token_accuracy": 0.152406769990921,
|
|
"num_tokens": 19697206.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 6.224672317504883,
|
|
"epoch": 0.9334157541504768,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004919764009283963,
|
|
"loss": 6.0471,
|
|
"mean_token_accuracy": 0.14844200015068054,
|
|
"num_tokens": 19706065.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 6.173615884780884,
|
|
"epoch": 0.9338572942423172,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004919680640054792,
|
|
"loss": 5.9629,
|
|
"mean_token_accuracy": 0.15830276012420655,
|
|
"num_tokens": 19715402.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 6.136301708221436,
|
|
"epoch": 0.9342988343341575,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.000491959722832281,
|
|
"loss": 5.9186,
|
|
"mean_token_accuracy": 0.16106877475976944,
|
|
"num_tokens": 19724328.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 6.099761629104615,
|
|
"epoch": 0.9347403744259979,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004919513774089653,
|
|
"loss": 6.0097,
|
|
"mean_token_accuracy": 0.16225920021533966,
|
|
"num_tokens": 19734087.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 6.261999607086182,
|
|
"epoch": 0.9351819145178382,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004919430277356955,
|
|
"loss": 5.988,
|
|
"mean_token_accuracy": 0.16102648824453353,
|
|
"num_tokens": 19743010.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 6.181056118011474,
|
|
"epoch": 0.9356234546096786,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004919346738126351,
|
|
"loss": 5.9494,
|
|
"mean_token_accuracy": 0.16381199955940245,
|
|
"num_tokens": 19752212.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 6.174293947219849,
|
|
"epoch": 0.9360649947015189,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004919263156399478,
|
|
"loss": 6.015,
|
|
"mean_token_accuracy": 0.15577296018600464,
|
|
"num_tokens": 19762496.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 6.186666774749756,
|
|
"epoch": 0.9365065347933592,
|
|
"grad_norm": 4.96875,
|
|
"learning_rate": 0.0004919179532177976,
|
|
"loss": 6.0245,
|
|
"mean_token_accuracy": 0.15240861624479293,
|
|
"num_tokens": 19772665.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 6.137942838668823,
|
|
"epoch": 0.9369480748851996,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004919095865463479,
|
|
"loss": 5.8469,
|
|
"mean_token_accuracy": 0.16629263162612914,
|
|
"num_tokens": 19781639.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 6.17881965637207,
|
|
"epoch": 0.9373896149770399,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004919012156257627,
|
|
"loss": 5.9596,
|
|
"mean_token_accuracy": 0.1548631563782692,
|
|
"num_tokens": 19791475.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 6.12343921661377,
|
|
"epoch": 0.9378311550688803,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004918928404562061,
|
|
"loss": 5.9502,
|
|
"mean_token_accuracy": 0.15676655918359755,
|
|
"num_tokens": 19800967.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 6.125112295150757,
|
|
"epoch": 0.9382726951607206,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004918844610378421,
|
|
"loss": 6.0685,
|
|
"mean_token_accuracy": 0.15577329844236373,
|
|
"num_tokens": 19810303.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 6.278899049758911,
|
|
"epoch": 0.9387142352525609,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004918760773708348,
|
|
"loss": 5.9912,
|
|
"mean_token_accuracy": 0.15593978464603425,
|
|
"num_tokens": 19819049.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 6.300095891952514,
|
|
"epoch": 0.9391557753444013,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004918676894553485,
|
|
"loss": 6.0213,
|
|
"mean_token_accuracy": 0.15708844661712645,
|
|
"num_tokens": 19828253.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 6.178868627548217,
|
|
"epoch": 0.9395973154362416,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004918592972915476,
|
|
"loss": 5.9873,
|
|
"mean_token_accuracy": 0.16300770342350007,
|
|
"num_tokens": 19837673.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 6.079726028442383,
|
|
"epoch": 0.940038855528082,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004918509008795963,
|
|
"loss": 6.0048,
|
|
"mean_token_accuracy": 0.15207261741161346,
|
|
"num_tokens": 19846289.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 6.096834373474121,
|
|
"epoch": 0.9404803956199222,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004918425002196594,
|
|
"loss": 5.9845,
|
|
"mean_token_accuracy": 0.1529189318418503,
|
|
"num_tokens": 19855384.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 6.148316192626953,
|
|
"epoch": 0.9409219357117626,
|
|
"grad_norm": 15.9375,
|
|
"learning_rate": 0.000491834095311901,
|
|
"loss": 5.9311,
|
|
"mean_token_accuracy": 0.16442809849977494,
|
|
"num_tokens": 19864688.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 6.205455541610718,
|
|
"epoch": 0.941363475803603,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.000491825686156486,
|
|
"loss": 5.9377,
|
|
"mean_token_accuracy": 0.16152185797691346,
|
|
"num_tokens": 19873692.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 6.235633182525635,
|
|
"epoch": 0.9418050158954433,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004918172727535792,
|
|
"loss": 6.0262,
|
|
"mean_token_accuracy": 0.15295447111129762,
|
|
"num_tokens": 19882063.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 6.193088674545288,
|
|
"epoch": 0.9422465559872837,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004918088551033454,
|
|
"loss": 5.9956,
|
|
"mean_token_accuracy": 0.15469479113817214,
|
|
"num_tokens": 19891727.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 6.111576414108276,
|
|
"epoch": 0.942688096079124,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004918004332059493,
|
|
"loss": 6.0266,
|
|
"mean_token_accuracy": 0.16044130325317382,
|
|
"num_tokens": 19901851.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 6.191736364364624,
|
|
"epoch": 0.9431296361709643,
|
|
"grad_norm": 4.6875,
|
|
"learning_rate": 0.0004917920070615561,
|
|
"loss": 5.9773,
|
|
"mean_token_accuracy": 0.1507607340812683,
|
|
"num_tokens": 19911092.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 6.124292087554932,
|
|
"epoch": 0.9435711762628046,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004917835766703307,
|
|
"loss": 5.9583,
|
|
"mean_token_accuracy": 0.16241815090179443,
|
|
"num_tokens": 19920842.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 6.205943632125854,
|
|
"epoch": 0.944012716354645,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004917751420324384,
|
|
"loss": 6.0482,
|
|
"mean_token_accuracy": 0.15033227056264878,
|
|
"num_tokens": 19930833.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 6.245380783081055,
|
|
"epoch": 0.9444542564464854,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004917667031480444,
|
|
"loss": 6.0621,
|
|
"mean_token_accuracy": 0.15881533920764923,
|
|
"num_tokens": 19940514.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 6.185396575927735,
|
|
"epoch": 0.9448957965383257,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004917582600173138,
|
|
"loss": 5.8882,
|
|
"mean_token_accuracy": 0.16307059526443482,
|
|
"num_tokens": 19948949.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 6.0753607749938965,
|
|
"epoch": 0.9453373366301661,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004917498126404123,
|
|
"loss": 5.8861,
|
|
"mean_token_accuracy": 0.16055179089307786,
|
|
"num_tokens": 19958410.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 6.1283721923828125,
|
|
"epoch": 0.9457788767220063,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004917413610175052,
|
|
"loss": 5.9033,
|
|
"mean_token_accuracy": 0.16776129007339477,
|
|
"num_tokens": 19968160.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 6.223766326904297,
|
|
"epoch": 0.9462204168138467,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004917329051487582,
|
|
"loss": 6.0449,
|
|
"mean_token_accuracy": 0.1501573257148266,
|
|
"num_tokens": 19976811.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 6.282238340377807,
|
|
"epoch": 0.946661956905687,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004917244450343368,
|
|
"loss": 6.1145,
|
|
"mean_token_accuracy": 0.14723313003778457,
|
|
"num_tokens": 19986326.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 6.090417909622192,
|
|
"epoch": 0.9471034969975274,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004917159806744067,
|
|
"loss": 5.8476,
|
|
"mean_token_accuracy": 0.15740818083286284,
|
|
"num_tokens": 19996255.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 6.161284685134888,
|
|
"epoch": 0.9475450370893678,
|
|
"grad_norm": 6.375,
|
|
"learning_rate": 0.0004917075120691338,
|
|
"loss": 6.0485,
|
|
"mean_token_accuracy": 0.1610925927758217,
|
|
"num_tokens": 20004805.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 6.204595232009888,
|
|
"epoch": 0.947986577181208,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004916990392186841,
|
|
"loss": 5.949,
|
|
"mean_token_accuracy": 0.1597094565629959,
|
|
"num_tokens": 20014189.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 6.234174203872681,
|
|
"epoch": 0.9484281172730484,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004916905621232233,
|
|
"loss": 5.9548,
|
|
"mean_token_accuracy": 0.16005349457263945,
|
|
"num_tokens": 20023261.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 6.092266082763672,
|
|
"epoch": 0.9488696573648887,
|
|
"grad_norm": 5.9375,
|
|
"learning_rate": 0.0004916820807829177,
|
|
"loss": 5.9201,
|
|
"mean_token_accuracy": 0.16162907779216767,
|
|
"num_tokens": 20032433.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 6.102322673797607,
|
|
"epoch": 0.9493111974567291,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004916735951979335,
|
|
"loss": 6.039,
|
|
"mean_token_accuracy": 0.15769112557172776,
|
|
"num_tokens": 20041455.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 6.188523387908935,
|
|
"epoch": 0.9497527375485694,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004916651053684366,
|
|
"loss": 6.0707,
|
|
"mean_token_accuracy": 0.15521103143692017,
|
|
"num_tokens": 20050088.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 6.220887088775635,
|
|
"epoch": 0.9501942776404098,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004916566112945936,
|
|
"loss": 6.015,
|
|
"mean_token_accuracy": 0.15838380306959152,
|
|
"num_tokens": 20059114.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 6.190140247344971,
|
|
"epoch": 0.9506358177322501,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004916481129765708,
|
|
"loss": 6.0082,
|
|
"mean_token_accuracy": 0.15650569051504135,
|
|
"num_tokens": 20068692.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 6.13848032951355,
|
|
"epoch": 0.9510773578240904,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004916396104145347,
|
|
"loss": 6.0573,
|
|
"mean_token_accuracy": 0.1557210013270378,
|
|
"num_tokens": 20078380.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 6.095428800582885,
|
|
"epoch": 0.9515188979159308,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004916311036086518,
|
|
"loss": 5.9188,
|
|
"mean_token_accuracy": 0.17131393253803254,
|
|
"num_tokens": 20087849.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 6.14254937171936,
|
|
"epoch": 0.9519604380077711,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004916225925590889,
|
|
"loss": 5.8453,
|
|
"mean_token_accuracy": 0.1693214550614357,
|
|
"num_tokens": 20097253.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 6.199139165878296,
|
|
"epoch": 0.9524019780996115,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004916140772660124,
|
|
"loss": 6.0141,
|
|
"mean_token_accuracy": 0.15481267273426055,
|
|
"num_tokens": 20105931.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 6.219844341278076,
|
|
"epoch": 0.9528435181914517,
|
|
"grad_norm": 7.75,
|
|
"learning_rate": 0.0004916055577295895,
|
|
"loss": 5.9411,
|
|
"mean_token_accuracy": 0.16423480063676835,
|
|
"num_tokens": 20115546.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 6.245632743835449,
|
|
"epoch": 0.9532850582832921,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004915970339499868,
|
|
"loss": 5.9491,
|
|
"mean_token_accuracy": 0.16496830433607101,
|
|
"num_tokens": 20125009.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 6.0463440895080565,
|
|
"epoch": 0.9537265983751325,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004915885059273714,
|
|
"loss": 5.9165,
|
|
"mean_token_accuracy": 0.16282762736082076,
|
|
"num_tokens": 20134007.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 6.1316979885101315,
|
|
"epoch": 0.9541681384669728,
|
|
"grad_norm": 4.59375,
|
|
"learning_rate": 0.0004915799736619104,
|
|
"loss": 5.9346,
|
|
"mean_token_accuracy": 0.16109953820705414,
|
|
"num_tokens": 20142617.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 6.1474696636199955,
|
|
"epoch": 0.9546096785588132,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.000491571437153771,
|
|
"loss": 5.9399,
|
|
"mean_token_accuracy": 0.16747409105300903,
|
|
"num_tokens": 20151732.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 6.218894624710083,
|
|
"epoch": 0.9550512186506535,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004915628964031202,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.15158325284719468,
|
|
"num_tokens": 20161733.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 6.227372789382935,
|
|
"epoch": 0.9554927587424938,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004915543514101253,
|
|
"loss": 5.9769,
|
|
"mean_token_accuracy": 0.15670328438282013,
|
|
"num_tokens": 20171022.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 6.172809410095215,
|
|
"epoch": 0.9559342988343341,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004915458021749541,
|
|
"loss": 6.0131,
|
|
"mean_token_accuracy": 0.15471852123737334,
|
|
"num_tokens": 20180809.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 6.175866937637329,
|
|
"epoch": 0.9563758389261745,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004915372486977736,
|
|
"loss": 5.9278,
|
|
"mean_token_accuracy": 0.16139951944351197,
|
|
"num_tokens": 20189614.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 6.228444051742554,
|
|
"epoch": 0.9568173790180149,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004915286909787516,
|
|
"loss": 6.0879,
|
|
"mean_token_accuracy": 0.1520192638039589,
|
|
"num_tokens": 20199136.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 6.1951131343841555,
|
|
"epoch": 0.9572589191098552,
|
|
"grad_norm": 4.5,
|
|
"learning_rate": 0.0004915201290180556,
|
|
"loss": 5.9582,
|
|
"mean_token_accuracy": 0.16031280308961868,
|
|
"num_tokens": 20208768.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 6.137907934188843,
|
|
"epoch": 0.9577004592016956,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004915115628158535,
|
|
"loss": 5.9426,
|
|
"mean_token_accuracy": 0.15742172300815582,
|
|
"num_tokens": 20218109.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 6.167422342300415,
|
|
"epoch": 0.9581419992935358,
|
|
"grad_norm": 3.984375,
|
|
"learning_rate": 0.000491502992372313,
|
|
"loss": 5.9709,
|
|
"mean_token_accuracy": 0.159721340239048,
|
|
"num_tokens": 20226768.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 6.164302730560303,
|
|
"epoch": 0.9585835393853762,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.000491494417687602,
|
|
"loss": 5.931,
|
|
"mean_token_accuracy": 0.16306218802928923,
|
|
"num_tokens": 20236519.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 6.12832612991333,
|
|
"epoch": 0.9590250794772165,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004914858387618886,
|
|
"loss": 5.9336,
|
|
"mean_token_accuracy": 0.16003130823373796,
|
|
"num_tokens": 20245611.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 6.034099531173706,
|
|
"epoch": 0.9594666195690569,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004914772555953406,
|
|
"loss": 5.8619,
|
|
"mean_token_accuracy": 0.16994949132204057,
|
|
"num_tokens": 20255089.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 6.136065864562989,
|
|
"epoch": 0.9599081596608973,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004914686681881264,
|
|
"loss": 6.0136,
|
|
"mean_token_accuracy": 0.1583478830754757,
|
|
"num_tokens": 20264794.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 6.162253999710083,
|
|
"epoch": 0.9603496997527375,
|
|
"grad_norm": 3.78125,
|
|
"learning_rate": 0.000491460076540414,
|
|
"loss": 5.8834,
|
|
"mean_token_accuracy": 0.17484040260314943,
|
|
"num_tokens": 20274088.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 6.193916702270508,
|
|
"epoch": 0.9607912398445779,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004914514806523718,
|
|
"loss": 6.0727,
|
|
"mean_token_accuracy": 0.15178250670433044,
|
|
"num_tokens": 20283837.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 6.193194770812989,
|
|
"epoch": 0.9612327799364182,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004914428805241683,
|
|
"loss": 5.9377,
|
|
"mean_token_accuracy": 0.15788443386554718,
|
|
"num_tokens": 20293287.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 6.091219902038574,
|
|
"epoch": 0.9616743200282586,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004914342761559718,
|
|
"loss": 5.9446,
|
|
"mean_token_accuracy": 0.15868934839963914,
|
|
"num_tokens": 20302262.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 6.24610071182251,
|
|
"epoch": 0.9621158601200989,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004914256675479509,
|
|
"loss": 6.0211,
|
|
"mean_token_accuracy": 0.15657830536365508,
|
|
"num_tokens": 20312475.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 6.239964199066162,
|
|
"epoch": 0.9625574002119393,
|
|
"grad_norm": 4.3125,
|
|
"learning_rate": 0.0004914170547002742,
|
|
"loss": 6.0375,
|
|
"mean_token_accuracy": 0.15694003701210021,
|
|
"num_tokens": 20322243.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 6.197062206268311,
|
|
"epoch": 0.9629989403037796,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.0004914084376131106,
|
|
"loss": 5.9302,
|
|
"mean_token_accuracy": 0.15753385573625564,
|
|
"num_tokens": 20331299.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 6.076598596572876,
|
|
"epoch": 0.9634404803956199,
|
|
"grad_norm": 4.71875,
|
|
"learning_rate": 0.0004913998162866288,
|
|
"loss": 5.8866,
|
|
"mean_token_accuracy": 0.16386901140213012,
|
|
"num_tokens": 20340800.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 6.118331813812256,
|
|
"epoch": 0.9638820204874603,
|
|
"grad_norm": 5.0,
|
|
"learning_rate": 0.0004913911907209976,
|
|
"loss": 5.9563,
|
|
"mean_token_accuracy": 0.16420629024505615,
|
|
"num_tokens": 20350292.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 6.187256240844727,
|
|
"epoch": 0.9643235605793006,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004913825609163861,
|
|
"loss": 6.0399,
|
|
"mean_token_accuracy": 0.15299595892429352,
|
|
"num_tokens": 20360109.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 6.1300853252410885,
|
|
"epoch": 0.964765100671141,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004913739268729633,
|
|
"loss": 5.8661,
|
|
"mean_token_accuracy": 0.16548800468444824,
|
|
"num_tokens": 20368917.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 6.2461127758026125,
|
|
"epoch": 0.9652066407629812,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004913652885908983,
|
|
"loss": 6.0697,
|
|
"mean_token_accuracy": 0.1535951465368271,
|
|
"num_tokens": 20378580.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 6.219760227203369,
|
|
"epoch": 0.9656481808548216,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004913566460703603,
|
|
"loss": 5.9033,
|
|
"mean_token_accuracy": 0.1624210759997368,
|
|
"num_tokens": 20387497.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 6.162945938110352,
|
|
"epoch": 0.966089720946662,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004913479993115187,
|
|
"loss": 6.0476,
|
|
"mean_token_accuracy": 0.15562895089387893,
|
|
"num_tokens": 20396586.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 6.174739599227905,
|
|
"epoch": 0.9665312610385023,
|
|
"grad_norm": 9.5625,
|
|
"learning_rate": 0.0004913393483145428,
|
|
"loss": 6.1271,
|
|
"mean_token_accuracy": 0.14758048504590987,
|
|
"num_tokens": 20406183.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 6.298451709747314,
|
|
"epoch": 0.9669728011303427,
|
|
"grad_norm": 4.71875,
|
|
"learning_rate": 0.0004913306930796022,
|
|
"loss": 6.0835,
|
|
"mean_token_accuracy": 0.14926106110215187,
|
|
"num_tokens": 20415716.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 6.254632377624512,
|
|
"epoch": 0.967414341222183,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004913220336068662,
|
|
"loss": 5.9834,
|
|
"mean_token_accuracy": 0.15914528518915178,
|
|
"num_tokens": 20424715.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 6.145887804031372,
|
|
"epoch": 0.9678558813140233,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004913133698965048,
|
|
"loss": 5.9686,
|
|
"mean_token_accuracy": 0.16440486609935762,
|
|
"num_tokens": 20434686.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 6.157244634628296,
|
|
"epoch": 0.9682974214058636,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004913047019486874,
|
|
"loss": 5.974,
|
|
"mean_token_accuracy": 0.16015694290399551,
|
|
"num_tokens": 20443619.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 6.139456415176392,
|
|
"epoch": 0.968738961497704,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004912960297635839,
|
|
"loss": 5.9023,
|
|
"mean_token_accuracy": 0.16531845480203627,
|
|
"num_tokens": 20453540.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 6.184057998657226,
|
|
"epoch": 0.9691805015895444,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.0004912873533413641,
|
|
"loss": 6.0138,
|
|
"mean_token_accuracy": 0.1574922278523445,
|
|
"num_tokens": 20463395.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 6.218158340454101,
|
|
"epoch": 0.9696220416813847,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004912786726821982,
|
|
"loss": 5.9655,
|
|
"mean_token_accuracy": 0.15509623140096665,
|
|
"num_tokens": 20472302.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 6.126210069656372,
|
|
"epoch": 0.970063581773225,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.000491269987786256,
|
|
"loss": 5.9908,
|
|
"mean_token_accuracy": 0.1569495067000389,
|
|
"num_tokens": 20482077.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 6.19876651763916,
|
|
"epoch": 0.9705051218650653,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004912612986537078,
|
|
"loss": 5.9797,
|
|
"mean_token_accuracy": 0.15929123461246492,
|
|
"num_tokens": 20492177.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 6.199370384216309,
|
|
"epoch": 0.9709466619569057,
|
|
"grad_norm": 4.59375,
|
|
"learning_rate": 0.0004912526052847238,
|
|
"loss": 6.0219,
|
|
"mean_token_accuracy": 0.1591154769062996,
|
|
"num_tokens": 20502063.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 6.135434913635254,
|
|
"epoch": 0.971388202048746,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004912439076794742,
|
|
"loss": 5.9438,
|
|
"mean_token_accuracy": 0.15248878076672553,
|
|
"num_tokens": 20510631.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 6.1080974578857425,
|
|
"epoch": 0.9718297421405864,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004912352058381293,
|
|
"loss": 5.9895,
|
|
"mean_token_accuracy": 0.15816915333271026,
|
|
"num_tokens": 20519978.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 6.161657285690308,
|
|
"epoch": 0.9722712822324268,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004912264997608599,
|
|
"loss": 5.9769,
|
|
"mean_token_accuracy": 0.15872621834278106,
|
|
"num_tokens": 20529346.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 6.2405179977417,
|
|
"epoch": 0.972712822324267,
|
|
"grad_norm": 5.375,
|
|
"learning_rate": 0.0004912177894478364,
|
|
"loss": 5.9468,
|
|
"mean_token_accuracy": 0.1512127101421356,
|
|
"num_tokens": 20537619.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 6.218065452575684,
|
|
"epoch": 0.9731543624161074,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004912090748992291,
|
|
"loss": 5.9873,
|
|
"mean_token_accuracy": 0.1572415143251419,
|
|
"num_tokens": 20547011.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 6.196943759918213,
|
|
"epoch": 0.9735959025079477,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004912003561152092,
|
|
"loss": 5.931,
|
|
"mean_token_accuracy": 0.15849291533231735,
|
|
"num_tokens": 20556425.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 6.156350564956665,
|
|
"epoch": 0.9740374425997881,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004911916330959472,
|
|
"loss": 5.9256,
|
|
"mean_token_accuracy": 0.16159031242132188,
|
|
"num_tokens": 20565330.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 6.072202873229981,
|
|
"epoch": 0.9744789826916284,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004911829058416141,
|
|
"loss": 6.0361,
|
|
"mean_token_accuracy": 0.16514350175857545,
|
|
"num_tokens": 20575320.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 6.181253576278687,
|
|
"epoch": 0.9749205227834687,
|
|
"grad_norm": 4.53125,
|
|
"learning_rate": 0.0004911741743523808,
|
|
"loss": 5.9265,
|
|
"mean_token_accuracy": 0.16285687908530236,
|
|
"num_tokens": 20585105.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 6.172753810882568,
|
|
"epoch": 0.9753620628753091,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004911654386284184,
|
|
"loss": 5.9814,
|
|
"mean_token_accuracy": 0.15713930875062943,
|
|
"num_tokens": 20593889.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 6.154466199874878,
|
|
"epoch": 0.9758036029671494,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.000491156698669898,
|
|
"loss": 6.0155,
|
|
"mean_token_accuracy": 0.1601693570613861,
|
|
"num_tokens": 20602322.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 6.21231894493103,
|
|
"epoch": 0.9762451430589898,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004911479544769908,
|
|
"loss": 6.1091,
|
|
"mean_token_accuracy": 0.14768424034118652,
|
|
"num_tokens": 20612077.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 6.289440536499024,
|
|
"epoch": 0.9766866831508301,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.000491139206049868,
|
|
"loss": 6.0462,
|
|
"mean_token_accuracy": 0.15645182877779007,
|
|
"num_tokens": 20620683.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 6.279990577697754,
|
|
"epoch": 0.9771282232426705,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004911304533887011,
|
|
"loss": 6.0929,
|
|
"mean_token_accuracy": 0.1489789068698883,
|
|
"num_tokens": 20631124.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 6.194825553894043,
|
|
"epoch": 0.9775697633345107,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004911216964936616,
|
|
"loss": 5.9338,
|
|
"mean_token_accuracy": 0.15422664284706117,
|
|
"num_tokens": 20640515.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 6.151896047592163,
|
|
"epoch": 0.9780113034263511,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004911129353649211,
|
|
"loss": 5.9407,
|
|
"mean_token_accuracy": 0.16204164773225785,
|
|
"num_tokens": 20649819.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 6.195270729064942,
|
|
"epoch": 0.9784528435181915,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.000491104170002651,
|
|
"loss": 5.9594,
|
|
"mean_token_accuracy": 0.15603119134902954,
|
|
"num_tokens": 20657831.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 6.219133758544922,
|
|
"epoch": 0.9788943836100318,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.000491095400407023,
|
|
"loss": 6.0647,
|
|
"mean_token_accuracy": 0.1545814350247383,
|
|
"num_tokens": 20666807.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 6.188013410568237,
|
|
"epoch": 0.9793359237018722,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004910866265782091,
|
|
"loss": 5.9122,
|
|
"mean_token_accuracy": 0.1632992908358574,
|
|
"num_tokens": 20674859.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 6.225031471252441,
|
|
"epoch": 0.9797774637937124,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004910778485163811,
|
|
"loss": 5.9995,
|
|
"mean_token_accuracy": 0.15673470944166185,
|
|
"num_tokens": 20684060.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 6.113849401473999,
|
|
"epoch": 0.9802190038855528,
|
|
"grad_norm": 3.828125,
|
|
"learning_rate": 0.000491069066221711,
|
|
"loss": 5.9228,
|
|
"mean_token_accuracy": 0.16676190495491028,
|
|
"num_tokens": 20693446.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 6.178444194793701,
|
|
"epoch": 0.9806605439773931,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004910602796943707,
|
|
"loss": 6.0555,
|
|
"mean_token_accuracy": 0.15749317556619644,
|
|
"num_tokens": 20702635.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 6.259019804000855,
|
|
"epoch": 0.9811020840692335,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004910514889345323,
|
|
"loss": 6.0168,
|
|
"mean_token_accuracy": 0.1519618071615696,
|
|
"num_tokens": 20712256.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 6.156629848480224,
|
|
"epoch": 0.9815436241610739,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004910426939423682,
|
|
"loss": 5.9555,
|
|
"mean_token_accuracy": 0.1574217200279236,
|
|
"num_tokens": 20720175.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 6.180657577514649,
|
|
"epoch": 0.9819851642529142,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004910338947180506,
|
|
"loss": 5.9952,
|
|
"mean_token_accuracy": 0.16044948101043702,
|
|
"num_tokens": 20729849.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 6.180977296829224,
