6035 lines
164 KiB
JSON
6035 lines
164 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.1979283499373227,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 3000,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 10.74233112335205,
|
||
|
|
"epoch": 0.00032988058322887113,
|
||
|
|
"grad_norm": 4.78125,
|
||
|
|
"learning_rate": 2e-06,
|
||
|
|
"loss": 10.8047,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 11578.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742351722717284,
|
||
|
|
"epoch": 0.0006597611664577423,
|
||
|
|
"grad_norm": 4.53125,
|
||
|
|
"learning_rate": 4.5e-06,
|
||
|
|
"loss": 10.7851,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 22232.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742332267761231,
|
||
|
|
"epoch": 0.0009896417496866134,
|
||
|
|
"grad_norm": 4.65625,
|
||
|
|
"learning_rate": 7e-06,
|
||
|
|
"loss": 10.8042,
|
||
|
|
"mean_token_accuracy": 7.412898703478277e-05,
|
||
|
|
"num_tokens": 35495.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.74229564666748,
|
||
|
|
"epoch": 0.0013195223329154845,
|
||
|
|
"grad_norm": 5.03125,
|
||
|
|
"learning_rate": 9.5e-06,
|
||
|
|
"loss": 10.7299,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 47005.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742135810852051,
|
||
|
|
"epoch": 0.0016494029161443558,
|
||
|
|
"grad_norm": 4.21875,
|
||
|
|
"learning_rate": 1.2e-05,
|
||
|
|
"loss": 10.6387,
|
||
|
|
"mean_token_accuracy": 0.00025946117821149526,
|
||
|
|
"num_tokens": 57675.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.741827201843261,
|
||
|
|
"epoch": 0.001979283499373227,
|
||
|
|
"grad_norm": 3.9375,
|
||
|
|
"learning_rate": 1.4500000000000002e-05,
|
||
|
|
"loss": 10.5537,
|
||
|
|
"mean_token_accuracy": 0.008250601799227297,
|
||
|
|
"num_tokens": 70455.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.7412504196167,
|
||
|
|
"epoch": 0.002309164082602098,
|
||
|
|
"grad_norm": 3.046875,
|
||
|
|
"learning_rate": 1.7000000000000003e-05,
|
||
|
|
"loss": 10.4147,
|
||
|
|
"mean_token_accuracy": 0.03285279367119074,
|
||
|
|
"num_tokens": 82422.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.7402099609375,
|
||
|
|
"epoch": 0.002639044665830969,
|
||
|
|
"grad_norm": 2.46875,
|
||
|
|
"learning_rate": 1.95e-05,
|
||
|
|
"loss": 10.2672,
|
||
|
|
"mean_token_accuracy": 0.036276179179549214,
|
||
|
|
"num_tokens": 92109.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.738385868072509,
|
||
|
|
"epoch": 0.0029689252490598403,
|
||
|
|
"grad_norm": 2.265625,
|
||
|
|
"learning_rate": 2.2e-05,
|
||
|
|
"loss": 10.18,
|
||
|
|
"mean_token_accuracy": 0.04042476825416088,
|
||
|
|
"num_tokens": 103440.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.736727714538574,
|
||
|
|
"epoch": 0.0032988058322887116,
|
||
|
|
"grad_norm": 2.0625,
|
||
|
|
"learning_rate": 2.4500000000000003e-05,
|
||
|
|
"loss": 10.1099,
|
||
|
|
"mean_token_accuracy": 0.04008350595831871,
|
||
|
|
"num_tokens": 114742.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.73554048538208,
|
||
|
|
"epoch": 0.0036286864155175825,
|
||
|
|
"grad_norm": 1.984375,
|
||
|
|
"learning_rate": 2.7e-05,
|
||
|
|
"loss": 10.0092,
|
||
|
|
"mean_token_accuracy": 0.043487312830984594,
|
||
|
|
"num_tokens": 125626.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.733216762542725,
|
||
|
|
"epoch": 0.003958566998746454,
|
||
|
|
"grad_norm": 1.9765625,
|
||
|
|
"learning_rate": 2.95e-05,
|
||
|
|
"loss": 9.976,
|
||
|
|
"mean_token_accuracy": 0.043048874288797376,
|
||
|
|
"num_tokens": 137957.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.730610179901124,
|
||
|
|
"epoch": 0.004288447581975325,
|
||
|
|
"grad_norm": 2.3125,
|
||
|
|
"learning_rate": 3.2e-05,
|
||
|
|
"loss": 9.9097,
|
||
|
|
"mean_token_accuracy": 0.036802740022540095,
|
||
|
|
"num_tokens": 148277.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.729512119293213,
|
||
|
|
"epoch": 0.004618328165204196,
|
||
|
|
"grad_norm": 1.7421875,
|
||
|
|
"learning_rate": 3.4500000000000005e-05,
|
||
|
|
"loss": 9.8853,
|
||
|
|
"mean_token_accuracy": 0.04078914504498243,
|
||
|
|
"num_tokens": 159878.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.727227592468262,
|
||
|
|
"epoch": 0.004948208748433067,
|
||
|
|
"grad_norm": 1.84375,
|
||
|
|
"learning_rate": 3.7e-05,
|
||
|
|
"loss": 9.7999,
|
||
|
|
"mean_token_accuracy": 0.04081474579870701,
|
||
|
|
"num_tokens": 172156.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.724674892425536,
|
||
|
|
"epoch": 0.005278089331661938,
|
||
|
|
"grad_norm": 1.734375,
|
||
|
|
"learning_rate": 3.95e-05,
|
||
|
|
"loss": 9.7314,
|
||
|
|
"mean_token_accuracy": 0.0359017526730895,
|
||
|
|
"num_tokens": 183913.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.720765209197998,
|
||
|
|
"epoch": 0.00560796991489081,
|
||
|
|
"grad_norm": 1.6796875,
|
||
|
|
"learning_rate": 4.2000000000000004e-05,
|
||
|
|
"loss": 9.6786,
|
||
|
|
"mean_token_accuracy": 0.041428479738533495,
|
||
|
|
"num_tokens": 195817.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.713240337371825,
|
||
|
|
"epoch": 0.005937850498119681,
|
||
|
|
"grad_norm": 1.75,
|
||
|
|
"learning_rate": 4.45e-05,
|
||
|
|
"loss": 9.6194,
|
||
|
|
"mean_token_accuracy": 0.0394784739241004,
|
||
|
|
"num_tokens": 207962.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.704511070251465,
|
||
|
|
"epoch": 0.0062677310813485515,
|
||
|
|
"grad_norm": 1.78125,
|
||
|
|
"learning_rate": 4.7000000000000004e-05,
|
||
|
|
"loss": 9.5465,
|
||
|
|
"mean_token_accuracy": 0.03562910072505474,
|
||
|
|
"num_tokens": 219781.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.693966960906982,
|
||
|
|
"epoch": 0.006597611664577423,
|
||
|
|
"grad_norm": 1.6953125,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"loss": 9.4197,
|
||
|
|
"mean_token_accuracy": 0.037568676844239236,
|
||
|
|
"num_tokens": 231163.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.679013442993163,
|
||
|
|
"epoch": 0.006927492247806294,
|
||
|
|
"grad_norm": 1.671875,
|
||
|
|
"learning_rate": 5.2e-05,
|
||
|
|
"loss": 9.326,
|
||
|
|
"mean_token_accuracy": 0.03616092000156641,
|
||
|
|
"num_tokens": 242141.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.657819652557373,
|
||
|
|
"epoch": 0.007257372831035165,
|
||
|
|
"grad_norm": 1.7109375,
|
||
|
|
"learning_rate": 5.45e-05,
|
||
|
|
"loss": 9.2134,
|
||
|
|
"mean_token_accuracy": 0.03960070498287678,
|
||
|
|
"num_tokens": 253879.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.626339530944824,
|
||
|
|
"epoch": 0.007587253414264037,
|
||
|
|
"grad_norm": 1.7578125,
|
||
|
|
"learning_rate": 5.7e-05,
|
||
|
|
"loss": 9.0565,
|
||
|
|
"mean_token_accuracy": 0.044448528438806534,
|
||
|
|
"num_tokens": 264486.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.585787487030029,
|
||
|
|
"epoch": 0.007917133997492908,
|
||
|
|
"grad_norm": 1.640625,
|
||
|
|
"learning_rate": 5.9499999999999996e-05,
|
||
|
|
"loss": 8.9692,
|
||
|
|
"mean_token_accuracy": 0.037905681505799295,
|
||
|
|
"num_tokens": 275750.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.545704460144043,
|
||
|
|
"epoch": 0.008247014580721778,
|
||
|
|
"grad_norm": 1.6015625,
|
||
|
|
"learning_rate": 6.2e-05,
|
||
|
|
"loss": 8.894,
|
||
|
|
"mean_token_accuracy": 0.042156589217484,
|
||
|
|
"num_tokens": 287746.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.492252826690674,
|
||
|
|
"epoch": 0.00857689516395065,
|
||
|
|
"grad_norm": 1.6015625,
|
||
|
|
"learning_rate": 6.450000000000001e-05,
|
||
|
|
"loss": 8.7427,
|
||
|
|
"mean_token_accuracy": 0.044464115798473355,
|
||
|
|
"num_tokens": 300383.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.41234998703003,
|
||
|
|
"epoch": 0.008906775747179522,
|
||
|
|
"grad_norm": 1.4765625,
|
||
|
|
"learning_rate": 6.7e-05,
|
||
|
|
"loss": 8.6308,
|
||
|
|
"mean_token_accuracy": 0.05071255713701248,
|
||
|
|
"num_tokens": 313091.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.307254981994628,
|
||
|
|
"epoch": 0.009236656330408393,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 6.950000000000001e-05,
|
||
|
|
"loss": 8.4857,
|
||
|
|
"mean_token_accuracy": 0.04862055517733097,
|
||
|
|
"num_tokens": 323251.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.19880542755127,
|
||
|
|
"epoch": 0.009566536913637264,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 7.2e-05,
|
||
|
|
"loss": 8.3857,
|
||
|
|
"mean_token_accuracy": 0.04940937012434006,
|
||
|
|
"num_tokens": 333707.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.061772537231445,
|
||
|
|
"epoch": 0.009896417496866134,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 7.45e-05,
|
||
|
|
"loss": 8.3134,
|
||
|
|
"mean_token_accuracy": 0.04397304020822048,
|
||
|
|
"num_tokens": 345426.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.90941858291626,
|
||
|
|
"epoch": 0.010226298080095005,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 7.7e-05,
|
||
|
|
"loss": 8.2127,
|
||
|
|
"mean_token_accuracy": 0.04301855657249689,
|
||
|
|
"num_tokens": 358876.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.72692346572876,
|
||
|
|
"epoch": 0.010556178663323876,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 7.950000000000001e-05,
|
||
|
|
"loss": 8.0847,
|
||
|
|
"mean_token_accuracy": 0.04769652187824249,
|
||
|
|
"num_tokens": 370955.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.496499633789062,
|
||
|
|
"epoch": 0.010886059246552749,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 8.2e-05,
|
||
|
|
"loss": 7.9552,
|
||
|
|
"mean_token_accuracy": 0.04982128106057644,
|
||
|
|
"num_tokens": 383667.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.298235988616943,
|
||
|
|
"epoch": 0.01121593982978162,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 8.450000000000001e-05,
|
||
|
|
"loss": 7.8896,
|
||
|
|
"mean_token_accuracy": 0.047108123824000356,
|
||
|
|
"num_tokens": 394347.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.061514949798584,
|
||
|
|
"epoch": 0.01154582041301049,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 8.7e-05,
|
||
|
|
"loss": 7.7922,
|
||
|
|
"mean_token_accuracy": 0.05443224273622036,
|
||
|
|
"num_tokens": 406589.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.849029541015625,
|
||
|
|
"epoch": 0.011875700996239361,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 8.95e-05,
|
||
|
|
"loss": 7.7205,
|
||
|
|
"mean_token_accuracy": 0.06005025506019592,
|
||
|
|
"num_tokens": 417462.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.702647686004639,
|
||
|
|
"epoch": 0.012205581579468232,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 9.2e-05,
|
||
|
|
"loss": 7.7819,
|
||
|
|
"mean_token_accuracy": 0.05638592652976513,
|
||
|
|
"num_tokens": 428076.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.6129864692688,
|
||
|
|
"epoch": 0.012535462162697103,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 9.45e-05,
|
||
|
|
"loss": 7.6524,
|
||
|
|
"mean_token_accuracy": 0.059817750751972196,
|
||
|
|
"num_tokens": 438714.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.444343852996827,
|
||
|
|
"epoch": 0.012865342745925976,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 9.7e-05,
|
||
|
|
"loss": 7.6408,
|
||
|
|
"mean_token_accuracy": 0.06158410720527172,
|
||
|
|
"num_tokens": 450373.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.418584156036378,
|
||
|
|
"epoch": 0.013195223329154846,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 9.95e-05,
|
||
|
|
"loss": 7.5929,
|
||
|
|
"mean_token_accuracy": 0.057680726051330566,
|
||
|
|
"num_tokens": 461201.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.309362125396728,
|
||
|
|
"epoch": 0.013525103912383717,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000102,
|
||
|
|
"loss": 7.5542,
|
||
|
|
"mean_token_accuracy": 0.06454258635640145,
|
||
|
|
"num_tokens": 471519.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.26671142578125,
|
||
|
|
"epoch": 0.013854984495612588,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00010449999999999999,
|
||
|
|
"loss": 7.5927,
|
||
|
|
"mean_token_accuracy": 0.05961795505136251,
|
||
|
|
"num_tokens": 483245.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.234414291381835,
|
||
|
|
"epoch": 0.014184865078841459,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.000107,
|
||
|
|
"loss": 7.4793,
|
||
|
|
"mean_token_accuracy": 0.06982782371342182,
|
||
|
|
"num_tokens": 494398.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.201716423034668,
|
||
|
|
"epoch": 0.01451474566207033,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0001095,
|
||
|
|
"loss": 7.4962,
|
||
|
|
"mean_token_accuracy": 0.06742062233388424,
|
||
|
|
"num_tokens": 505550.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.13823642730713,
|
||
|
|
"epoch": 0.014844626245299202,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.000112,
|
||
|
|
"loss": 7.4418,
|
||
|
|
"mean_token_accuracy": 0.06280249543488026,
|
||
|
|
"num_tokens": 515824.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.11952476501465,
|
||
|
|
"epoch": 0.015174506828528073,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0001145,
|
||
|
|
"loss": 7.4716,
|
||
|
|
"mean_token_accuracy": 0.06296740882098675,
|
||
|
|
"num_tokens": 527272.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.108990573883057,
|
||
|
|
"epoch": 0.015504387411756944,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00011700000000000001,
|
||
|
|
"loss": 7.4469,
|
||
|
|
"mean_token_accuracy": 0.06231762431561947,
|
||
|
|
"num_tokens": 537970.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.067597770690918,
|
||
|
|
"epoch": 0.015834267994985815,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00011949999999999999,
|
||
|
|
"loss": 7.3392,
|
||
|
|
"mean_token_accuracy": 0.06825867146253586,
|
||
|
|
"num_tokens": 549026.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.033491706848144,
|
||
|
|
"epoch": 0.016164148578214688,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.000122,
|
||
|
|
"loss": 7.4567,
|
||
|
|
"mean_token_accuracy": 0.06924333348870278,
|
||
|
|
"num_tokens": 561001.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.013448429107665,
|
||
|
|
"epoch": 0.016494029161443557,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.0001245,
|
||
|
|
"loss": 7.3986,
|
||
|
|
"mean_token_accuracy": 0.07052349597215653,
|
||
|
|
"num_tokens": 571910.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.004467582702636,
|
||
|
|
"epoch": 0.01682390974467243,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000127,
|
||
|
|
"loss": 7.3889,
|
||
|
|
"mean_token_accuracy": 0.0650747399777174,
|
||
|
|
"num_tokens": 583073.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.977169990539551,
|
||
|
|
"epoch": 0.0171537903279013,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0001295,
|
||
|
|
"loss": 7.3194,
|
||
|
|
"mean_token_accuracy": 0.07421667948365211,
|
||
|
|
"num_tokens": 593909.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.92542724609375,
|
||
|
|
"epoch": 0.01748367091113017,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.000132,
|
||
|
|
"loss": 7.347,
|
||
|
|
"mean_token_accuracy": 0.07075322493910789,
|
||
|
|
"num_tokens": 605235.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.959033679962158,
|
||
|
|
"epoch": 0.017813551494359044,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.00013450000000000002,
|
||
|
|
"loss": 7.2928,
|
||
|
|
"mean_token_accuracy": 0.07352816425263882,
|
||
|
|
"num_tokens": 616491.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.854368066787719,
|
||
|
|
"epoch": 0.018143432077587913,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.00013700000000000002,
|
||
|
|
"loss": 7.301,
|
||
|
|
"mean_token_accuracy": 0.07566386498510838,
|
||
|
|
"num_tokens": 627576.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.89704909324646,
