3823058c68
Model: fpadovani/eus-latn-100mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.26492405510420347,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 7.639010858535767,
|
|
"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
|
|
}
|
|
],
|
|
"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": 8221684432896000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|