|
|
"epoch": 0.9824267043447545,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004910250912617519,
|
|
"loss": 5.9287,
|
|
"mean_token_accuracy": 0.16036087423563003,
|
|
"num_tokens": 20739129.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 6.130973815917969,
|
|
"epoch": 0.9828682444365948,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004910162835736445,
|
|
"loss": 5.8996,
|
|
"mean_token_accuracy": 0.16647030115127565,
|
|
"num_tokens": 20748632.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 6.19669394493103,
|
|
"epoch": 0.9833097845284352,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 0.000491007471653901,
|
|
"loss": 5.9654,
|
|
"mean_token_accuracy": 0.1556306153535843,
|
|
"num_tokens": 20758535.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 6.193940210342407,
|
|
"epoch": 0.9837513246202755,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004909986555026939,
|
|
"loss": 5.9795,
|
|
"mean_token_accuracy": 0.15689342916011811,
|
|
"num_tokens": 20768982.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 6.205114030838013,
|
|
"epoch": 0.9841928647121159,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.000490989835120196,
|
|
"loss": 6.0411,
|
|
"mean_token_accuracy": 0.1563404068350792,
|
|
"num_tokens": 20778936.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 6.167696332931518,
|
|
"epoch": 0.9846344048039563,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004909810105065801,
|
|
"loss": 6.0345,
|
|
"mean_token_accuracy": 0.15165605247020722,
|
|
"num_tokens": 20788618.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 6.2161524295806885,
|
|
"epoch": 0.9850759448957965,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004909721816620191,
|
|
"loss": 6.0159,
|
|
"mean_token_accuracy": 0.1615686759352684,
|
|
"num_tokens": 20797721.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 6.186040878295898,
|
|
"epoch": 0.9855174849876369,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004909633485866857,
|
|
"loss": 5.9761,
|
|
"mean_token_accuracy": 0.16043892204761506,
|
|
"num_tokens": 20807305.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 6.07858567237854,
|
|
"epoch": 0.9859590250794772,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004909545112807533,
|
|
"loss": 5.9331,
|
|
"mean_token_accuracy": 0.1650419846177101,
|
|
"num_tokens": 20816984.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 6.1921858310699465,
|
|
"epoch": 0.9864005651713176,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004909456697443948,
|
|
"loss": 6.0483,
|
|
"mean_token_accuracy": 0.152926018089056,
|
|
"num_tokens": 20825738.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 6.22014422416687,
|
|
"epoch": 0.9868421052631579,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.0004909368239777835,
|
|
"loss": 5.9935,
|
|
"mean_token_accuracy": 0.1584202915430069,
|
|
"num_tokens": 20834135.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 6.304402923583984,
|
|
"epoch": 0.9872836453549982,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004909279739810926,
|
|
"loss": 6.0888,
|
|
"mean_token_accuracy": 0.15151295438408852,
|
|
"num_tokens": 20843689.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 6.219657325744629,
|
|
"epoch": 0.9877251854468386,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004909191197544954,
|
|
"loss": 5.9551,
|
|
"mean_token_accuracy": 0.1585159108042717,
|
|
"num_tokens": 20851724.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 6.251550006866455,
|
|
"epoch": 0.9881667255386789,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004909102612981655,
|
|
"loss": 6.1485,
|
|
"mean_token_accuracy": 0.14939290881156922,
|
|
"num_tokens": 20862325.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 6.225513887405396,
|
|
"epoch": 0.9886082656305193,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004909013986122763,
|
|
"loss": 5.9396,
|
|
"mean_token_accuracy": 0.16449217200279237,
|
|
"num_tokens": 20871046.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 6.2365467071533205,
|
|
"epoch": 0.9890498057223596,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.0004908925316970016,
|
|
"loss": 5.9695,
|
|
"mean_token_accuracy": 0.15662687718868257,
|
|
"num_tokens": 20881605.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 6.089207506179809,
|
|
"epoch": 0.9894913458142,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.000490883660552515,
|
|
"loss": 5.9293,
|
|
"mean_token_accuracy": 0.15434980243444443,
|
|
"num_tokens": 20891170.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 6.140697956085205,
|
|
"epoch": 0.9899328859060402,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004908747851789902,
|
|
"loss": 5.9338,
|
|
"mean_token_accuracy": 0.14825039803981782,
|
|
"num_tokens": 20900307.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 6.206425142288208,
|
|
"epoch": 0.9903744259978806,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004908659055766011,
|
|
"loss": 6.0787,
|
|
"mean_token_accuracy": 0.1500147297978401,
|
|
"num_tokens": 20910623.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 6.315029430389404,
|
|
"epoch": 0.990815966089721,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004908570217455218,
|
|
"loss": 5.9929,
|
|
"mean_token_accuracy": 0.16046351343393325,
|
|
"num_tokens": 20919744.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 6.202160263061524,
|
|
"epoch": 0.9912575061815613,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004908481336859262,
|
|
"loss": 6.0605,
|
|
"mean_token_accuracy": 0.15378574877977372,
|
|
"num_tokens": 20928701.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 6.174495458602905,
|
|
"epoch": 0.9916990462734017,
|
|
"grad_norm": 4.0625,
|
|
"learning_rate": 0.0004908392413979884,
|
|
"loss": 6.0277,
|
|
"mean_token_accuracy": 0.14975389391183852,
|
|
"num_tokens": 20937786.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 6.186076211929321,
|
|
"epoch": 0.9921405863652419,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004908303448818825,
|
|
"loss": 5.9562,
|
|
"mean_token_accuracy": 0.16092230379581451,
|
|
"num_tokens": 20947214.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 6.109399318695068,
|
|
"epoch": 0.9925821264570823,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.000490821444137783,
|
|
"loss": 6.0237,
|
|
"mean_token_accuracy": 0.1595834255218506,
|
|
"num_tokens": 20956041.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 6.1674988746643065,
|
|
"epoch": 0.9930236665489226,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004908125391658641,
|
|
"loss": 6.0311,
|
|
"mean_token_accuracy": 0.15522620379924773,
|
|
"num_tokens": 20966162.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 6.203303289413452,
|
|
"epoch": 0.993465206640763,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004908036299663003,
|
|
"loss": 6.0081,
|
|
"mean_token_accuracy": 0.1580747187137604,
|
|
"num_tokens": 20976025.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 6.190470504760742,
|
|
"epoch": 0.9939067467326034,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004907947165392662,
|
|
"loss": 6.0132,
|
|
"mean_token_accuracy": 0.1540180116891861,
|
|
"num_tokens": 20985606.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 6.189827251434326,
|
|
"epoch": 0.9943482868244437,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004907857988849363,
|
|
"loss": 6.0122,
|
|
"mean_token_accuracy": 0.1569234013557434,
|
|
"num_tokens": 20994308.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 6.114636325836182,
|
|
"epoch": 0.994789826916284,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004907768770034853,
|
|
"loss": 5.9451,
|
|
"mean_token_accuracy": 0.16427878886461258,
|
|
"num_tokens": 21003783.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 6.157221126556396,
|
|
"epoch": 0.9952313670081243,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.000490767950895088,
|
|
"loss": 5.9323,
|
|
"mean_token_accuracy": 0.15766710937023162,
|
|
"num_tokens": 21012870.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 6.245476579666137,
|
|
"epoch": 0.9956729070999647,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004907590205599192,
|
|
"loss": 6.0218,
|
|
"mean_token_accuracy": 0.1500089094042778,
|
|
"num_tokens": 21021987.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 6.177654600143432,
|
|
"epoch": 0.996114447191805,
|
|
"grad_norm": 5.6875,
|
|
"learning_rate": 0.000490750085998154,
|
|
"loss": 6.01,
|
|
"mean_token_accuracy": 0.1551889404654503,
|
|
"num_tokens": 21030977.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 6.102250242233277,
|
|
"epoch": 0.9965559872836454,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004907411472099672,
|
|
"loss": 5.974,
|
|
"mean_token_accuracy": 0.15588120222091675,
|
|
"num_tokens": 21039259.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 6.218702745437622,
|
|
"epoch": 0.9969975273754857,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004907322041955341,
|
|
"loss": 6.0466,
|
|
"mean_token_accuracy": 0.1561511978507042,
|
|
"num_tokens": 21049321.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 6.286624622344971,
|
|
"epoch": 0.997439067467326,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004907232569550298,
|
|
"loss": 6.0963,
|
|
"mean_token_accuracy": 0.15165919065475464,
|
|
"num_tokens": 21059469.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 6.217846250534057,
|
|
"epoch": 0.9978806075591664,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004907143054886297,
|
|
"loss": 6.0264,
|
|
"mean_token_accuracy": 0.15524942427873611,
|
|
"num_tokens": 21068694.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 6.136050844192505,
|
|
"epoch": 0.9983221476510067,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.000490705349796509,
|
|
"loss": 5.9753,
|
|
"mean_token_accuracy": 0.15849747359752656,
|
|
"num_tokens": 21077232.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 6.226991510391235,
|
|
"epoch": 0.9987636877428471,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004906963898788431,
|
|
"loss": 5.9824,
|
|
"mean_token_accuracy": 0.154877470433712,
|
|
"num_tokens": 21086517.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 6.236574411392212,
|
|
"epoch": 0.9992052278346873,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004906874257358075,
|
|
"loss": 6.0508,
|
|
"mean_token_accuracy": 0.16054894030094147,
|
|
"num_tokens": 21096969.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 6.190933656692505,
|
|
"epoch": 0.9996467679265277,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.000490678457367578,
|
|
"loss": 5.9732,
|
|
"mean_token_accuracy": 0.15344223529100418,
|
|
"num_tokens": 21106554.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 6.206276178359985,
|
|
"epoch": 1.000088308018368,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004906694847743302,
|
|
"loss": 5.9893,
|
|
"mean_token_accuracy": 0.15358800143003465,
|
|
"num_tokens": 21114829.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 6.214368391036987,
|
|
"epoch": 1.0005298481102085,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004906605079562399,
|
|
"loss": 5.9471,
|
|
"mean_token_accuracy": 0.16381950825452804,
|
|
"num_tokens": 21123568.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 6.154477500915528,
|
|
"epoch": 1.0009713882020488,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004906515269134827,
|
|
"loss": 5.9903,
|
|
"mean_token_accuracy": 0.15432658270001412,
|
|
"num_tokens": 21132811.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 6.174828577041626,
|
|
"epoch": 1.001412928293889,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004906425416462349,
|
|
"loss": 6.0133,
|
|
"mean_token_accuracy": 0.15606007725000381,
|
|
"num_tokens": 21141549.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 6.1920520782470705,
|
|
"epoch": 1.0018544683857293,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004906335521546723,
|
|
"loss": 5.9161,
|
|
"mean_token_accuracy": 0.1637442409992218,
|
|
"num_tokens": 21150603.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 6.032572221755982,
|
|
"epoch": 1.0022960084775698,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004906245584389712,
|
|
"loss": 5.7609,
|
|
"mean_token_accuracy": 0.17506401091814042,
|
|
"num_tokens": 21159842.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 6.12627854347229,
|
|
"epoch": 1.00273754856941,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004906155604993075,
|
|
"loss": 5.8985,
|
|
"mean_token_accuracy": 0.1639697715640068,
|
|
"num_tokens": 21169139.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 6.089358377456665,
|
|
"epoch": 1.0031790886612504,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004906065583358576,
|
|
"loss": 5.8647,
|
|
"mean_token_accuracy": 0.16264504343271255,
|
|
"num_tokens": 21178059.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 6.115440225601196,
|
|
"epoch": 1.0036206287530909,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004905975519487978,
|
|
"loss": 5.8943,
|
|
"mean_token_accuracy": 0.1575951173901558,
|
|
"num_tokens": 21187966.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 6.09847412109375,
|
|
"epoch": 1.0040621688449312,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004905885413383046,
|
|
"loss": 5.9365,
|
|
"mean_token_accuracy": 0.15951112359762193,
|
|
"num_tokens": 21197460.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 6.166648912429809,
|
|
"epoch": 1.0045037089367714,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004905795265045546,
|
|
"loss": 5.9483,
|
|
"mean_token_accuracy": 0.1568487100303173,
|
|
"num_tokens": 21206977.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 6.168020343780517,
|
|
"epoch": 1.0049452490286117,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004905705074477242,
|
|
"loss": 5.9052,
|
|
"mean_token_accuracy": 0.15654271543025972,
|
|
"num_tokens": 21216046.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 6.181176233291626,
|
|
"epoch": 1.0053867891204522,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004905614841679901,
|
|
"loss": 5.9385,
|
|
"mean_token_accuracy": 0.15977095663547516,
|
|
"num_tokens": 21225612.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 6.1381330490112305,
|
|
"epoch": 1.0058283292122925,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004905524566655292,
|
|
"loss": 5.8602,
|
|
"mean_token_accuracy": 0.16055045053362846,
|
|
"num_tokens": 21233641.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 6.090469884872436,
|
|
"epoch": 1.0062698693041328,
|
|
"grad_norm": 5.96875,
|
|
"learning_rate": 0.0004905434249405183,
|
|
"loss": 5.9051,
|
|
"mean_token_accuracy": 0.15970632433891296,
|
|
"num_tokens": 21243444.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 6.095047521591186,
|
|
"epoch": 1.0067114093959733,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004905343889931342,
|
|
"loss": 5.8751,
|
|
"mean_token_accuracy": 0.16488119661808015,
|
|
"num_tokens": 21253473.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 6.152161026000977,
|
|
"epoch": 1.0071529494878135,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.000490525348823554,
|
|
"loss": 5.844,
|
|
"mean_token_accuracy": 0.17127221822738647,
|
|
"num_tokens": 21262049.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 6.125896072387695,
|
|
"epoch": 1.0075944895796538,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.0004905163044319549,
|
|
"loss": 5.8781,
|
|
"mean_token_accuracy": 0.15909457951784134,
|
|
"num_tokens": 21270909.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 6.091321897506714,
|
|
"epoch": 1.008036029671494,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004905072558185139,
|
|
"loss": 5.9928,
|
|
"mean_token_accuracy": 0.1581793926656246,
|
|
"num_tokens": 21280503.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 6.166311883926392,
|
|
"epoch": 1.0084775697633346,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004904982029834083,
|
|
"loss": 5.951,
|
|
"mean_token_accuracy": 0.15546180456876754,
|
|
"num_tokens": 21289957.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 6.182868528366089,
|
|
"epoch": 1.0089191098551749,
|
|
"grad_norm": 8.375,
|
|
"learning_rate": 0.0004904891459268154,
|
|
"loss": 5.9537,
|
|
"mean_token_accuracy": 0.15713533461093904,
|
|
"num_tokens": 21298799.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 6.142367506027222,
|
|
"epoch": 1.0093606499470151,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004904800846489128,
|
|
"loss": 5.9532,
|
|
"mean_token_accuracy": 0.156003238260746,
|
|
"num_tokens": 21308251.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 6.201836109161377,
|
|
"epoch": 1.0098021900388556,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004904710191498779,
|
|
"loss": 5.9665,
|
|
"mean_token_accuracy": 0.1572624810039997,
|
|
"num_tokens": 21317705.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 6.180490493774414,
|
|
"epoch": 1.010243730130696,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.0004904619494298882,
|
|
"loss": 5.929,
|
|
"mean_token_accuracy": 0.15343269407749177,
|
|
"num_tokens": 21326867.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 6.190150737762451,
|
|
"epoch": 1.0106852702225362,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004904528754891215,
|
|
"loss": 5.9551,
|
|
"mean_token_accuracy": 0.16153139024972915,
|
|
"num_tokens": 21336054.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 6.165220642089844,
|
|
"epoch": 1.0111268103143765,
|
|
"grad_norm": 4.53125,
|
|
"learning_rate": 0.0004904437973277555,
|
|
"loss": 5.8814,
|
|
"mean_token_accuracy": 0.16096238791942596,
|
|
"num_tokens": 21344457.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 6.2367006778717045,
|
|
"epoch": 1.011568350406217,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.0004904347149459681,
|
|
"loss": 5.9824,
|
|
"mean_token_accuracy": 0.1612090528011322,
|
|
"num_tokens": 21353639.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 6.103877258300781,
|
|
"epoch": 1.0120098904980572,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004904256283439371,
|
|
"loss": 5.7885,
|
|
"mean_token_accuracy": 0.16498116105794908,
|
|
"num_tokens": 21362005.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 6.1524499416351315,
|
|
"epoch": 1.0124514305898975,
|
|
"grad_norm": 3.859375,
|
|
"learning_rate": 0.0004904165375218405,
|
|
"loss": 5.9533,
|
|
"mean_token_accuracy": 0.15746854841709138,
|
|
"num_tokens": 21371917.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 6.16218113899231,
|
|
"epoch": 1.012892970681738,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.0004904074424798565,
|
|
"loss": 5.9735,
|
|
"mean_token_accuracy": 0.15811279118061067,
|
|
"num_tokens": 21381500.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 6.175776100158691,
|
|
"epoch": 1.0133345107735783,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004903983432181632,
|
|
"loss": 5.8288,
|
|
"mean_token_accuracy": 0.16764068305492402,
|
|
"num_tokens": 21391280.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 6.2048516273498535,
|
|
"epoch": 1.0137760508654186,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004903892397369388,
|
|
"loss": 5.9268,
|
|
"mean_token_accuracy": 0.15447692275047303,
|
|
"num_tokens": 21400371.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 6.035159730911255,
|
|
"epoch": 1.0142175909572588,
|
|
"grad_norm": 3.65625,
|
|
"learning_rate": 0.0004903801320363618,
|
|
"loss": 5.9501,
|
|
"mean_token_accuracy": 0.16072324067354202,
|
|
"num_tokens": 21410493.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 6.150381088256836,
|
|
"epoch": 1.0146591310490993,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004903710201166105,
|
|
"loss": 6.0369,
|
|
"mean_token_accuracy": 0.14643384665250778,
|
|
"num_tokens": 21420516.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 6.187597990036011,
|
|
"epoch": 1.0151006711409396,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004903619039778634,
|
|
"loss": 5.9575,
|
|
"mean_token_accuracy": 0.15411232709884642,
|
|
"num_tokens": 21429614.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 6.219703292846679,
|
|
"epoch": 1.0155422112327799,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.000490352783620299,
|
|
"loss": 5.9102,
|
|
"mean_token_accuracy": 0.1611112102866173,
|
|
"num_tokens": 21438595.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 6.2136434555053714,
|
|
"epoch": 1.0159837513246204,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004903436590440961,
|
|
"loss": 5.9671,
|
|
"mean_token_accuracy": 0.15861888378858566,
|
|
"num_tokens": 21447708.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 6.180592584609985,
|
|
"epoch": 1.0164252914164607,
|
|
"grad_norm": 4.5625,
|
|
"learning_rate": 0.0004903345302494334,
|
|
"loss": 5.9205,
|
|
"mean_token_accuracy": 0.1601620078086853,
|
|
"num_tokens": 21457210.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 6.191863584518432,
|
|
"epoch": 1.016866831508301,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004903253972364897,
|
|
"loss": 5.9389,
|
|
"mean_token_accuracy": 0.15268738567829132,
|
|
"num_tokens": 21466247.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 6.164012002944946,
|
|
"epoch": 1.0173083716001412,
|
|
"grad_norm": 4.40625,
|
|
"learning_rate": 0.0004903162600054439,
|
|
"loss": 5.8735,
|
|
"mean_token_accuracy": 0.1608436480164528,
|
|
"num_tokens": 21475634.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 6.195175266265869,
|
|
"epoch": 1.0177499116919817,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004903071185564751,
|
|
"loss": 6.0045,
|
|
"mean_token_accuracy": 0.15861720144748687,
|
|
"num_tokens": 21485523.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 6.1413788318634035,
|
|
"epoch": 1.018191451783822,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004902979728897623,
|
|
"loss": 5.9403,
|
|
"mean_token_accuracy": 0.1597276136279106,
|
|
"num_tokens": 21494909.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 6.155840253829956,
|
|
"epoch": 1.0186329918756623,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004902888230054846,
|
|
"loss": 5.9702,
|
|
"mean_token_accuracy": 0.15895597785711288,
|
|
"num_tokens": 21504413.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 6.122620058059693,
|
|
"epoch": 1.0190745319675028,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004902796689038213,
|
|
"loss": 5.8599,
|
|
"mean_token_accuracy": 0.16754451021552086,
|
|
"num_tokens": 21514068.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 6.154145002365112,
|
|
"epoch": 1.019516072059343,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004902705105849517,
|
|
"loss": 5.8788,
|
|
"mean_token_accuracy": 0.16204680800437926,
|
|
"num_tokens": 21523536.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 6.113324308395386,
|
|
"epoch": 1.0199576121511833,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004902613480490553,
|
|
"loss": 5.965,
|
|
"mean_token_accuracy": 0.15359012633562089,
|
|
"num_tokens": 21532554.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 6.049493074417114,
|
|
"epoch": 1.0203991522430236,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.0004902521812963116,
|
|
"loss": 5.8511,
|
|
"mean_token_accuracy": 0.16149965971708297,
|
|
"num_tokens": 21542508.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 6.200096559524536,
|
|
"epoch": 1.020840692334864,
|
|
"grad_norm": 4.3125,
|
|
"learning_rate": 0.0004902430103268998,
|
|
"loss": 5.9368,
|
|
"mean_token_accuracy": 0.14979047179222107,
|
|
"num_tokens": 21551954.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 6.244258451461792,
|
|
"epoch": 1.0212822324267044,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004902338351410002,
|
|
"loss": 5.8989,
|
|
"mean_token_accuracy": 0.16174011081457138,
|
|
"num_tokens": 21561676.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 6.194683694839478,
|
|
"epoch": 1.0217237725185446,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.000490224655738792,
|
|
"loss": 5.9995,
|
|
"mean_token_accuracy": 0.1473441541194916,
|
|
"num_tokens": 21571916.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 6.119585227966309,
|
|
"epoch": 1.0221653126103851,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004902154721204552,
|
|
"loss": 5.9213,
|
|
"mean_token_accuracy": 0.16167986690998076,
|
|
"num_tokens": 21581892.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 6.128266525268555,
|
|
"epoch": 1.0226068527022254,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004902062842861696,
|
|
"loss": 5.8725,
|
|
"mean_token_accuracy": 0.16149003356695174,
|
|
"num_tokens": 21591390.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 6.196033906936646,
|
|
"epoch": 1.0230483927940657,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004901970922361154,
|
|
"loss": 5.9845,
|
|
"mean_token_accuracy": 0.15903691053390503,
|
|
"num_tokens": 21600766.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 6.170470571517944,
|
|
"epoch": 1.023489932885906,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004901878959704726,
|
|
"loss": 5.8975,
|
|
"mean_token_accuracy": 0.16713234633207322,
|
|
"num_tokens": 21609264.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 6.205210113525391,
|
|
"epoch": 1.0239314729777464,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004901786954894212,
|
|
"loss": 5.9855,
|
|
"mean_token_accuracy": 0.1524491161108017,
|
|
"num_tokens": 21618409.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 6.130446910858154,
|
|
"epoch": 1.0243730130695867,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004901694907931416,
|
|
"loss": 5.8477,
|
|
"mean_token_accuracy": 0.15585287660360336,
|
|
"num_tokens": 21628158.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 6.152302265167236,
|
|
"epoch": 1.024814553161427,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.000490160281881814,
|
|
"loss": 5.9875,
|
|
"mean_token_accuracy": 0.16069798320531845,
|
|
"num_tokens": 21637859.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 6.184852123260498,
|
|
"epoch": 1.0252560932532675,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004901510687556188,
|
|
"loss": 5.9927,
|
|
"mean_token_accuracy": 0.15484195500612258,
|
|
"num_tokens": 21647389.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 6.150085973739624,
|
|
"epoch": 1.0256976333451078,
|
|
"grad_norm": 8.125,
|
|
"learning_rate": 0.0004901418514147367,
|
|
"loss": 5.9445,
|
|
"mean_token_accuracy": 0.15903750360012053,
|
|
"num_tokens": 21655857.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 6.150744438171387,
|
|
"epoch": 1.026139173436948,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.000490132629859348,
|
|
"loss": 5.8962,
|
|
"mean_token_accuracy": 0.16650709062814711,
|
|
"num_tokens": 21666150.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 6.154983329772949,
|
|
"epoch": 1.0265807135287883,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004901234040896334,
|
|
"loss": 5.9416,
|
|
"mean_token_accuracy": 0.15803727358579636,
|
|
"num_tokens": 21675662.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 6.196630907058716,
|
|
"epoch": 1.0270222536206288,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004901141741057737,
|
|
"loss": 5.9894,
|
|
"mean_token_accuracy": 0.15326767265796662,
|
|
"num_tokens": 21685721.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 6.1874120235443115,
|
|
"epoch": 1.027463793712469,
|
|
"grad_norm": 4.6875,
|
|
"learning_rate": 0.0004901049399079495,
|
|
"loss": 5.947,
|
|
"mean_token_accuracy": 0.16126787662506104,
|
|
"num_tokens": 21694507.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 6.195686292648316,
|
|
"epoch": 1.0279053338043094,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004900957014963421,
|
|
"loss": 5.9507,
|
|
"mean_token_accuracy": 0.1644703760743141,
|
|
"num_tokens": 21704092.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 6.100425577163696,
|
|
"epoch": 1.0283468738961499,
|
|
"grad_norm": 3.796875,
|
|
"learning_rate": 0.0004900864588711321,
|
|
"loss": 5.8766,
|
|
"mean_token_accuracy": 0.16685758382081986,
|
|
"num_tokens": 21713313.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 6.11095404624939,
|
|
"epoch": 1.0287884139879901,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004900772120325008,
|
|
"loss": 5.9207,
|
|
"mean_token_accuracy": 0.16339877992868423,
|
|
"num_tokens": 21721622.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 6.114428520202637,
|
|
"epoch": 1.0292299540798304,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004900679609806291,
|
|
"loss": 5.8843,
|
|
"mean_token_accuracy": 0.1624878764152527,
|
|
"num_tokens": 21730914.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 6.149040985107422,
|
|
"epoch": 1.0296714941716707,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004900587057156985,
|
|
"loss": 5.8667,
|
|
"mean_token_accuracy": 0.163518089056015,
|
|
"num_tokens": 21740124.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 6.176793336868286,
|
|
"epoch": 1.0301130342635112,
|
|
"grad_norm": 4.53125,
|
|
"learning_rate": 0.0004900494462378902,
|
|
"loss": 5.9652,
|
|
"mean_token_accuracy": 0.1554120734333992,
|
|
"num_tokens": 21750013.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 6.1557331562042235,
|
|
"epoch": 1.0305545743553515,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004900401825473854,
|
|
"loss": 5.9452,
|
|
"mean_token_accuracy": 0.158529195189476,
|
|
"num_tokens": 21758842.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 6.116462087631225,
|
|
"epoch": 1.0309961144471917,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004900309146443658,
|
|
"loss": 5.8492,
|
|
"mean_token_accuracy": 0.1661784291267395,
|
|
"num_tokens": 21767002.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 6.13418664932251,
|
|
"epoch": 1.0314376545390322,
|
|
"grad_norm": 3.953125,
|
|
"learning_rate": 0.0004900216425290128,
|
|
"loss": 5.946,