|
||
|
|
"epoch": 0.018473312660816785,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0001395,
|
||
|
|
"loss": 7.2279,
|
||
|
|
"mean_token_accuracy": 0.07298410087823867,
|
||
|
|
"num_tokens": 638833.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.945636034011841,
|
||
|
|
"epoch": 0.018803193244045655,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00014199999999999998,
|
||
|
|
"loss": 7.3253,
|
||
|
|
"mean_token_accuracy": 0.06714979782700539,
|
||
|
|
"num_tokens": 648954.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.888553476333618,
|
||
|
|
"epoch": 0.019133073827274527,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0001445,
|
||
|
|
"loss": 7.2291,
|
||
|
|
"mean_token_accuracy": 0.07276964522898197,
|
||
|
|
"num_tokens": 659653.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.827844858169556,
|
||
|
|
"epoch": 0.019462954410503396,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.000147,
|
||
|
|
"loss": 7.3204,
|
||
|
|
"mean_token_accuracy": 0.0698035504668951,
|
||
|
|
"num_tokens": 671282.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.846695137023926,
|
||
|
|
"epoch": 0.01979283499373227,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.0001495,
|
||
|
|
"loss": 7.2734,
|
||
|
|
"mean_token_accuracy": 0.06930247582495212,
|
||
|
|
"num_tokens": 683096.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.817320489883423,
|
||
|
|
"epoch": 0.02012271557696114,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.000152,
|
||
|
|
"loss": 7.2386,
|
||
|
|
"mean_token_accuracy": 0.07485006004571915,
|
||
|
|
"num_tokens": 694278.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.90717658996582,
|
||
|
|
"epoch": 0.02045259616019001,
|
||
|
|
"grad_norm": 0.76953125,
|
||
|
|
"learning_rate": 0.00015450000000000001,
|
||
|
|
"loss": 7.2358,
|
||
|
|
"mean_token_accuracy": 0.0718875303864479,
|
||
|
|
"num_tokens": 705878.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.742885494232178,
|
||
|
|
"epoch": 0.020782476743418883,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.000157,
|
||
|
|
"loss": 7.1725,
|
||
|
|
"mean_token_accuracy": 0.0757001593708992,
|
||
|
|
"num_tokens": 717459.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.795225667953491,
|
||
|
|
"epoch": 0.021112357326647752,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0001595,
|
||
|
|
"loss": 7.1761,
|
||
|
|
"mean_token_accuracy": 0.07542249858379364,
|
||
|
|
"num_tokens": 726708.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.819357681274414,
|
||
|
|
"epoch": 0.021442237909876625,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000162,
|
||
|
|
"loss": 7.1691,
|
||
|
|
"mean_token_accuracy": 0.07912719771265983,
|
||
|
|
"num_tokens": 736799.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.716309642791748,
|
||
|
|
"epoch": 0.021772118493105497,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00016450000000000001,
|
||
|
|
"loss": 7.1528,
|
||
|
|
"mean_token_accuracy": 0.07632440999150276,
|
||
|
|
"num_tokens": 747820.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.650016450881958,
|
||
|
|
"epoch": 0.022101999076334367,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.00016700000000000002,
|
||
|
|
"loss": 7.1569,
|
||
|
|
"mean_token_accuracy": 0.07818866521120071,
|
||
|
|
"num_tokens": 757938.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.751991653442383,
|
||
|
|
"epoch": 0.02243187965956324,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.00016950000000000003,
|
||
|
|
"loss": 7.1513,
|
||
|
|
"mean_token_accuracy": 0.07743561789393424,
|
||
|
|
"num_tokens": 768900.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.693883180618286,
|
||
|
|
"epoch": 0.02276176024279211,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00017199999999999998,
|
||
|
|
"loss": 7.218,
|
||
|
|
"mean_token_accuracy": 0.07597828209400177,
|
||
|
|
"num_tokens": 780839.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.725241041183471,
|
||
|
|
"epoch": 0.02309164082602098,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.00017449999999999999,
|
||
|
|
"loss": 7.1578,
|
||
|
|
"mean_token_accuracy": 0.07896500080823898,
|
||
|
|
"num_tokens": 793144.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.7039953708648685,
|
||
|
|
"epoch": 0.02342152140924985,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.000177,
|
||
|
|
"loss": 7.1385,
|
||
|
|
"mean_token_accuracy": 0.0761062603443861,
|
||
|
|
"num_tokens": 805293.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.650927495956421,
|
||
|
|
"epoch": 0.023751401992478723,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0001795,
|
||
|
|
"loss": 7.0847,
|
||
|
|
"mean_token_accuracy": 0.07881326377391815,
|
||
|
|
"num_tokens": 817313.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.617914915084839,
|
||
|
|
"epoch": 0.024081282575707595,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.000182,
|
||
|
|
"loss": 7.039,
|
||
|
|
"mean_token_accuracy": 0.07709232643246651,
|
||
|
|
"num_tokens": 827823.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.612017059326172,
|
||
|
|
"epoch": 0.024411163158936464,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0001845,
|
||
|
|
"loss": 7.0581,
|
||
|
|
"mean_token_accuracy": 0.07990295961499214,
|
||
|
|
"num_tokens": 839221.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.634074735641479,
|
||
|
|
"epoch": 0.024741043742165337,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.000187,
|
||
|
|
"loss": 7.0299,
|
||
|
|
"mean_token_accuracy": 0.0763829343020916,
|
||
|
|
"num_tokens": 850616.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.552822065353394,
|
||
|
|
"epoch": 0.025070924325394206,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0001895,
|
||
|
|
"loss": 7.0531,
|
||
|
|
"mean_token_accuracy": 0.07905212491750717,
|
||
|
|
"num_tokens": 862467.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6426232814788815,
|
||
|
|
"epoch": 0.02540080490862308,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000192,
|
||
|
|
"loss": 7.0412,
|
||
|
|
"mean_token_accuracy": 0.07432318702340127,
|
||
|
|
"num_tokens": 872130.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.561140012741089,
|
||
|
|
"epoch": 0.02573068549185195,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0001945,
|
||
|
|
"loss": 7.0034,
|
||
|
|
"mean_token_accuracy": 0.08546995297074318,
|
||
|
|
"num_tokens": 883598.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.582135248184204,
|
||
|
|
"epoch": 0.02606056607508082,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.00019700000000000002,
|
||
|
|
"loss": 7.0003,
|
||
|
|
"mean_token_accuracy": 0.07829435840249062,
|
||
|
|
"num_tokens": 896478.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.555583810806274,
|
||
|
|
"epoch": 0.026390446658309693,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.00019950000000000002,
|
||
|
|
"loss": 7.0712,
|
||
|
|
"mean_token_accuracy": 0.07842531427741051,
|
||
|
|
"num_tokens": 909351.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.550145435333252,
|
||
|
|
"epoch": 0.026720327241538562,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.000202,
|
||
|
|
"loss": 7.0363,
|
||
|
|
"mean_token_accuracy": 0.08111794963479042,
|
||
|
|
"num_tokens": 920170.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.451640224456787,
|
||
|
|
"epoch": 0.027050207824767435,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00020449999999999998,
|
||
|
|
"loss": 6.978,
|
||
|
|
"mean_token_accuracy": 0.0850048691034317,
|
||
|
|
"num_tokens": 929498.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.552112293243408,
|
||
|
|
"epoch": 0.027380088407996304,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000207,
|
||
|
|
"loss": 6.9678,
|
||
|
|
"mean_token_accuracy": 0.07753312811255456,
|
||
|
|
"num_tokens": 939975.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.444381189346314,
|
||
|
|
"epoch": 0.027709968991225176,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0002095,
|
||
|
|
"loss": 6.9504,
|
||
|
|
"mean_token_accuracy": 0.0817045159637928,
|
||
|
|
"num_tokens": 950593.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.561855220794678,
|
||
|
|
"epoch": 0.02803984957445405,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.000212,
|
||
|
|
"loss": 6.9561,
|
||
|
|
"mean_token_accuracy": 0.08070995509624482,
|
||
|
|
"num_tokens": 962281.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.47752628326416,
|
||
|
|
"epoch": 0.028369730157682918,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0002145,
|
||
|
|
"loss": 6.8784,
|
||
|
|
"mean_token_accuracy": 0.08914879560470582,
|
||
|
|
"num_tokens": 972717.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.474664211273193,
|
||
|
|
"epoch": 0.02869961074091179,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00021700000000000002,
|
||
|
|
"loss": 6.8833,
|
||
|
|
"mean_token_accuracy": 0.08555072918534279,
|
||
|
|
"num_tokens": 983669.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.426136112213134,
|
||
|
|
"epoch": 0.02902949132414066,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0002195,
|
||
|
|
"loss": 6.8871,
|
||
|
|
"mean_token_accuracy": 0.08220960162580013,
|
||
|
|
"num_tokens": 994528.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.392468643188477,
|
||
|
|
"epoch": 0.029359371907369532,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000222,
|
||
|
|
"loss": 6.8482,
|
||
|
|
"mean_token_accuracy": 0.0958639606833458,
|
||
|
|
"num_tokens": 1005445.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.446725940704345,
|
||
|
|
"epoch": 0.029689252490598405,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0002245,
|
||
|
|
"loss": 7.0157,
|
||
|
|
"mean_token_accuracy": 0.0827529065310955,
|
||
|
|
"num_tokens": 1018747.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.441160249710083,
|
||
|
|
"epoch": 0.030019133073827274,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00022700000000000002,
|
||
|
|
"loss": 6.8981,
|
||
|
|
"mean_token_accuracy": 0.08528381213545799,
|
||
|
|
"num_tokens": 1028956.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.43569803237915,
|
||
|
|
"epoch": 0.030349013657056147,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.00022950000000000002,
|
||
|
|
"loss": 7.0367,
|
||
|
|
"mean_token_accuracy": 0.07986071296036243,
|
||
|
|
"num_tokens": 1041227.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.422861957550049,
|
||
|
|
"epoch": 0.030678894240285016,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.00023200000000000003,
|
||
|
|
"loss": 6.9143,
|
||
|
|
"mean_token_accuracy": 0.07918849810957909,
|
||
|
|
"num_tokens": 1053002.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4423298835754395,
|
||
|
|
"epoch": 0.03100877482351389,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.00023449999999999998,
|
||
|
|
"loss": 6.9095,
|
||
|
|
"mean_token_accuracy": 0.08558695167303085,
|
||
|
|
"num_tokens": 1063693.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.416697883605957,
|
||
|
|
"epoch": 0.03133865540674276,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.000237,
|
||
|
|
"loss": 6.88,
|
||
|
|
"mean_token_accuracy": 0.09078652560710906,
|
||
|
|
"num_tokens": 1074245.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.32618203163147,
|
||
|
|
"epoch": 0.03166853598997163,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0002395,
|
||
|
|
"loss": 6.8789,
|
||
|
|
"mean_token_accuracy": 0.08656272403895855,
|
||
|
|
"num_tokens": 1084663.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.368553400039673,
|
||
|
|
"epoch": 0.0319984165732005,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.000242,
|
||
|
|
"loss": 6.8227,
|
||
|
|
"mean_token_accuracy": 0.0852760024368763,
|
||
|
|
"num_tokens": 1094777.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.348766326904297,
|
||
|
|
"epoch": 0.032328297156429375,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0002445,
|
||
|
|
"loss": 6.8406,
|
||
|
|
"mean_token_accuracy": 0.08816310912370681,
|
||
|
|
"num_tokens": 1106712.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.286499500274658,
|
||
|
|
"epoch": 0.03265817773965824,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.000247,
|
||
|
|
"loss": 6.8402,
|
||
|
|
"mean_token_accuracy": 0.09093867242336273,
|
||
|
|
"num_tokens": 1118488.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.348550319671631,
|
||
|
|
"epoch": 0.032988058322887114,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0002495,
|
||
|
|
"loss": 6.8115,
|
||
|
|
"mean_token_accuracy": 0.08822314143180847,
|
||
|
|
"num_tokens": 1128803.0,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.325877618789673,
|
||
|
|
"epoch": 0.033317938906115986,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000252,
|
||
|
|
"loss": 6.7801,
|
||
|
|
"mean_token_accuracy": 0.09269751161336899,
|
||
|
|
"num_tokens": 1140081.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.249666023254394,
|
||
|
|
"epoch": 0.03364781948934486,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0002545,
|
||
|
|
"loss": 6.8423,
|
||
|
|
"mean_token_accuracy": 0.08509944006800652,
|
||
|
|
"num_tokens": 1151740.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.387292528152466,
|
||
|
|
"epoch": 0.03397770007257373,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.000257,
|
||
|
|
"loss": 6.9424,
|
||
|
|
"mean_token_accuracy": 0.08753601871430874,
|
||
|
|
"num_tokens": 1163554.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.363021564483643,
|
||
|
|
"epoch": 0.0343075806558026,
|
||
|
|
"grad_norm": 1.8828125,
|
||
|
|
"learning_rate": 0.0002595,
|
||
|
|
"loss": 6.8149,
|
||
|
|
"mean_token_accuracy": 0.09259535372257233,
|
||
|
|
"num_tokens": 1174634.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.142534828186035,
|
||
|
|
"epoch": 0.03463746123903147,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.000262,
|
||
|
|
"loss": 6.7739,
|
||
|
|
"mean_token_accuracy": 0.08925415575504303,
|
||
|
|
"num_tokens": 1186640.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.303580617904663,
|
||
|
|
"epoch": 0.03496734182226034,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.00026450000000000003,
|
||
|
|
"loss": 6.7195,
|
||
|
|
"mean_token_accuracy": 0.08907380253076554,
|
||
|
|
"num_tokens": 1197168.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.284749698638916,
|
||
|
|
"epoch": 0.035297222405489215,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00026700000000000004,
|
||
|
|
"loss": 6.7724,
|
||
|
|
"mean_token_accuracy": 0.09144287258386612,
|
||
|
|
"num_tokens": 1208560.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.210066461563111,
|
||
|
|
"epoch": 0.03562710298871809,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00026950000000000005,
|
||
|
|
"loss": 6.753,
|
||
|
|
"mean_token_accuracy": 0.0977034792304039,
|
||
|
|
"num_tokens": 1220492.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2108320713043215,
|
||
|
|
"epoch": 0.03595698357194695,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00027200000000000005,
|
||
|
|
"loss": 6.7249,
|
||
|
|
"mean_token_accuracy": 0.09175074473023415,
|
||
|
|
"num_tokens": 1232753.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.252335834503174,
|
||
|
|
"epoch": 0.036286864155175826,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0002745,
|
||
|
|
"loss": 6.845,
|
||
|
|
"mean_token_accuracy": 0.08571628406643868,
|
||
|
|
"num_tokens": 1244972.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.234958124160767,
|
||
|
|
"epoch": 0.0366167447384047,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.000277,
|
||
|
|
"loss": 6.7357,
|
||
|
|
"mean_token_accuracy": 0.09484243839979171,
|
||
|
|
"num_tokens": 1256101.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.181823444366455,
|
||
|
|
"epoch": 0.03694662532163357,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0002795,
|
||
|
|
"loss": 6.7857,
|
||
|
|
"mean_token_accuracy": 0.0866756096482277,
|
||
|
|
"num_tokens": 1268932.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.200888061523438,
|
||
|
|
"epoch": 0.037276505904862436,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00028199999999999997,
|
||
|
|
"loss": 6.695,
|
||
|
|
"mean_token_accuracy": 0.08639899343252182,
|
||
|
|
"num_tokens": 1278799.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.22176570892334,
|
||
|
|
"epoch": 0.03760638648809131,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0002845,
|
||
|
|
"loss": 6.7409,
|
||
|
|
"mean_token_accuracy": 0.09684469699859619,
|
||
|
|
"num_tokens": 1288703.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.088978052139282,
|
||
|
|
"epoch": 0.03793626707132018,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000287,
|
||
|
|
"loss": 6.6848,
|
||
|
|
"mean_token_accuracy": 0.09133393913507462,
|
||
|
|
"num_tokens": 1300718.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.159674024581909,
|
||
|
|
"epoch": 0.038266147654549054,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0002895,
|
||
|
|
"loss": 6.6556,
|
||
|
|
"mean_token_accuracy": 0.09586420208215714,
|
||
|
|
"num_tokens": 1311735.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.153814125061035,
|
||
|
|
"epoch": 0.03859602823777793,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000292,
|
||
|
|
"loss": 6.6843,
|
||
|
|
"mean_token_accuracy": 0.09448647424578667,
|
||
|
|
"num_tokens": 1322027.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.167168998718262,
|
||
|
|
"epoch": 0.03892590882100679,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0002945,
|
||
|
|
"loss": 6.6957,
|
||
|
|
"mean_token_accuracy": 0.09144030138850212,
|
||
|
|
"num_tokens": 1331326.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.153041696548462,
|
||
|
|
"epoch": 0.039255789404235665,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000297,
|
||
|
|
"loss": 6.7088,
|
||
|
|
"mean_token_accuracy": 0.09533656612038613,
|
||
|
|
"num_tokens": 1342064.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.149514245986938,
|
||
|
|
"epoch": 0.03958566998746454,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0002995,
|
||
|
|
"loss": 6.7807,
|
||
|
|
"mean_token_accuracy": 0.09185100421309471,
|
||
|
|
"num_tokens": 1354257.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.18934383392334,
|
||
|
|
"epoch": 0.03991555057069341,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.000302,
|
||
|
|
"loss": 6.6781,
|
||
|
|
"mean_token_accuracy": 0.09455206841230393,
|
||
|
|
"num_tokens": 1365757.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1387965202331545,
|
||
|
|
"epoch": 0.04024543115392228,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0003045,
|
||
|
|
"loss": 6.7468,
|
||
|
|
"mean_token_accuracy": 0.09017066359519958,
|
||
|
|
"num_tokens": 1376655.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.205080175399781,
|
||
|
|
"epoch": 0.04057531173715115,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000307,
|
||
|
|
"loss": 6.7564,
|
||
|
|
"mean_token_accuracy": 0.09203101694583893,
|
||
|
|
"num_tokens": 1390293.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.02491946220398,
|
||
|
|
"epoch": 0.04090519232038002,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0003095,
|
||
|
|
"loss": 6.6195,
|
||
|
|
"mean_token_accuracy": 0.0970487006008625,
|
||
|
|
"num_tokens": 1402595.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1582615852355955,
|
||
|
|
"epoch": 0.041235072903608894,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000312,
|
||
|
|
"loss": 6.6489,
|
||
|
|
"mean_token_accuracy": 0.09517830908298493,
|
||
|
|
"num_tokens": 1413574.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.061727285385132,
|
||
|
|
"epoch": 0.041564953486837766,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0003145,
|
||
|
|
"loss": 6.6651,
|
||
|
|
"mean_token_accuracy": 0.08918783366680146,
|
||
|
|
"num_tokens": 1425520.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.056548929214477,
|
||
|
|
"epoch": 0.04189483407006664,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.000317,
|
||
|
|
"loss": 6.6162,
|
||
|
|
"mean_token_accuracy": 0.09108572974801063,
|
||
|
|
"num_tokens": 1436285.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.118799352645874,
|
||
|
|
"epoch": 0.042224714653295504,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0003195,
|
||
|
|
"loss": 6.6136,
|
||
|
|
"mean_token_accuracy": 0.10142198577523232,
|
||
|
|
"num_tokens": 1447194.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.015072345733643,
|
||
|
|
"epoch": 0.04255459523652438,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.000322,
|
||
|
|
"loss": 6.6271,
|
||
|
|
"mean_token_accuracy": 0.09909635856747627,
|
||
|
|
"num_tokens": 1459587.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.023969030380249,
|
||
|
|
"epoch": 0.04288447581975325,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.00032450000000000003,
|
||
|
|
"loss": 6.7239,
|
||
|
|
"mean_token_accuracy": 0.08922117725014686,
|
||
|
|
"num_tokens": 1472677.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.125645780563355,
|
||
|
|
"epoch": 0.04321435640298212,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.00032700000000000003,
|
||
|
|
"loss": 6.6676,
|
||
|
|
"mean_token_accuracy": 0.09377843365073205,
|
||
|
|
"num_tokens": 1484307.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.98760347366333,
|
||
|
|
"epoch": 0.043544236986210995,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.00032950000000000004,
|
||
|
|
"loss": 6.5969,
|
||
|
|
"mean_token_accuracy": 0.09738756716251373,
|
||
|
|
"num_tokens": 1496198.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.049053001403808,
|
||
|
|
"epoch": 0.04387411756943986,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00033200000000000005,
|
||
|
|
"loss": 6.5415,
|
||
|
|
"mean_token_accuracy": 0.09548762142658233,
|
||
|
|
"num_tokens": 1507439.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.902269315719605,
|
||
|
|
"epoch": 0.04420399815266873,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.00033450000000000005,
|
||
|
|
"loss": 6.5666,
|
||
|
|
"mean_token_accuracy": 0.09989230334758759,
|
||
|
|
"num_tokens": 1518176.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.977385139465332,
|
||
|
|
"epoch": 0.044533878735897606,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000337,
|
||
|
|
"loss": 6.5591,
|
||
|
|
"mean_token_accuracy": 0.09720836281776428,
|
||
|
|
"num_tokens": 1529095.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.00214319229126,
|
||
|
|
"epoch": 0.04486375931912648,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0003395,
|
||
|
|
"loss": 6.5559,
|
||
|
|
"mean_token_accuracy": 0.09865213707089424,
|
||
|
|
"num_tokens": 1539431.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.024150228500366,
|
||
|
|
"epoch": 0.045193639902355344,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.000342,
|
||
|
|
"loss": 6.6248,
|
||
|
|
"mean_token_accuracy": 0.09451132789254188,
|
||
|
|
"num_tokens": 1550878.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.005107450485229,
|
||
|
|
"epoch": 0.04552352048558422,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.00034449999999999997,
|
||
|
|
"loss": 6.5717,
|
||
|
|
"mean_token_accuracy": 0.10220879390835762,
|
||
|
|
"num_tokens": 1561416.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.985655498504639,
|
||
|
|
"epoch": 0.04585340106881309,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.000347,
|
||
|
|
"loss": 6.5954,
|
||
|
|
"mean_token_accuracy": 0.10094324424862862,
|
||
|
|
"num_tokens": 1574470.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.93547043800354,
|
||
|
|
"epoch": 0.04618328165204196,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0003495,
|
||
|
|
"loss": 6.5503,
|
||
|
|
"mean_token_accuracy": 0.09845736622810364,
|
||
|
|
"num_tokens": 1586021.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.906772899627685,
|
||
|
|
"epoch": 0.046513162235270834,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000352,
|
||
|
|
"loss": 6.563,
|
||
|
|
"mean_token_accuracy": 0.09999166876077652,
|
||
|
|
"num_tokens": 1597500.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.013272094726562,
|
||
|
|
"epoch": 0.0468430428184997,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0003545,
|
||
|
|
"loss": 6.5971,
|
||
|
|
"mean_token_accuracy": 0.0965078391134739,
|
||
|
|
"num_tokens": 1609797.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.930358076095581,
|
||
|
|
"epoch": 0.04717292340172857,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000357,
|
||
|
|
"loss": 6.551,
|
||
|
|
"mean_token_accuracy": 0.1009341761469841,
|
||
|
|
"num_tokens": 1620613.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.000537967681884,
|
||
|
|
"epoch": 0.047502803984957445,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0003595,
|
||
|
|
"loss": 6.553,
|
||
|
|
"mean_token_accuracy": 0.10127959176898002,
|
||
|
|
"num_tokens": 1631542.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.929404783248901,
|
||
|
|
"epoch": 0.04783268456818632,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.000362,
|
||
|
|
"loss": 6.4644,
|
||
|
|
"mean_token_accuracy": 0.10010106787085533,
|
||
|
|
"num_tokens": 1641783.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.827300930023194,
|
||
|
|
"epoch": 0.04816256515141519,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0003645,
|
||
|
|
"loss": 6.6008,
|
||
|
|
"mean_token_accuracy": 0.09775333851575851,
|
||
|
|
"num_tokens": 1652938.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.95234055519104,
|
||
|
|
"epoch": 0.048492445734644056,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000367,
|
||
|
|
"loss": 6.4386,
|
||
|
|
"mean_token_accuracy": 0.10487373694777488,
|
||
|
|
"num_tokens": 1663214.0,
|
||
|
|
"step": 735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.972109842300415,
|
||
|
|
"epoch": 0.04882232631787293,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0003695,
|
||
|
|
"loss": 6.6092,
|
||
|
|
"mean_token_accuracy": 0.09515793696045875,
|
||
|
|
"num_tokens": 1674845.0,
|
||
|
|
"step": 740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.853538131713867,
|
||
|
|
"epoch": 0.0491522069011018,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000372,
|
||
|
|
"loss": 6.4916,
|
||
|
|
"mean_token_accuracy": 0.10413750782608985,
|
||
|
|
"num_tokens": 1685222.0,
|
||
|
|
"step": 745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.949459981918335,
|
||
|
|
"epoch": 0.049482087484330674,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0003745,
|
||
|
|
"loss": 6.5191,
|
||
|
|
"mean_token_accuracy": 0.09741224348545074,
|
||
|
|
"num_tokens": 1696520.0,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.861531782150268,
|
||
|
|
"epoch": 0.049811968067559546,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000377,
|
||
|
|
"loss": 6.5043,
|
||
|
|
"mean_token_accuracy": 0.10009976252913474,
|
||
|
|
"num_tokens": 1706888.0,
|
||
|
|
"step": 755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.85313572883606,
|
||
|
|
"epoch": 0.05014184865078841,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0003795,
|
||
|
|
"loss": 6.5053,
|
||
|
|
"mean_token_accuracy": 0.10150282755494118,
|
||
|
|
"num_tokens": 1718023.0,
|
||
|
|
"step": 760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.816460084915161,
|
||
|
|
"epoch": 0.050471729234017285,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000382,
|
||
|
|
"loss": 6.447,
|
||
|
|
"mean_token_accuracy": 0.10082821324467658,
|
||
|
|
"num_tokens": 1729291.0,
|
||
|
|
"step": 765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.867931795120239,
|
||
|
|
"epoch": 0.05080160981724616,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0003845,
|
||
|
|
"loss": 6.5009,
|
||
|
|
"mean_token_accuracy": 0.10062082186341285,
|
||
|
|
"num_tokens": 1740801.0,
|
||
|
|
"step": 770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.793792390823365,
|
||
|
|
"epoch": 0.05113149040047503,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.00038700000000000003,
|
||
|
|
"loss": 6.4479,
|
||
|
|
"mean_token_accuracy": 0.10480978637933731,
|
||
|
|
"num_tokens": 1750933.0,
|
||
|
|
"step": 775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.777090930938721,
|
||
|
|
"epoch": 0.0514613709837039,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00038950000000000003,
|
||
|
|
"loss": 6.5029,
|
||
|
|
"mean_token_accuracy": 0.09836127161979676,
|
||
|
|
"num_tokens": 1761820.0,
|
||
|
|
"step": 780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.843807744979858,
|
||
|
|
"epoch": 0.05179125156693277,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00039200000000000004,
|
||
|
|
"loss": 6.3851,
|
||
|
|
"mean_token_accuracy": 0.10793521851301194,
|
||
|
|
"num_tokens": 1771628.0,
|
||
|
|
"step": 785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.779563665390015,
|
||
|
|
"epoch": 0.05212113215016164,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.00039450000000000005,
|
||
|
|
"loss": 6.4118,
|
||
|
|
"mean_token_accuracy": 0.10292888209223747,
|
||
|
|
"num_tokens": 1783360.0,
|
||
|
|
"step": 790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.869561862945557,
|
||
|
|
"epoch": 0.05245101273339051,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00039700000000000005,
|
||
|
|
"loss": 6.4721,
|
||
|
|
"mean_token_accuracy": 0.10269110351800918,
|
||
|
|
"num_tokens": 1794831.0,
|
||
|
|
"step": 795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.757121276855469,
|
||
|
|
"epoch": 0.052780893316619386,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0003995,
|
||
|
|
"loss": 6.3996,
|
||
|
|
"mean_token_accuracy": 0.10898642167448998,
|
||
|
|
"num_tokens": 1805056.0,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.742442893981933,
|
||
|
|
"epoch": 0.05311077389984825,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000402,
|
||
|
|
"loss": 6.3521,
|
||
|
|
"mean_token_accuracy": 0.10676872208714486,
|
||
|
|
"num_tokens": 1815233.0,
|
||
|
|
"step": 805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.787021493911743,
|
||
|
|
"epoch": 0.053440654483077124,
|
||
|
|
"grad_norm": 1.7265625,
|
||
|
|
"learning_rate": 0.0004045,
|
||
|
|
"loss": 6.611,
|
||
|
|
"mean_token_accuracy": 0.09833935126662255,
|
||
|
|
"num_tokens": 1826376.0,
|
||
|
|
"step": 810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.929257822036743,
|
||
|
|
"epoch": 0.053770535066306,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00040699999999999997,
|
||
|
|
"loss": 6.5177,
|
||
|
|
"mean_token_accuracy": 0.1020083598792553,
|
||
|
|
"num_tokens": 1836326.0,
|
||
|
|
"step": 815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.732786750793457,
|
||
|
|
"epoch": 0.05410041564953487,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004095,
|
||
|
|
"loss": 6.4724,
|
||
|
|
"mean_token_accuracy": 0.10276546701788902,
|
||
|
|
"num_tokens": 1847796.0,
|
||
|
|
"step": 820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.75844931602478,
|
||
|
|
"epoch": 0.05443029623276374,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.000412,
|
||
|
|
"loss": 6.3888,
|
||
|
|
"mean_token_accuracy": 0.10622160062193871,
|
||
|
|
"num_tokens": 1858470.0,
|
||
|
|
"step": 825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7840691089630125,
|
||
|
|
"epoch": 0.05476017681599261,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004145,
|
||
|
|
"loss": 6.4729,
|
||
|
|
"mean_token_accuracy": 0.10429331809282302,
|
||
|
|
"num_tokens": 1870368.0,
|
||
|
|
"step": 830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.742818212509155,
|
||
|
|