|
|
"mean_token_accuracy": 0.1634654611349106,
|
|
"num_tokens": 21775372.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 6.157120037078857,
|
|
"epoch": 1.0318791946308725,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004900123662015082,
|
|
"loss": 5.9946,
|
|
"mean_token_accuracy": 0.1534305691719055,
|
|
"num_tokens": 21784541.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 6.193939828872681,
|
|
"epoch": 1.0323207347227128,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004900030856620336,
|
|
"loss": 5.8802,
|
|
"mean_token_accuracy": 0.16111927032470702,
|
|
"num_tokens": 21794525.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 6.254008054733276,
|
|
"epoch": 1.032762274814553,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004899938009107708,
|
|
"loss": 5.9328,
|
|
"mean_token_accuracy": 0.15929633378982544,
|
|
"num_tokens": 21804469.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 6.096216106414795,
|
|
"epoch": 1.0332038149063936,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004899845119479019,
|
|
"loss": 5.9296,
|
|
"mean_token_accuracy": 0.16315037310123442,
|
|
"num_tokens": 21813986.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 6.149116039276123,
|
|
"epoch": 1.0336453549982338,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004899752187736085,
|
|
"loss": 5.9257,
|
|
"mean_token_accuracy": 0.16401932388544083,
|
|
"num_tokens": 21824083.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 6.121707201004028,
|
|
"epoch": 1.0340868950900741,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004899659213880728,
|
|
"loss": 5.8642,
|
|
"mean_token_accuracy": 0.16949550211429595,
|
|
"num_tokens": 21833526.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 6.1797881603240965,
|
|
"epoch": 1.0345284351819146,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004899566197914771,
|
|
"loss": 5.9265,
|
|
"mean_token_accuracy": 0.16507390141487122,
|
|
"num_tokens": 21842537.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 6.175706672668457,
|
|
"epoch": 1.034969975273755,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004899473139840033,
|
|
"loss": 5.9196,
|
|
"mean_token_accuracy": 0.15725167691707612,
|
|
"num_tokens": 21851604.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 6.090625,
|
|
"epoch": 1.0354115153655952,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004899380039658339,
|
|
"loss": 5.9913,
|
|
"mean_token_accuracy": 0.15647540837526322,
|
|
"num_tokens": 21861480.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 6.141532373428345,
|
|
"epoch": 1.0358530554574354,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004899286897371513,
|
|
"loss": 5.9551,
|
|
"mean_token_accuracy": 0.1585635870695114,
|
|
"num_tokens": 21870901.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 6.136163282394409,
|
|
"epoch": 1.036294595549276,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.000489919371298138,
|
|
"loss": 5.8344,
|
|
"mean_token_accuracy": 0.17009264677762986,
|
|
"num_tokens": 21880491.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 6.09901065826416,
|
|
"epoch": 1.0367361356411162,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004899100486489763,
|
|
"loss": 5.937,
|
|
"mean_token_accuracy": 0.15906979888677597,
|
|
"num_tokens": 21889833.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 6.076237916946411,
|
|
"epoch": 1.0371776757329565,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004899007217898491,
|
|
"loss": 5.945,
|
|
"mean_token_accuracy": 0.15788724273443222,
|
|
"num_tokens": 21899222.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 6.227149915695191,
|
|
"epoch": 1.037619215824797,
|
|
"grad_norm": 3.8125,
|
|
"learning_rate": 0.0004898913907209389,
|
|
"loss": 5.9578,
|
|
"mean_token_accuracy": 0.15345034524798393,
|
|
"num_tokens": 21908848.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 6.198890542984008,
|
|
"epoch": 1.0380607559166373,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004898820554424285,
|
|
"loss": 5.8843,
|
|
"mean_token_accuracy": 0.15585824102163315,
|
|
"num_tokens": 21917867.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 6.2142982006073,
|
|
"epoch": 1.0385022960084775,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.000489872715954501,
|
|
"loss": 5.9687,
|
|
"mean_token_accuracy": 0.152188478410244,
|
|
"num_tokens": 21927476.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 6.214330387115479,
|
|
"epoch": 1.0389438361003178,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004898633722573391,
|
|
"loss": 6.0303,
|
|
"mean_token_accuracy": 0.15347810685634614,
|
|
"num_tokens": 21937068.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 6.129259490966797,
|
|
"epoch": 1.0393853761921583,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.000489854024351126,
|
|
"loss": 5.8966,
|
|
"mean_token_accuracy": 0.16052083373069764,
|
|
"num_tokens": 21946144.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 6.185786390304566,
|
|
"epoch": 1.0398269162839986,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004898446722360446,
|
|
"loss": 5.8318,
|
|
"mean_token_accuracy": 0.16848260313272476,
|
|
"num_tokens": 21955346.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 6.1774369239807125,
|
|
"epoch": 1.0402684563758389,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004898353159122784,
|
|
"loss": 5.9246,
|
|
"mean_token_accuracy": 0.15950198024511336,
|
|
"num_tokens": 21965034.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 6.155341625213623,
|
|
"epoch": 1.0407099964676794,
|
|
"grad_norm": 5.71875,
|
|
"learning_rate": 0.0004898259553800106,
|
|
"loss": 5.9058,
|
|
"mean_token_accuracy": 0.15801970213651656,
|
|
"num_tokens": 21975167.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 6.178949689865112,
|
|
"epoch": 1.0411515365595196,
|
|
"grad_norm": 3.71875,
|
|
"learning_rate": 0.0004898165906394244,
|
|
"loss": 5.8888,
|
|
"mean_token_accuracy": 0.1605347737669945,
|
|
"num_tokens": 21984372.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 6.113554239273071,
|
|
"epoch": 1.04159307665136,
|
|
"grad_norm": 3.6875,
|
|
"learning_rate": 0.0004898072216907033,
|
|
"loss": 5.8976,
|
|
"mean_token_accuracy": 0.15484814941883088,
|
|
"num_tokens": 21993513.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 6.145312404632568,
|
|
"epoch": 1.0420346167432002,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004897978485340311,
|
|
"loss": 5.9649,
|
|
"mean_token_accuracy": 0.15129612386226654,
|
|
"num_tokens": 22002593.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 6.229594421386719,
|
|
"epoch": 1.0424761568350407,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.000489788471169591,
|
|
"loss": 5.9708,
|
|
"mean_token_accuracy": 0.15879204273223876,
|
|
"num_tokens": 22012296.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 6.222621250152588,
|
|
"epoch": 1.042917696926881,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004897790895975671,
|
|
"loss": 6.0244,
|
|
"mean_token_accuracy": 0.15057723820209504,
|
|
"num_tokens": 22021267.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 6.146600437164307,
|
|
"epoch": 1.0433592370187212,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.0004897697038181428,
|
|
"loss": 5.9483,
|
|
"mean_token_accuracy": 0.16155195981264114,
|
|
"num_tokens": 22030878.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 6.079737377166748,
|
|
"epoch": 1.0438007771105617,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004897603138315022,
|
|
"loss": 5.9586,
|
|
"mean_token_accuracy": 0.16057838797569274,
|
|
"num_tokens": 22040245.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 6.184117650985717,
|
|
"epoch": 1.044242317202402,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004897509196378293,
|
|
"loss": 5.9458,
|
|
"mean_token_accuracy": 0.16077676713466643,
|
|
"num_tokens": 22050169.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 6.250207996368408,
|
|
"epoch": 1.0446838572942423,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.000489741521237308,
|
|
"loss": 5.9736,
|
|
"mean_token_accuracy": 0.15720196366310119,
|
|
"num_tokens": 22059168.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 6.138293361663818,
|
|
"epoch": 1.0451253973860826,
|
|
"grad_norm": 6.5,
|
|
"learning_rate": 0.0004897321186301223,
|
|
"loss": 5.9075,
|
|
"mean_token_accuracy": 0.1591096416115761,
|
|
"num_tokens": 22068326.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 6.160605764389038,
|
|
"epoch": 1.045566937477923,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004897227118164566,
|
|
"loss": 5.9326,
|
|
"mean_token_accuracy": 0.16288507133722305,
|
|
"num_tokens": 22078026.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 6.159685182571411,
|
|
"epoch": 1.0460084775697633,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.000489713300796495,
|
|
"loss": 5.9839,
|
|
"mean_token_accuracy": 0.15039085000753402,
|
|
"num_tokens": 22088230.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 6.077940797805786,
|
|
"epoch": 1.0464500176616036,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004897038855704221,
|
|
"loss": 5.795,
|
|
"mean_token_accuracy": 0.17047708332538605,
|
|
"num_tokens": 22096667.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 6.1295373916625975,
|
|
"epoch": 1.0468915577534441,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004896944661384222,
|
|
"loss": 5.9218,
|
|
"mean_token_accuracy": 0.16085873395204545,
|
|
"num_tokens": 22106871.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 6.202170372009277,
|
|
"epoch": 1.0473330978452844,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004896850425006797,
|
|
"loss": 5.8754,
|
|
"mean_token_accuracy": 0.1568978562951088,
|
|
"num_tokens": 22114954.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 6.123904180526734,
|
|
"epoch": 1.0477746379371247,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.0004896756146573794,
|
|
"loss": 5.9086,
|
|
"mean_token_accuracy": 0.15844995230436326,
|
|
"num_tokens": 22125293.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 6.214665269851684,
|
|
"epoch": 1.048216178028965,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004896661826087059,
|
|
"loss": 5.9516,
|
|
"mean_token_accuracy": 0.16156904697418212,
|
|
"num_tokens": 22133731.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 6.090568351745605,
|
|
"epoch": 1.0486577181208054,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004896567463548439,
|
|
"loss": 5.9287,
|
|
"mean_token_accuracy": 0.15373207181692122,
|
|
"num_tokens": 22143007.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 6.097213315963745,
|
|
"epoch": 1.0490992582126457,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004896473058959783,
|
|
"loss": 5.9702,
|
|
"mean_token_accuracy": 0.16133466511964797,
|
|
"num_tokens": 22152044.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 6.24034276008606,
|
|
"epoch": 1.049540798304486,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004896378612322942,
|
|
"loss": 6.006,
|
|
"mean_token_accuracy": 0.15323544591665267,
|
|
"num_tokens": 22161473.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 6.170629644393921,
|
|
"epoch": 1.0499823383963265,
|
|
"grad_norm": 4.40625,
|
|
"learning_rate": 0.0004896284123639763,
|
|
"loss": 5.9185,
|
|
"mean_token_accuracy": 0.1587260454893112,
|
|
"num_tokens": 22171704.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 6.1624367237091064,
|
|
"epoch": 1.0504238784881668,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.00048961895929121,
|
|
"loss": 5.9177,
|
|
"mean_token_accuracy": 0.15345404297113419,
|
|
"num_tokens": 22180593.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 6.148451614379883,
|
|
"epoch": 1.050865418580007,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004896095020141802,
|
|
"loss": 5.8895,
|
|
"mean_token_accuracy": 0.16307324469089507,
|
|
"num_tokens": 22189552.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 6.156101417541504,
|
|
"epoch": 1.0513069586718473,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004896000405330724,
|
|
"loss": 5.9152,
|
|
"mean_token_accuracy": 0.15955967903137208,
|
|
"num_tokens": 22199314.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 6.04547085762024,
|
|
"epoch": 1.0517484987636878,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000489590574848072,
|
|
"loss": 5.8943,
|
|
"mean_token_accuracy": 0.16911342293024062,
|
|
"num_tokens": 22208128.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 6.062590312957764,
|
|
"epoch": 1.052190038855528,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.000489581104959364,
|
|
"loss": 5.8633,
|
|
"mean_token_accuracy": 0.1628858581185341,
|
|
"num_tokens": 22217700.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 6.165154886245728,
|
|
"epoch": 1.0526315789473684,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004895716308671343,
|
|
"loss": 5.9322,
|
|
"mean_token_accuracy": 0.1612838864326477,
|
|
"num_tokens": 22225941.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 6.1347064018249515,
|
|
"epoch": 1.0530731190392089,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004895621525715685,
|
|
"loss": 5.8912,
|
|
"mean_token_accuracy": 0.16051552891731263,
|
|
"num_tokens": 22234935.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 6.132886457443237,
|
|
"epoch": 1.0535146591310491,
|
|
"grad_norm": 4.34375,
|
|
"learning_rate": 0.0004895526700728521,
|
|
"loss": 5.9747,
|
|
"mean_token_accuracy": 0.16112820357084273,
|
|
"num_tokens": 22244087.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 6.146267557144165,
|
|
"epoch": 1.0539561992228894,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004895431833711708,
|
|
"loss": 5.9258,
|
|
"mean_token_accuracy": 0.15657443851232528,
|
|
"num_tokens": 22254277.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 6.17157735824585,
|
|
"epoch": 1.0543977393147297,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.0004895336924667107,
|
|
"loss": 5.8815,
|
|
"mean_token_accuracy": 0.16508007943630218,
|
|
"num_tokens": 22263150.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 6.173756694793701,
|
|
"epoch": 1.0548392794065702,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004895241973596576,
|
|
"loss": 5.9115,
|
|
"mean_token_accuracy": 0.16058234125375748,
|
|
"num_tokens": 22271973.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 6.107911205291748,
|
|
"epoch": 1.0552808194984105,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004895146980501973,
|
|
"loss": 5.8854,
|
|
"mean_token_accuracy": 0.1664498120546341,
|
|
"num_tokens": 22280637.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 6.124010848999023,
|
|
"epoch": 1.0557223595902507,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004895051945385163,
|
|
"loss": 5.9039,
|
|
"mean_token_accuracy": 0.16170118302106856,
|
|
"num_tokens": 22290601.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 6.182231855392456,
|
|
"epoch": 1.0561638996820912,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004894956868248004,
|
|
"loss": 5.9424,
|
|
"mean_token_accuracy": 0.1595696061849594,
|
|
"num_tokens": 22300212.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 6.214186763763427,
|
|
"epoch": 1.0566054397739315,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004894861749092359,
|
|
"loss": 5.9153,
|
|
"mean_token_accuracy": 0.1592661112546921,
|
|
"num_tokens": 22309171.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 6.099295663833618,
|
|
"epoch": 1.0570469798657718,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004894766587920094,
|
|
"loss": 5.9269,
|
|
"mean_token_accuracy": 0.16791395246982574,
|
|
"num_tokens": 22318457.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 6.208569288253784,
|
|
"epoch": 1.057488519957612,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.000489467138473307,
|
|
"loss": 5.9277,
|
|
"mean_token_accuracy": 0.1591622695326805,
|
|
"num_tokens": 22327077.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 6.142443895339966,
|
|
"epoch": 1.0579300600494526,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004894576139533154,
|
|
"loss": 5.9294,
|
|
"mean_token_accuracy": 0.1621837630867958,
|
|
"num_tokens": 22336259.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 6.147655057907104,
|
|
"epoch": 1.0583716001412928,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 0.000489448085232221,
|
|
"loss": 5.8967,
|
|
"mean_token_accuracy": 0.17437706738710404,
|
|
"num_tokens": 22344978.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 6.140650081634521,
|
|
"epoch": 1.058813140233133,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004894385523102107,
|
|
"loss": 5.9268,
|
|
"mean_token_accuracy": 0.157879801094532,
|
|
"num_tokens": 22353950.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 6.189157724380493,
|
|
"epoch": 1.0592546803249736,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004894290151874711,
|
|
"loss": 5.8813,
|
|
"mean_token_accuracy": 0.15687581300735473,
|
|
"num_tokens": 22363100.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 6.090399932861328,
|
|
"epoch": 1.0596962204168139,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.000489419473864189,
|
|
"loss": 5.8611,
|
|
"mean_token_accuracy": 0.16944732517004013,
|
|
"num_tokens": 22371979.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.0596962204168139,
|
|
"eval_entropy": 5.936019211852267,
|
|
"eval_loss": 6.008758068084717,
|
|
"eval_mean_token_accuracy": 0.16387403600808076,
|
|
"eval_num_tokens": 22371979.0,
|
|
"eval_runtime": 26.0247,
|
|
"eval_samples_per_second": 1356.981,
|
|
"eval_steps_per_second": 169.647,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 6.114017915725708,
|
|
"epoch": 1.0601377605086542,
|
|
"grad_norm": 4.5,
|
|
"learning_rate": 0.0004894099283405515,
|
|
"loss": 5.8816,
|
|
"mean_token_accuracy": 0.16182024776935577,
|
|
"num_tokens": 22380987.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 6.134852933883667,
|
|
"epoch": 1.0605793006004944,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.0004894003786167452,
|
|
"loss": 5.9509,
|
|
"mean_token_accuracy": 0.1527145341038704,
|
|
"num_tokens": 22389367.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 6.195053482055664,
|
|
"epoch": 1.061020840692335,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004893908246929576,
|
|
"loss": 6.0065,
|
|
"mean_token_accuracy": 0.1539388418197632,
|
|
"num_tokens": 22399158.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 6.239836120605469,
|
|
"epoch": 1.0614623807841752,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004893812665693755,
|
|
"loss": 5.9707,
|
|
"mean_token_accuracy": 0.15816060453653336,
|
|
"num_tokens": 22408245.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 6.172027349472046,
|
|
"epoch": 1.0619039208760155,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004893717042461865,
|
|
"loss": 5.9485,
|
|
"mean_token_accuracy": 0.16011442244052887,
|
|
"num_tokens": 22417014.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 6.192820358276367,
|
|
"epoch": 1.062345460967856,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004893621377235777,
|
|
"loss": 5.8893,
|
|
"mean_token_accuracy": 0.16173512786626815,
|
|
"num_tokens": 22426504.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 6.2348034381866455,
|
|
"epoch": 1.0627870010596963,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 0.0004893525670017364,
|
|
"loss": 5.9944,
|
|
"mean_token_accuracy": 0.15601857602596284,
|
|
"num_tokens": 22435859.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 6.217994928359985,
|
|
"epoch": 1.0632285411515365,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004893429920808503,
|
|
"loss": 5.9204,
|
|
"mean_token_accuracy": 0.16233511120080948,
|
|
"num_tokens": 22445112.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 6.179212856292724,
|
|
"epoch": 1.0636700812433768,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.000489333412961107,
|
|
"loss": 5.9679,
|
|
"mean_token_accuracy": 0.15648476928472518,
|
|
"num_tokens": 22454602.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 6.229143381118774,
|
|
"epoch": 1.0641116213352173,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004893238296426939,
|
|
"loss": 5.9923,
|
|
"mean_token_accuracy": 0.1561363086104393,
|
|
"num_tokens": 22463918.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 6.149765300750732,
|
|
"epoch": 1.0645531614270576,
|
|
"grad_norm": 3.65625,
|
|
"learning_rate": 0.0004893142421257989,
|
|
"loss": 5.8841,
|
|
"mean_token_accuracy": 0.15609944760799407,
|
|
"num_tokens": 22473059.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 6.110332059860229,
|
|
"epoch": 1.0649947015188979,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004893046504106099,
|
|
"loss": 5.9448,
|
|
"mean_token_accuracy": 0.15709808468818665,
|
|
"num_tokens": 22482615.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 6.111856079101562,
|
|
"epoch": 1.0654362416107384,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.0004892950544973145,
|
|
"loss": 5.8673,
|
|
"mean_token_accuracy": 0.16662584245204926,
|
|
"num_tokens": 22492141.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 6.180486536026001,
|
|
"epoch": 1.0658777817025786,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004892854543861009,
|
|
"loss": 5.8295,
|
|
"mean_token_accuracy": 0.16754715293645858,
|
|
"num_tokens": 22502084.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 6.156108236312866,
|
|
"epoch": 1.066319321794419,
|
|
"grad_norm": 3.828125,
|
|
"learning_rate": 0.0004892758500771572,
|
|
"loss": 5.8538,
|
|
"mean_token_accuracy": 0.1638255760073662,
|
|
"num_tokens": 22510565.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 6.177877473831177,
|
|
"epoch": 1.0667608618862592,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004892662415706714,
|
|
"loss": 5.9665,
|
|
"mean_token_accuracy": 0.15753857493400575,
|
|
"num_tokens": 22520089.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 6.118342351913452,
|
|
"epoch": 1.0672024019780997,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004892566288668319,
|
|
"loss": 5.8933,
|
|
"mean_token_accuracy": 0.1633586660027504,
|
|
"num_tokens": 22529008.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 6.140356922149659,
|
|
"epoch": 1.06764394206994,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 0.0004892470119658267,
|
|
"loss": 5.8654,
|
|
"mean_token_accuracy": 0.164863882958889,
|
|
"num_tokens": 22538040.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 6.191899681091309,
|
|
"epoch": 1.0680854821617802,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004892373908678445,
|
|
"loss": 5.9458,
|
|
"mean_token_accuracy": 0.15595253705978393,
|
|
"num_tokens": 22548786.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 6.234998321533203,
|
|
"epoch": 1.0685270222536207,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004892277655730736,
|
|
"loss": 5.9289,
|
|
"mean_token_accuracy": 0.162250292301178,
|
|
"num_tokens": 22559841.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 6.207377529144287,
|
|
"epoch": 1.068968562345461,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004892181360817027,
|
|
"loss": 5.867,
|
|
"mean_token_accuracy": 0.1664956107735634,
|
|
"num_tokens": 22569338.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 6.111291885375977,
|
|
"epoch": 1.0694101024373013,
|
|
"grad_norm": 5.125,
|
|
"learning_rate": 0.0004892085023939204,
|
|
"loss": 5.9291,
|
|
"mean_token_accuracy": 0.155917289853096,
|
|
"num_tokens": 22578184.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 6.176279306411743,
|
|
"epoch": 1.0698516425291416,
|
|
"grad_norm": 4.375,
|
|
"learning_rate": 0.0004891988645099151,
|
|
"loss": 6.0379,
|
|
"mean_token_accuracy": 0.1512170098721981,
|
|
"num_tokens": 22587007.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 6.1934202194213865,
|
|
"epoch": 1.070293182620982,
|
|
"grad_norm": 20.0,
|
|
"learning_rate": 0.0004891892224298761,
|
|
"loss": 5.958,
|
|
"mean_token_accuracy": 0.15347342044115067,
|
|
"num_tokens": 22596898.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 6.175861072540283,
|
|
"epoch": 1.0707347227128223,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.000489179576153992,
|
|
"loss": 5.8603,
|
|
"mean_token_accuracy": 0.17192627489566803,
|
|
"num_tokens": 22605627.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 6.128075122833252,
|
|
"epoch": 1.0711762628046626,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004891699256824518,
|
|
"loss": 5.8313,
|
|
"mean_token_accuracy": 0.16555165946483613,
|
|
"num_tokens": 22615269.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 6.102174139022827,
|
|
"epoch": 1.071617802896503,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.0004891602710154446,
|
|
"loss": 5.8827,
|
|
"mean_token_accuracy": 0.1575715348124504,
|
|
"num_tokens": 22625048.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 6.094519901275635,
|
|
"epoch": 1.0720593429883434,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004891506121531593,
|
|
"loss": 5.8761,
|
|
"mean_token_accuracy": 0.1634797066450119,
|
|
"num_tokens": 22634146.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 6.146231031417846,
|
|
"epoch": 1.0725008830801837,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.0004891409490957855,
|
|
"loss": 5.9562,
|
|
"mean_token_accuracy": 0.159510750323534,
|
|
"num_tokens": 22642915.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 6.2338377952575685,
|
|
"epoch": 1.072942423172024,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004891312818435122,
|
|
"loss": 5.8788,
|
|
"mean_token_accuracy": 0.15790450870990752,
|
|
"num_tokens": 22651546.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 6.223159980773926,
|
|
"epoch": 1.0733839632638644,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.000489121610396529,
|
|
"loss": 5.9171,
|
|
"mean_token_accuracy": 0.1610031321644783,
|
|
"num_tokens": 22660712.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 6.140164184570312,
|
|
"epoch": 1.0738255033557047,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004891119347550251,
|
|
"loss": 5.8801,
|
|
"mean_token_accuracy": 0.16884622126817703,
|
|
"num_tokens": 22669428.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 6.134841394424439,
|
|
"epoch": 1.074267043447545,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004891022549191902,
|
|
"loss": 5.9763,
|
|
"mean_token_accuracy": 0.15740178823471068,
|
|
"num_tokens": 22679126.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 6.046198177337646,
|
|
"epoch": 1.0747085835393855,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004890925708892138,
|
|
"loss": 5.8643,
|
|
"mean_token_accuracy": 0.16726138740777968,
|
|
"num_tokens": 22688640.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 6.173946762084961,
|
|
"epoch": 1.0751501236312258,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 0.000489082882665286,
|
|
"loss": 5.8406,
|
|
"mean_token_accuracy": 0.16655810922384262,
|
|
"num_tokens": 22698158.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 6.106610918045044,
|
|
"epoch": 1.075591663723066,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.000489073190247596,
|
|
"loss": 5.7853,
|
|
"mean_token_accuracy": 0.17605790197849275,
|
|
"num_tokens": 22707649.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 6.20052547454834,
|
|
"epoch": 1.0760332038149063,
|
|
"grad_norm": 3.859375,
|
|
"learning_rate": 0.000489063493636334,
|
|
"loss": 5.9799,
|
|
"mean_token_accuracy": 0.1654104471206665,
|
|
"num_tokens": 22717123.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 6.157053995132446,
|
|
"epoch": 1.0764747439067468,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004890537928316901,
|
|
"loss": 5.9086,
|
|
"mean_token_accuracy": 0.16282155960798264,
|
|
"num_tokens": 22725921.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 6.175580406188965,
|
|
"epoch": 1.076916283998587,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004890440878338538,
|
|
"loss": 6.0119,
|
|
"mean_token_accuracy": 0.15466470122337342,
|
|
"num_tokens": 22735798.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 6.1869574069976805,
|
|
"epoch": 1.0773578240904274,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004890343786430158,
|
|
"loss": 5.9862,
|
|
"mean_token_accuracy": 0.1566761016845703,
|
|
"num_tokens": 22745583.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 6.1388157367706295,
|
|
"epoch": 1.0777993641822678,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.000489024665259366,
|
|
"loss": 5.8229,
|
|
"mean_token_accuracy": 0.1679653689265251,
|
|
"num_tokens": 22754693.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 6.05749831199646,
|
|
"epoch": 1.0782409042741081,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.0004890149476830947,
|
|
"loss": 5.8255,
|
|
"mean_token_accuracy": 0.16756767332553862,
|
|
"num_tokens": 22763416.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 6.107419824600219,
|
|
"epoch": 1.0786824443659484,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004890052259143924,
|
|
"loss": 5.8998,
|
|
"mean_token_accuracy": 0.1657376393675804,
|
|
"num_tokens": 22772411.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 6.068491840362549,
|
|
"epoch": 1.0791239844577887,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004889954999534493,
|
|
"loss": 5.7567,
|
|
"mean_token_accuracy": 0.1732191562652588,
|
|
"num_tokens": 22780148.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 6.0916108131408695,
|
|
"epoch": 1.0795655245496292,
|
|
"grad_norm": 4.625,
|
|
"learning_rate": 0.0004889857698004561,
|
|
"loss": 5.869,
|
|
"mean_token_accuracy": 0.16153077334165572,
|
|
"num_tokens": 22789453.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 6.190332221984863,
|
|
"epoch": 1.0800070646414694,
|
|
"grad_norm": 3.984375,
|
|
"learning_rate": 0.0004889760354556033,
|
|
"loss": 5.9167,
|
|
"mean_token_accuracy": 0.16472706943750381,
|
|