"epoch": 0.05509005739922148,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.000417,
|
||
|
|
"loss": 6.4328,
|
||
|
|
"mean_token_accuracy": 0.10953493639826775,
|
||
|
|
"num_tokens": 1881841.0,
|
||
|
|
"step": 835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.755731439590454,
|
||
|
|
"epoch": 0.05541993798245035,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004195,
|
||
|
|
"loss": 6.3925,
|
||
|
|
"mean_token_accuracy": 0.1099935881793499,
|
||
|
|
"num_tokens": 1892589.0,
|
||
|
|
"step": 840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.69039740562439,
|
||
|
|
"epoch": 0.055749818565679225,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.000422,
|
||
|
|
"loss": 6.3673,
|
||
|
|
"mean_token_accuracy": 0.11012204438447952,
|
||
|
|
"num_tokens": 1903730.0,
|
||
|
|
"step": 845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7573614597320555,
|
||
|
|
"epoch": 0.0560796991489081,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004245,
|
||
|
|
"loss": 6.4302,
|
||
|
|
"mean_token_accuracy": 0.1086188443005085,
|
||
|
|
"num_tokens": 1914872.0,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.760918712615966,
|
||
|
|
"epoch": 0.056409579732136964,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.000427,
|
||
|
|
"loss": 6.458,
|
||
|
|
"mean_token_accuracy": 0.10401058197021484,
|
||
|
|
"num_tokens": 1926127.0,
|
||
|
|
"step": 855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.707938003540039,
|
||
|
|
"epoch": 0.056739460315365836,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004295,
|
||
|
|
"loss": 6.4261,
|
||
|
|
"mean_token_accuracy": 0.10297657176852226,
|
||
|
|
"num_tokens": 1938867.0,
|
||
|
|
"step": 860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.701300954818725,
|
||
|
|
"epoch": 0.05706934089859471,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.000432,
|
||
|
|
"loss": 6.3721,
|
||
|
|
"mean_token_accuracy": 0.11107245236635208,
|
||
|
|
"num_tokens": 1950379.0,
|
||
|
|
"step": 865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.717032527923584,
|
||
|
|
"epoch": 0.05739922148182358,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004345,
|
||
|
|
"loss": 6.3958,
|
||
|
|
"mean_token_accuracy": 0.10820549428462982,
|
||
|
|
"num_tokens": 1961628.0,
|
||
|
|
"step": 870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7236415386199955,
|
||
|
|
"epoch": 0.057729102065052454,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.000437,
|
||
|
|
"loss": 6.4058,
|
||
|
|
"mean_token_accuracy": 0.10361326783895493,
|
||
|
|
"num_tokens": 1971580.0,
|
||
|
|
"step": 875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.726569175720215,
|
||
|
|
"epoch": 0.05805898264828132,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004395,
|
||
|
|
"loss": 6.4085,
|
||
|
|
"mean_token_accuracy": 0.10312368124723434,
|
||
|
|
"num_tokens": 1981789.0,
|
||
|
|
"step": 880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.681711912155151,
|
||
|
|
"epoch": 0.05838886323151019,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000442,
|
||
|
|
"loss": 6.3067,
|
||
|
|
"mean_token_accuracy": 0.1060155376791954,
|
||
|
|
"num_tokens": 1992667.0,
|
||
|
|
"step": 885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.598890781402588,
|
||
|
|
"epoch": 0.058718743814739065,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004445,
|
||
|
|
"loss": 6.3319,
|
||
|
|
"mean_token_accuracy": 0.11056532859802246,
|
||
|
|
"num_tokens": 2003864.0,
|
||
|
|
"step": 890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.65644645690918,
|
||
|
|
"epoch": 0.05904862439796794,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.000447,
|
||
|
|
"loss": 6.4309,
|
||
|
|
"mean_token_accuracy": 0.10145750418305396,
|
||
|
|
"num_tokens": 2017399.0,
|
||
|
|
"step": 895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.609835195541382,
|
||
|
|
"epoch": 0.05937850498119681,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00044950000000000003,
|
||
|
|
"loss": 6.3656,
|
||
|
|
"mean_token_accuracy": 0.10574300587177277,
|
||
|
|
"num_tokens": 2027924.0,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7295098304748535,
|
||
|
|
"epoch": 0.059708385564425676,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.00045200000000000004,
|
||
|
|
"loss": 6.2793,
|
||
|
|
"mean_token_accuracy": 0.11127018183469772,
|
||
|
|
"num_tokens": 2040174.0,
|
||
|
|
"step": 905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5820475101470945,
|
||
|
|
"epoch": 0.06003826614765455,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.00045450000000000004,
|
||
|
|
"loss": 6.3755,
|
||
|
|
"mean_token_accuracy": 0.10315576866269112,
|
||
|
|
"num_tokens": 2052564.0,
|
||
|
|
"step": 910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.776964807510376,
|
||
|
|
"epoch": 0.06036814673088342,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00045700000000000005,
|
||
|
|
"loss": 6.4174,
|
||
|
|
"mean_token_accuracy": 0.10292134135961532,
|
||
|
|
"num_tokens": 2063211.0,
|
||
|
|
"step": 915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.646928071975708,
|
||
|
|
"epoch": 0.06069802731411229,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00045950000000000006,
|
||
|
|
"loss": 6.327,
|
||
|
|
"mean_token_accuracy": 0.10777697786688804,
|
||
|
|
"num_tokens": 2075434.0,
|
||
|
|
"step": 920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.594566106796265,
|
||
|
|
"epoch": 0.061027907897341166,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000462,
|
||
|
|
"loss": 6.3556,
|
||
|
|
"mean_token_accuracy": 0.1038420632481575,
|
||
|
|
"num_tokens": 2087969.0,
|
||
|
|
"step": 925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.745871925354004,
|
||
|
|
"epoch": 0.06135778848057003,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004645,
|
||
|
|
"loss": 6.393,
|
||
|
|
"mean_token_accuracy": 0.10197513997554779,
|
||
|
|
"num_tokens": 2098469.0,
|
||
|
|
"step": 930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.559610033035279,
|
||
|
|
"epoch": 0.061687669063798904,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000467,
|
||
|
|
"loss": 6.2796,
|
||
|
|
"mean_token_accuracy": 0.10989089384675026,
|
||
|
|
"num_tokens": 2108739.0,
|
||
|
|
"step": 935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.695238208770752,
|
||
|
|
"epoch": 0.06201754964702778,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004695,
|
||
|
|
"loss": 6.3878,
|
||
|
|
"mean_token_accuracy": 0.10769468769431115,
|
||
|
|
"num_tokens": 2120234.0,
|
||
|
|
"step": 940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.584358024597168,
|
||
|
|
"epoch": 0.06234743023025665,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000472,
|
||
|
|
"loss": 6.2652,
|
||
|
|
"mean_token_accuracy": 0.10648446381092072,
|
||
|
|
"num_tokens": 2131585.0,
|
||
|
|
"step": 945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.645196437835693,
|
||
|
|
"epoch": 0.06267731081348552,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004745,
|
||
|
|
"loss": 6.4332,
|
||
|
|
"mean_token_accuracy": 0.10639934986829758,
|
||
|
|
"num_tokens": 2144537.0,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.700238752365112,
|
||
|
|
"epoch": 0.06300719139671439,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.000477,
|
||
|
|
"loss": 6.3867,
|
||
|
|
"mean_token_accuracy": 0.10446119010448456,
|
||
|
|
"num_tokens": 2157468.0,
|
||
|
|
"step": 955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.525477313995362,
|
||
|
|
"epoch": 0.06333707197994326,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004795,
|
||
|
|
"loss": 6.3074,
|
||
|
|
"mean_token_accuracy": 0.10612000674009323,
|
||
|
|
"num_tokens": 2169099.0,
|
||
|
|
"step": 960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.564707183837891,
|
||
|
|
"epoch": 0.06366695256317213,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000482,
|
||
|
|
"loss": 6.2871,
|
||
|
|
"mean_token_accuracy": 0.11626865863800048,
|
||
|
|
"num_tokens": 2179970.0,
|
||
|
|
"step": 965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.564694499969482,
|
||
|
|
"epoch": 0.063996833146401,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004845,
|
||
|
|
"loss": 6.3363,
|
||
|
|
"mean_token_accuracy": 0.10973790585994721,
|
||
|
|
"num_tokens": 2191455.0,
|
||
|
|
"step": 970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.749835729598999,
|
||
|
|
"epoch": 0.06432671372962988,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.000487,
|
||
|
|
"loss": 6.4757,
|
||
|
|
"mean_token_accuracy": 0.09981689378619193,
|
||
|
|
"num_tokens": 2202711.0,
|
||
|
|
"step": 975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.565635728836059,
|
||
|
|
"epoch": 0.06465659431285875,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004895,
|
||
|
|
"loss": 6.2468,
|
||
|
|
"mean_token_accuracy": 0.11120761334896087,
|
||
|
|
"num_tokens": 2214035.0,
|
||
|
|
"step": 980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.568064403533936,
|
||
|
|
"epoch": 0.06498647489608762,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.000492,
|
||
|
|
"loss": 6.2674,
|
||
|
|
"mean_token_accuracy": 0.1099687896668911,
|
||
|
|
"num_tokens": 2225437.0,
|
||
|
|
"step": 985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.664786672592163,
|
||
|
|
"epoch": 0.06531635547931648,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004945,
|
||
|
|
"loss": 6.3445,
|
||
|
|
"mean_token_accuracy": 0.10701494589447975,
|
||
|
|
"num_tokens": 2235693.0,
|
||
|
|
"step": 990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5984398365020756,
|
||
|
|
"epoch": 0.06564623606254535,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000497,
|
||
|
|
"loss": 6.2887,
|
||
|
|
"mean_token_accuracy": 0.11571999564766884,
|
||
|
|
"num_tokens": 2245850.0,
|
||
|
|
"step": 995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.527003002166748,
|
||
|
|
"epoch": 0.06597611664577423,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004995,
|
||
|
|
"loss": 6.346,
|
||
|
|
"mean_token_accuracy": 0.10999381244182586,
|
||
|
|
"num_tokens": 2257056.0,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.618610429763794,
|
||
|
|
"epoch": 0.0663059972290031,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.000499998026082006,
|
||
|
|
"loss": 6.4444,
|
||
|
|
"mean_token_accuracy": 0.10575283989310265,
|
||
|
|
"num_tokens": 2270421.0,
|
||
|
|
"step": 1005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.540064334869385,
|
||
|
|
"epoch": 0.06663587781223197,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004999900070995136,
|
||
|
|
"loss": 6.2778,
|
||
|
|
"mean_token_accuracy": 0.11337646692991257,
|
||
|
|
"num_tokens": 2282404.0,
|
||
|
|
"step": 1010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.535987138748169,
|
||
|
|
"epoch": 0.06696575839546084,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999758199023239,
|
||
|
|
"loss": 6.2074,
|
||
|
|
"mean_token_accuracy": 0.11448908373713493,
|
||
|
|
"num_tokens": 2292610.0,
|
||
|
|
"step": 1015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.527937507629394,
|
||
|
|
"epoch": 0.06729563897868972,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999554648793858,
|
||
|
|
"loss": 6.2561,
|
||
|
|
"mean_token_accuracy": 0.1101236142218113,
|
||
|
|
"num_tokens": 2303230.0,
|
||
|
|
"step": 1020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.496319580078125,
|
||
|
|
"epoch": 0.06762551956191859,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999289425887425,
|
||
|
|
"loss": 6.3138,
|
||
|
|
"mean_token_accuracy": 0.10930130183696747,
|
||
|
|
"num_tokens": 2316522.0,
|
||
|
|
"step": 1025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.530350017547607,
|
||
|
|
"epoch": 0.06795540014514746,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998962537575161,
|
||
|
|
"loss": 6.2444,
|
||
|
|
"mean_token_accuracy": 0.11181065291166306,
|
||
|
|
"num_tokens": 2327136.0,
|
||
|
|
"step": 1030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.482801723480224,
|
||
|
|
"epoch": 0.06828528072837632,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998573992818874,
|
||
|
|
"loss": 6.2218,
|
||
|
|
"mean_token_accuracy": 0.11561196967959404,
|
||
|
|
"num_tokens": 2337787.0,
|
||
|
|
"step": 1035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.492512369155884,
|
||
|
|
"epoch": 0.0686151613116052,
|
||
|
|
"grad_norm": 0.80078125,
|
||
|
|
"learning_rate": 0.0004998123802270715,
|
||
|
|
"loss": 6.2251,
|
||
|
|
"mean_token_accuracy": 0.11074953898787498,
|
||
|
|
"num_tokens": 2349983.0,
|
||
|
|
"step": 1040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.534840440750122,
|
||
|
|
"epoch": 0.06894504189483407,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997611978272886,
|
||
|
|
"loss": 6.3348,
|
||
|
|
"mean_token_accuracy": 0.10682928562164307,
|
||
|
|
"num_tokens": 2361673.0,
|
||
|
|
"step": 1045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.641943311691284,
|
||
|
|
"epoch": 0.06927492247806294,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004997038534857298,
|
||
|
|
"loss": 6.3282,
|
||
|
|
"mean_token_accuracy": 0.11464205458760261,
|
||
|
|
"num_tokens": 2373877.0,
|
||
|
|
"step": 1050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.475301933288574,
|
||
|
|
"epoch": 0.06960480306129181,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004996403487745194,
|
||
|
|
"loss": 6.1952,
|
||
|
|
"mean_token_accuracy": 0.1164882704615593,
|
||
|
|
"num_tokens": 2384558.0,
|
||
|
|
"step": 1055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.53571629524231,
|
||
|
|
"epoch": 0.06993468364452068,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000499570685434671,
|
||
|
|
"loss": 6.2885,
|
||
|
|
"mean_token_accuracy": 0.10790699049830436,
|
||
|
|
"num_tokens": 2395333.0,
|
||
|
|
"step": 1060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.446133232116699,
|
||
|
|
"epoch": 0.07026456422774956,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004994948653760405,
|
||
|
|
"loss": 6.214,
|
||
|
|
"mean_token_accuracy": 0.11159637048840523,
|
||
|
|
"num_tokens": 2407100.0,
|
||
|
|
"step": 1065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.443557214736939,
|
||
|
|
"epoch": 0.07059444481097843,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004994128906772729,
|
||
|
|
"loss": 6.1596,
|
||
|
|
"mean_token_accuracy": 0.11595186367630958,
|
||
|
|
"num_tokens": 2418137.0,
|
||
|
|
"step": 1070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.414693832397461,
|
||
|
|
"epoch": 0.0709243253942073,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.000499324763585746,
|
||
|
|
"loss": 6.2505,
|
||
|
|
"mean_token_accuracy": 0.11329601109027862,
|
||
|
|
"num_tokens": 2429058.0,
|
||
|
|
"step": 1075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.513547801971436,
|
||
|
|
"epoch": 0.07125420597743617,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004992304865175085,
|
||
|
|
"loss": 6.24,
|
||
|
|
"mean_token_accuracy": 0.11459704115986824,
|
||
|
|
"num_tokens": 2440716.0,
|
||
|
|
"step": 1080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.54072585105896,
|
||
|
|
"epoch": 0.07158408656066503,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004991300620572138,
|
||
|
|
"loss": 6.2677,
|
||
|
|
"mean_token_accuracy": 0.11517914533615112,
|
||
|
|
"num_tokens": 2451189.0,
|
||
|
|
"step": 1085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.368064117431641,
|
||
|
|
"epoch": 0.0719139671438939,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004990234929580494,
|
||
|
|
"loss": 6.2162,
|
||
|
|
"mean_token_accuracy": 0.11259195283055305,
|
||
|
|
"num_tokens": 2462860.0,
|
||
|
|
"step": 1090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.493119239807129,
|
||
|
|
"epoch": 0.07224384772712278,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004989107821416609,