"num_tokens": 22798800.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 6.125522041320801,
|
|
"epoch": 1.0804486047333097,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004889662969190817,
|
|
"loss": 5.9726,
|
|
"mean_token_accuracy": 0.1637173995375633,
|
|
"num_tokens": 22807766.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 6.102245473861695,
|
|
"epoch": 1.0808901448251502,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004889565541910822,
|
|
"loss": 5.8814,
|
|
"mean_token_accuracy": 0.16091295182704926,
|
|
"num_tokens": 22817316.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 6.132245779037476,
|
|
"epoch": 1.0813316849169905,
|
|
"grad_norm": 3.78125,
|
|
"learning_rate": 0.0004889468072717953,
|
|
"loss": 5.9222,
|
|
"mean_token_accuracy": 0.16387611627578735,
|
|
"num_tokens": 22827082.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 6.159386014938354,
|
|
"epoch": 1.0817732250088308,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004889370561614122,
|
|
"loss": 5.9044,
|
|
"mean_token_accuracy": 0.16351822763681412,
|
|
"num_tokens": 22836114.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 6.191832399368286,
|
|
"epoch": 1.082214765100671,
|
|
"grad_norm": 5.09375,
|
|
"learning_rate": 0.0004889273008601238,
|
|
"loss": 6.0257,
|
|
"mean_token_accuracy": 0.15433973893523217,
|
|
"num_tokens": 22845653.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 6.22887487411499,
|
|
"epoch": 1.0826563051925115,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004889175413681213,
|
|
"loss": 5.9441,
|
|
"mean_token_accuracy": 0.16206600964069368,
|
|
"num_tokens": 22855472.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 6.143603515625,
|
|
"epoch": 1.0830978452843518,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004889077776855957,
|
|
"loss": 5.8751,
|
|
"mean_token_accuracy": 0.16495681256055833,
|
|
"num_tokens": 22864223.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 6.133127117156983,
|
|
"epoch": 1.083539385376192,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004888980098127385,
|
|
"loss": 5.9604,
|
|
"mean_token_accuracy": 0.15613909363746642,
|
|
"num_tokens": 22872868.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 6.190570926666259,
|
|
"epoch": 1.0839809254680326,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004888882377497409,
|
|
"loss": 5.9698,
|
|
"mean_token_accuracy": 0.15288522988557815,
|
|
"num_tokens": 22881867.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 6.202322006225586,
|
|
"epoch": 1.0844224655598729,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004888784614967943,
|
|
"loss": 5.8926,
|
|
"mean_token_accuracy": 0.15369175523519515,
|
|
"num_tokens": 22890904.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 6.130778217315674,
|
|
"epoch": 1.0848640056517131,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004888686810540905,
|
|
"loss": 5.8424,
|
|
"mean_token_accuracy": 0.1671067714691162,
|
|
"num_tokens": 22900128.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 6.162302684783936,
|
|
"epoch": 1.0853055457435534,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004888588964218208,
|
|
"loss": 5.9475,
|
|
"mean_token_accuracy": 0.15772829204797745,
|
|
"num_tokens": 22910101.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 6.16146240234375,
|
|
"epoch": 1.085747085835394,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004888491076001768,
|
|
"loss": 5.8911,
|
|
"mean_token_accuracy": 0.1635946586728096,
|
|
"num_tokens": 22919372.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 6.167607736587525,
|
|
"epoch": 1.0861886259272342,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004888393145893505,
|
|
"loss": 5.9287,
|
|
"mean_token_accuracy": 0.15791655331850052,
|
|
"num_tokens": 22929053.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 6.098089218139648,
|
|
"epoch": 1.0866301660190745,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004888295173895335,
|
|
"loss": 5.8579,
|
|
"mean_token_accuracy": 0.16462911069393157,
|
|
"num_tokens": 22938173.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 6.102741050720215,
|
|
"epoch": 1.087071706110915,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004888197160009181,
|
|
"loss": 5.9862,
|
|
"mean_token_accuracy": 0.15943123251199723,
|
|
"num_tokens": 22947076.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 6.113621377944947,
|
|
"epoch": 1.0875132462027552,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.000488809910423696,
|
|
"loss": 5.9082,
|
|
"mean_token_accuracy": 0.16993424743413926,
|
|
"num_tokens": 22956267.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 6.262680530548096,
|
|
"epoch": 1.0879547862945955,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004888001006580592,
|
|
"loss": 5.9979,
|
|
"mean_token_accuracy": 0.1547674521803856,
|
|
"num_tokens": 22966751.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 6.077016067504883,
|
|
"epoch": 1.0883963263864358,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004887902867042002,
|
|
"loss": 5.9194,
|
|
"mean_token_accuracy": 0.16017358005046844,
|
|
"num_tokens": 22975862.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 6.117411947250366,
|
|
"epoch": 1.0888378664782763,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004887804685623111,
|
|
"loss": 5.8654,
|
|
"mean_token_accuracy": 0.16339120864868165,
|
|
"num_tokens": 22985085.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 6.240997791290283,
|
|
"epoch": 1.0892794065701166,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.0004887706462325841,
|
|
"loss": 6.0032,
|
|
"mean_token_accuracy": 0.15804048776626586,
|
|
"num_tokens": 22993718.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 6.155885887145996,
|
|
"epoch": 1.0897209466619568,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004887608197152117,
|
|
"loss": 5.8497,
|
|
"mean_token_accuracy": 0.17430692464113234,
|
|
"num_tokens": 23002611.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 6.117863702774048,
|
|
"epoch": 1.0901624867537973,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004887509890103864,
|
|
"loss": 6.0135,
|
|
"mean_token_accuracy": 0.15509911328554155,
|
|
"num_tokens": 23012333.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 6.161442995071411,
|
|
"epoch": 1.0906040268456376,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.0004887411541183009,
|
|
"loss": 5.9338,
|
|
"mean_token_accuracy": 0.1575099855661392,
|
|
"num_tokens": 23020998.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 6.215446281433105,
|
|
"epoch": 1.091045566937478,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004887313150391477,
|
|
"loss": 5.9363,
|
|
"mean_token_accuracy": 0.15863421857357024,
|
|
"num_tokens": 23029520.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 6.200163316726685,
|
|
"epoch": 1.0914871070293182,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004887214717731196,
|
|
"loss": 5.9947,
|
|
"mean_token_accuracy": 0.15386056303977966,
|
|
"num_tokens": 23039224.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 6.1819822788238525,
|
|
"epoch": 1.0919286471211587,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004887116243204094,
|
|
"loss": 5.8827,
|
|
"mean_token_accuracy": 0.16292284280061722,
|
|
"num_tokens": 23047851.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 6.038466930389404,
|
|
"epoch": 1.092370187212999,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.00048870177268121,
|
|
"loss": 5.9087,
|
|
"mean_token_accuracy": 0.1561818964779377,
|
|
"num_tokens": 23057242.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 6.126602554321289,
|
|
"epoch": 1.0928117273048392,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004886919168557145,
|
|
"loss": 6.0226,
|
|
"mean_token_accuracy": 0.15501100122928618,
|
|
"num_tokens": 23066873.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 6.198664236068725,
|
|
"epoch": 1.0932532673966797,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004886820568441158,
|
|
"loss": 6.0039,
|
|
"mean_token_accuracy": 0.1533634513616562,
|
|
"num_tokens": 23076448.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 6.210957050323486,
|
|
"epoch": 1.09369480748852,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004886721926466072,
|
|
"loss": 5.9044,
|
|
"mean_token_accuracy": 0.15767279267311096,
|
|
"num_tokens": 23084759.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 6.116765308380127,
|
|
"epoch": 1.0941363475803603,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004886623242633817,
|
|
"loss": 5.8428,
|
|
"mean_token_accuracy": 0.16857688128948212,
|
|
"num_tokens": 23093236.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 6.1179845333099365,
|
|
"epoch": 1.0945778876722005,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.000488652451694633,
|
|
"loss": 5.8985,
|
|
"mean_token_accuracy": 0.16083543747663498,
|
|
"num_tokens": 23101621.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 6.1819006443023685,
|
|
"epoch": 1.095019427764041,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004886425749405542,
|
|
"loss": 5.9501,
|
|
"mean_token_accuracy": 0.15517825186252593,
|
|
"num_tokens": 23110882.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 6.236010360717773,
|
|
"epoch": 1.0954609678558813,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004886326940013388,
|
|
"loss": 5.9398,
|
|
"mean_token_accuracy": 0.1623895585536957,
|
|
"num_tokens": 23120669.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 6.144532537460327,
|
|
"epoch": 1.0959025079477216,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004886228088771805,
|
|
"loss": 5.8506,
|
|
"mean_token_accuracy": 0.161375030875206,
|
|
"num_tokens": 23129524.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 6.0762065887451175,
|
|
"epoch": 1.096344048039562,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004886129195682729,
|
|
"loss": 5.9163,
|
|
"mean_token_accuracy": 0.15916515290737152,
|
|
"num_tokens": 23139144.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 6.101714324951172,
|
|
"epoch": 1.0967855881314024,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004886030260748096,
|
|
"loss": 5.8357,
|
|
"mean_token_accuracy": 0.16195028424263,
|
|
"num_tokens": 23148600.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 6.122948122024536,
|
|
"epoch": 1.0972271282232426,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004885931283969845,
|
|
"loss": 5.8164,
|
|
"mean_token_accuracy": 0.16671625077724456,
|
|
"num_tokens": 23156831.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 6.231880044937133,
|
|
"epoch": 1.097668668315083,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004885832265349915,
|
|
"loss": 5.993,
|
|
"mean_token_accuracy": 0.15441508293151857,
|
|
"num_tokens": 23166453.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 6.151757001876831,
|
|
"epoch": 1.0981102084069234,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004885733204890246,
|
|
"loss": 5.8598,
|
|
"mean_token_accuracy": 0.15992325395345688,
|
|
"num_tokens": 23175832.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 6.1306596279144285,
|
|
"epoch": 1.0985517484987637,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004885634102592778,
|
|
"loss": 5.887,
|
|
"mean_token_accuracy": 0.16349006593227386,
|
|
"num_tokens": 23185349.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 6.144681596755982,
|
|
"epoch": 1.098993288590604,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004885534958459454,
|
|
"loss": 6.0362,
|
|
"mean_token_accuracy": 0.15734102576971054,
|
|
"num_tokens": 23195391.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 6.112054252624512,
|
|
"epoch": 1.0994348286824445,
|
|
"grad_norm": 3.953125,
|
|
"learning_rate": 0.0004885435772492213,
|
|
"loss": 5.9729,
|
|
"mean_token_accuracy": 0.15919270664453505,
|
|
"num_tokens": 23204689.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 6.134461545944214,
|
|
"epoch": 1.0998763687742847,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004885336544693,
|
|
"loss": 5.9124,
|
|
"mean_token_accuracy": 0.166460819542408,
|
|
"num_tokens": 23213182.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 6.083830499649048,
|
|
"epoch": 1.100317908866125,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004885237275063758,
|
|
"loss": 5.913,
|
|
"mean_token_accuracy": 0.1541294515132904,
|
|
"num_tokens": 23222058.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 6.193151569366455,
|
|
"epoch": 1.1007594489579653,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004885137963606433,
|
|
"loss": 5.9547,
|
|
"mean_token_accuracy": 0.16158088445663452,
|
|
"num_tokens": 23231747.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 6.175371170043945,
|
|
"epoch": 1.1012009890498058,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004885038610322969,
|
|
"loss": 5.8995,
|
|
"mean_token_accuracy": 0.16137738078832625,
|
|
"num_tokens": 23240402.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 6.202411127090454,
|
|
"epoch": 1.101642529141646,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004884939215215314,
|
|
"loss": 5.9631,
|
|
"mean_token_accuracy": 0.16475873440504074,
|
|
"num_tokens": 23249344.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 6.184190273284912,
|
|
"epoch": 1.1020840692334863,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004884839778285413,
|
|
"loss": 5.9529,
|
|
"mean_token_accuracy": 0.16150661706924438,
|
|
"num_tokens": 23258157.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 6.092105579376221,
|
|
"epoch": 1.1025256093253268,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004884740299535216,
|
|
"loss": 5.932,
|
|
"mean_token_accuracy": 0.14843451157212256,
|
|
"num_tokens": 23267798.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 6.161636066436768,
|
|
"epoch": 1.1029671494171671,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.000488464077896667,
|
|
"loss": 5.9454,
|
|
"mean_token_accuracy": 0.1618686556816101,
|
|
"num_tokens": 23276429.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 6.1453760147094725,
|
|
"epoch": 1.1034086895090074,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004884541216581724,
|
|
"loss": 5.8573,
|
|
"mean_token_accuracy": 0.15965035557746887,
|
|
"num_tokens": 23285878.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 6.116464996337891,
|
|
"epoch": 1.1038502296008477,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.000488444161238233,
|
|
"loss": 5.8777,
|
|
"mean_token_accuracy": 0.16719256043434144,
|
|
"num_tokens": 23295683.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 6.148839902877808,
|
|
"epoch": 1.1042917696926882,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 0.0004884341966370439,
|
|
"loss": 5.9604,
|
|
"mean_token_accuracy": 0.15567479133605958,
|
|
"num_tokens": 23305539.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 6.147060394287109,
|
|
"epoch": 1.1047333097845284,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004884242278548003,
|
|
"loss": 5.9269,
|
|
"mean_token_accuracy": 0.16066510677337648,
|
|
"num_tokens": 23314889.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 6.170310401916504,
|
|
"epoch": 1.1051748498763687,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004884142548916975,
|
|
"loss": 5.9554,
|
|
"mean_token_accuracy": 0.15886897593736649,
|
|
"num_tokens": 23324425.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 6.123000907897949,
|
|
"epoch": 1.1056163899682092,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004884042777479308,
|
|
"loss": 5.856,
|
|
"mean_token_accuracy": 0.1647001251578331,
|
|
"num_tokens": 23332994.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 6.141663312911987,
|
|
"epoch": 1.1060579300600495,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004883942964236957,
|
|
"loss": 5.8317,
|
|
"mean_token_accuracy": 0.16078163534402848,
|
|
"num_tokens": 23342108.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 6.086635971069336,
|
|
"epoch": 1.1064994701518898,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004883843109191877,
|
|
"loss": 5.8503,
|
|
"mean_token_accuracy": 0.16816559433937073,
|
|
"num_tokens": 23351439.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 6.159261703491211,
|
|
"epoch": 1.10694101024373,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.0004883743212346021,
|
|
"loss": 5.9539,
|
|
"mean_token_accuracy": 0.16020542681217192,
|
|
"num_tokens": 23360591.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 6.167931842803955,
|
|
"epoch": 1.1073825503355705,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.0004883643273701353,
|
|
"loss": 5.9077,
|
|
"mean_token_accuracy": 0.163707834482193,
|
|
"num_tokens": 23369854.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 6.166998195648193,
|
|
"epoch": 1.1078240904274108,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.0004883543293259826,
|
|
"loss": 5.9789,
|
|
"mean_token_accuracy": 0.1555547297000885,
|
|
"num_tokens": 23378071.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 6.157186269760132,
|
|
"epoch": 1.108265630519251,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004883443271023397,
|
|
"loss": 5.9746,
|
|
"mean_token_accuracy": 0.15041225999593735,
|
|
"num_tokens": 23387083.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 6.142925882339478,
|
|
"epoch": 1.1087071706110916,
|
|
"grad_norm": 7.125,
|
|
"learning_rate": 0.000488334320699403,
|
|
"loss": 5.7993,
|
|
"mean_token_accuracy": 0.16230424791574477,
|
|
"num_tokens": 23395008.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 6.18157548904419,
|
|
"epoch": 1.1091487107029319,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004883243101173681,
|
|
"loss": 5.9053,
|
|
"mean_token_accuracy": 0.16364568918943406,
|
|
"num_tokens": 23404193.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 6.128438568115234,
|
|
"epoch": 1.1095902507947721,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.0004883142953564315,
|
|
"loss": 5.9004,
|
|
"mean_token_accuracy": 0.16206439658999444,
|
|
"num_tokens": 23413353.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 6.139471435546875,
|
|
"epoch": 1.1100317908866124,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.000488304276416789,
|
|
"loss": 5.9472,
|
|
"mean_token_accuracy": 0.16016733050346374,
|
|
"num_tokens": 23422797.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 6.216736316680908,
|
|
"epoch": 1.110473330978453,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004882942532986372,
|
|
"loss": 6.025,
|
|
"mean_token_accuracy": 0.16250147074460983,
|
|
"num_tokens": 23432705.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 6.159796333312988,
|
|
"epoch": 1.1109148710702932,
|
|
"grad_norm": 3.78125,
|
|
"learning_rate": 0.0004882842260021721,
|
|
"loss": 5.8848,
|
|
"mean_token_accuracy": 0.1626063108444214,
|
|
"num_tokens": 23441613.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 6.101108741760254,
|
|
"epoch": 1.1113564111621335,
|
|
"grad_norm": 4.8125,
|
|
"learning_rate": 0.00048827419452759045,
|
|
"loss": 5.9605,
|
|
"mean_token_accuracy": 0.15925377756357192,
|
|
"num_tokens": 23450975.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 6.157285881042481,
|
|
"epoch": 1.111797951253974,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00048826415887508857,
|
|
"loss": 5.9438,
|
|
"mean_token_accuracy": 0.1590849280357361,
|
|
"num_tokens": 23460646.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 6.33017578125,
|
|
"epoch": 1.1122394913458142,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.00048825411904486303,
|
|
"loss": 6.0191,
|
|
"mean_token_accuracy": 0.14977509528398514,
|
|
"num_tokens": 23470454.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 6.1781083106994625,
|
|
"epoch": 1.1126810314376545,
|
|
"grad_norm": 3.640625,
|
|
"learning_rate": 0.0004882440750371108,
|
|
"loss": 5.9155,
|
|
"mean_token_accuracy": 0.16248905658721924,
|
|
"num_tokens": 23480013.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 6.124111938476562,
|
|
"epoch": 1.1131225715294948,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.00048823402685202824,
|
|
"loss": 5.8974,
|
|
"mean_token_accuracy": 0.1607903614640236,
|
|
"num_tokens": 23489485.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 6.042632579803467,
|
|
"epoch": 1.1135641116213353,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004882239744898124,
|
|
"loss": 5.8813,
|
|
"mean_token_accuracy": 0.1654872253537178,
|
|
"num_tokens": 23498147.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 6.011892986297608,
|
|
"epoch": 1.1140056517131756,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004882139179506602,
|
|
"loss": 5.7956,
|
|
"mean_token_accuracy": 0.1666394755244255,
|
|
"num_tokens": 23506614.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 6.153559684753418,
|
|
"epoch": 1.1144471918050158,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004882038572347685,
|
|
"loss": 6.0483,
|
|
"mean_token_accuracy": 0.1509348526597023,
|
|
"num_tokens": 23514927.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 6.217209100723267,
|
|
"epoch": 1.1148887318968563,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.00048819379234233464,
|
|
"loss": 6.0366,
|
|
"mean_token_accuracy": 0.15386761873960494,
|
|
"num_tokens": 23525298.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 6.3298015117645265,
|
|
"epoch": 1.1153302719886966,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004881837232735556,
|
|
"loss": 5.9483,
|
|
"mean_token_accuracy": 0.15949916541576387,
|
|
"num_tokens": 23533995.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 6.083431768417358,
|
|
"epoch": 1.1157718120805369,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004881736500286286,
|
|
"loss": 5.9297,
|
|
"mean_token_accuracy": 0.15916224122047423,
|
|
"num_tokens": 23543900.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 6.156477165222168,
|
|
"epoch": 1.1162133521723772,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.00048816357260775115,
|
|
"loss": 5.9899,
|
|
"mean_token_accuracy": 0.15882350504398346,
|
|
"num_tokens": 23553790.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 6.1945747375488285,
|
|
"epoch": 1.1166548922642177,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.0004881534910111204,
|
|
"loss": 5.9494,
|
|
"mean_token_accuracy": 0.16102498918771743,
|
|
"num_tokens": 23563473.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 6.224649858474732,
|
|
"epoch": 1.117096432356058,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00048814340523893406,
|
|
"loss": 5.8307,
|
|
"mean_token_accuracy": 0.1708875447511673,
|
|
"num_tokens": 23572495.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 6.1610143184661865,
|
|
"epoch": 1.1175379724478982,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00048813331529138965,
|
|
"loss": 6.007,
|
|
"mean_token_accuracy": 0.14832639172673226,
|
|
"num_tokens": 23582945.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 6.175566339492798,
|
|
"epoch": 1.1179795125397387,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004881232211686848,
|
|
"loss": 6.038,
|
|
"mean_token_accuracy": 0.14907224103808403,
|
|
"num_tokens": 23592370.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 6.194454860687256,
|
|
"epoch": 1.118421052631579,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004881131228710172,
|
|
"loss": 5.9674,
|
|
"mean_token_accuracy": 0.15318025052547454,
|
|
"num_tokens": 23601589.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 6.215276527404785,
|
|
"epoch": 1.1188625927234193,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.0004881030203985848,
|
|
"loss": 5.9012,
|
|
"mean_token_accuracy": 0.1597913920879364,
|
|
"num_tokens": 23611456.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 6.1739644527435305,
|
|
"epoch": 1.1193041328152595,
|
|
"grad_norm": 5.78125,
|
|
"learning_rate": 0.00048809291375158544,
|
|
"loss": 5.9085,
|
|
"mean_token_accuracy": 0.15762727260589598,
|
|
"num_tokens": 23620362.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 6.175387573242188,
|
|
"epoch": 1.1197456729071,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048808280293021703,
|
|
"loss": 5.9482,
|
|
"mean_token_accuracy": 0.16135822236537933,
|
|
"num_tokens": 23629647.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 6.173170709609986,
|
|
"epoch": 1.1201872129989403,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 0.00048807268793467774,
|
|
"loss": 5.8904,
|
|
"mean_token_accuracy": 0.16001069843769072,
|
|
"num_tokens": 23639201.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 6.141100263595581,
|
|
"epoch": 1.1206287530907806,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.00048806256876516565,
|
|
"loss": 5.875,
|
|
"mean_token_accuracy": 0.1625053733587265,
|
|
"num_tokens": 23648166.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 6.107354784011841,
|
|
"epoch": 1.121070293182621,
|
|
"grad_norm": 4.3125,
|
|
"learning_rate": 0.00048805244542187906,
|
|
"loss": 6.0437,
|
|
"mean_token_accuracy": 0.15732126981019973,
|
|
"num_tokens": 23658478.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 6.123895168304443,
|
|
"epoch": 1.1215118332744614,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004880423179050161,
|
|
"loss": 5.8395,
|
|
"mean_token_accuracy": 0.1617825448513031,
|
|
"num_tokens": 23667934.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 6.099366903305054,
|
|
"epoch": 1.1219533733663016,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004880321862147755,
|
|
"loss": 5.8988,
|
|
"mean_token_accuracy": 0.1578386642038822,
|
|
"num_tokens": 23676164.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 6.167014312744141,
|
|
"epoch": 1.122394913458142,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00048802205035135537,
|
|
"loss": 5.9692,
|
|
"mean_token_accuracy": 0.15662605315446854,
|
|
"num_tokens": 23686223.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 6.179031658172607,
|
|
"epoch": 1.1228364535499824,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048801191031495444,
|
|
"loss": 5.9846,
|
|
"mean_token_accuracy": 0.1548076316714287,
|
|
"num_tokens": 23695043.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 6.259233999252319,
|
|
"epoch": 1.1232779936418227,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004880017661057714,
|
|
"loss": 5.9884,
|
|
"mean_token_accuracy": 0.15324808657169342,
|
|
"num_tokens": 23704248.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 6.214432859420777,
|
|
"epoch": 1.123719533733663,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.0004879916177240049,
|
|
"loss": 5.8863,
|
|
"mean_token_accuracy": 0.15993714332580566,
|
|
"num_tokens": 23713724.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 6.30100383758545,
|
|
"epoch": 1.1241610738255035,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004879814651698537,
|
|
"loss": 6.0732,
|
|
"mean_token_accuracy": 0.1507812835276127,
|
|
"num_tokens": 23723039.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 6.16924638748169,
|
|
"epoch": 1.1246026139173437,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048797130844351673,
|
|
"loss": 5.8503,
|
|
"mean_token_accuracy": 0.15733642876148224,
|
|
"num_tokens": 23732024.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 6.12670316696167,
|
|
"epoch": 1.125044154009184,
|
|
"grad_norm": 4.40625,
|
|
"learning_rate": 0.00048796114754519294,
|
|
"loss": 5.9876,
|
|
"mean_token_accuracy": 0.15579846501350403,
|
|
"num_tokens": 23740739.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 6.108487462997436,
|
|
"epoch": 1.1254856941010243,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00048795098247508145,
|
|
"loss": 5.918,
|
|
"mean_token_accuracy": 0.15626540333032607,
|
|
"num_tokens": 23750405.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 6.16664080619812,
|
|
"epoch": 1.1259272341928648,
|
|
"grad_norm": 6.8125,
|
|
"learning_rate": 0.0004879408132333813,
|
|
"loss": 5.9109,
|
|
"mean_token_accuracy": 0.16076355725526809,
|
|
"num_tokens": 23759318.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 6.214537191390991,
|
|
"epoch": 1.126368774284705,
|
|
"grad_norm": 5.4375,
|
|
"learning_rate": 0.00048793063982029166,
|
|
"loss": 6.0286,
|
|
"mean_token_accuracy": 0.15366530269384385,
|
|
"num_tokens": 23769202.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 6.163922071456909,
|
|
"epoch": 1.1268103143765453,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000487920462236012,
|
|
"loss": 5.8883,
|
|
"mean_token_accuracy": 0.1640685483813286,
|
|
"num_tokens": 23778478.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 6.1662345886230465,
|
|
"epoch": 1.1272518544683856,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.0004879102804807415,
|
|
"loss": 5.9802,
|
|
"mean_token_accuracy": 0.15960298031568526,
|
|
"num_tokens": 23788044.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 6.157622671127319,
|
|
"epoch": 1.127693394560226,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.00048790009455467967,
|
|
"loss": 5.9573,
|
|
"mean_token_accuracy": 0.1509365901350975,
|
|
"num_tokens": 23796351.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 6.168710517883301,
|
|
"epoch": 1.1281349346520664,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004878899044580261,
|
|
"loss": 5.9644,
|
|
"mean_token_accuracy": 0.1563441962003708,
|
|
"num_tokens": 23805553.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 6.151319456100464,
|
|
"epoch": 1.1285764747439067,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.00048787971019098044,
|
|
"loss": 5.8118,
|
|
"mean_token_accuracy": 0.1696744054555893,
|
|
"num_tokens": 23813742.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 6.161671113967896,
|
|
"epoch": 1.1290180148357472,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004878695117537423,
|
|
"loss": 5.9251,
|
|
"mean_token_accuracy": 0.16025556176900863,
|
|
"num_tokens": 23822135.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 6.222481203079224,
|
|
"epoch": 1.1294595549275874,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004878593091465114,
|
|
"loss": 5.9833,
|
|
"mean_token_accuracy": 0.16105886101722716,
|
|
"num_tokens": 23832021.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 6.202785634994507,
|
|
"epoch": 1.1299010950194277,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004878491023694877,
|
|
"loss": 5.9417,
|
|
"mean_token_accuracy": 0.15718482732772826,
|
|
"num_tokens": 23842432.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 6.217890501022339,
|
|
"epoch": 1.1303426351112682,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004878388914228713,
|
|
"loss": 5.9836,
|
|
"mean_token_accuracy": 0.15357162952423095,
|
|
"num_tokens": 23852172.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 6.137939214706421,
|
|
"epoch": 1.1307841752031085,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004878286763068619,
|
|
"loss": 5.8557,
|
|
"mean_token_accuracy": 0.16467740535736083,
|
|
"num_tokens": 23861178.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 6.180500316619873,
|
|
"epoch": 1.1312257152949488,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004878184570216598,
|
|
"loss": 5.9759,
|
|
"mean_token_accuracy": 0.15340608656406401,
|
|
"num_tokens": 23869998.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 6.15168833732605,
|
|
"epoch": 1.131667255386789,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00048780823356746523,
|
|
"loss": 5.9132,
|
|
"mean_token_accuracy": 0.1560283973813057,
|
|
"num_tokens": 23880404.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 6.174927854537964,
|
|
"epoch": 1.1321087954786295,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004877980059444784,
|
|
"loss": 5.8418,
|
|
"mean_token_accuracy": 0.15855402797460555,
|
|
"num_tokens": 23889643.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 6.198969888687134,
|
|
"epoch": 1.1325503355704698,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004877877741528996,
|
|
"loss": 5.9169,
|
|
"mean_token_accuracy": 0.16071036607027053,
|
|
"num_tokens": 23899264.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 6.180214929580688,
|
|
"epoch": 1.13299187566231,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004877775381929294,
|
|
"loss": 5.9635,
|
|
"mean_token_accuracy": 0.15552644431591034,
|
|
"num_tokens": 23908685.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 6.152384996414185,
|
|
"epoch": 1.1334334157541504,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004877672980647682,
|
|
"loss": 5.9497,
|
|
"mean_token_accuracy": 0.15492501258850097,
|
|
"num_tokens": 23917838.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 6.194139194488526,
|
|
"epoch": 1.1338749558459909,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.00048775705376861663,
|
|
"loss": 5.9523,
|
|
"mean_token_accuracy": 0.1608953669667244,
|
|
"num_tokens": 23927498.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 6.2101281642913815,
|
|
"epoch": 1.1343164959378311,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004877468053046753,
|
|
"loss": 5.9693,
|
|
"mean_token_accuracy": 0.16637535393238068,
|
|
"num_tokens": 23936205.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 6.113933992385864,
|
|
"epoch": 1.1347580360296714,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.00048773655267314516,
|
|
"loss": 5.8724,
|
|
"mean_token_accuracy": 0.16375424861907958,
|
|
"num_tokens": 23945897.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 6.2041229724884035,
|
|
"epoch": 1.135199576121512,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004877262958742268,
|
|
"loss": 5.903,
|
|
"mean_token_accuracy": 0.15940342396497725,
|
|
"num_tokens": 23954873.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 6.126399993896484,
|
|
"epoch": 1.1356411162133522,
|
|
"grad_norm": 4.71875,
|
|
"learning_rate": 0.00048771603490812144,
|
|
"loss": 6.0093,
|
|
"mean_token_accuracy": 0.15629909709095954,
|
|
"num_tokens": 23964631.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 6.16305980682373,
|
|
"epoch": 1.1360826563051925,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004877057697750299,
|
|
"loss": 5.8912,
|
|
"mean_token_accuracy": 0.1583813928067684,
|
|
"num_tokens": 23973935.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 6.210225296020508,
|
|
"epoch": 1.136524196397033,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004876955004751533,
|
|
"loss": 6.0135,
|
|
"mean_token_accuracy": 0.15347768515348434,
|
|
"num_tokens": 23984340.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 6.267869281768799,
|
|
"epoch": 1.1369657364888732,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.00048768522700869284,
|
|
"loss": 6.0876,
|
|
"mean_token_accuracy": 0.1525693953037262,
|
|
"num_tokens": 23994387.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 6.127750015258789,
|
|
"epoch": 1.1374072765807135,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048767494937584964,
|
|
"loss": 5.8996,
|
|
"mean_token_accuracy": 0.1604439526796341,
|
|
"num_tokens": 24003391.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 6.143089723587036,
|
|
"epoch": 1.1378488166725538,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048766466757682527,
|
|
"loss": 5.8791,
|
|
"mean_token_accuracy": 0.1647971972823143,
|
|
"num_tokens": 24013501.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 6.130701732635498,
|
|
"epoch": 1.1382903567643943,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004876543816118209,
|
|
"loss": 5.8413,
|
|
"mean_token_accuracy": 0.16390649527311324,
|
|
"num_tokens": 24022675.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 6.2308478355407715,
|
|
"epoch": 1.1387318968562345,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00048764409148103815,
|
|
"loss": 6.0174,
|
|
"mean_token_accuracy": 0.15676412284374236,
|
|
"num_tokens": 24032542.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 6.176291275024414,
|
|
"epoch": 1.1391734369480748,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004876337971846787,
|
|
"loss": 5.8946,
|
|
"mean_token_accuracy": 0.16045114845037461,
|
|
"num_tokens": 24041342.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 6.171636152267456,
|
|
"epoch": 1.139614977039915,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.000487623498722944,
|
|
"loss": 5.9422,
|
|
"mean_token_accuracy": 0.16535146534442902,
|
|
"num_tokens": 24051429.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 6.186244201660156,
|
|
"epoch": 1.1400565171317556,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004876131960960358,
|
|
"loss": 5.917,
|
|
"mean_token_accuracy": 0.1657955154776573,
|
|
"num_tokens": 24061074.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 6.168979454040527,
|
|
"epoch": 1.1404980572235959,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.00048760288930415615,
|
|
"loss": 5.9204,
|
|
"mean_token_accuracy": 0.16312191486358643,
|
|
"num_tokens": 24069622.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 6.14166259765625,
|
|
"epoch": 1.1409395973154361,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00048759257834750673,
|
|
"loss": 5.9566,
|
|
"mean_token_accuracy": 0.1613275185227394,
|
|
"num_tokens": 24078393.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 6.1301041603088375,
|
|
"epoch": 1.1413811374072766,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004875822632262897,
|
|
"loss": 5.9338,
|
|
"mean_token_accuracy": 0.1595478229224682,
|
|
"num_tokens": 24089157.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 6.162030458450317,
|
|
"epoch": 1.141822677499117,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00048757194394070697,
|
|
"loss": 5.897,
|
|
"mean_token_accuracy": 0.1616758957505226,
|
|
"num_tokens": 24098022.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 6.127862882614136,
|
|
"epoch": 1.1422642175909572,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048756162049096077,
|
|
"loss": 5.8588,
|
|
"mean_token_accuracy": 0.1631949618458748,
|
|
"num_tokens": 24107629.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 6.1903746128082275,
|
|
"epoch": 1.1427057576827977,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.00048755129287725334,
|
|
"loss": 5.9263,
|
|
"mean_token_accuracy": 0.16060164272785188,
|
|
"num_tokens": 24116903.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 6.098018407821655,
|
|
"epoch": 1.143147297774638,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048754096109978684,
|
|
"loss": 5.8663,
|
|
"mean_token_accuracy": 0.15904103517532348,
|
|
"num_tokens": 24126433.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 6.237703943252564,
|
|
"epoch": 1.1435888378664782,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004875306251587639,
|
|
"loss": 6.0814,
|
|
"mean_token_accuracy": 0.1499664954841137,
|
|
"num_tokens": 24136603.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 6.198658990859985,
|
|
"epoch": 1.1440303779583185,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004875202850543869,
|
|
"loss": 5.9421,
|
|
"mean_token_accuracy": 0.1543191336095333,
|
|
"num_tokens": 24145656.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 6.168276786804199,
|
|
"epoch": 1.144471918050159,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048750994078685837,
|
|
"loss": 5.9868,
|
|
"mean_token_accuracy": 0.1520389199256897,
|
|
"num_tokens": 24155044.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 6.168300819396973,
|
|
"epoch": 1.1449134581419993,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004874995923563809,
|
|
"loss": 5.9176,
|
|
"mean_token_accuracy": 0.16050723642110826,
|
|
"num_tokens": 24163987.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 6.210289192199707,
|
|
"epoch": 1.1453549982338396,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004874892397631573,
|
|
"loss": 5.8959,
|
|
"mean_token_accuracy": 0.15463410168886185,
|
|
"num_tokens": 24173542.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 6.0940813541412355,
|
|
"epoch": 1.1457965383256798,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004874788830073904,
|
|
"loss": 5.8971,
|
|
"mean_token_accuracy": 0.15726284980773925,
|
|
"num_tokens": 24182785.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 6.151674413681031,
|
|
"epoch": 1.1462380784175203,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.000487468522089283,
|
|
"loss": 5.9204,
|
|
"mean_token_accuracy": 0.15491933822631837,
|
|
"num_tokens": 24193477.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 6.147600507736206,
|
|
"epoch": 1.1466796185093606,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00048745815700903806,
|
|
"loss": 5.9047,
|
|
"mean_token_accuracy": 0.1584320306777954,
|
|
"num_tokens": 24202289.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 6.048496198654175,
|
|
"epoch": 1.147121158601201,
|
|
"grad_norm": 7.4375,
|
|
"learning_rate": 0.00048744778776685865,
|
|
"loss": 5.8398,
|
|
"mean_token_accuracy": 0.16988199353218078,
|
|
"num_tokens": 24212199.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 6.139628458023071,
|
|
"epoch": 1.1475626986930414,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.00048743741436294794,
|
|
"loss": 5.9561,
|
|
"mean_token_accuracy": 0.16567686945199966,
|
|
"num_tokens": 24220984.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 6.161849308013916,
|
|
"epoch": 1.1480042387848817,
|
|
"grad_norm": 3.96875,
|
|
"learning_rate": 0.0004874270367975091,
|
|
"loss": 5.9217,
|
|
"mean_token_accuracy": 0.1658036917448044,
|
|
"num_tokens": 24229599.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 6.172030305862426,
|
|
"epoch": 1.148445778876722,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004874166550707454,
|
|
"loss": 5.9468,
|
|
"mean_token_accuracy": 0.15842569917440413,
|
|
"num_tokens": 24238721.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 6.188222360610962,
|
|
"epoch": 1.1488873189685624,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00048740626918286026,
|
|
"loss": 5.9527,
|
|
"mean_token_accuracy": 0.15307596549391747,
|
|
"num_tokens": 24248431.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 6.1717675685882565,
|
|
"epoch": 1.1493288590604027,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.00048739587913405706,
|
|
"loss": 5.9031,
|
|
"mean_token_accuracy": 0.16315290853381156,
|
|
"num_tokens": 24257770.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 6.195352554321289,
|
|
"epoch": 1.149770399152243,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048738548492453944,
|
|
"loss": 5.9111,
|
|
"mean_token_accuracy": 0.15852010399103164,
|
|
"num_tokens": 24266402.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 6.182618618011475,
|
|
"epoch": 1.1502119392440833,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004873750865545109,
|
|
"loss": 5.9073,
|
|
"mean_token_accuracy": 0.15980733186006546,
|
|
"num_tokens": 24275164.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 6.1739013671875,
|
|
"epoch": 1.1506534793359238,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00048736468402417525,
|
|
"loss": 5.9877,
|
|
"mean_token_accuracy": 0.15904164016246797,
|
|
"num_tokens": 24285650.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 6.1579667091369625,
|
|
"epoch": 1.151095019427764,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00048735427733373617,
|
|
"loss": 5.9313,
|
|
"mean_token_accuracy": 0.1569092810153961,
|
|
"num_tokens": 24294745.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 6.212623643875122,
|
|
"epoch": 1.1515365595196043,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00048734386648339767,
|
|
"loss": 5.9126,
|
|
"mean_token_accuracy": 0.1645822435617447,
|
|
"num_tokens": 24303837.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 6.121044731140136,
|
|
"epoch": 1.1519780996114446,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004873334514733634,
|
|
"loss": 5.9815,
|
|
"mean_token_accuracy": 0.15832275301218032,
|
|
"num_tokens": 24313417.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 6.228082180023193,
|
|
"epoch": 1.152419639703285,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004873230323038378,
|
|
"loss": 5.8974,
|
|
"mean_token_accuracy": 0.16411705017089845,
|
|
"num_tokens": 24322439.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 6.249577903747559,
|
|
"epoch": 1.1528611797951254,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004873126089750246,
|
|
"loss": 5.9566,
|
|
"mean_token_accuracy": 0.16161733716726304,
|
|
"num_tokens": 24332509.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 6.156072044372559,
|
|
"epoch": 1.1533027198869656,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004873021814871282,
|
|
"loss": 5.9777,
|
|
"mean_token_accuracy": 0.1539487287402153,
|
|
"num_tokens": 24342252.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 6.118894624710083,
|
|
"epoch": 1.1537442599788061,
|
|
"grad_norm": 9.1875,
|
|
"learning_rate": 0.0004872917498403528,
|
|
"loss": 5.9761,
|
|
"mean_token_accuracy": 0.1629844516515732,
|
|
"num_tokens": 24352459.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 6.198663759231567,
|
|
"epoch": 1.1541858000706464,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004872813140349028,
|
|
"loss": 5.8607,
|
|
"mean_token_accuracy": 0.16332223117351533,
|
|
"num_tokens": 24361788.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 6.217107486724854,
|
|
"epoch": 1.1546273401624867,
|
|
"grad_norm": 4.5625,
|
|
"learning_rate": 0.0004872708740709825,
|
|
"loss": 5.9483,
|
|
"mean_token_accuracy": 0.15652839541435243,
|
|
"num_tokens": 24372117.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 6.111956453323364,
|
|
"epoch": 1.1550688802543272,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00048726042994879656,
|
|
"loss": 5.8875,
|
|
"mean_token_accuracy": 0.16594249457120896,
|
|
"num_tokens": 24380833.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 6.110033416748047,
|
|
"epoch": 1.1555104203461675,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.00048724998166854944,
|
|
"loss": 5.9825,
|
|
"mean_token_accuracy": 0.16378928273916243,
|
|
"num_tokens": 24390258.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 6.196791553497315,
|
|
"epoch": 1.1559519604380077,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.000487239529230446,
|
|
"loss": 5.9789,
|
|
"mean_token_accuracy": 0.15774571001529694,
|
|
"num_tokens": 24399359.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 6.209712028503418,
|
|
"epoch": 1.156393500529848,
|
|
"grad_norm": 15.875,
|
|
"learning_rate": 0.00048722907263469084,
|
|
"loss": 5.9585,
|
|
"mean_token_accuracy": 0.16555930078029632,
|
|
"num_tokens": 24408012.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 6.235305643081665,
|
|
"epoch": 1.1568350406216885,
|
|
"grad_norm": 3.65625,
|
|
"learning_rate": 0.0004872186118814889,
|
|
"loss": 5.9484,
|
|
"mean_token_accuracy": 0.15444328933954238,
|
|
"num_tokens": 24416804.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 6.080541563034058,
|
|
"epoch": 1.1572765807135288,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048720814697104497,
|
|
"loss": 5.7509,
|
|
"mean_token_accuracy": 0.1696800172328949,
|
|
"num_tokens": 24425401.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 6.037707424163818,
|
|
"epoch": 1.157718120805369,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048719767790356415,
|
|
"loss": 5.826,
|
|
"mean_token_accuracy": 0.16340615302324296,
|
|
"num_tokens": 24434473.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 6.227966976165772,
|
|
"epoch": 1.1581596608972093,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048718720467925156,
|
|
"loss": 6.043,
|
|
"mean_token_accuracy": 0.14917874932289124,
|
|
"num_tokens": 24443154.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 6.215178680419922,
|
|
"epoch": 1.1586012009890498,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004871767272983122,
|
|
"loss": 5.8801,
|
|
"mean_token_accuracy": 0.1701144054532051,
|
|
"num_tokens": 24451308.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 6.184889650344848,
|
|
"epoch": 1.1590427410808901,
|
|
"grad_norm": 6.21875,
|
|
"learning_rate": 0.0004871662457609515,
|
|
"loss": 5.8974,
|
|
"mean_token_accuracy": 0.16406641006469727,
|
|
"num_tokens": 24459997.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 6.141274261474609,
|
|
"epoch": 1.1594842811727304,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004871557600673747,
|
|
"loss": 5.9277,
|
|
"mean_token_accuracy": 0.16226707100868226,
|
|
"num_tokens": 24469448.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 6.129578638076782,
|
|
"epoch": 1.1599258212645709,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.00048714527021778714,
|
|
"loss": 5.9128,
|
|
"mean_token_accuracy": 0.160499732196331,
|
|
"num_tokens": 24478304.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 6.115665864944458,
|
|
"epoch": 1.1603673613564112,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.0004871347762123945,
|
|
"loss": 5.8106,
|
|
"mean_token_accuracy": 0.1724348247051239,
|
|
"num_tokens": 24487300.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 6.113453578948975,
|
|
"epoch": 1.1608089014482514,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048712427805140224,
|
|
"loss": 5.901,
|
|
"mean_token_accuracy": 0.16196317970752716,
|
|
"num_tokens": 24495893.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 6.1374163150787355,
|
|
"epoch": 1.161250441540092,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004871137757350159,
|
|
"loss": 5.8662,
|
|
"mean_token_accuracy": 0.16316550970077515,
|
|
"num_tokens": 24504603.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 6.122546243667602,
|
|
"epoch": 1.1616919816319322,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 0.00048710326926344153,
|
|
"loss": 5.8635,
|
|
"mean_token_accuracy": 0.16920806989073753,
|
|
"num_tokens": 24513148.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 6.23073000907898,
|
|
"epoch": 1.1621335217237725,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.00048709275863688455,
|
|
"loss": 6.0072,
|
|
"mean_token_accuracy": 0.15268441587686538,
|
|
"num_tokens": 24524006.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 6.177923154830933,
|
|
"epoch": 1.1625750618156128,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00048708224385555116,
|
|
"loss": 5.8387,
|
|
"mean_token_accuracy": 0.17196518182754517,
|
|
"num_tokens": 24532468.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 6.164284515380859,
|
|
"epoch": 1.1630166019074533,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004870717249196472,
|
|
"loss": 5.9401,
|
|
"mean_token_accuracy": 0.15457817912101746,
|
|
"num_tokens": 24540887.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 6.185343647003174,
|
|
"epoch": 1.1634581419992935,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004870612018293788,
|
|
"loss": 5.879,
|
|
"mean_token_accuracy": 0.1544166013598442,
|
|
"num_tokens": 24550565.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 6.209562587738037,
|
|
"epoch": 1.1638996820911338,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.000487050674584952,
|
|
"loss": 5.8445,
|
|
"mean_token_accuracy": 0.16708905547857283,
|
|
"num_tokens": 24560283.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 6.11170654296875,
|
|
"epoch": 1.164341222182974,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.000487040143186573,
|
|
"loss": 5.8311,
|
|
"mean_token_accuracy": 0.16198592782020568,
|
|
"num_tokens": 24569527.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 6.0781200408935545,
|
|
"epoch": 1.1647827622748146,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048702960763444833,
|
|
"loss": 5.9204,
|
|
"mean_token_accuracy": 0.1569120854139328,
|
|
"num_tokens": 24578702.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 6.204309177398682,
|
|
"epoch": 1.1652243023666549,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.0004870190679287842,
|
|
"loss": 5.8865,
|
|
"mean_token_accuracy": 0.16081749945878981,
|
|
"num_tokens": 24588252.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 6.1760461807250975,
|
|
"epoch": 1.1656658424584951,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004870085240697871,
|
|
"loss": 5.8617,
|
|
"mean_token_accuracy": 0.1601746678352356,
|
|
"num_tokens": 24596989.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 6.150515747070313,
|
|
"epoch": 1.1661073825503356,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 0.00048699797605766365,
|
|
"loss": 5.9995,
|
|
"mean_token_accuracy": 0.15753665268421174,
|
|
"num_tokens": 24607051.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 6.2017967224121096,
|
|
"epoch": 1.166548922642176,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.00048698742389262036,
|
|
"loss": 5.9867,
|
|
"mean_token_accuracy": 0.15080763548612594,
|
|
"num_tokens": 24616561.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 6.182310962677002,
|
|
"epoch": 1.1669904627340162,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048697686757486397,
|
|
"loss": 5.9579,
|
|
"mean_token_accuracy": 0.15699755102396012,
|
|
"num_tokens": 24625942.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 6.223864126205444,
|
|
"epoch": 1.1674320028258567,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004869663071046013,
|
|
"loss": 5.9254,
|
|
"mean_token_accuracy": 0.15231055542826652,
|
|
"num_tokens": 24635646.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 6.083964204788208,
|
|
"epoch": 1.167873542917697,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.00048695574248203935,
|
|
"loss": 5.9577,
|
|
"mean_token_accuracy": 0.15992813110351561,
|
|
"num_tokens": 24645147.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 6.091044330596924,
|
|
"epoch": 1.1683150830095372,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004869451737073848,
|
|
"loss": 5.9298,
|
|
"mean_token_accuracy": 0.15731989741325378,
|
|
"num_tokens": 24654796.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 6.1002613544464115,
|
|
"epoch": 1.1687566231013775,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004869346007808449,
|
|
"loss": 5.8666,
|
|
"mean_token_accuracy": 0.16188845038414001,
|
|
"num_tokens": 24663765.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 6.262855482101441,
|
|
"epoch": 1.169198163193218,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.00048692402370262674,
|
|
"loss": 5.9849,
|
|
"mean_token_accuracy": 0.1545178234577179,
|
|
"num_tokens": 24673758.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 6.221972465515137,
|
|
"epoch": 1.1696397032850583,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.00048691344247293747,
|
|
"loss": 5.8467,
|
|
"mean_token_accuracy": 0.16410696357488633,
|
|
"num_tokens": 24682751.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 6.158407592773438,
|
|
"epoch": 1.1700812433768986,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048690285709198435,
|
|
"loss": 5.9597,
|
|
"mean_token_accuracy": 0.158477720618248,
|
|
"num_tokens": 24691375.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 6.144349384307861,
|
|
"epoch": 1.1705227834687388,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004868922675599747,
|
|
"loss": 5.9008,
|
|
"mean_token_accuracy": 0.16543617844581604,
|
|
"num_tokens": 24699852.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 6.151238584518433,
|
|
"epoch": 1.1709643235605793,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004868816738771162,
|
|
"loss": 5.8205,
|
|
"mean_token_accuracy": 0.1628445565700531,
|
|
"num_tokens": 24708857.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 6.1484630584716795,
|
|
"epoch": 1.1714058636524196,
|
|
"grad_norm": 3.53125,
|
|
"learning_rate": 0.0004868710760436161,
|
|
"loss": 5.978,
|
|
"mean_token_accuracy": 0.15893639922142028,
|
|
"num_tokens": 24718262.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 6.137684535980225,
|
|
"epoch": 1.1718474037442599,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.00048686047405968217,
|
|
"loss": 5.9552,
|
|
"mean_token_accuracy": 0.16079557538032532,
|
|
"num_tokens": 24727458.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 6.207680511474609,
|
|
"epoch": 1.1722889438361004,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048684986792552206,
|
|
"loss": 6.0053,
|
|
"mean_token_accuracy": 0.15345407724380494,
|
|
"num_tokens": 24737297.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 6.25681734085083,
|
|
"epoch": 1.1727304839279407,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00048683925764134346,
|
|
"loss": 5.8994,
|
|
"mean_token_accuracy": 0.16747342348098754,
|
|
"num_tokens": 24746939.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 6.186113262176514,
|
|
"epoch": 1.173172024019781,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004868286432073543,
|
|
"loss": 6.0444,
|
|
"mean_token_accuracy": 0.1579015001654625,
|
|
"num_tokens": 24756907.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 6.110030841827393,
|
|
"epoch": 1.1736135641116214,
|
|
"grad_norm": 5.5,
|
|
"learning_rate": 0.00048681802462376253,
|
|
"loss": 5.846,
|
|
"mean_token_accuracy": 0.16282231509685516,
|
|
"num_tokens": 24765997.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 6.228509187698364,
|
|
"epoch": 1.1740551042034617,
|
|
"grad_norm": 4.0625,
|
|
"learning_rate": 0.00048680740189077605,
|
|
"loss": 5.9229,
|
|
"mean_token_accuracy": 0.15141807049512862,
|
|
"num_tokens": 24775090.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 6.174625825881958,
|
|
"epoch": 1.174496644295302,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00048679677500860314,
|
|
"loss": 5.9026,
|
|
"mean_token_accuracy": 0.16119746267795562,
|
|
"num_tokens": 24784709.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 6.20410304069519,
|
|
"epoch": 1.1749381843871423,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004867861439774519,
|
|
"loss": 5.9244,
|
|
"mean_token_accuracy": 0.1608407825231552,
|
|
"num_tokens": 24794473.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 6.1915966987609865,
|
|
"epoch": 1.1753797244789828,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00048677550879753037,
|
|
"loss": 6.0279,
|
|
"mean_token_accuracy": 0.1547059342265129,
|
|
"num_tokens": 24804718.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 6.1425261974334715,
|
|
"epoch": 1.175821264570823,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048676486946904715,
|
|
"loss": 5.9228,
|
|
"mean_token_accuracy": 0.15841422826051713,
|
|
"num_tokens": 24813632.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 6.083115434646606,
|
|
"epoch": 1.1762628046626633,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004867542259922105,
|
|
"loss": 5.8547,
|
|
"mean_token_accuracy": 0.1671317309141159,
|
|
"num_tokens": 24823395.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 6.2250324249267575,
|
|
"epoch": 1.1767043447545038,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004867435783672291,
|
|
"loss": 5.9713,
|
|
"mean_token_accuracy": 0.15184925198554994,
|
|
"num_tokens": 24832869.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 6.231447219848633,
|
|
"epoch": 1.177145884846344,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004867329265943114,
|
|
"loss": 5.8908,
|
|
"mean_token_accuracy": 0.1585858106613159,
|
|
"num_tokens": 24841706.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 6.206498670578003,
|
|
"epoch": 1.1775874249381844,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004867222706736661,
|
|
"loss": 5.9315,
|
|
"mean_token_accuracy": 0.1613654911518097,
|
|
"num_tokens": 24851149.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 6.197022247314453,
|
|
"epoch": 1.1780289650300246,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004867116106055019,
|
|
"loss": 5.8945,
|
|
"mean_token_accuracy": 0.16297131925821304,
|
|
"num_tokens": 24860002.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 6.128525114059448,
|
|