|
||
|
|
"loss": 6.2409,
|
||
|
|
"mean_token_accuracy": 0.10539431199431419,
|
||
|
|
"num_tokens": 2475555.0,
|
||
|
|
"step": 1095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.490513038635254,
|
||
|
|
"epoch": 0.07257372831035165,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004987919326980723,
|
||
|
|
"loss": 6.2706,
|
||
|
|
"mean_token_accuracy": 0.10943889692425728,
|
||
|
|
"num_tokens": 2485599.0,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.487355518341064,
|
||
|
|
"epoch": 0.07290360889358052,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004986669478856011,
|
||
|
|
"loss": 6.1315,
|
||
|
|
"mean_token_accuracy": 0.11551824659109115,
|
||
|
|
"num_tokens": 2495857.0,
|
||
|
|
"step": 1105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.396845865249634,
|
||
|
|
"epoch": 0.0732334894768094,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004985358311307688,
|
||
|
|
"loss": 6.2302,
|
||
|
|
"mean_token_accuracy": 0.11530223116278648,
|
||
|
|
"num_tokens": 2506330.0,
|
||
|
|
"step": 1110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.506023502349853,
|
||
|
|
"epoch": 0.07356337006003827,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004983985860282081,
|
||
|
|
"loss": 6.2103,
|
||
|
|
"mean_token_accuracy": 0.10762735083699226,
|
||
|
|
"num_tokens": 2518181.0,
|
||
|
|
"step": 1115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.457603454589844,
|
||
|
|
"epoch": 0.07389325064326714,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004982552163405623,
|
||
|
|
"loss": 6.1525,
|
||
|
|
"mean_token_accuracy": 0.11814433187246323,
|
||
|
|
"num_tokens": 2528346.0,
|
||
|
|
"step": 1120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.366501569747925,
|
||
|
|
"epoch": 0.07422313122649601,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.0004981057259983839,
|
||
|
|
"loss": 6.2237,
|
||
|
|
"mean_token_accuracy": 0.10850833207368851,
|
||
|
|
"num_tokens": 2539922.0,
|
||
|
|
"step": 1125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.438397979736328,
|
||
|
|
"epoch": 0.07455301180972487,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004979501191000262,
|
||
|
|
"loss": 6.1788,
|
||
|
|
"mean_token_accuracy": 0.11676511541008949,
|
||
|
|
"num_tokens": 2551145.0,
|
||
|
|
"step": 1130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.468164253234863,
|
||
|
|
"epoch": 0.07488289239295375,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004977883999115311,
|
||
|
|
"loss": 6.2688,
|
||
|
|
"mean_token_accuracy": 0.11262761503458023,
|
||
|
|
"num_tokens": 2562178.0,
|
||
|
|
"step": 1135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.552046442031861,
|
||
|
|
"epoch": 0.07521277297618262,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004976205728665113,
|
||
|
|
"loss": 6.3198,
|
||
|
|
"mean_token_accuracy": 0.11036192998290062,
|
||
|
|
"num_tokens": 2574002.0,
|
||
|
|
"step": 1140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.409352016448975,
|
||
|
|
"epoch": 0.07554265355941149,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004974466425660307,
|
||
|
|
"loss": 6.2251,
|
||
|
|
"mean_token_accuracy": 0.11538875252008438,
|
||
|
|
"num_tokens": 2584049.0,
|
||
|
|
"step": 1145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.411483907699585,
|
||
|
|
"epoch": 0.07587253414264036,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0004972666137784759,
|
||
|
|
"loss": 6.2128,
|
||
|
|
"mean_token_accuracy": 0.11105952560901641,
|
||
|
|
"num_tokens": 2597415.0,
|
||
|
|
"step": 1150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.43424391746521,
|
||
|
|
"epoch": 0.07620241472586924,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.0004970804914394271,
|
||
|
|
"loss": 6.1614,
|
||
|
|
"mean_token_accuracy": 0.11391298174858093,
|
||
|
|
"num_tokens": 2609381.0,
|
||
|
|
"step": 1155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.408471488952637,
|
||
|
|
"epoch": 0.07653229530909811,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004968882806515225,
|
||
|
|
"loss": 6.2488,
|
||
|
|
"mean_token_accuracy": 0.11827918812632561,
|
||
|
|
"num_tokens": 2620525.0,
|
||
|
|
"step": 1160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.377165603637695,
|
||
|
|
"epoch": 0.07686217589232698,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004966899866843177,
|
||
|
|
"loss": 6.1652,
|
||
|
|
"mean_token_accuracy": 0.11539266556501389,
|
||
|
|
"num_tokens": 2631978.0,
|
||
|
|
"step": 1165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.42329421043396,
|
||
|
|
"epoch": 0.07719205647555585,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.000496485614974142,
|
||
|
|
"loss": 6.1672,
|
||
|
|
"mean_token_accuracy": 0.11286110579967498,
|
||
|
|
"num_tokens": 2643083.0,
|
||
|
|
"step": 1170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.415650844573975,
|
||
|
|
"epoch": 0.07752193705878473,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004962751711239492,
|
||
|
|
"loss": 6.1571,
|
||
|
|
"mean_token_accuracy": 0.11403257474303245,
|
||
|
|
"num_tokens": 2654175.0,
|
||
|
|
"step": 1175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.43393087387085,
|
||
|
|
"epoch": 0.07785181764201358,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004960586609031636,
|
||
|
|
"loss": 6.1244,
|
||
|
|
"mean_token_accuracy": 0.11616934239864349,
|
||
|
|
"num_tokens": 2665513.0,
|
||
|
|
"step": 1180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3165178298950195,
|
||
|
|
"epoch": 0.07818169822524246,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004958360902475224,
|
||
|
|
"loss": 6.1381,
|
||
|
|
"mean_token_accuracy": 0.1166747473180294,
|
||
|
|
"num_tokens": 2675842.0,
|
||
|
|
"step": 1185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.44808874130249,
|
||
|
|
"epoch": 0.07851157880847133,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004956074652589125,
|
||
|
|
"loss": 6.289,
|
||
|
|
"mean_token_accuracy": 0.11076370999217033,
|
||
|
|
"num_tokens": 2687289.0,
|
||
|
|
"step": 1190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.45378532409668,
|
||
|
|
"epoch": 0.0788414593917002,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004953727922052035,
|
||
|
|
"loss": 6.1818,
|
||
|
|
"mean_token_accuracy": 0.11144861951470375,
|
||
|
|
"num_tokens": 2698409.0,
|
||
|
|
"step": 1195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.291270208358765,
|
||
|
|
"epoch": 0.07917133997492908,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004951320775200756,
|
||
|
|
"loss": 6.1305,
|
||
|
|
"mean_token_accuracy": 0.11825140044093133,
|
||
|
|
"num_tokens": 2708695.0,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.438046884536743,
|
||
|
|
"epoch": 0.07950122055815795,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004948853278028436,
|
||
|
|
"loss": 6.1106,
|
||
|
|
"mean_token_accuracy": 0.1234841413795948,
|
||
|
|
"num_tokens": 2719631.0,
|
||
|
|
"step": 1205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.41588134765625,
|
||
|
|
"epoch": 0.07983110114138682,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004946325498182755,
|
||
|
|
"loss": 6.2096,
|
||
|
|
"mean_token_accuracy": 0.11646713688969612,
|
||
|
|
"num_tokens": 2730070.0,
|
||
|
|
"step": 1210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.370893335342407,
|
||
|
|
"epoch": 0.08016098172461569,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004943737504964076,
|
||
|
|
"loss": 6.2039,
|
||
|
|
"mean_token_accuracy": 0.11152140498161316,
|
||
|
|
"num_tokens": 2741450.0,
|
||
|
|
"step": 1215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.430210828781128,
|
||
|
|
"epoch": 0.08049086230784457,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000494108936932354,
|
||
|
|
"loss": 6.1301,
|
||
|
|
"mean_token_accuracy": 0.12166139110922813,
|
||
|
|
"num_tokens": 2752108.0,
|
||
|
|
"step": 1220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.321960210800171,
|
||
|
|
"epoch": 0.08082074289107344,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004938381163861124,
|
||
|
|
"loss": 6.1902,
|
||
|
|
"mean_token_accuracy": 0.11438200101256371,
|
||
|
|
"num_tokens": 2763041.0,
|
||
|
|
"step": 1225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4781797409057615,
|
||
|
|
"epoch": 0.0811506234743023,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004935612962823645,
|
||
|
|
"loss": 6.142,
|
||
|
|
"mean_token_accuracy": 0.11679482907056808,
|
||
|
|
"num_tokens": 2773140.0,
|
||
|
|
"step": 1230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.29995551109314,
|
||
|
|
"epoch": 0.08148050405753117,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004932784842102739,
|
||
|
|
"loss": 6.1152,
|
||
|
|
"mean_token_accuracy": 0.1186187893152237,
|
||
|
|
"num_tokens": 2783811.0,
|
||
|
|
"step": 1235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.400778293609619,
|
||
|
|
"epoch": 0.08181038464076004,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004929896879232758,
|
||
|
|
"loss": 6.0916,
|
||
|
|
"mean_token_accuracy": 0.11716892346739768,
|
||
|
|
"num_tokens": 2793957.0,
|
||
|
|
"step": 1240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.376893854141235,
|
||
|
|
"epoch": 0.08214026522398891,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004926949153388668,
|
||
|
|
"loss": 6.1916,
|
||
|
|
"mean_token_accuracy": 0.11219452396035194,
|
||
|
|
"num_tokens": 2804750.0,
|
||
|
|
"step": 1245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.390607213973999,
|
||
|
|
"epoch": 0.08247014580721779,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004923941745383859,
|
||
|
|
"loss": 6.2091,
|
||
|
|
"mean_token_accuracy": 0.11758575886487961,
|
||
|
|
"num_tokens": 2815559.0,
|
||
|
|
"step": 1250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.337049102783203,
|
||
|
|
"epoch": 0.08280002639044666,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.000492087473766794,
|
||
|
|
"loss": 6.0389,
|
||
|
|
"mean_token_accuracy": 0.1198160044848919,
|
||
|
|
"num_tokens": 2826450.0,
|
||
|
|
"step": 1255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.270413160324097,
|
||
|
|
"epoch": 0.08312990697367553,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000491774821432448,
|
||
|
|
"loss": 6.2178,
|
||
|
|
"mean_token_accuracy": 0.11123397275805473,
|
||
|
|
"num_tokens": 2837471.0,
|
||
|
|
"step": 1260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.503760528564453,
|
||
|
|
"epoch": 0.0834597875569044,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004914562261068693,
|
||
|
|
"loss": 6.2566,
|
||
|
|
"mean_token_accuracy": 0.11070210263133048,
|
||
|
|
"num_tokens": 2849110.0,
|
||
|
|
"step": 1265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.296745872497558,
|
||
|
|
"epoch": 0.08378966814013328,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004911316965245098,
|
||
|
|
"loss": 6.0871,
|
||
|
|
"mean_token_accuracy": 0.12081556469202041,
|
||
|
|
"num_tokens": 2860675.0,
|
||
|
|
"step": 1270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.326677370071411,
|
||
|
|
"epoch": 0.08411954872336214,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.000490801241582512,
|
||
|
|
"loss": 6.1927,
|
||
|
|
"mean_token_accuracy": 0.11729966774582863,
|
||
|
|
"num_tokens": 2872482.0,
|
||
|
|
"step": 1275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.381938552856445,
|
||
|
|
"epoch": 0.08444942930659101,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000490464870340465,
|
||
|
|
"loss": 6.0714,
|
||
|
|
"mean_token_accuracy": 0.1179822638630867,
|
||
|
|
"num_tokens": 2882199.0,
|
||
|
|
"step": 1280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.34971432685852,
|
||
|
|
"epoch": 0.08477930988981988,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004901225920201563,
|
||
|
|
"loss": 6.1134,
|
||
|
|
"mean_token_accuracy": 0.11833830401301385,
|
||
|
|
"num_tokens": 2892581.0,
|
||
|
|
"step": 1285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.351896286010742,
|
||
|
|
"epoch": 0.08510919047304875,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.000489774416005319,
|
||
|
|
"loss": 6.1352,
|
||
|
|
"mean_token_accuracy": 0.1160293884575367,
|
||
|
|
"num_tokens": 2904105.0,
|
||
|
|
"step": 1290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.32787446975708,
|
||
|
|
"epoch": 0.08543907105627763,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004894203518413742,
|
||
|
|
"loss": 6.0727,
|
||
|
|
"mean_token_accuracy": 0.11833698526024819,
|
||
|
|
"num_tokens": 2914818.0,
|
||
|
|
"step": 1295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.283242845535279,
|
||
|
|
"epoch": 0.0857689516395065,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004890604092351701,
|
||
|
|
"loss": 6.0902,
|
||
|
|
"mean_token_accuracy": 0.11517246216535568,
|
||
|
|
"num_tokens": 2925904.0,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.411873006820679,
|
||
|
|
"epoch": 0.08609883222273537,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.000488694598054715,
|
||
|
|
"loss": 6.1266,
|
||
|
|
"mean_token_accuracy": 0.12158060446381569,
|
||
|
|
"num_tokens": 2937177.0,
|
||
|
|
"step": 1305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.264025449752808,
|
||
|
|
"epoch": 0.08642871280596424,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004883229283289071,
|
||
|
|
"loss": 6.1313,
|
||
|
|
"mean_token_accuracy": 0.11671579852700234,
|
||
|
|
"num_tokens": 2948641.0,
|
||
|
|
"step": 1310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.323843240737915,
|
||
|
|
"epoch": 0.08675859338919312,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00048794541024725993,
|
||
|
|
"loss": 6.1582,
|
||
|
|
"mean_token_accuracy": 0.11641139760613442,
|
||
|
|
"num_tokens": 2960308.0,
|
||
|
|
"step": 1315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.296243333816529,
|
||
|
|
"epoch": 0.08708847397242199,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0004875620541596221,
|
||
|
|
"loss": 6.1697,
|
||
|
|
"mean_token_accuracy": 0.12116853073239327,
|
||
|
|
"num_tokens": 2972666.0,
|
||
|
|
"step": 1320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.374683809280396,
|
||
|
|
"epoch": 0.08741835455565085,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00048717287057589454,
|
||
|
|
"loss": 6.163,
|
||
|
|
"mean_token_accuracy": 0.1157516896724701,
|
||
|
|
"num_tokens": 2982894.0,
|
||
|
|
"step": 1325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.366577816009522,
|
||
|
|
"epoch": 0.08774823513887972,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004867778701657417,
|
||
|
|
"loss": 6.0644,
|
||
|
|
"mean_token_accuracy": 0.12436588779091835,
|
||
|
|
"num_tokens": 2992617.0,
|
||
|
|
"step": 1330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.234115743637085,
|
||
|
|
"epoch": 0.0880781157221086,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00048637706375829955,
|
||
|
|
"loss": 6.0646,
|
||
|
|
"mean_token_accuracy": 0.11831269934773445,
|
||
|
|
"num_tokens": 3003439.0,
|
||
|
|
"step": 1335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.431392860412598,
|
||
|
|
"epoch": 0.08840799630533747,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000485970462341878,
|
||
|
|
"loss": 6.2486,
|
||
|
|
"mean_token_accuracy": 0.11635357066988945,
|
||
|
|
"num_tokens": 3015204.0,
|
||
|
|
"step": 1340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.386788988113404,
|
||
|
|
"epoch": 0.08873787688856634,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.00048555807706366044,
|
||
|
|
"loss": 6.1794,
|
||
|
|
"mean_token_accuracy": 0.12042261585593224,
|
||
|
|
"num_tokens": 3026624.0,
|
||
|
|
"step": 1345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.286476135253906,
|
||
|
|