"epoch": 1.1784705051218651,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048670094639002766,
|
|
"loss": 5.986,
|
|
"mean_token_accuracy": 0.15572923123836518,
|
|
"num_tokens": 24869457.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 6.04019341468811,
|
|
"epoch": 1.1789120452137054,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004866902780274523,
|
|
"loss": 5.9126,
|
|
"mean_token_accuracy": 0.1607941582798958,
|
|
"num_tokens": 24879527.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 6.146878337860107,
|
|
"epoch": 1.1793535853055457,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004866796055179847,
|
|
"loss": 5.933,
|
|
"mean_token_accuracy": 0.16120410561561585,
|
|
"num_tokens": 24889401.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 6.216059970855713,
|
|
"epoch": 1.1797951253973862,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004866689288618342,
|
|
"loss": 5.9333,
|
|
"mean_token_accuracy": 0.15970335453748702,
|
|
"num_tokens": 24897911.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 6.1216864585876465,
|
|
"epoch": 1.1802366654892265,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004866582480592096,
|
|
"loss": 5.8886,
|
|
"mean_token_accuracy": 0.1663259521126747,
|
|
"num_tokens": 24906969.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 6.1119410514831545,
|
|
"epoch": 1.1806782055810667,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004866475631103203,
|
|
"loss": 5.9225,
|
|
"mean_token_accuracy": 0.16083779484033583,
|
|
"num_tokens": 24915713.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 6.141808748245239,
|
|
"epoch": 1.181119745672907,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.00048663687401537573,
|
|
"loss": 5.9279,
|
|
"mean_token_accuracy": 0.15738131999969482,
|
|
"num_tokens": 24925484.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 6.169105577468872,
|
|
"epoch": 1.1815612857647475,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048662618077458507,
|
|
"loss": 5.9477,
|
|
"mean_token_accuracy": 0.1669459268450737,
|
|
"num_tokens": 24934751.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 6.197234058380127,
|
|
"epoch": 1.1820028258565878,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004866154833881579,
|
|
"loss": 5.9893,
|
|
"mean_token_accuracy": 0.15621086210012436,
|
|
"num_tokens": 24945059.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 6.202260875701905,
|
|
"epoch": 1.182444365948428,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004866047818563038,
|
|
"loss": 5.9611,
|
|
"mean_token_accuracy": 0.15845003873109817,
|
|
"num_tokens": 24954678.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 6.127795648574829,
|
|
"epoch": 1.1828859060402686,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004865940761792323,
|
|
"loss": 5.9429,
|
|
"mean_token_accuracy": 0.15084182769060134,
|
|
"num_tokens": 24964093.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 6.235414981842041,
|
|
"epoch": 1.1833274461321088,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004865833663571533,
|
|
"loss": 5.8759,
|
|
"mean_token_accuracy": 0.16595400273799896,
|
|
"num_tokens": 24973903.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 6.107465744018555,
|
|
"epoch": 1.183768986223949,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048657265239027635,
|
|
"loss": 5.8899,
|
|
"mean_token_accuracy": 0.160612852871418,
|
|
"num_tokens": 24982458.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 6.080062198638916,
|
|
"epoch": 1.1842105263157894,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004865619342788116,
|
|
"loss": 5.944,
|
|
"mean_token_accuracy": 0.157385890185833,
|
|
"num_tokens": 24992233.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 6.184826898574829,
|
|
"epoch": 1.1846520664076299,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 0.00048655121202296873,
|
|
"loss": 5.8856,
|
|
"mean_token_accuracy": 0.15693662613630294,
|
|
"num_tokens": 25001855.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 6.161380243301392,
|
|
"epoch": 1.1850936064994702,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00048654048562295807,
|
|
"loss": 5.7895,
|
|
"mean_token_accuracy": 0.16418375819921494,
|
|
"num_tokens": 25010950.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 6.184538125991821,
|
|
"epoch": 1.1855351465913104,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004865297550789895,
|
|
"loss": 5.979,
|
|
"mean_token_accuracy": 0.15356025993824005,
|
|
"num_tokens": 25020816.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 6.228384256362915,
|
|
"epoch": 1.185976686683151,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004865190203912734,
|
|
"loss": 5.9976,
|
|
"mean_token_accuracy": 0.15983387678861619,
|
|
"num_tokens": 25030236.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 6.137870597839355,
|
|
"epoch": 1.1864182267749912,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00048650828156001995,
|
|
"loss": 5.8861,
|
|
"mean_token_accuracy": 0.16400271505117417,
|
|
"num_tokens": 25040236.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 6.173695373535156,
|
|
"epoch": 1.1868597668668315,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004864975385854396,
|
|
"loss": 6.007,
|
|
"mean_token_accuracy": 0.15775451213121414,
|
|
"num_tokens": 25049835.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 6.154194355010986,
|
|
"epoch": 1.1873013069586718,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00048648679146774275,
|
|
"loss": 5.9501,
|
|
"mean_token_accuracy": 0.1562986582517624,
|
|
"num_tokens": 25058947.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 6.193396091461182,
|
|
"epoch": 1.1877428470505123,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004864760402071399,
|
|
"loss": 5.9294,
|
|
"mean_token_accuracy": 0.1595063403248787,
|
|
"num_tokens": 25069128.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 6.186780643463135,
|
|
"epoch": 1.1881843871423525,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.00048646528480384175,
|
|
"loss": 5.9879,
|
|
"mean_token_accuracy": 0.1523025467991829,
|
|
"num_tokens": 25079717.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 6.118858861923218,
|
|
"epoch": 1.1886259272341928,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004864545252580588,
|
|
"loss": 5.9238,
|
|
"mean_token_accuracy": 0.15855868086218833,
|
|
"num_tokens": 25088656.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 6.136055564880371,
|
|
"epoch": 1.1890674673260333,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048644376157000213,
|
|
"loss": 5.926,
|
|
"mean_token_accuracy": 0.15793594121932983,
|
|
"num_tokens": 25098066.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 6.149987506866455,
|
|
"epoch": 1.1895090074178736,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004864329937398823,
|
|
"loss": 5.9553,
|
|
"mean_token_accuracy": 0.15770915821194648,
|
|
"num_tokens": 25107530.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 6.171546888351441,
|
|
"epoch": 1.1899505475097139,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00048642222176791043,
|
|
"loss": 5.8863,
|
|
"mean_token_accuracy": 0.15822558850049973,
|
|
"num_tokens": 25116226.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 6.150636959075928,
|
|
"epoch": 1.1903920876015541,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004864114456542975,
|
|
"loss": 6.0269,
|
|
"mean_token_accuracy": 0.14910721331834792,
|
|
"num_tokens": 25125619.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 6.1670585632324215,
|
|
"epoch": 1.1908336276933946,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004864006653992546,
|
|
"loss": 5.8844,
|
|
"mean_token_accuracy": 0.1635897010564804,
|
|
"num_tokens": 25134782.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 6.239220666885376,
|
|
"epoch": 1.191275167785235,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.00048638988100299283,
|
|
"loss": 5.9466,
|
|
"mean_token_accuracy": 0.1643083930015564,
|
|
"num_tokens": 25144709.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 6.202182865142822,
|
|
"epoch": 1.1917167078770752,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004863790924657236,
|
|
"loss": 5.8333,
|
|
"mean_token_accuracy": 0.1616229996085167,
|
|
"num_tokens": 25153771.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 6.113958311080933,
|
|
"epoch": 1.1921582479689157,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.000486368299787658,
|
|
"loss": 5.962,
|
|
"mean_token_accuracy": 0.16108824014663697,
|
|
"num_tokens": 25163217.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 6.113112735748291,
|
|
"epoch": 1.192599788060756,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048635750296900784,
|
|
"loss": 5.9725,
|
|
"mean_token_accuracy": 0.15988246351480484,
|
|
"num_tokens": 25172762.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 6.173691082000732,
|
|
"epoch": 1.1930413281525962,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004863467020099842,
|
|
"loss": 5.8777,
|
|
"mean_token_accuracy": 0.16410644203424454,
|
|
"num_tokens": 25182349.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 6.234494829177857,
|
|
"epoch": 1.1934828682444365,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048633589691079895,
|
|
"loss": 5.9839,
|
|
"mean_token_accuracy": 0.15102794617414475,
|
|
"num_tokens": 25191971.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 6.113103628158569,
|
|
"epoch": 1.193924408336277,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004863250876716637,
|
|
"loss": 5.7549,
|
|
"mean_token_accuracy": 0.16959406286478043,
|
|
"num_tokens": 25200476.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 6.056025171279908,
|
|
"epoch": 1.1943659484281173,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004863142742927902,
|
|
"loss": 5.8709,
|
|
"mean_token_accuracy": 0.16417582482099533,
|
|
"num_tokens": 25209748.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 6.177553796768189,
|
|
"epoch": 1.1948074885199576,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004863034567743901,
|
|
"loss": 5.9467,
|
|
"mean_token_accuracy": 0.15654509365558625,
|
|
"num_tokens": 25220140.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 6.11725435256958,
|
|
"epoch": 1.195249028611798,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004862926351166756,
|
|
"loss": 5.8271,
|
|
"mean_token_accuracy": 0.1715938687324524,
|
|
"num_tokens": 25228424.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 6.212284183502197,
|
|
"epoch": 1.1956905687036383,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004862818093198585,
|
|
"loss": 5.95,
|
|
"mean_token_accuracy": 0.1611993908882141,
|
|
"num_tokens": 25237448.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 6.115144205093384,
|
|
"epoch": 1.1961321087954786,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004862709793841509,
|
|
"loss": 5.8446,
|
|
"mean_token_accuracy": 0.1682332143187523,
|
|
"num_tokens": 25247124.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 6.005498456954956,
|
|
"epoch": 1.1965736488873189,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048626014530976495,
|
|
"loss": 5.8935,
|
|
"mean_token_accuracy": 0.16573696881532668,
|
|
"num_tokens": 25257363.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 6.1136373519897464,
|
|
"epoch": 1.1970151889791594,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00048624930709691296,
|
|
"loss": 5.9502,
|
|
"mean_token_accuracy": 0.15379948765039445,
|
|
"num_tokens": 25266837.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 6.195064306259155,
|
|
"epoch": 1.1974567290709996,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048623846474580716,
|
|
"loss": 6.0006,
|
|
"mean_token_accuracy": 0.15028007179498673,
|
|
"num_tokens": 25275767.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 6.231287050247192,
|
|
"epoch": 1.19789826916284,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00048622761825665994,
|
|
"loss": 5.9334,
|
|
"mean_token_accuracy": 0.15911966562271118,
|
|
"num_tokens": 25285212.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 6.095887994766235,
|
|
"epoch": 1.1983398092546804,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004862167676296839,
|
|
"loss": 5.8442,
|
|
"mean_token_accuracy": 0.16009492799639702,
|
|
"num_tokens": 25294698.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 6.059245014190674,
|
|
"epoch": 1.1987813493465207,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.0004862059128650915,
|
|
"loss": 5.9115,
|
|
"mean_token_accuracy": 0.16499557793140412,
|
|
"num_tokens": 25304343.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 6.1906756401062015,
|
|
"epoch": 1.199222889438361,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048619505396309525,
|
|
"loss": 5.8242,
|
|
"mean_token_accuracy": 0.15956140011548997,
|
|
"num_tokens": 25312542.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 6.173790645599365,
|
|
"epoch": 1.1996644295302012,
|
|
"grad_norm": 4.65625,
|
|
"learning_rate": 0.0004861841909239081,
|
|
"loss": 5.9449,
|
|
"mean_token_accuracy": 0.16140115708112718,
|
|
"num_tokens": 25322665.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 6.129951047897339,
|
|
"epoch": 1.2001059696220417,
|
|
"grad_norm": 5.84375,
|
|
"learning_rate": 0.00048617332374774276,
|
|
"loss": 5.9005,
|
|
"mean_token_accuracy": 0.16430671364068986,
|
|
"num_tokens": 25332234.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 6.182890844345093,
|
|
"epoch": 1.200547509713882,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.00048616245243481216,
|
|
"loss": 5.9934,
|
|
"mean_token_accuracy": 0.15685328394174575,
|
|
"num_tokens": 25341462.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 6.131249046325683,
|
|
"epoch": 1.2009890498057223,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00048615157698532913,
|
|
"loss": 5.9169,
|
|
"mean_token_accuracy": 0.16424605399370193,
|
|
"num_tokens": 25351771.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 6.136184453964233,
|
|
"epoch": 1.2014305898975628,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00048614069739950683,
|
|
"loss": 5.8721,
|
|
"mean_token_accuracy": 0.16261929720640184,
|
|
"num_tokens": 25360108.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 6.131735229492188,
|
|
"epoch": 1.201872129989403,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004861298136775583,
|
|
"loss": 5.8891,
|
|
"mean_token_accuracy": 0.1624024197459221,
|
|
"num_tokens": 25369635.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 6.100260639190674,
|
|
"epoch": 1.2023136700812433,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004861189258196969,
|
|
"loss": 5.8581,
|
|
"mean_token_accuracy": 0.16749583333730697,
|
|
"num_tokens": 25379623.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 6.163019418716431,
|
|
"epoch": 1.2027552101730836,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004861080338261357,
|
|
"loss": 5.9406,
|
|
"mean_token_accuracy": 0.15702980607748032,
|
|
"num_tokens": 25388591.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 6.17725977897644,
|
|
"epoch": 1.2031967502649241,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004860971376970882,
|
|
"loss": 5.8435,
|
|
"mean_token_accuracy": 0.16299673914909363,
|
|
"num_tokens": 25397865.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 6.075814199447632,
|
|
"epoch": 1.2036382903567644,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.00048608623743276794,
|
|
"loss": 5.7859,
|
|
"mean_token_accuracy": 0.16911190748214722,
|
|
"num_tokens": 25407143.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 6.1407585620880125,
|
|
"epoch": 1.2040798304486047,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.00048607533303338823,
|
|
"loss": 5.9284,
|
|
"mean_token_accuracy": 0.16223665624856948,
|
|
"num_tokens": 25415721.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 6.14788932800293,
|
|
"epoch": 1.2045213705404452,
|
|
"grad_norm": 6.875,
|
|
"learning_rate": 0.00048606442449916284,
|
|
"loss": 5.9796,
|
|
"mean_token_accuracy": 0.1607537016272545,
|
|
"num_tokens": 25425319.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 6.1613319396972654,
|
|
"epoch": 1.2049629106322854,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048605351183030537,
|
|
"loss": 5.9161,
|
|
"mean_token_accuracy": 0.16481170803308487,
|
|
"num_tokens": 25435477.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 6.137243270874023,
|
|
"epoch": 1.2054044507241257,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004860425950270296,
|
|
"loss": 5.9081,
|
|
"mean_token_accuracy": 0.16187706589698792,
|
|
"num_tokens": 25445633.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 6.131955146789551,
|
|
"epoch": 1.205845990815966,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00048603167408954953,
|
|
"loss": 5.8764,
|
|
"mean_token_accuracy": 0.15950068980455398,
|
|
"num_tokens": 25455228.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 6.148524236679077,
|
|
"epoch": 1.2062875309078065,
|
|
"grad_norm": 5.40625,
|
|
"learning_rate": 0.00048602074901807894,
|
|
"loss": 5.8819,
|
|
"mean_token_accuracy": 0.16517825722694396,
|
|
"num_tokens": 25463992.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 6.175719308853149,
|
|
"epoch": 1.2067290709996468,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00048600981981283185,
|
|
"loss": 5.8634,
|
|
"mean_token_accuracy": 0.16691384613513946,
|
|
"num_tokens": 25472985.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 6.140690469741822,
|
|
"epoch": 1.207170611091487,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004859988864740225,
|
|
"loss": 5.8818,
|
|
"mean_token_accuracy": 0.16197107136249542,
|
|
"num_tokens": 25482165.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 6.056623315811157,
|
|
"epoch": 1.2076121511833275,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004859879490018649,
|
|
"loss": 5.9793,
|
|
"mean_token_accuracy": 0.16203480511903762,
|
|
"num_tokens": 25490643.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 6.120284461975098,
|
|
"epoch": 1.2080536912751678,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004859770073965733,
|
|
"loss": 5.8664,
|
|
"mean_token_accuracy": 0.1650485798716545,
|
|
"num_tokens": 25499954.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 6.209693431854248,
|
|
"epoch": 1.208495231367008,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00048596606165836223,
|
|
"loss": 5.9249,
|
|
"mean_token_accuracy": 0.15819624364376067,
|
|
"num_tokens": 25509512.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 6.172435998916626,
|
|
"epoch": 1.2089367714588484,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00048595511178744594,
|
|
"loss": 5.8412,
|
|
"mean_token_accuracy": 0.16026907190680503,
|
|
"num_tokens": 25518909.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 6.0585425853729244,
|
|
"epoch": 1.2093783115506889,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.000485944157784039,
|
|
"loss": 5.9203,
|
|
"mean_token_accuracy": 0.15861292630434037,
|
|
"num_tokens": 25528221.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 6.139790153503418,
|
|
"epoch": 1.2098198516425291,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.000485933199648356,
|
|
"loss": 5.9234,
|
|
"mean_token_accuracy": 0.16150010973215104,
|
|
"num_tokens": 25537428.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 6.163102626800537,
|
|
"epoch": 1.2102613917343694,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.00048592223738061155,
|
|
"loss": 5.9159,
|
|
"mean_token_accuracy": 0.1621326193213463,
|
|
"num_tokens": 25547608.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 6.2079113006591795,
|
|
"epoch": 1.21070293182621,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00048591127098102045,
|
|
"loss": 5.9825,
|
|
"mean_token_accuracy": 0.1559573456645012,
|
|
"num_tokens": 25557482.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 6.12672758102417,
|
|
"epoch": 1.2111444719180502,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004859003004497974,
|
|
"loss": 5.8604,
|
|
"mean_token_accuracy": 0.1620791271328926,
|
|
"num_tokens": 25566967.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 6.152239274978638,
|
|
"epoch": 1.2115860120098905,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.00048588932578715754,
|
|
"loss": 5.8578,
|
|
"mean_token_accuracy": 0.16489053815603255,
|
|
"num_tokens": 25576114.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 6.210437774658203,
|
|
"epoch": 1.2120275521017307,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00048587834699331567,
|
|
"loss": 6.0647,
|
|
"mean_token_accuracy": 0.14975523203611374,
|
|
"num_tokens": 25585953.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 6.2288818359375,
|
|
"epoch": 1.2124690921935712,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.000485867364068487,
|
|
"loss": 6.0321,
|
|
"mean_token_accuracy": 0.15451286286115645,
|
|
"num_tokens": 25595445.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 6.230136966705322,
|
|
"epoch": 1.2129106322854115,
|
|
"grad_norm": 5.4375,
|
|
"learning_rate": 0.00048585637701288646,
|
|
"loss": 5.9031,
|
|
"mean_token_accuracy": 0.16195821315050124,
|
|
"num_tokens": 25605883.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 6.194358062744141,
|
|
"epoch": 1.2133521723772518,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004858453858267295,
|
|
"loss": 5.9484,
|
|
"mean_token_accuracy": 0.1579759567975998,
|
|
"num_tokens": 25615653.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 6.095244264602661,
|
|
"epoch": 1.2137937124690923,
|
|
"grad_norm": 5.46875,
|
|
"learning_rate": 0.0004858343905102314,
|
|
"loss": 5.871,
|
|
"mean_token_accuracy": 0.16299858391284944,
|
|
"num_tokens": 25625043.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 6.165210485458374,
|
|
"epoch": 1.2142352525609326,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048582339106360736,
|
|
"loss": 5.8855,
|
|
"mean_token_accuracy": 0.16728933155536652,
|
|
"num_tokens": 25633642.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 6.2057489395141605,
|
|
"epoch": 1.2146767926527728,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048581238748707304,
|
|
"loss": 5.9392,
|
|
"mean_token_accuracy": 0.15919444113969802,
|
|
"num_tokens": 25642154.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 6.133049726486206,
|
|
"epoch": 1.2151183327446131,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.000485801379780844,
|
|
"loss": 5.8307,
|
|
"mean_token_accuracy": 0.16360081136226653,
|
|
"num_tokens": 25650250.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 6.115797424316407,
|
|
"epoch": 1.2155598728364536,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.00048579036794513584,
|
|
"loss": 5.8827,
|
|
"mean_token_accuracy": 0.16627621203660964,
|
|
"num_tokens": 25659789.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 6.120511722564697,
|
|
"epoch": 1.216001412928294,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00048577935198016413,
|
|
"loss": 5.9403,
|
|
"mean_token_accuracy": 0.15867630243301392,
|
|
"num_tokens": 25668658.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 6.160347652435303,
|
|
"epoch": 1.2164429530201342,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004857683318861449,
|
|
"loss": 5.9365,
|
|
"mean_token_accuracy": 0.15854731649160386,
|
|
"num_tokens": 25679082.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 6.202041149139404,
|
|
"epoch": 1.2168844931119747,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00048575730766329384,
|
|
"loss": 5.9092,
|
|
"mean_token_accuracy": 0.15646228790283204,
|
|
"num_tokens": 25688408.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 6.1509631156921385,
|
|
"epoch": 1.217326033203815,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00048574627931182704,
|
|
"loss": 5.8894,
|
|
"mean_token_accuracy": 0.16455817371606826,
|
|
"num_tokens": 25697415.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 6.15203971862793,
|
|
"epoch": 1.2177675732956552,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048573524683196047,
|
|
"loss": 5.9599,
|
|
"mean_token_accuracy": 0.15235176384449006,
|
|
"num_tokens": 25706330.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 6.21326093673706,
|
|
"epoch": 1.2182091133874955,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004857242102239102,
|
|
"loss": 5.9326,
|
|
"mean_token_accuracy": 0.15663277059793473,
|
|
"num_tokens": 25716198.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 6.211286830902099,
|
|
"epoch": 1.218650653479336,
|
|
"grad_norm": 11.5625,
|
|
"learning_rate": 0.0004857131694878926,
|
|
"loss": 5.9214,
|
|
"mean_token_accuracy": 0.15139016807079314,
|
|
"num_tokens": 25726486.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 6.147220516204834,
|
|
"epoch": 1.2190921935711763,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00048570212462412376,
|
|
"loss": 5.8401,
|
|
"mean_token_accuracy": 0.16819383352994918,
|
|
"num_tokens": 25735559.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 6.137135219573975,
|
|
"epoch": 1.2195337336630165,
|
|
"grad_norm": 4.46875,
|
|
"learning_rate": 0.0004856910756328202,
|
|
"loss": 5.922,
|
|
"mean_token_accuracy": 0.15584810078144073,
|
|
"num_tokens": 25744781.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 6.105981111526489,
|
|
"epoch": 1.219975273754857,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048568002251419835,
|
|
"loss": 5.8809,
|
|
"mean_token_accuracy": 0.16684502214193345,
|
|
"num_tokens": 25753984.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 6.161437606811523,
|
|
"epoch": 1.2204168138466973,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004856689652684746,
|
|
"loss": 5.9624,
|
|
"mean_token_accuracy": 0.15715058296918868,
|
|
"num_tokens": 25763378.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 6.21608190536499,
|
|
"epoch": 1.2208583539385376,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004856579038958656,
|
|
"loss": 5.876,
|
|
"mean_token_accuracy": 0.16399963051080704,
|
|
"num_tokens": 25771907.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 6.160857629776001,
|
|
"epoch": 1.2212998940303779,
|
|
"grad_norm": 7.46875,
|
|
"learning_rate": 0.00048564683839658805,
|
|
"loss": 5.9255,
|
|
"mean_token_accuracy": 0.16224211305379868,
|
|
"num_tokens": 25780464.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 6.106551647186279,
|
|
"epoch": 1.2217414341222184,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00048563576877085887,
|
|
"loss": 5.9417,
|
|
"mean_token_accuracy": 0.16728258579969407,
|
|
"num_tokens": 25790300.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 6.125736951828003,
|
|
"epoch": 1.2221829742140586,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004856246950188947,
|
|
"loss": 5.848,
|
|
"mean_token_accuracy": 0.1637830078601837,
|
|
"num_tokens": 25799103.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 6.183549404144287,
|
|
"epoch": 1.222624514305899,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048561361714091257,
|
|
"loss": 5.9488,
|
|
"mean_token_accuracy": 0.15795571282505988,
|
|
"num_tokens": 25808506.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 6.169549608230591,
|
|
"epoch": 1.2230660543977394,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048560253513712945,
|
|
"loss": 5.897,
|
|
"mean_token_accuracy": 0.15889372080564498,
|
|
"num_tokens": 25817965.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 6.093393850326538,
|
|
"epoch": 1.2235075944895797,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004855914490077624,
|
|
"loss": 5.8957,
|
|
"mean_token_accuracy": 0.1627109855413437,
|
|
"num_tokens": 25827874.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 6.239730882644653,
|
|
"epoch": 1.22394913458142,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048558035875302864,
|
|
"loss": 5.9811,
|
|
"mean_token_accuracy": 0.16338664591312407,
|
|
"num_tokens": 25836840.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 6.169374942779541,
|
|
"epoch": 1.2243906746732602,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004855692643731455,
|
|
"loss": 5.895,
|
|
"mean_token_accuracy": 0.16576620787382126,
|
|
"num_tokens": 25846344.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 6.13448429107666,
|
|
"epoch": 1.2248322147651007,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00048555816586833006,
|
|
"loss": 5.8724,
|
|
"mean_token_accuracy": 0.16877156645059585,
|
|
"num_tokens": 25855336.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 6.169673919677734,
|
|
"epoch": 1.225273754856941,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00048554706323880007,
|
|
"loss": 5.9226,
|
|
"mean_token_accuracy": 0.16086411774158477,
|
|
"num_tokens": 25864402.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 6.134567975997925,
|
|
"epoch": 1.2257152949487813,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004855359564847728,
|
|
"loss": 5.9041,
|
|
"mean_token_accuracy": 0.15963491350412368,
|
|
"num_tokens": 25873326.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 6.154598522186279,
|
|
"epoch": 1.2261568350406218,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048552484560646585,
|
|
"loss": 6.0001,
|
|
"mean_token_accuracy": 0.1461065262556076,
|
|
"num_tokens": 25882521.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 6.144202804565429,
|
|
"epoch": 1.226598375132462,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048551373060409694,
|
|
"loss": 5.8178,
|
|
"mean_token_accuracy": 0.16841204911470414,
|
|
"num_tokens": 25891087.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 6.154122352600098,
|
|
"epoch": 1.2270399152243023,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00048550261147788375,
|
|
"loss": 5.88,
|
|
"mean_token_accuracy": 0.15948003083467482,
|
|
"num_tokens": 25900757.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 6.139804744720459,
|
|
"epoch": 1.2274814553161426,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00048549148822804415,
|
|
"loss": 5.8697,
|
|
"mean_token_accuracy": 0.1640913486480713,
|
|
"num_tokens": 25909801.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 6.183643770217896,
|
|
"epoch": 1.227922995407983,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000485480360854796,
|
|
"loss": 5.9958,
|
|
"mean_token_accuracy": 0.14888071939349173,
|
|
"num_tokens": 25919142.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 6.179129362106323,
|
|
"epoch": 1.2283645354998234,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004854692293583573,
|
|
"loss": 5.8762,
|
|
"mean_token_accuracy": 0.16878688782453538,
|
|
"num_tokens": 25927560.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 6.1683567523956295,
|
|
"epoch": 1.2288060755916637,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00048545809373894605,
|
|
"loss": 5.9942,
|
|
"mean_token_accuracy": 0.15973826497793198,
|
|
"num_tokens": 25937184.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 6.271181583404541,
|
|
"epoch": 1.2292476156835042,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048544695399678044,
|
|
"loss": 6.0021,
|
|
"mean_token_accuracy": 0.1467764362692833,
|
|
"num_tokens": 25946641.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 6.237927389144898,
|
|
"epoch": 1.2296891557753444,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004854358101320787,
|
|
"loss": 6.049,
|
|
"mean_token_accuracy": 0.16022181808948516,
|
|
"num_tokens": 25955910.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 6.144511890411377,
|
|
"epoch": 1.2301306958671847,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048542466214505914,
|
|
"loss": 5.9394,
|
|
"mean_token_accuracy": 0.16163881719112397,
|
|
"num_tokens": 25966580.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 6.1884512424469,
|
|
"epoch": 1.230572235959025,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00048541351003594015,
|
|
"loss": 5.8176,
|
|
"mean_token_accuracy": 0.16138723194599153,
|
|
"num_tokens": 25975815.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 6.10997896194458,
|
|
"epoch": 1.2310137760508655,
|
|
"grad_norm": 3.71875,
|
|
"learning_rate": 0.0004854023538049401,
|
|
"loss": 5.9121,
|
|
"mean_token_accuracy": 0.16547756046056747,
|
|
"num_tokens": 25984784.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 6.098403596878052,
|
|
"epoch": 1.2314553161427058,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00048539119345227774,
|
|
"loss": 5.8799,
|
|
"mean_token_accuracy": 0.1653710812330246,
|
|
"num_tokens": 25994125.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 6.143418645858764,
|
|
"epoch": 1.231896856234546,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004853800289781714,
|
|
"loss": 5.8921,
|
|
"mean_token_accuracy": 0.16527310907840728,
|
|
"num_tokens": 26002876.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 6.166758871078491,
|
|
"epoch": 1.2323383963263865,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00048536886038284,
|
|
"loss": 5.9019,
|
|
"mean_token_accuracy": 0.16711250096559524,
|
|
"num_tokens": 26012591.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 6.178992080688476,
|
|
"epoch": 1.2327799364182268,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048535768766650225,
|
|
"loss": 6.003,
|
|
"mean_token_accuracy": 0.1515873596072197,
|
|
"num_tokens": 26022107.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 6.178382539749146,
|
|
"epoch": 1.233221476510067,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.000485346510829377,
|
|
"loss": 5.9639,
|
|
"mean_token_accuracy": 0.16601064056158066,
|
|
"num_tokens": 26031035.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 6.125119733810425,
|
|
"epoch": 1.2336630166019074,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048533532987168334,
|
|
"loss": 5.826,
|
|
"mean_token_accuracy": 0.16693026423454285,
|
|
"num_tokens": 26039980.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 6.188949108123779,
|
|
"epoch": 1.2341045566937479,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00048532414479364016,
|
|
"loss": 6.0172,
|
|
"mean_token_accuracy": 0.1519097715616226,
|
|
"num_tokens": 26049389.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 6.151670598983765,
|
|
"epoch": 1.2345460967855881,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004853129555954666,
|
|
"loss": 5.8962,
|
|
"mean_token_accuracy": 0.16317246705293656,
|
|
"num_tokens": 26058868.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 6.136835813522339,
|
|
"epoch": 1.2349876368774284,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004853017622773818,
|
|
"loss": 5.9526,
|
|
"mean_token_accuracy": 0.15672052949666976,
|
|
"num_tokens": 26068025.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 6.173934078216552,
|
|
"epoch": 1.235429176969269,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004852905648396051,
|
|
"loss": 5.9081,
|
|
"mean_token_accuracy": 0.1544721782207489,
|
|
"num_tokens": 26076410.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 6.128337287902832,
|
|
"epoch": 1.2358707170611092,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048527936328235583,
|
|
"loss": 5.8651,
|
|
"mean_token_accuracy": 0.16472303867340088,
|
|
"num_tokens": 26085624.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 6.173004293441773,
|
|
"epoch": 1.2363122571529495,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004852681576058534,
|
|
"loss": 5.9532,
|
|
"mean_token_accuracy": 0.15905184745788575,
|
|
"num_tokens": 26094898.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 6.140864658355713,
|
|
"epoch": 1.2367537972447897,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004852569478103174,
|
|
"loss": 5.9093,
|
|
"mean_token_accuracy": 0.1570506900548935,
|
|
"num_tokens": 26105041.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 6.144279956817627,
|
|
"epoch": 1.2371953373366302,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00048524573389596736,
|
|
"loss": 5.8933,
|
|
"mean_token_accuracy": 0.16431440263986588,
|
|
"num_tokens": 26114140.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 6.07152738571167,
|
|
"epoch": 1.2376368774284705,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.00048523451586302295,
|
|
"loss": 5.7642,
|
|
"mean_token_accuracy": 0.16753955632448198,
|
|
"num_tokens": 26122611.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 6.05628514289856,
|
|
"epoch": 1.2380784175203108,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000485223293711704,
|
|
"loss": 5.8383,
|
|
"mean_token_accuracy": 0.1654874250292778,
|
|
"num_tokens": 26131548.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 6.102871990203857,
|
|
"epoch": 1.2385199576121513,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048521206744223024,
|
|
"loss": 5.8317,
|
|
"mean_token_accuracy": 0.15633988827466966,
|
|
"num_tokens": 26139806.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 6.184936237335205,
|
|
"epoch": 1.2389614977039916,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048520083705482165,
|
|
"loss": 5.9427,
|
|
"mean_token_accuracy": 0.1581635892391205,
|
|
"num_tokens": 26148960.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 6.18954291343689,
|
|
"epoch": 1.2394030377958318,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004851896025496982,
|
|
"loss": 5.9559,
|
|
"mean_token_accuracy": 0.1615045428276062,
|
|
"num_tokens": 26158498.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 6.075376701354981,
|
|
"epoch": 1.239844577887672,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00048517836392707994,
|
|
"loss": 5.8065,
|
|
"mean_token_accuracy": 0.1683821365237236,
|
|
"num_tokens": 26167319.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 6.022907018661499,
|
|
"epoch": 1.2402861179795126,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048516712118718713,
|
|
"loss": 5.8174,
|
|
"mean_token_accuracy": 0.16261593699455262,
|
|
"num_tokens": 26176059.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 6.102324914932251,
|
|
"epoch": 1.2407276580713529,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004851558743302399,
|
|
"loss": 5.8302,
|
|
"mean_token_accuracy": 0.1683965727686882,
|
|
"num_tokens": 26185102.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 6.158196020126343,
|
|
"epoch": 1.2411691981631932,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004851446233564586,
|
|
"loss": 5.8742,
|
|
"mean_token_accuracy": 0.1645967409014702,
|
|
"num_tokens": 26194873.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 6.1414063453674315,
|
|
"epoch": 1.2416107382550337,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004851333682660637,
|
|
"loss": 5.9206,
|
|
"mean_token_accuracy": 0.15780261307954788,
|
|
"num_tokens": 26205362.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 6.062950515747071,
|
|
"epoch": 1.242052278346874,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.00048512210905927555,
|
|
"loss": 5.8143,
|
|
"mean_token_accuracy": 0.16553541123867035,
|
|
"num_tokens": 26214266.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 6.242000102996826,
|
|
"epoch": 1.2424938184387142,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004851108457363149,
|
|
"loss": 5.9881,
|
|
"mean_token_accuracy": 0.16291094869375228,
|
|
"num_tokens": 26223069.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 6.16287899017334,
|
|
"epoch": 1.2429353585305545,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004850995782974022,
|
|
"loss": 5.9039,
|
|
"mean_token_accuracy": 0.16355999261140824,
|
|
"num_tokens": 26232547.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 6.16363377571106,
|
|
"epoch": 1.243376898622395,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004850883067427582,
|
|
"loss": 5.8891,
|
|
"mean_token_accuracy": 0.15883788019418715,
|
|
"num_tokens": 26241014.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 6.083933115005493,
|
|
"epoch": 1.2438184387142353,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048507703107260384,
|
|
"loss": 5.9343,
|
|
"mean_token_accuracy": 0.1633957013487816,
|
|
"num_tokens": 26250784.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 6.136890459060669,
|
|
"epoch": 1.2442599788060755,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048506575128715984,
|
|
"loss": 5.8564,
|
|
"mean_token_accuracy": 0.16451779007911682,
|
|
"num_tokens": 26259769.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 6.17093334197998,
|
|
"epoch": 1.244701518897916,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004850544673866474,
|
|
"loss": 5.8908,
|
|
"mean_token_accuracy": 0.15885442569851876,
|
|
"num_tokens": 26269038.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 6.182549715042114,
|
|
"epoch": 1.2451430589897563,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004850431793712873,
|
|
"loss": 5.8784,
|
|
"mean_token_accuracy": 0.15211578011512755,
|
|
"num_tokens": 26278657.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 6.090300464630127,
|
|
"epoch": 1.2455845990815966,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00048503188724130075,
|
|
"loss": 5.8797,
|
|
"mean_token_accuracy": 0.16596818417310716,
|
|
"num_tokens": 26287458.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 6.125815773010254,
|
|
"epoch": 1.2460261391734369,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.000485020590996909,
|
|
"loss": 5.9272,
|
|
"mean_token_accuracy": 0.15662363916635513,
|
|
"num_tokens": 26296324.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 6.149014949798584,
|
|
"epoch": 1.2464676792652774,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00048500929063833334,
|
|
"loss": 5.8424,
|
|
"mean_token_accuracy": 0.16634784489870072,
|
|
"num_tokens": 26304799.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 6.131788158416748,
|
|
"epoch": 1.2469092193571176,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00048499798616579505,
|
|
"loss": 5.9649,
|
|
"mean_token_accuracy": 0.1626861184835434,
|
|
"num_tokens": 26314223.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 6.180202770233154,
|
|
"epoch": 1.247350759448958,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048498667757951574,
|
|
"loss": 5.9632,
|
|
"mean_token_accuracy": 0.1531592920422554,
|
|
"num_tokens": 26323599.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 6.151395988464356,
|
|
"epoch": 1.2477922995407984,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004849753648797168,
|
|
"loss": 5.9923,
|
|
"mean_token_accuracy": 0.15974041521549226,
|
|
"num_tokens": 26331929.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 6.127089214324951,
|
|
"epoch": 1.2482338396326387,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004849640480666199,
|
|
"loss": 5.8848,
|
|
"mean_token_accuracy": 0.16590515971183778,
|
|
"num_tokens": 26340929.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 6.214146089553833,
|
|
"epoch": 1.248675379724479,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004849527271404467,
|
|
"loss": 5.8569,
|
|
"mean_token_accuracy": 0.15572652220726013,
|
|
"num_tokens": 26350393.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 6.212586307525635,
|
|
"epoch": 1.2491169198163192,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048494140210141897,
|
|
"loss": 6.0766,
|
|
"mean_token_accuracy": 0.15760573968291283,
|
|
"num_tokens": 26360709.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 6.143700647354126,
|
|
"epoch": 1.2495584599081597,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048493007294975855,
|
|
"loss": 5.8686,
|
|
"mean_token_accuracy": 0.16504170149564742,
|
|
"num_tokens": 26369447.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 6.146756267547607,
|
|
"epoch": 1.25,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00048491873968568746,
|
|
"loss": 5.855,
|
|
"mean_token_accuracy": 0.16688266023993492,
|
|
"num_tokens": 26379281.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.988578414916992,
|
|
"epoch": 1.2504415400918403,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004849074023094276,
|
|
"loss": 5.7976,
|
|
"mean_token_accuracy": 0.17447122633457185,
|
|
"num_tokens": 26387664.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.986051416397094,
|
|
"epoch": 1.2508830801836806,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048489606082120106,
|
|
"loss": 5.8213,
|
|
"mean_token_accuracy": 0.15860421657562257,
|
|
"num_tokens": 26397485.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 6.107970714569092,
|
|
"epoch": 1.251324620275521,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004848847152212301,
|
|
"loss": 5.7964,
|
|
"mean_token_accuracy": 0.1685743436217308,
|
|
"num_tokens": 26406307.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 6.193047094345093,
|
|
"epoch": 1.2517661603673613,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.000484873365509737,
|
|
"loss": 6.0017,
|
|
"mean_token_accuracy": 0.15746570080518724,
|
|
"num_tokens": 26416155.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 6.133742761611939,
|
|
"epoch": 1.2522077004592016,
|
|
"grad_norm": 4.65625,
|
|
"learning_rate": 0.00048486201168694397,
|
|
"loss": 5.8793,
|
|
"mean_token_accuracy": 0.16526299417018891,
|
|
"num_tokens": 26424147.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 6.1153538703918455,
|
|
"epoch": 1.252649240551042,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.00048485065375307353,
|
|
"loss": 5.8863,
|
|
"mean_token_accuracy": 0.16146370023488998,
|
|
"num_tokens": 26433249.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 6.137222003936768,
|
|
"epoch": 1.2530907806428824,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00048483929170834805,
|
|
"loss": 5.9433,
|
|
"mean_token_accuracy": 0.16384687423706054,
|
|
"num_tokens": 26442346.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 6.146828317642212,
|
|
"epoch": 1.2535323207347226,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00048482792555299027,
|
|
"loss": 5.8913,
|
|
"mean_token_accuracy": 0.16533481031656266,
|
|
"num_tokens": 26450885.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 6.143717241287232,
|
|
"epoch": 1.2539738608265631,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004848165552872227,
|
|
"loss": 5.9226,
|
|
"mean_token_accuracy": 0.16853769421577453,
|
|
"num_tokens": 26459827.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 6.089367198944092,
|
|
"epoch": 1.2544154009184034,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004848051809112682,
|
|
"loss": 5.9073,
|
|
"mean_token_accuracy": 0.1613314315676689,
|
|
"num_tokens": 26468357.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 6.1293073177337645,
|
|
"epoch": 1.2548569410102437,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048479380242534955,
|
|
"loss": 5.9997,
|
|
"mean_token_accuracy": 0.1588381201028824,
|
|
"num_tokens": 26477396.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 6.179404830932617,
|
|
"epoch": 1.2552984811020842,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004847824198296896,
|
|
"loss": 5.948,
|
|
"mean_token_accuracy": 0.1606784790754318,
|
|
"num_tokens": 26486468.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 6.213735294342041,
|
|
"epoch": 1.2557400211939245,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004847710331245113,
|
|
"loss": 5.8993,
|
|
"mean_token_accuracy": 0.1633673846721649,
|
|
"num_tokens": 26496157.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 6.061906909942627,
|
|
"epoch": 1.2561815612857647,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048475964231003776,
|
|
"loss": 5.7761,
|
|
"mean_token_accuracy": 0.17620088160037994,
|
|
"num_tokens": 26504573.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 6.01952805519104,
|
|
"epoch": 1.256623101377605,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004847482473864922,
|
|
"loss": 5.751,
|
|
"mean_token_accuracy": 0.17447698712348939,
|
|
"num_tokens": 26513441.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 6.1289002895355225,
|
|
"epoch": 1.2570646414694453,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.0004847368483540977,
|
|
"loss": 5.9697,
|
|
"mean_token_accuracy": 0.15450180172920228,
|
|
"num_tokens": 26522911.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 6.088858222961425,
|
|
"epoch": 1.2575061815612858,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048472544521307765,
|
|
"loss": 5.8259,
|
|
"mean_token_accuracy": 0.168184857070446,
|
|
"num_tokens": 26531388.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 6.148261499404907,
|
|
"epoch": 1.257947721653126,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004847140379636554,
|
|
"loss": 5.8277,
|
|
"mean_token_accuracy": 0.1657315105199814,
|
|
"num_tokens": 26540500.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 6.1033295631408695,
|
|
"epoch": 1.2583892617449663,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004847026266060545,
|
|
"loss": 5.8336,
|
|
"mean_token_accuracy": 0.16738886535167694,
|
|
"num_tokens": 26550041.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 6.08073844909668,
|
|
"epoch": 1.2588308018368068,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004846912111404983,
|
|
"loss": 5.8132,
|
|
"mean_token_accuracy": 0.16374696642160416,
|
|
"num_tokens": 26559594.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 6.134618186950684,
|
|
"epoch": 1.2592723419286471,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00048467979156721055,
|
|
"loss": 5.8958,
|
|
"mean_token_accuracy": 0.16100245267152785,
|
|
"num_tokens": 26569143.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 6.075584793090821,
|
|
"epoch": 1.2597138820204874,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048466836788641496,
|
|
"loss": 5.8709,
|
|
"mean_token_accuracy": 0.16191661655902861,
|
|
"num_tokens": 26578040.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 6.110110807418823,
|
|
"epoch": 1.260155422112328,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00048465694009833525,
|
|
"loss": 5.9016,
|
|
"mean_token_accuracy": 0.16245102733373643,
|
|
"num_tokens": 26588283.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 6.169938564300537,
|
|
"epoch": 1.2605969622041682,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048464550820319537,
|
|
"loss": 5.9417,
|
|
"mean_token_accuracy": 0.15852103233337403,
|
|
"num_tokens": 26597815.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 6.100296974182129,
|
|
"epoch": 1.2610385022960084,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004846340722012192,
|
|
"loss": 5.9146,
|
|
"mean_token_accuracy": 0.1597320780158043,
|
|
"num_tokens": 26606752.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 6.158532190322876,
|
|
"epoch": 1.261480042387849,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004846226320926308,
|
|
"loss": 5.8915,
|
|
"mean_token_accuracy": 0.16063199043273926,
|
|
"num_tokens": 26615312.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 6.184799385070801,
|
|
"epoch": 1.2619215824796892,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004846111878776542,
|
|
"loss": 5.8876,
|
|
"mean_token_accuracy": 0.16116779446601867,
|
|
"num_tokens": 26624642.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 6.052973508834839,
|
|
"epoch": 1.2623631225715295,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004845997395565137,
|
|
"loss": 5.7603,
|
|
"mean_token_accuracy": 0.17240442037582399,
|
|
"num_tokens": 26633250.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 6.061658334732056,
|
|
"epoch": 1.2628046626633698,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.0004845882871294335,
|
|
"loss": 5.92,
|
|
"mean_token_accuracy": 0.16076537370681762,
|
|
"num_tokens": 26642422.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 6.150954103469848,
|
|
"epoch": 1.26324620275521,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004845768305966379,
|
|
"loss": 5.9583,
|
|
"mean_token_accuracy": 0.15743603110313414,
|
|
"num_tokens": 26651978.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 6.1525288105010985,
|
|
"epoch": 1.2636877428470505,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004845653699583515,
|
|
"loss": 5.9573,
|
|
"mean_token_accuracy": 0.1546889066696167,
|
|
"num_tokens": 26662075.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 6.153447103500366,
|
|
"epoch": 1.2641292829388908,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048455390521479855,
|
|
"loss": 5.8636,
|
|
"mean_token_accuracy": 0.16401289254426957,
|
|
"num_tokens": 26670813.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 6.144858694076538,
|
|
"epoch": 1.264570823030731,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00048454243636620383,
|
|
"loss": 5.8906,
|
|
"mean_token_accuracy": 0.16578105837106705,
|
|
"num_tokens": 26679867.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 6.084038591384887,
|
|
"epoch": 1.2650123631225716,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000484530963412792,
|
|
"loss": 5.9121,
|
|
"mean_token_accuracy": 0.15640238672494888,
|
|
"num_tokens": 26688523.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 6.114808654785156,
|
|
"epoch": 1.2654539032144119,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048451948635478765,
|
|
"loss": 5.9695,
|
|
"mean_token_accuracy": 0.16364617198705672,
|
|
"num_tokens": 26697922.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 6.158629322052002,
|
|
"epoch": 1.2658954433062521,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004845080051924158,
|
|
"loss": 5.9157,
|
|
"mean_token_accuracy": 0.15545468032360077,
|
|
"num_tokens": 26707058.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 6.158748531341553,
|
|
"epoch": 1.2663369833980926,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004844965199259013,
|
|
"loss": 5.9035,
|
|
"mean_token_accuracy": 0.16495700180530548,
|
|
"num_tokens": 26715873.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 6.170320844650268,
|
|
"epoch": 1.266778523489933,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004844850305554692,
|
|
"loss": 5.9055,
|
|
"mean_token_accuracy": 0.16377891302108766,
|
|
"num_tokens": 26726253.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 6.143414831161499,
|
|
"epoch": 1.2672200635817732,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00048447353708134426,
|
|
"loss": 5.9287,
|
|
"mean_token_accuracy": 0.16029662042856216,
|
|
"num_tokens": 26737077.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 6.134037160873413,
|
|
"epoch": 1.2676616036736137,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.000484462039503752,
|
|
"loss": 5.9326,
|
|
"mean_token_accuracy": 0.15892160981893538,
|
|
"num_tokens": 26746603.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 6.08798565864563,
|
|
"epoch": 1.268103143765454,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00048445053782291753,
|
|
"loss": 5.8972,
|
|
"mean_token_accuracy": 0.16114922016859054,
|
|
"num_tokens": 26756174.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 6.116337156295776,
|
|
"epoch": 1.2685446838572942,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00048443903203906614,
|
|
"loss": 5.8928,
|
|
"mean_token_accuracy": 0.16467928588390351,
|
|
"num_tokens": 26765124.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 6.109856700897216,
|
|
"epoch": 1.2689862239491345,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004844275221524232,
|
|
"loss": 5.8811,
|
|
"mean_token_accuracy": 0.17070176005363463,
|
|
"num_tokens": 26774438.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 6.210801219940185,
|
|
"epoch": 1.2694277640409748,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00048441600816321424,
|
|
"loss": 5.9172,
|
|
"mean_token_accuracy": 0.1579091191291809,
|
|
"num_tokens": 26783613.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 6.105120325088501,
|
|
"epoch": 1.2698693041328153,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004844044900716647,
|
|
"loss": 5.7676,
|
|
"mean_token_accuracy": 0.16843381524085999,
|
|
"num_tokens": 26792136.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 6.0391148090362545,
|
|
"epoch": 1.2703108442246556,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004843929678780004,
|
|
"loss": 5.7884,
|
|
"mean_token_accuracy": 0.17705477327108382,
|
|
"num_tokens": 26801481.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 6.069174575805664,
|
|
"epoch": 1.2707523843164958,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004843814415824469,
|
|
"loss": 5.8658,
|
|
"mean_token_accuracy": 0.16673449277877808,
|
|
"num_tokens": 26810503.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 6.198712348937988,
|
|
"epoch": 1.2711939244083363,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00048436991118523003,
|
|
"loss": 5.9038,
|
|
"mean_token_accuracy": 0.16482168734073638,
|
|
"num_tokens": 26820007.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 6.135466194152832,
|
|
"epoch": 1.2716354645001766,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.00048435837668657565,
|
|
"loss": 5.8228,
|
|
"mean_token_accuracy": 0.1683567062020302,
|
|
"num_tokens": 26829088.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 6.088929128646851,
|
|
"epoch": 1.272077004592017,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004843468380867098,
|
|
"loss": 5.9164,
|
|
"mean_token_accuracy": 0.16359835118055344,
|
|
"num_tokens": 26838619.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 6.108640670776367,
|
|
"epoch": 1.2725185446838574,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004843352953858585,
|
|
"loss": 5.9344,
|
|
"mean_token_accuracy": 0.1615082025527954,
|
|
"num_tokens": 26848728.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 6.143708229064941,
|
|
"epoch": 1.2729600847756977,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004843237485842477,
|
|
"loss": 5.8505,
|
|
"mean_token_accuracy": 0.17027464807033538,
|
|
"num_tokens": 26859293.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 6.12141752243042,
|
|
"epoch": 1.273401624867538,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048431219768210374,
|
|
"loss": 5.9081,
|
|
"mean_token_accuracy": 0.1629863888025284,
|
|
"num_tokens": 26868818.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 6.207045698165894,
|
|
"epoch": 1.2738431649593784,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004843006426796529,
|
|
"loss": 5.991,
|
|
"mean_token_accuracy": 0.1566545620560646,
|
|
"num_tokens": 26879245.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 6.158621215820313,
|
|
"epoch": 1.2742847050512187,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004842890835771215,
|
|
"loss": 5.8771,
|
|
"mean_token_accuracy": 0.1620942696928978,
|
|
"num_tokens": 26888074.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 6.132410717010498,
|
|
"epoch": 1.274726245143059,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.000484277520374736,
|
|
"loss": 5.9138,
|
|
"mean_token_accuracy": 0.15504443496465684,
|
|
"num_tokens": 26897324.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 6.2166553974151615,
|
|
"epoch": 1.2751677852348993,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00048426595307272285,
|
|
"loss": 6.0221,
|
|
"mean_token_accuracy": 0.15333397835493087,
|
|
"num_tokens": 26906797.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 6.209755325317383,
|
|
"epoch": 1.2756093253267395,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048425438167130875,
|
|
"loss": 5.9388,
|
|
"mean_token_accuracy": 0.1663684904575348,
|
|
"num_tokens": 26915737.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 6.081834125518799,
|
|
"epoch": 1.27605086541858,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048424280617072026,
|
|
"loss": 5.8803,
|
|
"mean_token_accuracy": 0.16682081371545793,
|
|
"num_tokens": 26925364.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 6.108405208587646,
|
|
"epoch": 1.2764924055104203,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048423122657118424,
|
|
"loss": 5.8691,
|
|
"mean_token_accuracy": 0.1697370171546936,