"epoch": 0.08906775747179521,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00048513991922939756,
|
||
|
|
"loss": 6.0423,
|
||
|
|
"mean_token_accuracy": 0.12152522057294846,
|
||
|
|
"num_tokens": 3037828.0,
|
||
|
|
"step": 1350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.296923875808716,
|
||
|
|
"epoch": 0.08939763805502408,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.00048471600030309744,
|
||
|
|
"loss": 6.0494,
|
||
|
|
"mean_token_accuracy": 0.12242811545729637,
|
||
|
|
"num_tokens": 3049666.0,
|
||
|
|
"step": 1355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2433209896087645,
|
||
|
|
"epoch": 0.08972751863825296,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.00048428633190671186,
|
||
|
|
"loss": 6.0924,
|
||
|
|
"mean_token_accuracy": 0.1256846785545349,
|
||
|
|
"num_tokens": 3061090.0,
|
||
|
|
"step": 1360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.278544187545776,
|
||
|
|
"epoch": 0.09005739922148183,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004838509258198167,
|
||
|
|
"loss": 6.1306,
|
||
|
|
"mean_token_accuracy": 0.11453063562512397,
|
||
|
|
"num_tokens": 3073031.0,
|
||
|
|
"step": 1365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.26322603225708,
|
||
|
|
"epoch": 0.09038727980471069,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.00048340979397929,
|
||
|
|
"loss": 6.0688,
|
||
|
|
"mean_token_accuracy": 0.12036575302481652,
|
||
|
|
"num_tokens": 3084858.0,
|
||
|
|
"step": 1370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.407075834274292,
|
||
|
|
"epoch": 0.09071716038793956,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.00048296294847898386,
|
||
|
|
"loss": 6.1054,
|
||
|
|
"mean_token_accuracy": 0.11281666085124016,
|
||
|
|
"num_tokens": 3095554.0,
|
||
|
|
"step": 1375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.248094177246093,
|
||
|
|
"epoch": 0.09104704097116843,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004825104015693934,
|
||
|
|
"loss": 6.0643,
|
||
|
|
"mean_token_accuracy": 0.1204713374376297,
|
||
|
|
"num_tokens": 3107164.0,
|
||
|
|
"step": 1380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2559247493743895,
|
||
|
|
"epoch": 0.0913769215543973,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004820521656573208,
|
||
|
|
"loss": 6.1536,
|
||
|
|
"mean_token_accuracy": 0.1127657175064087,
|
||
|
|
"num_tokens": 3118681.0,
|
||
|
|
"step": 1385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.407009935379028,
|
||
|
|
"epoch": 0.09170680213762618,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.00048158825330553505,
|
||
|
|
"loss": 6.1101,
|
||
|
|
"mean_token_accuracy": 0.11909232214093209,
|
||
|
|
"num_tokens": 3130604.0,
|
||
|
|
"step": 1390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.287244367599487,
|
||
|
|
"epoch": 0.09203668272085505,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.00048111867723242763,
|
||
|
|
"loss": 6.1052,
|
||
|
|
"mean_token_accuracy": 0.116939115524292,
|
||
|
|
"num_tokens": 3141774.0,
|
||
|
|
"step": 1395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.28112907409668,
|
||
|
|
"epoch": 0.09236656330408392,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004806434503116637,
|
||
|
|
"loss": 6.0033,
|
||
|
|
"mean_token_accuracy": 0.12666950821876527,
|
||
|
|
"num_tokens": 3151693.0,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.246624565124511,
|
||
|
|
"epoch": 0.0926964438873128,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004801625855718296,
|
||
|
|
"loss": 5.9844,
|
||
|
|
"mean_token_accuracy": 0.1263419881463051,
|
||
|
|
"num_tokens": 3162832.0,
|
||
|
|
"step": 1405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.230603456497192,
|
||
|
|
"epoch": 0.09302632447054167,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.00047967609619607477,
|
||
|
|
"loss": 6.0362,
|
||
|
|
"mean_token_accuracy": 0.13186612203717232,
|
||
|
|
"num_tokens": 3174048.0,
|
||
|
|
"step": 1410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.197139406204224,
|
||
|
|
"epoch": 0.09335620505377054,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004791839955217513,
|
||
|
|
"loss": 6.0143,
|
||
|
|
"mean_token_accuracy": 0.12525417655706406,
|
||
|
|
"num_tokens": 3185451.0,
|
||
|
|
"step": 1415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.291043329238891,
|
||
|
|
"epoch": 0.0936860856369994,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.00047868629704004786,
|
||
|
|
"loss": 6.0907,
|
||
|
|
"mean_token_accuracy": 0.12228038236498832,
|
||
|
|
"num_tokens": 3197405.0,
|
||
|
|
"step": 1420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.288193607330323,
|
||
|
|
"epoch": 0.09401596622022827,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.00047818301439561965,
|
||
|
|
"loss": 6.0708,
|
||
|
|
"mean_token_accuracy": 0.12197377160191536,
|
||
|
|
"num_tokens": 3208421.0,
|
||
|
|
"step": 1425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2467175960540775,
|
||
|
|
"epoch": 0.09434584680345715,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00047767416138621454,
|
||
|
|
"loss": 5.9793,
|
||
|
|
"mean_token_accuracy": 0.12171160653233529,
|
||
|
|
"num_tokens": 3219745.0,
|
||
|
|
"step": 1430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.232208776473999,
|
||
|
|
"epoch": 0.09467572738668602,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.000477159751962295,
|
||
|
|
"loss": 6.0716,
|
||
|
|
"mean_token_accuracy": 0.12090381532907486,
|
||
|
|
"num_tokens": 3231347.0,
|
||
|
|
"step": 1435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.211804819107056,
|
||
|
|
"epoch": 0.09500560796991489,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.00047663980022665507,
|
||
|
|
"loss": 6.0455,
|
||
|
|
"mean_token_accuracy": 0.12001732885837554,
|
||
|
|
"num_tokens": 3242616.0,
|
||
|
|
"step": 1440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.160833644866943,
|
||
|
|
"epoch": 0.09533548855314376,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.00047611432043403437,
|
||
|
|
"loss": 5.9419,
|
||
|
|
"mean_token_accuracy": 0.1280081771314144,
|
||
|
|
"num_tokens": 3253697.0,
|
||
|
|
"step": 1445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.303204488754273,
|
||
|
|
"epoch": 0.09566536913637264,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004755833269907267,
|
||
|
|
"loss": 6.0534,
|
||
|
|
"mean_token_accuracy": 0.1217152826488018,
|
||
|
|
"num_tokens": 3263800.0,
|
||
|
|
"step": 1450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.257365798950195,
|
||
|
|
"epoch": 0.09599524971960151,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004750468344541857,
|
||
|
|
"loss": 6.0204,
|
||
|
|
"mean_token_accuracy": 0.12240952104330063,
|
||
|
|
"num_tokens": 3274538.0,
|
||
|
|
"step": 1455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.264223718643189,
|
||
|
|
"epoch": 0.09632513030283038,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00047450485753262525,
|
||
|
|
"loss": 6.0163,
|
||
|
|
"mean_token_accuracy": 0.1247081845998764,
|
||
|
|
"num_tokens": 3285719.0,
|
||
|
|
"step": 1460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.265989780426025,
|
||
|
|
"epoch": 0.09665501088605925,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.00047395741108461633,
|
||
|
|
"loss": 6.1308,
|
||
|
|
"mean_token_accuracy": 0.11454476118087768,
|
||
|
|
"num_tokens": 3296715.0,
|
||
|
|
"step": 1465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.278552579879761,
|
||
|
|
"epoch": 0.09698489146928811,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.00047340451011867985,
|
||
|
|
"loss": 6.0749,
|
||
|
|
"mean_token_accuracy": 0.12230216190218926,
|
||
|
|
"num_tokens": 3308800.0,
|
||
|
|
"step": 1470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.281282806396485,
|
||
|
|
"epoch": 0.09731477205251698,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.00047284616979287515,
|
||
|
|
"loss": 6.1972,
|
||
|
|
"mean_token_accuracy": 0.12018877789378166,
|
||
|
|
"num_tokens": 3322180.0,
|
||
|
|
"step": 1475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.260345363616944,
|
||
|
|
"epoch": 0.09764465263574586,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.00047228240541438433,
|
||
|
|
"loss": 5.9877,
|
||
|
|
"mean_token_accuracy": 0.11602422222495079,
|
||
|
|
"num_tokens": 3333363.0,
|
||
|
|
"step": 1480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2602760791778564,
|
||
|
|
"epoch": 0.09797453321897473,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.00047171323243909257,
|
||
|
|
"loss": 6.0591,
|
||
|
|
"mean_token_accuracy": 0.12210157290101051,
|
||
|
|
"num_tokens": 3345040.0,
|
||
|
|
"step": 1485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.321555471420288,
|
||
|
|
"epoch": 0.0983044138022036,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.00047113866647116457,
|
||
|
|
"loss": 6.1333,
|
||
|
|
"mean_token_accuracy": 0.1185726396739483,
|
||
|
|
"num_tokens": 3356445.0,
|
||
|
|
"step": 1490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.195455074310303,
|
||
|
|
"epoch": 0.09863429438543247,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004705587232626164,
|
||
|
|
"loss": 5.9938,
|
||
|
|
"mean_token_accuracy": 0.1257028914988041,
|
||
|
|
"num_tokens": 3366948.0,
|
||
|
|
"step": 1495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.255468225479126,
|
||
|
|
"epoch": 0.09896417496866135,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.00046997341871288424,
|
||
|
|
"loss": 6.0501,
|
||
|
|
"mean_token_accuracy": 0.11747408881783486,
|
||
|
|
"num_tokens": 3378616.0,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.102145862579346,
|
||
|
|
"epoch": 0.09929405555189022,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004693827688683879,
|
||
|
|
"loss": 5.942,
|
||
|
|
"mean_token_accuracy": 0.12176220938563347,
|
||
|
|
"num_tokens": 3390384.0,
|
||
|
|
"step": 1505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.270010757446289,
|
||
|
|
"epoch": 0.09962393613511909,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004687867899220914,
|
||
|
|
"loss": 6.0223,
|
||
|
|
"mean_token_accuracy": 0.12289982810616493,
|
||
|
|
"num_tokens": 3401904.0,
|
||
|
|
"step": 1510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.241530799865723,
|
||
|
|
"epoch": 0.09995381671834795,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.00046818549821305846,
|
||
|
|
"loss": 6.0222,
|
||
|
|
"mean_token_accuracy": 0.12228552997112274,
|
||
|
|
"num_tokens": 3413691.0,
|
||
|
|
"step": 1515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.143762922286987,
|
||
|
|
"epoch": 0.10028369730157682,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00046757891022600494,
|
||
|
|
"loss": 5.9354,
|
||
|
|
"mean_token_accuracy": 0.12270262986421585,
|
||
|
|
"num_tokens": 3423751.0,
|
||
|
|
"step": 1520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.193496513366699,
|
||
|
|
"epoch": 0.1006135778848057,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004669670425908471,
|
||
|
|
"loss": 6.1507,
|
||
|
|
"mean_token_accuracy": 0.11703718826174736,
|
||
|
|
"num_tokens": 3436597.0,
|
||
|
|
"step": 1525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.327424764633179,
|
||
|
|
"epoch": 0.10094345846803457,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004663499120822451,
|
||
|
|
"loss": 6.0602,
|
||
|
|
"mean_token_accuracy": 0.12643541246652604,
|
||
|
|
"num_tokens": 3447705.0,
|
||
|
|
"step": 1530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2434529781341555,
|
||
|
|
"epoch": 0.10127333905126344,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004657275356191437,
|
||
|
|
"loss": 6.0483,
|
||
|
|
"mean_token_accuracy": 0.12049341946840286,
|
||
|
|
"num_tokens": 3458643.0,
|
||
|
|
"step": 1535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.196995782852173,
|
||
|
|
"epoch": 0.10160321963449231,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00046509993026430804,
|
||
|
|
"loss": 6.0711,
|
||
|
|
"mean_token_accuracy": 0.12196420207619667,
|
||
|
|
"num_tokens": 3469050.0,
|
||
|
|
"step": 1540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.269529151916504,
|
||
|
|
"epoch": 0.10193310021772119,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004644671132238558,
|
||
|
|
"loss": 6.0342,
|
||
|
|
"mean_token_accuracy": 0.12130389660596848,
|
||
|
|
"num_tokens": 3480379.0,
|
||
|
|
"step": 1545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1761744022369385,
|
||
|
|
"epoch": 0.10226298080095006,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.00046382910184678585,
|
||
|
|
"loss": 6.0408,
|
||
|
|
"mean_token_accuracy": 0.12561473324894906,
|
||
|
|
"num_tokens": 3492678.0,
|
||
|
|
"step": 1550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.277125024795533,
|
||
|
|
"epoch": 0.10259286138417893,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004631859136245025,
|
||
|
|
"loss": 6.0195,
|
||
|
|
"mean_token_accuracy": 0.12293133214116096,
|
||
|
|
"num_tokens": 3503932.0,
|
||
|
|
"step": 1555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.234262895584107,
|
||
|
|
"epoch": 0.1029227419674078,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004625375661903357,
|
||
|
|
"loss": 6.0505,
|
||
|
|
"mean_token_accuracy": 0.12323530092835426,
|
||
|
|
"num_tokens": 3517102.0,
|
||
|
|
"step": 1560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.253872871398926,
|
||
|
|
"epoch": 0.10325262255063666,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00046188407731905787,
|
||
|
|
"loss": 6.0115,
|
||
|
|
"mean_token_accuracy": 0.12458823323249817,
|
||
|
|
"num_tokens": 3530101.0,
|
||
|
|
"step": 1565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.12779860496521,
|
||
|
|
"epoch": 0.10358250313386554,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00046122546492639643,
|
||
|
|
"loss": 5.9591,
|
||
|
|
"mean_token_accuracy": 0.13248580545186997,
|
||
|
|
"num_tokens": 3540631.0,
|
||
|
|
"step": 1570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.294931316375733,
|
||
|
|
"epoch": 0.10391238371709441,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.000460561747068543,
|
||
|
|
"loss": 6.0822,
|
||
|
|
"mean_token_accuracy": 0.12522295564413072,
|
||
|
|
"num_tokens": 3552730.0,
|
||
|
|
"step": 1575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.171346712112427,
|
||
|
|
"epoch": 0.10424226430032328,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004598929419416578,
|
||
|
|
"loss": 6.0096,
|
||
|
|
"mean_token_accuracy": 0.12023151516914368,
|
||
|
|
"num_tokens": 3562997.0,
|
||
|
|
"step": 1580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.178964471817016,
|
||
|
|
"epoch": 0.10457214488355215,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.00045921906788137123,
|
||
|
|
"loss": 5.914,
|
||
|
|
"mean_token_accuracy": 0.12756141573190688,
|
||
|
|
"num_tokens": 3574946.0,
|
||
|
|
"step": 1585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.188223600387573,
|
||
|
|
"epoch": 0.10490202546678103,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.00045854014336228115,
|
||
|
|
"loss": 6.0343,
|
||
|
|
"mean_token_accuracy": 0.12333807945251465,
|
||
|
|
"num_tokens": 3586922.0,
|
||
|
|
"step": 1590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.235507917404175,
|
||
|
|
"epoch": 0.1052319060500099,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.00045785618699744615,
|
||
|
|
"loss": 6.0905,
|
||
|
|
"mean_token_accuracy": 0.11987906247377396,
|
||
|
|
"num_tokens": 3598824.0,
|
||
|
|
"step": 1595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.201266145706176,
|
||
|
|
"epoch": 0.10556178663323877,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.00045716721753787543,
|
||
|
|
"loss": 5.9968,
|
||
|
|
"mean_token_accuracy": 0.12334208115935326,
|
||
|
|
"num_tokens": 3610814.0,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.224771499633789,
|
||
|
|
"epoch": 0.10589166721646764,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004564732538720148,
|
||
|
|
"loss": 6.001,
|
||
|
|
"mean_token_accuracy": 0.1251366674900055,
|
||
|
|
"num_tokens": 3622284.0,
|
||
|
|
"step": 1605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.11914963722229,
|
||
|
|
"epoch": 0.1062215477996965,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.00045577431502522877,
|
||
|
|
"loss": 5.9085,
|
||
|
|
"mean_token_accuracy": 0.1288203664124012,
|
||
|
|
"num_tokens": 3633760.0,
|
||
|
|
"step": 1610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.199207162857055,
|
||
|
|
"epoch": 0.10655142838292538,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004550704201592787,
|
||
|
|
"loss": 6.0102,
|
||
|
|
"mean_token_accuracy": 0.1252448245882988,
|
||
|
|
"num_tokens": 3644667.0,
|
||
|
|
"step": 1615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2114036083221436,
|
||
|
|
"epoch": 0.10688130896615425,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004543615885717981,
|
||
|
|
"loss": 5.9609,
|
||
|
|
"mean_token_accuracy": 0.1275472305715084,
|
||
|
|
"num_tokens": 3655375.0,
|
||
|
|
"step": 1620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.193666744232178,
|
||
|
|
"epoch": 0.10721118954938312,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.00045364783969576296,
|
||
|
|
"loss": 5.9602,
|
||
|
|
"mean_token_accuracy": 0.12853190824389457,
|
||
|
|
"num_tokens": 3666911.0,
|
||
|
|
"step": 1625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1601011753082275,
|
||
|
|
"epoch": 0.107541070132612,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004529291930989592,
|
||
|
|
"loss": 5.9892,
|
||
|
|
"mean_token_accuracy": 0.12578651905059815,
|
||
|
|
"num_tokens": 3678251.0,
|
||
|
|
"step": 1630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.170024251937866,
|
||
|
|
"epoch": 0.10787095071584087,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004522056684834464,
|
||
|
|
"loss": 5.9657,
|
||
|
|
"mean_token_accuracy": 0.123971738666296,
|
||
|
|
"num_tokens": 3690099.0,
|
||
|
|
"step": 1635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.169254636764526,
|
||
|
|
"epoch": 0.10820083129906974,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004514772856850173,
|
||
|
|
"loss": 6.0247,
|
||
|
|
"mean_token_accuracy": 0.12748396769165993,
|
||
|
|
"num_tokens": 3701856.0,
|
||
|
|
"step": 1640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.24689679145813,
|
||
|
|
"epoch": 0.10853071188229861,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004507440646726542,
|
||
|
|
"loss": 6.1407,
|
||
|
|
"mean_token_accuracy": 0.11711174249649048,
|
||
|
|
"num_tokens": 3713985.0,
|
||
|
|
"step": 1645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.239718580245972,
|
||
|
|
"epoch": 0.10886059246552748,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004500060255479818,
|
||
|
|
"loss": 6.0464,
|
||
|
|
"mean_token_accuracy": 0.12184103205800056,
|
||
|
|
"num_tokens": 3726176.0,
|
||
|
|
"step": 1650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.112149381637574,
|
||
|
|
"epoch": 0.10919047304875636,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004492631885447151,
|
||
|
|
"loss": 5.8415,
|
||
|
|
"mean_token_accuracy": 0.1293956719338894,
|
||
|
|
"num_tokens": 3737305.0,
|
||
|
|
"step": 1655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.18146014213562,
|
||
|
|
"epoch": 0.10952035363198522,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00044851557402810616,
|
||
|
|
"loss": 6.0193,
|
||
|
|
"mean_token_accuracy": 0.12377961277961731,
|
||
|
|
"num_tokens": 3748282.0,
|
||
|
|
"step": 1660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.169847440719605,
|
||
|
|
"epoch": 0.10985023421521409,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.00044776320249438444,
|
||
|
|
"loss": 5.8795,
|
||
|
|
"mean_token_accuracy": 0.13224580138921738,
|
||
|
|
"num_tokens": 3759035.0,
|
||
|
|
"step": 1665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.111970567703247,
|
||
|
|
"epoch": 0.11018011479844296,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00044700609457019565,
|
||
|
|
"loss": 5.9106,
|
||
|
|
"mean_token_accuracy": 0.1316598728299141,
|
||
|
|
"num_tokens": 3769833.0,
|
||
|
|
"step": 1670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.205641174316407,
|
||
|
|
"epoch": 0.11050999538167183,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004462442710120359,
|
||
|
|
"loss": 6.0289,
|
||
|
|
"mean_token_accuracy": 0.1224887952208519,
|
||
|
|
"num_tokens": 3781424.0,
|
||
|
|
"step": 1675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.17392635345459,
|
||
|
|
"epoch": 0.1108398759649007,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.000445477752705683,
|
||
|
|
"loss": 6.0018,
|
||
|
|
"mean_token_accuracy": 0.12416321039199829,
|
||
|
|
"num_tokens": 3792697.0,
|
||
|
|
"step": 1680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.113514137268067,
|
||
|
|
"epoch": 0.11116975654812958,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.00044470656066562336,
|
||
|
|
"loss": 5.8768,
|
||
|
|
"mean_token_accuracy": 0.127310561388731,
|
||
|
|
"num_tokens": 3804250.0,
|
||
|
|
"step": 1685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.104232978820801,
|
||
|
|
"epoch": 0.11149963713135845,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004439307160344765,
|
||
|
|
"loss": 5.9735,
|
||
|
|
"mean_token_accuracy": 0.11756366044282913,
|
||
|
|
"num_tokens": 3816723.0,
|
||
|
|
"step": 1690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.176311063766479,
|
||
|
|
"epoch": 0.11182951771458732,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00044315024008241473,
|
||
|
|
"loss": 5.8784,
|
||
|
|
"mean_token_accuracy": 0.12866798862814904,
|
||
|
|
"num_tokens": 3827765.0,
|
||
|
|
"step": 1695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1176502227783205,
|
||
|
|
"epoch": 0.1121593982978162,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004423651542065806,
|
||
|
|
"loss": 5.9289,
|
||
|
|
"mean_token_accuracy": 0.11890131905674935,
|
||
|
|
"num_tokens": 3839261.0,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.112108898162842,
|
||
|
|
"epoch": 0.11248927888104507,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00044157547993050006,
|
||
|
|
"loss": 5.9902,
|
||
|
|
"mean_token_accuracy": 0.12579327300190926,
|
||
|
|
"num_tokens": 3851532.0,
|
||
|
|
"step": 1705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.173661804199218,
|
||
|
|
"epoch": 0.11281915946427393,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.00044078123890349227,
|
||
|
|
"loss": 5.9612,
|
||
|
|
"mean_token_accuracy": 0.12136413753032685,
|
||
|
|
"num_tokens": 3863412.0,
|
||
|
|
"step": 1710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.149047422409057,
|
||
|
|
"epoch": 0.1131490400475028,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.00043998245290007606,
|
||
|
|
"loss": 5.8447,
|
||
|
|
"mean_token_accuracy": 0.1302158772945404,
|
||
|
|
"num_tokens": 3873660.0,
|
||
|
|
"step": 1715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.139502668380738,
|
||
|
|
"epoch": 0.11347892063073167,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00043917914381937323,
|
||
|
|
"loss": 5.9496,
|
||
|
|
"mean_token_accuracy": 0.1236309438943863,
|
||
|
|
"num_tokens": 3884998.0,
|
||
|
|
"step": 1720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1464558124542235,
|
||
|
|
"epoch": 0.11380880121396054,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.00043837133368450815,
|
||
|
|
"loss": 5.9224,
|
||
|
|
"mean_token_accuracy": 0.12901559025049208,
|
||
|
|
"num_tokens": 3896449.0,
|
||
|
|
"step": 1725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.137756109237671,
|
||
|
|
"epoch": 0.11413868179718942,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004375590446420037,
|
||
|
|
"loss": 5.9308,
|
||
|
|
"mean_token_accuracy": 0.13310305252671242,
|
||
|
|
"num_tokens": 3907446.0,
|
||
|
|
"step": 1730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.098831748962402,
|
||
|
|
"epoch": 0.11446856238041829,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004367422989611743,
|
||
|
|
"loss": 5.8629,
|
||
|
|
"mean_token_accuracy": 0.1335848443210125,
|
||
|
|
"num_tokens": 3919132.0,
|
||
|
|
"step": 1735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.173413896560669,
|
||
|
|
"epoch": 0.11479844296364716,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004359211190335153,
|
||
|
|
"loss": 6.0455,
|
||
|
|
"mean_token_accuracy": 0.12229348495602607,
|
||
|
|
"num_tokens": 3930929.0,
|
||
|
|
"step": 1740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.193883085250855,
|
||
|
|
"epoch": 0.11512832354687604,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00043509552737208923,
|
||
|
|
"loss": 6.0236,
|
||
|
|
"mean_token_accuracy": 0.125267543643713,
|
||
|
|
"num_tokens": 3943358.0,
|
||
|
|
"step": 1745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.212734508514404,
|
||
|
|
"epoch": 0.11545820413010491,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.00043426554661090853,
|
||
|
|
"loss": 6.0313,
|
||
|
|
"mean_token_accuracy": 0.12616485729813576,
|
||
|
|
"num_tokens": 3953642.0,
|
||
|
|
"step": 1750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.239323616027832,
|
||
|
|
"epoch": 0.11578808471333377,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00043343119950431516,
|
||
|
|
"loss": 6.032,
|
||
|
|
"mean_token_accuracy": 0.12373298928141593,
|
||
|
|
"num_tokens": 3965905.0,
|
||
|
|
"step": 1755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.083920526504516,
|
||
|
|
"epoch": 0.11611796529656264,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.00043259250892635644,
|
||
|
|
"loss": 5.9464,
|
||
|
|
"mean_token_accuracy": 0.12747222036123276,
|
||
|
|
"num_tokens": 3977729.0,
|
||
|
|
"step": 1760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2404697895050045,
|
||
|
|
"epoch": 0.11644784587979151,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004317494978701582,
|
||
|
|
"loss": 5.9506,
|
||
|
|
"mean_token_accuracy": 0.1291648544371128,
|
||
|
|
"num_tokens": 3989346.0,
|
||
|
|
"step": 1765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.123899602890015,
|
||
|
|
"epoch": 0.11677772646302038,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004309021894472943,
|
||
|
|
"loss": 5.9999,
|
||
|
|
"mean_token_accuracy": 0.11715613603591919,
|
||
|
|
"num_tokens": 4000997.0,
|
||
|
|
"step": 1770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.185966205596924,
|
||
|
|
"epoch": 0.11710760704624926,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004300506068871534,
|
||
|
|
"loss": 5.8902,
|
||
|
|
"mean_token_accuracy": 0.1294801838696003,
|
||
|
|
"num_tokens": 4012087.0,
|
||
|
|
"step": 1775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.123832750320434,
|
||
|
|
"epoch": 0.11743748762947813,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00042919477353630135,
|
||
|
|
"loss": 5.9016,
|
||
|
|
"mean_token_accuracy": 0.1290864586830139,
|
||
|
|
"num_tokens": 4021877.0,
|
||
|
|
"step": 1780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.074026346206665,
|
||
|
|
"epoch": 0.117767368212707,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000428334712857842,
|
||
|
|
"loss": 5.8715,
|
||
|
|
"mean_token_accuracy": 0.12763532623648643,
|
||
|
|
"num_tokens": 4032590.0,
|
||
|
|
"step": 1785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.133955097198486,
|
||
|
|
"epoch": 0.11809724879593587,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00042747044843077304,
|
||
|
|
"loss": 5.8885,
|
||
|
|
"mean_token_accuracy": 0.13011712655425073,
|
||
|
|
"num_tokens": 4042888.0,
|
||
|
|
"step": 1790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.093007373809814,
|
||
|
|
"epoch": 0.11842712937916475,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00042660200394934047,
|
||
|
|
"loss": 5.8691,
|
||
|
|
"mean_token_accuracy": 0.13210372030735015,
|
||
|
|
"num_tokens": 4053081.0,
|
||
|
|
"step": 1795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.095946455001831,
|
||
|
|
"epoch": 0.11875700996239362,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.00042572940322238844,
|
||
|
|
"loss": 5.9411,
|
||
|
|
"mean_token_accuracy": 0.12647043392062188,
|
||
|
|
"num_tokens": 4063683.0,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.065203905105591,
|
||
|
|
"epoch": 0.11908689054562248,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.00042485267017270664,
|
||
|
|
"loss": 5.8352,
|
||
|
|
"mean_token_accuracy": 0.1315798580646515,
|
||
|
|
"num_tokens": 4074502.0,
|
||
|
|
"step": 1805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.016225814819336,
|
||
|
|
"epoch": 0.11941677112885135,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004239718288363745,
|
||
|
|
"loss": 5.8457,
|
||
|
|
"mean_token_accuracy": 0.12952971011400222,
|
||
|
|
"num_tokens": 4085866.0,
|
||
|
|
"step": 1810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.075180578231811,
|
||
|
|
"epoch": 0.11974665171208022,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004230869033621023,
|
||
|
|
"loss": 5.9234,
|
||
|
|
"mean_token_accuracy": 0.1321993961930275,
|
||
|
|
"num_tokens": 4098157.0,
|
||
|
|
"step": 1815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.099708414077758,
|
||
|
|
"epoch": 0.1200765322953091,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004221979180105688,
|
||
|
|
"loss": 5.8457,
|
||
|
|
"mean_token_accuracy": 0.1320454455912113,
|
||
|
|
"num_tokens": 4108922.0,
|
||
|
|
"step": 1820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.049484586715698,
|
||
|
|
"epoch": 0.12040641287853797,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.00042130489715375645,
|
||
|
|
"loss": 5.8695,
|
||
|
|
"mean_token_accuracy": 0.12669327035546302,
|
||
|
|
"num_tokens": 4120240.0,
|
||
|
|
"step": 1825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.043438339233399,
|
||
|
|
"epoch": 0.12073629346176684,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00042040786527428335,
|
||
|
|
"loss": 5.728,
|
||
|
|
"mean_token_accuracy": 0.14360663741827012,
|
||
|
|
"num_tokens": 4130766.0,
|
||
|
|
"step": 1830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.077558612823486,
|
||
|
|
"epoch": 0.12106617404499571,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004195068469647315,
|
||
|
|
"loss": 5.8673,
|
||
|
|
"mean_token_accuracy": 0.1369071461260319,
|
||
|
|
"num_tokens": 4140371.0,
|
||
|
|
"step": 1835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.978666830062866,
|
||
|
|
"epoch": 0.12139605462822459,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.00041860186692697297,
|
||
|
|
"loss": 5.8044,
|
||
|
|
"mean_token_accuracy": 0.13305559307336806,
|
||
|
|
"num_tokens": 4151875.0,
|
||
|
|
"step": 1840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.073175477981567,
|
||
|
|
"epoch": 0.12172593521145346,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.00041769294997149264,
|
||
|
|
"loss": 5.8687,
|
||
|
|
"mean_token_accuracy": 0.1320350855588913,
|
||
|
|
"num_tokens": 4162941.0,
|
||
|
|
"step": 1845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.160045576095581,
|
||
|
|
"epoch": 0.12205581579468233,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004167801210167081,
|
||
|
|
"loss": 5.8859,
|
||
|
|
"mean_token_accuracy": 0.13151889070868492,
|
||
|
|
"num_tokens": 4174770.0,
|
||
|
|
"step": 1850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.052571964263916,
|
||
|
|
"epoch": 0.12238569637791119,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004158634050882861,
|
||
|
|
"loss": 5.9214,
|
||
|
|
"mean_token_accuracy": 0.1273489125072956,
|
||