|
|
"num_tokens": 26935188.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 6.109171676635742,
|
|
"epoch": 1.2769339456022606,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00048421964287292745,
|
|
"loss": 5.8597,
|
|
"mean_token_accuracy": 0.16356942057609558,
|
|
"num_tokens": 26944606.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 6.183118057250977,
|
|
"epoch": 1.277375485694101,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004842080550761769,
|
|
"loss": 5.9759,
|
|
"mean_token_accuracy": 0.15626660883426666,
|
|
"num_tokens": 26955147.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 6.133596706390381,
|
|
"epoch": 1.2778170257859414,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004841964631811595,
|
|
"loss": 5.9184,
|
|
"mean_token_accuracy": 0.1682221621274948,
|
|
"num_tokens": 26964243.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 6.190114974975586,
|
|
"epoch": 1.2782585658777816,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00048418486718810244,
|
|
"loss": 5.9028,
|
|
"mean_token_accuracy": 0.16112356930971145,
|
|
"num_tokens": 26973284.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 6.18262734413147,
|
|
"epoch": 1.2787001059696221,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004841732670972327,
|
|
"loss": 5.9903,
|
|
"mean_token_accuracy": 0.1584943115711212,
|
|
"num_tokens": 26982757.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 6.164980840682984,
|
|
"epoch": 1.2791416460614624,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004841616629087776,
|
|
"loss": 5.9234,
|
|
"mean_token_accuracy": 0.15870108753442763,
|
|
"num_tokens": 26991784.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 6.195461940765381,
|
|
"epoch": 1.2795831861533027,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048415005462296455,
|
|
"loss": 5.925,
|
|
"mean_token_accuracy": 0.15015334486961365,
|
|
"num_tokens": 27000700.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 6.165881538391114,
|
|
"epoch": 1.2800247262451432,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004841384422400209,
|
|
"loss": 5.881,
|
|
"mean_token_accuracy": 0.17133558839559554,
|
|
"num_tokens": 27010089.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 6.090375089645386,
|
|
"epoch": 1.2804662663369835,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004841268257601741,
|
|
"loss": 5.885,
|
|
"mean_token_accuracy": 0.16691755950450898,
|
|
"num_tokens": 27018961.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 6.148070478439331,
|
|
"epoch": 1.2809078064288237,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004841152051836517,
|
|
"loss": 5.9356,
|
|
"mean_token_accuracy": 0.16089101135730743,
|
|
"num_tokens": 27027905.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 6.140289926528931,
|
|
"epoch": 1.281349346520664,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048410358051068135,
|
|
"loss": 5.859,
|
|
"mean_token_accuracy": 0.16071921437978745,
|
|
"num_tokens": 27036969.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 6.054096698760986,
|
|
"epoch": 1.2817908866125043,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004840919517414908,
|
|
"loss": 5.8292,
|
|
"mean_token_accuracy": 0.17177568078041078,
|
|
"num_tokens": 27046654.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 6.160114002227783,
|
|
"epoch": 1.2822324267043448,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048408031887630775,
|
|
"loss": 5.9421,
|
|
"mean_token_accuracy": 0.16171510368585587,
|
|
"num_tokens": 27058492.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 6.185419082641602,
|
|
"epoch": 1.282673966796185,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004840686819153604,
|
|
"loss": 5.9313,
|
|
"mean_token_accuracy": 0.16024121046066284,
|
|
"num_tokens": 27068863.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 6.132033395767212,
|
|
"epoch": 1.2831155068880253,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004840570408588762,
|
|
"loss": 5.8992,
|
|
"mean_token_accuracy": 0.16224589496850966,
|
|
"num_tokens": 27078793.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 6.066058921813965,
|
|
"epoch": 1.2835570469798658,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004840453957070836,
|
|
"loss": 5.7058,
|
|
"mean_token_accuracy": 0.17713941931724547,
|
|
"num_tokens": 27087093.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 6.119988012313843,
|
|
"epoch": 1.283998587071706,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00048403374646021057,
|
|
"loss": 5.8232,
|
|
"mean_token_accuracy": 0.16361542344093322,
|
|
"num_tokens": 27096601.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 6.100772953033447,
|
|
"epoch": 1.2844401271635464,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.00048402209311848533,
|
|
"loss": 5.8515,
|
|
"mean_token_accuracy": 0.16600432693958284,
|
|
"num_tokens": 27105041.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 6.101114559173584,
|
|
"epoch": 1.2848816672553869,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048401043568213614,
|
|
"loss": 5.927,
|
|
"mean_token_accuracy": 0.16112814247608184,
|
|
"num_tokens": 27114252.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 6.143374300003051,
|
|
"epoch": 1.2853232073472272,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004839987741513914,
|
|
"loss": 5.851,
|
|
"mean_token_accuracy": 0.16172419786453246,
|
|
"num_tokens": 27122480.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 6.114062023162842,
|
|
"epoch": 1.2857647474390674,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00048398710852647954,
|
|
"loss": 5.9046,
|
|
"mean_token_accuracy": 0.159881991147995,
|
|
"num_tokens": 27132322.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 6.0440285205841064,
|
|
"epoch": 1.286206287530908,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048397543880762905,
|
|
"loss": 5.7701,
|
|
"mean_token_accuracy": 0.17634997218847276,
|
|
"num_tokens": 27140782.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 6.061186504364014,
|
|
"epoch": 1.2866478276227482,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.00048396376499506866,
|
|
"loss": 5.8139,
|
|
"mean_token_accuracy": 0.16377085894346238,
|
|
"num_tokens": 27150058.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 6.089512825012207,
|
|
"epoch": 1.2870893677145885,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048395208708902686,
|
|
"loss": 5.8486,
|
|
"mean_token_accuracy": 0.16396327018737794,
|
|
"num_tokens": 27159574.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 6.119163084030151,
|
|
"epoch": 1.2875309078064288,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00048394040508973257,
|
|
"loss": 5.8675,
|
|
"mean_token_accuracy": 0.1665537938475609,
|
|
"num_tokens": 27168025.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 6.033315896987915,
|
|
"epoch": 1.287972447898269,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004839287189974145,
|
|
"loss": 5.8759,
|
|
"mean_token_accuracy": 0.16489376351237298,
|
|
"num_tokens": 27177108.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 6.097931241989135,
|
|
"epoch": 1.2884139879901095,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048391702881230177,
|
|
"loss": 5.9287,
|
|
"mean_token_accuracy": 0.1560143455862999,
|
|
"num_tokens": 27187486.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 6.214470434188843,
|
|
"epoch": 1.2888555280819498,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004839053345346232,
|
|
"loss": 5.9183,
|
|
"mean_token_accuracy": 0.15378315448760987,
|
|
"num_tokens": 27195962.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 6.122103357315064,
|
|
"epoch": 1.28929706817379,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004838936361646079,
|
|
"loss": 5.8991,
|
|
"mean_token_accuracy": 0.16736670732498168,
|
|
"num_tokens": 27206354.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 6.027134132385254,
|
|
"epoch": 1.2897386082656306,
|
|
"grad_norm": 5.5625,
|
|
"learning_rate": 0.0004838819337024852,
|
|
"loss": 5.7738,
|
|
"mean_token_accuracy": 0.1755576863884926,
|
|
"num_tokens": 27215326.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 6.133112668991089,
|
|
"epoch": 1.2901801483574709,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00048387022714848406,
|
|
"loss": 5.8949,
|
|
"mean_token_accuracy": 0.1606071799993515,
|
|
"num_tokens": 27224253.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 6.138223695755005,
|
|
"epoch": 1.2906216884493111,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.000483858516502834,
|
|
"loss": 5.8747,
|
|
"mean_token_accuracy": 0.16328553929924966,
|
|
"num_tokens": 27233007.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 6.104684782028198,
|
|
"epoch": 1.2910632285411516,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004838468017657644,
|
|
"loss": 5.8134,
|
|
"mean_token_accuracy": 0.16842241287231446,
|
|
"num_tokens": 27242127.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 6.124634170532227,
|
|
"epoch": 1.291504768632992,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048383508293750474,
|
|
"loss": 5.974,
|
|
"mean_token_accuracy": 0.15246982127428055,
|
|
"num_tokens": 27252753.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 6.151149320602417,
|
|
"epoch": 1.2919463087248322,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004838233600182846,
|
|
"loss": 5.9559,
|
|
"mean_token_accuracy": 0.15627553910017014,
|
|
"num_tokens": 27262498.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 6.214147233963013,
|
|
"epoch": 1.2923878488166727,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004838116330083336,
|
|
"loss": 5.9429,
|
|
"mean_token_accuracy": 0.15430187582969665,
|
|
"num_tokens": 27271524.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 6.033311462402343,
|
|
"epoch": 1.292829388908513,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004837999019078814,
|
|
"loss": 5.7891,
|
|
"mean_token_accuracy": 0.17727081030607222,
|
|
"num_tokens": 27280649.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 6.132535409927368,
|
|
"epoch": 1.2932709290003532,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004837881667171579,
|
|
"loss": 5.8911,
|
|
"mean_token_accuracy": 0.15832727998495102,
|
|
"num_tokens": 27289593.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 6.154211759567261,
|
|
"epoch": 1.2937124690921935,
|
|
"grad_norm": 5.09375,
|
|
"learning_rate": 0.00048377642743639297,
|
|
"loss": 5.8838,
|
|
"mean_token_accuracy": 0.15846479535102845,
|
|
"num_tokens": 27298070.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 6.0713883399963375,
|
|
"epoch": 1.2941540091840338,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004837646840658166,
|
|
"loss": 5.8367,
|
|
"mean_token_accuracy": 0.16703768968582153,
|
|
"num_tokens": 27306738.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 6.057452917098999,
|
|
"epoch": 1.2945955492758743,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00048375293660565875,
|
|
"loss": 5.806,
|
|
"mean_token_accuracy": 0.1690780997276306,
|
|
"num_tokens": 27315243.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 6.063826990127564,
|
|
"epoch": 1.2950370893677146,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004837411850561496,
|
|
"loss": 5.827,
|
|
"mean_token_accuracy": 0.16601891815662384,
|
|
"num_tokens": 27325327.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 6.135980796813965,
|
|
"epoch": 1.2954786294595548,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048372942941751935,
|
|
"loss": 5.8388,
|
|
"mean_token_accuracy": 0.16478551179170609,
|
|
"num_tokens": 27333436.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 6.142597389221192,
|
|
"epoch": 1.2959201695513953,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004837176696899984,
|
|
"loss": 5.9235,
|
|
"mean_token_accuracy": 0.15309327989816665,
|
|
"num_tokens": 27342689.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 6.159892749786377,
|
|
"epoch": 1.2963617096432356,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00048370590587381684,
|
|
"loss": 5.9153,
|
|
"mean_token_accuracy": 0.16493655294179915,
|
|
"num_tokens": 27352347.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 6.1565186977386475,
|
|
"epoch": 1.2968032497350759,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048369413796920535,
|
|
"loss": 5.9271,
|
|
"mean_token_accuracy": 0.15912128239870071,
|
|
"num_tokens": 27362153.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 6.053378105163574,
|
|
"epoch": 1.2972447898269164,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004836823659763944,
|
|
"loss": 5.8673,
|
|
"mean_token_accuracy": 0.1583820253610611,
|
|
"num_tokens": 27371126.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 6.070938777923584,
|
|
"epoch": 1.2976863299187567,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00048367058989561457,
|
|
"loss": 5.8012,
|
|
"mean_token_accuracy": 0.1651498258113861,
|
|
"num_tokens": 27380727.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 6.123284435272216,
|
|
"epoch": 1.298127870010597,
|
|
"grad_norm": 8.75,
|
|
"learning_rate": 0.0004836588097270966,
|
|
"loss": 5.8562,
|
|
"mean_token_accuracy": 0.16518203765153885,
|
|
"num_tokens": 27389970.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 6.07294864654541,
|
|
"epoch": 1.2985694101024374,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048364702547107113,
|
|
"loss": 5.7924,
|
|
"mean_token_accuracy": 0.16545184776186944,
|
|
"num_tokens": 27399177.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 6.131297159194946,
|
|
"epoch": 1.2990109501942777,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004836352371277692,
|
|
"loss": 5.9119,
|
|
"mean_token_accuracy": 0.16712456047534943,
|
|
"num_tokens": 27408776.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 6.1579790115356445,
|
|
"epoch": 1.299452490286118,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004836234446974216,
|
|
"loss": 5.9211,
|
|
"mean_token_accuracy": 0.15698197185993196,
|
|
"num_tokens": 27418708.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 6.161049127578735,
|
|
"epoch": 1.2998940303779583,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004836116481802593,
|
|
"loss": 5.8676,
|
|
"mean_token_accuracy": 0.16068847924470903,
|
|
"num_tokens": 27428027.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 6.059080743789673,
|
|
"epoch": 1.3003355704697985,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048359984757651356,
|
|
"loss": 5.8477,
|
|
"mean_token_accuracy": 0.167088121175766,
|
|
"num_tokens": 27438214.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 6.089139747619629,
|
|
"epoch": 1.300777110561639,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00048358804288641536,
|
|
"loss": 5.8079,
|
|
"mean_token_accuracy": 0.1652594432234764,
|
|
"num_tokens": 27447413.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 6.043606090545654,
|
|
"epoch": 1.3012186506534793,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048357623411019607,
|
|
"loss": 5.8367,
|
|
"mean_token_accuracy": 0.16637206077575684,
|
|
"num_tokens": 27456316.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 6.027954626083374,
|
|
"epoch": 1.3016601907453196,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000483564421248087,
|
|
"loss": 5.8795,
|
|
"mean_token_accuracy": 0.16721034198999404,
|
|
"num_tokens": 27465346.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 6.0546328067779545,
|
|
"epoch": 1.30210173083716,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048355260430031947,
|
|
"loss": 5.734,
|
|
"mean_token_accuracy": 0.1723693937063217,
|
|
"num_tokens": 27473367.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 6.189047908782959,
|
|
"epoch": 1.3025432709290004,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.000483540783267125,
|
|
"loss": 5.9092,
|
|
"mean_token_accuracy": 0.15992856174707412,
|
|
"num_tokens": 27482187.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 6.041848230361938,
|
|
"epoch": 1.3029848110208406,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048352895814873526,
|
|
"loss": 5.8628,
|
|
"mean_token_accuracy": 0.16338201314210893,
|
|
"num_tokens": 27492406.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 6.137863254547119,
|
|
"epoch": 1.3034263511126811,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004835171289453818,
|
|
"loss": 5.9298,
|
|
"mean_token_accuracy": 0.166038478910923,
|
|
"num_tokens": 27501929.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 6.13617787361145,
|
|
"epoch": 1.3038678912045214,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004835052956572964,
|
|
"loss": 5.7808,
|
|
"mean_token_accuracy": 0.1754772201180458,
|
|
"num_tokens": 27510657.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 6.070120143890381,
|
|
"epoch": 1.3043094312963617,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048349345828471084,
|
|
"loss": 5.9116,
|
|
"mean_token_accuracy": 0.1547280415892601,
|
|
"num_tokens": 27519726.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 6.0759790420532225,
|
|
"epoch": 1.3047509713882022,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00048348161682785704,
|
|
"loss": 5.8346,
|
|
"mean_token_accuracy": 0.16799575984477996,
|
|
"num_tokens": 27528876.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 6.152000617980957,
|
|
"epoch": 1.3051925114800424,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004834697712869669,
|
|
"loss": 5.8871,
|
|
"mean_token_accuracy": 0.16133493781089783,
|
|
"num_tokens": 27537782.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 6.131542634963989,
|
|
"epoch": 1.3056340515718827,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004834579216622725,
|
|
"loss": 5.91,
|
|
"mean_token_accuracy": 0.15888519287109376,
|
|
"num_tokens": 27547322.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 6.066386461257935,
|
|
"epoch": 1.306075591663723,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000483446067954006,
|
|
"loss": 5.8444,
|
|
"mean_token_accuracy": 0.16652489006519317,
|
|
"num_tokens": 27556070.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 6.074157190322876,
|
|
"epoch": 1.3065171317555633,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00048343421016239945,
|
|
"loss": 5.7794,
|
|
"mean_token_accuracy": 0.17245520651340485,
|
|
"num_tokens": 27565951.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 6.137390661239624,
|
|
"epoch": 1.3069586718474038,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004834223482876854,
|
|
"loss": 5.8563,
|
|
"mean_token_accuracy": 0.16035415083169938,
|
|
"num_tokens": 27575102.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 6.1102954864501955,
|
|
"epoch": 1.307400211939244,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004834104823300961,
|
|
"loss": 5.9327,
|
|
"mean_token_accuracy": 0.15517421066761017,
|
|
"num_tokens": 27584854.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 6.087147808074951,
|
|
"epoch": 1.3078417520310843,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00048339861228986395,
|
|
"loss": 5.8791,
|
|
"mean_token_accuracy": 0.16814199835062027,
|
|
"num_tokens": 27593403.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 6.150009822845459,
|
|
"epoch": 1.3082832921229248,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00048338673816722145,
|
|
"loss": 5.9597,
|
|
"mean_token_accuracy": 0.16064391434192657,
|
|
"num_tokens": 27602162.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 6.095381069183349,
|
|
"epoch": 1.308724832214765,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.00048337485996240127,
|
|
"loss": 5.9436,
|
|
"mean_token_accuracy": 0.15897045135498047,
|
|
"num_tokens": 27611433.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 6.117966175079346,
|
|
"epoch": 1.3091663723066054,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004833629776756362,
|
|
"loss": 5.7991,
|
|
"mean_token_accuracy": 0.16362854093313217,
|
|
"num_tokens": 27620443.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 6.164895009994507,
|
|
"epoch": 1.3096079123984459,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00048335109130715875,
|
|
"loss": 5.8608,
|
|
"mean_token_accuracy": 0.16003518104553222,
|
|
"num_tokens": 27629507.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 6.107555246353149,
|
|
"epoch": 1.3100494524902861,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004833392008572021,
|
|
"loss": 5.8665,
|
|
"mean_token_accuracy": 0.16597609370946884,
|
|
"num_tokens": 27638355.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 6.1141993522644045,
|
|
"epoch": 1.3104909925821264,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.00048332730632599883,
|
|
"loss": 5.9061,
|
|
"mean_token_accuracy": 0.16002965420484544,
|
|
"num_tokens": 27649074.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 6.130582714080811,
|
|
"epoch": 1.310932532673967,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004833154077137821,
|
|
"loss": 5.9186,
|
|
"mean_token_accuracy": 0.16170259714126586,
|
|
"num_tokens": 27658564.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 6.117284917831421,
|
|
"epoch": 1.3113740727658072,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048330350502078515,
|
|
"loss": 5.8453,
|
|
"mean_token_accuracy": 0.1653812810778618,
|
|
"num_tokens": 27667963.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 6.132467746734619,
|
|
"epoch": 1.3118156128576475,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048329159824724087,
|
|
"loss": 5.9281,
|
|
"mean_token_accuracy": 0.1623508483171463,
|
|
"num_tokens": 27677528.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 6.1240575313568115,
|
|
"epoch": 1.3122571529494877,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00048327968739338275,
|
|
"loss": 5.8323,
|
|
"mean_token_accuracy": 0.17114934474229812,
|
|
"num_tokens": 27687659.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 6.027389669418335,
|
|
"epoch": 1.312698693041328,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.00048326777245944396,
|
|
"loss": 5.7765,
|
|
"mean_token_accuracy": 0.1733567014336586,
|
|
"num_tokens": 27697222.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 6.070391416549683,
|
|
"epoch": 1.3131402331331685,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.000483255853445658,
|
|
"loss": 5.8606,
|
|
"mean_token_accuracy": 0.16391192525625228,
|
|
"num_tokens": 27705664.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 6.034143924713135,
|
|
"epoch": 1.3135817732250088,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048324393035225824,
|
|
"loss": 5.7994,
|
|
"mean_token_accuracy": 0.1712170198559761,
|
|
"num_tokens": 27714879.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 6.087355995178223,
|
|
"epoch": 1.314023313316849,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004832320031794783,
|
|
"loss": 5.9291,
|
|
"mean_token_accuracy": 0.15606244653463364,
|
|
"num_tokens": 27724749.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 6.1193657398223875,
|
|
"epoch": 1.3144648534086896,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004832200719275519,
|
|
"loss": 5.883,
|
|
"mean_token_accuracy": 0.1629638969898224,
|
|
"num_tokens": 27733109.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.940599203109741,
|
|
"epoch": 1.3149063935005298,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004832081365967128,
|
|
"loss": 5.6814,
|
|
"mean_token_accuracy": 0.17373916655778884,
|
|
"num_tokens": 27742079.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 6.133149671554565,
|
|
"epoch": 1.3153479335923701,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.00048319619718719455,
|
|
"loss": 5.9351,
|
|
"mean_token_accuracy": 0.15382995456457138,
|
|
"num_tokens": 27750900.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 6.117257022857666,
|
|
"epoch": 1.3157894736842106,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00048318425369923133,
|
|
"loss": 5.8121,
|
|
"mean_token_accuracy": 0.17089105993509293,
|
|
"num_tokens": 27760392.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 6.077043914794922,
|
|
"epoch": 1.316231013776051,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004831723061330569,
|
|
"loss": 5.8621,
|
|
"mean_token_accuracy": 0.16401863396167754,
|
|
"num_tokens": 27768805.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 6.14566478729248,
|
|
"epoch": 1.3166725538678912,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048316035448890546,
|
|
"loss": 5.9572,
|
|
"mean_token_accuracy": 0.15272333323955536,
|
|
"num_tokens": 27777165.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 6.142856931686401,
|
|
"epoch": 1.3171140939597317,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.000483148398767011,
|
|
"loss": 5.8941,
|
|
"mean_token_accuracy": 0.1675186425447464,
|
|
"num_tokens": 27786709.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 6.020650815963745,
|
|
"epoch": 1.317555634051572,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00048313643896760776,
|
|
"loss": 5.8282,
|
|
"mean_token_accuracy": 0.1644199937582016,
|
|
"num_tokens": 27795977.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 6.069112348556518,
|
|
"epoch": 1.3179971741434122,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048312447509093017,
|
|
"loss": 5.8497,
|
|
"mean_token_accuracy": 0.1610893115401268,
|
|
"num_tokens": 27804838.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 6.1101641178131105,
|
|
"epoch": 1.3184387142352525,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004831125071372124,
|
|
"loss": 5.8168,
|
|
"mean_token_accuracy": 0.17083584368228913,
|
|
"num_tokens": 27813245.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 6.143509101867676,
|
|
"epoch": 1.3188802543270928,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004831005351066889,
|
|
"loss": 5.9462,
|
|
"mean_token_accuracy": 0.1577487975358963,
|
|
"num_tokens": 27822509.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 6.057284212112426,
|
|
"epoch": 1.3193217944189333,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004830885589995944,
|
|
"loss": 5.739,
|
|
"mean_token_accuracy": 0.17275231033563615,
|
|
"num_tokens": 27831140.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 6.113650321960449,
|
|
"epoch": 1.3197633345107735,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.00048307657881616333,
|
|
"loss": 5.8685,
|
|
"mean_token_accuracy": 0.16350204795598983,
|
|
"num_tokens": 27839537.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 6.093905973434448,
|
|
"epoch": 1.3202048746026138,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048306459455663045,
|
|
"loss": 5.8371,
|
|
"mean_token_accuracy": 0.16539138406515122,
|
|
"num_tokens": 27848888.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 6.192476367950439,
|
|
"epoch": 1.3206464146944543,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004830526062212305,
|
|
"loss": 5.9064,
|
|
"mean_token_accuracy": 0.16160476952791214,
|
|
"num_tokens": 27858910.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 6.081178760528564,
|
|
"epoch": 1.3210879547862946,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048304061381019826,
|
|
"loss": 5.7951,
|
|
"mean_token_accuracy": 0.16869389712810517,
|
|
"num_tokens": 27867967.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 6.000652122497558,
|
|
"epoch": 1.3215294948781349,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00048302861732376875,
|
|
"loss": 5.8202,
|
|
"mean_token_accuracy": 0.1637197270989418,
|
|
"num_tokens": 27877317.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 6.110893774032593,
|
|
"epoch": 1.3219710349699754,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048301661676217693,
|
|
"loss": 5.8824,
|
|
"mean_token_accuracy": 0.16272113025188445,
|
|
"num_tokens": 27886400.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 6.110931062698365,
|
|
"epoch": 1.3224125750618156,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004830046121256579,
|
|
"loss": 5.8643,
|
|
"mean_token_accuracy": 0.16234778612852097,
|
|
"num_tokens": 27895816.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 6.176324319839478,
|
|
"epoch": 1.322854115153656,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004829926034144468,
|
|
"loss": 5.9098,
|
|
"mean_token_accuracy": 0.16054308861494065,
|
|
"num_tokens": 27905614.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 6.206574010848999,
|
|
"epoch": 1.3232956552454964,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004829805906287789,
|
|
"loss": 5.9158,
|
|
"mean_token_accuracy": 0.1620567411184311,
|
|
"num_tokens": 27914714.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 6.07873158454895,
|
|
"epoch": 1.3237371953373367,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004829685737688895,
|
|
"loss": 5.8619,
|
|
"mean_token_accuracy": 0.1676024705171585,
|
|
"num_tokens": 27924821.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 6.125785398483276,
|
|
"epoch": 1.324178735429177,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00048295655283501403,
|
|
"loss": 5.9145,
|
|
"mean_token_accuracy": 0.1634213760495186,
|
|
"num_tokens": 27934028.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 6.137412214279175,
|
|
"epoch": 1.3246202755210172,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.000482944527827388,
|
|
"loss": 5.8734,
|
|
"mean_token_accuracy": 0.1577913299202919,
|
|
"num_tokens": 27943550.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.3246202755210172,
|
|
"eval_entropy": 5.9305301974070845,
|
|
"eval_loss": 5.950167179107666,
|
|
"eval_mean_token_accuracy": 0.16813784923514147,
|
|
"eval_num_tokens": 27943550.0,
|
|
"eval_runtime": 26.3542,
|
|
"eval_samples_per_second": 1340.013,
|
|
"eval_steps_per_second": 167.525,
|
|
"step": 15000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 113230,
|
|
"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": 4.1384083216896e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|