|
|
"num_tokens": 4185169.0,
|
||
|
|
"step": 1855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.039424037933349,
|
||
|
|
"epoch": 0.12271557696114006,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004149428273184569,
|
||
|
|
"loss": 5.8932,
|
||
|
|
"mean_token_accuracy": 0.1261409156024456,
|
||
|
|
"num_tokens": 4196840.0,
|
||
|
|
"step": 1860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.111230182647705,
|
||
|
|
"epoch": 0.12304545754436894,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004140184129453253,
|
||
|
|
"loss": 5.8782,
|
||
|
|
"mean_token_accuracy": 0.12893069237470628,
|
||
|
|
"num_tokens": 4208304.0,
|
||
|
|
"step": 1865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0603667259216305,
|
||
|
|
"epoch": 0.12337533812759781,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000413090187312178,
|
||
|
|
"loss": 5.8894,
|
||
|
|
"mean_token_accuracy": 0.12972930669784546,
|
||
|
|
"num_tokens": 4219591.0,
|
||
|
|
"step": 1870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.076956701278687,
|
||
|
|
"epoch": 0.12370521871082668,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004121581758667898,
|
||
|
|
"loss": 5.9484,
|
||
|
|
"mean_token_accuracy": 0.12848909422755242,
|
||
|
|
"num_tokens": 4232018.0,
|
||
|
|
"step": 1875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.126820135116577,
|
||
|
|
"epoch": 0.12403509929405555,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.00041122240416072533,
|
||
|
|
"loss": 5.8712,
|
||
|
|
"mean_token_accuracy": 0.13103963136672975,
|
||
|
|
"num_tokens": 4243933.0,
|
||
|
|
"step": 1880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.107426929473877,
|
||
|
|
"epoch": 0.12436497987728443,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004102828978486385,
|
||
|
|
"loss": 5.8547,
|
||
|
|
"mean_token_accuracy": 0.13372569903731346,
|
||
|
|
"num_tokens": 4254471.0,
|
||
|
|
"step": 1885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.086618280410766,
|
||
|
|
"epoch": 0.1246948604605133,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004093396826875695,
|
||
|
|
"loss": 5.9448,
|
||
|
|
"mean_token_accuracy": 0.1257178656756878,
|
||
|
|
"num_tokens": 4266377.0,
|
||
|
|
"step": 1890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.116164064407348,
|
||
|
|
"epoch": 0.12502474104374217,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.00040839278453623837,
|
||
|
|
"loss": 5.8208,
|
||
|
|
"mean_token_accuracy": 0.13271296247839928,
|
||
|
|
"num_tokens": 4277972.0,
|
||
|
|
"step": 1895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.045373964309692,
|
||
|
|
"epoch": 0.12535462162697103,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004074422293543363,
|
||
|
|
"loss": 5.9118,
|
||
|
|
"mean_token_accuracy": 0.12806374952197075,
|
||
|
|
"num_tokens": 4289262.0,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.13698091506958,
|
||
|
|
"epoch": 0.12568450221019992,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004064880432018137,
|
||
|
|
"loss": 5.8853,
|
||
|
|
"mean_token_accuracy": 0.12667523100972175,
|
||
|
|
"num_tokens": 4299416.0,
|
||
|
|
"step": 1905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.087643766403199,
|
||
|
|
"epoch": 0.12601438279342878,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.00040553025223816615,
|
||
|
|
"loss": 5.878,
|
||
|
|
"mean_token_accuracy": 0.12547796964645386,
|
||
|
|
"num_tokens": 4309990.0,
|
||
|
|
"step": 1910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.063091564178467,
|
||
|
|
"epoch": 0.12634426337665766,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.00040456888272171653,
|
||
|
|
"loss": 5.7841,
|
||
|
|
"mean_token_accuracy": 0.13362204283475876,
|
||
|
|
"num_tokens": 4320825.0,
|
||
|
|
"step": 1915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.094519853591919,
|
||
|
|
"epoch": 0.12667414395988652,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00040360396100889577,
|
||
|
|
"loss": 5.8638,
|
||
|
|
"mean_token_accuracy": 0.13135677948594093,
|
||
|
|
"num_tokens": 4332113.0,
|
||
|
|
"step": 1920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0757499694824215,
|
||
|
|
"epoch": 0.12700402454311538,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004026355135535202,
|
||
|
|
"loss": 5.9009,
|
||
|
|
"mean_token_accuracy": 0.12676777616143226,
|
||
|
|
"num_tokens": 4343436.0,
|
||
|
|
"step": 1925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.073655843734741,
|
||
|
|
"epoch": 0.12733390512634427,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.000401663566906066,
|
||
|
|
"loss": 5.8777,
|
||
|
|
"mean_token_accuracy": 0.13043420612812043,
|
||
|
|
"num_tokens": 4354582.0,
|
||
|
|
"step": 1930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.046963214874268,
|
||
|
|
"epoch": 0.12766378570957312,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00040068814771294134,
|
||
|
|
"loss": 5.8272,
|
||
|
|
"mean_token_accuracy": 0.13648442775011063,
|
||
|
|
"num_tokens": 4365175.0,
|
||
|
|
"step": 1935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.065089368820191,
|
||
|
|
"epoch": 0.127993666292802,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0003997092827157562,
|
||
|
|
"loss": 5.82,
|
||
|
|
"mean_token_accuracy": 0.13603207170963288,
|
||
|
|
"num_tokens": 4377613.0,
|
||
|
|
"step": 1940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.055947399139404,
|
||
|
|
"epoch": 0.12832354687603087,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000398726998750589,
|
||
|
|
"loss": 5.8924,
|
||
|
|
"mean_token_accuracy": 0.1285402812063694,
|
||
|
|
"num_tokens": 4389829.0,
|
||
|
|
"step": 1945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.076267719268799,
|
||
|
|
"epoch": 0.12865342745925976,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00039774132274725076,
|
||
|
|
"loss": 5.8538,
|
||
|
|
"mean_token_accuracy": 0.12974862307310103,
|
||
|
|
"num_tokens": 4401437.0,
|
||
|
|
"step": 1950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.996847915649414,
|
||
|
|
"epoch": 0.12898330804248861,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.00039675228172854707,
|
||
|
|
"loss": 5.778,
|
||
|
|
"mean_token_accuracy": 0.13621187210083008,
|
||
|
|
"num_tokens": 4413235.0,
|
||
|
|
"step": 1955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.989922285079956,
|
||
|
|
"epoch": 0.1293131886257175,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0003957599028095371,
|
||
|
|
"loss": 5.8291,
|
||
|
|
"mean_token_accuracy": 0.13967953771352767,
|
||
|
|
"num_tokens": 4424686.0,
|
||
|
|
"step": 1960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.066288852691651,
|
||
|
|
"epoch": 0.12964306920894636,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00039476421319679017,
|
||
|
|
"loss": 5.7897,
|
||
|
|
"mean_token_accuracy": 0.1325330153107643,
|
||
|
|
"num_tokens": 4435176.0,
|
||
|
|
"step": 1965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.971096801757812,
|
||
|
|
"epoch": 0.12997294979217525,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00039376524018764,
|
||
|
|
"loss": 5.8371,
|
||
|
|
"mean_token_accuracy": 0.13270480558276176,
|
||
|
|
"num_tokens": 4446923.0,
|
||
|
|
"step": 1970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.158391284942627,
|
||
|
|
"epoch": 0.1303028303754041,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00039276301116943616,
|
||
|
|
"loss": 5.8719,
|
||
|
|
"mean_token_accuracy": 0.13505094796419143,
|
||
|
|
"num_tokens": 4457820.0,
|
||
|
|
"step": 1975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.048366212844849,
|
||
|
|
"epoch": 0.13063271095863296,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0003917575536187936,
|
||
|
|
"loss": 5.7773,
|
||
|
|
"mean_token_accuracy": 0.13880621865391732,
|
||
|
|
"num_tokens": 4468761.0,
|
||
|
|
"step": 1980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.035593795776367,
|
||
|
|
"epoch": 0.13096259154186185,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00039074889510083894,
|
||
|
|
"loss": 5.8267,
|
||
|
|
"mean_token_accuracy": 0.13596638068556785,
|
||
|
|
"num_tokens": 4480352.0,
|
||
|
|
"step": 1985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.898376989364624,
|
||
|
|
"epoch": 0.1312924721250907,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.00038973706326845495,
|
||
|
|
"loss": 5.811,
|
||
|
|
"mean_token_accuracy": 0.13567186892032623,
|
||
|
|
"num_tokens": 4490792.0,
|
||
|
|
"step": 1990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.099267053604126,
|
||
|
|
"epoch": 0.1316223527083196,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0003887220858615225,
|
||
|
|
"loss": 5.8935,
|
||
|
|
"mean_token_accuracy": 0.12728226855397223,
|
||
|
|
"num_tokens": 4502293.0,
|
||
|
|
"step": 1995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.147139596939087,
|
||
|
|
"epoch": 0.13195223329154845,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0003877039907061597,
|
||
|
|
"loss": 5.865,
|
||
|
|
"mean_token_accuracy": 0.12852602377533912,
|
||
|
|
"num_tokens": 4512476.0,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.030910348892212,
|
||
|
|
"epoch": 0.13228211387477734,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0003866828057139598,
|
||
|
|
"loss": 5.778,
|
||
|
|
"mean_token_accuracy": 0.12960575222969056,
|
||
|
|
"num_tokens": 4523874.0,
|
||
|
|
"step": 2005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.02244291305542,
|
||
|
|
"epoch": 0.1326119944580062,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00038565855888122503,
|
||
|
|
"loss": 5.756,
|
||
|
|
"mean_token_accuracy": 0.1418381743133068,
|
||
|
|
"num_tokens": 4534845.0,
|
||
|
|
"step": 2010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.081170845031738,
|
||
|
|
"epoch": 0.13294187504123509,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.00038463127828819975,
|
||
|
|
"loss": 5.8407,
|
||
|
|
"mean_token_accuracy": 0.13504794910550116,
|
||
|
|
"num_tokens": 4545616.0,
|
||
|
|
"step": 2015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.961184883117676,
|
||
|
|
"epoch": 0.13327175562446394,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00038360099209830043,
|
||
|
|
"loss": 5.7999,
|
||
|
|
"mean_token_accuracy": 0.13850362598896027,
|
||
|
|
"num_tokens": 4555834.0,
|
||
|
|
"step": 2020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.073493432998657,
|
||
|
|
"epoch": 0.1336016362076928,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.0003825677285573433,
|
||
|
|
"loss": 5.8102,
|
||
|
|
"mean_token_accuracy": 0.13600170686841012,
|
||
|
|
"num_tokens": 4568671.0,
|
||
|
|
"step": 2025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.988195705413818,
|
||
|
|
"epoch": 0.1339315167909217,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00038153151599277027,
|
||
|
|
"loss": 5.7546,
|
||
|
|
"mean_token_accuracy": 0.13271748498082162,
|
||
|
|
"num_tokens": 4579114.0,
|
||
|
|
"step": 2030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.002746438980102,
|
||
|
|
"epoch": 0.13426139737415055,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0003804923828128723,
|
||
|
|
"loss": 5.8049,
|
||
|
|
"mean_token_accuracy": 0.135003512352705,
|
||
|
|
"num_tokens": 4589587.0,
|
||
|
|
"step": 2035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.995663833618164,
|
||
|
|
"epoch": 0.13459127795737943,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0003794503575060104,
|
||
|
|
"loss": 5.7251,
|
||
|
|
"mean_token_accuracy": 0.13719758689403533,
|
||
|
|
"num_tokens": 4600287.0,
|
||
|
|
"step": 2040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.052637004852295,
|
||
|
|
"epoch": 0.1349211585406083,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.00037840546863983484,
|
||
|
|
"loss": 5.8284,
|
||
|
|
"mean_token_accuracy": 0.136325104534626,
|
||
|
|
"num_tokens": 4611279.0,
|
||
|
|
"step": 2045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0248448848724365,
|
||
|
|
"epoch": 0.13525103912383718,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0003773577448605015,
|
||
|
|
"loss": 5.8822,
|
||
|
|
"mean_token_accuracy": 0.1325960010290146,
|
||
|
|
"num_tokens": 4622109.0,
|
||
|
|
"step": 2050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.07674765586853,
|
||
|
|
"epoch": 0.13558091970706604,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0003763072148918872,
|
||
|
|
"loss": 5.813,
|
||
|
|
"mean_token_accuracy": 0.13159040361642838,
|
||
|
|
"num_tokens": 4633857.0,
|
||
|
|
"step": 2055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.988399410247803,
|
||
|
|
"epoch": 0.13591080029029493,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0003752539075348017,
|
||
|
|
"loss": 5.7702,
|
||
|
|
"mean_token_accuracy": 0.1334913082420826,
|
||
|
|
"num_tokens": 4644528.0,
|
||
|
|
"step": 2060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.084853076934815,
|
||
|
|
"epoch": 0.13624068087352378,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00037419785166619817,
|
||
|
|
"loss": 5.8331,
|
||
|
|
"mean_token_accuracy": 0.13030101507902145,
|
||
|
|
"num_tokens": 4655950.0,
|
||
|
|
"step": 2065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9883557796478275,
|
||
|
|
"epoch": 0.13657056145675264,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0003731390762383818,
|
||
|
|
"loss": 5.7613,
|
||
|
|
"mean_token_accuracy": 0.13080518394708635,
|
||
|
|
"num_tokens": 4668083.0,
|
||
|
|
"step": 2070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9485790729522705,
|
||
|
|
"epoch": 0.13690044203998153,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0003720776102782158,
|
||
|
|
"loss": 5.7137,
|
||
|
|
"mean_token_accuracy": 0.1412648528814316,
|
||
|
|
"num_tokens": 4679430.0,
|
||
|
|
"step": 2075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.044094228744507,
|
||
|
|
"epoch": 0.1372303226232104,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00037101348288632555,
|
||
|
|
"loss": 5.7696,
|
||
|
|
"mean_token_accuracy": 0.13095248267054557,
|
||
|
|
"num_tokens": 4690331.0,
|
||
|
|
"step": 2080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0202226638793945,
|
||
|
|
"epoch": 0.13756020320643927,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.0003699467232363012,
|
||
|
|
"loss": 5.9044,
|
||
|
|
"mean_token_accuracy": 0.13258501812815665,
|
||
|
|
"num_tokens": 4701012.0,
|
||
|
|
"step": 2085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9732335090637205,
|
||
|
|
"epoch": 0.13789008378966813,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0003688773605738973,
|
||
|
|
"loss": 5.7729,
|
||
|
|
"mean_token_accuracy": 0.1296282432973385,
|
||
|
|
"num_tokens": 4711043.0,
|
||
|
|
"step": 2090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.042768955230713,
|
||
|
|
"epoch": 0.13821996437289702,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.00036780542421623134,
|
||
|
|
"loss": 5.7791,
|
||
|
|
"mean_token_accuracy": 0.14066991284489633,
|
||
|
|
"num_tokens": 4723596.0,
|
||
|
|
"step": 2095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.997233295440674,
|
||
|
|
"epoch": 0.13854984495612588,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0003667309435509802,
|
||
|
|
"loss": 5.8,
|
||
|
|
"mean_token_accuracy": 0.13357228115200998,
|
||
|
|
"num_tokens": 4733911.0,
|
||
|
|
"step": 2100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.021502113342285,
|
||
|
|
"epoch": 0.13887972553935476,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0003656539480355741,
|
||
|
|
"loss": 5.8083,
|
||
|
|
"mean_token_accuracy": 0.13234125226736068,
|
||
|
|
"num_tokens": 4745958.0,
|
||
|
|
"step": 2105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.01106629371643,
|
||
|
|
"epoch": 0.13920960612258362,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0003645744671963891,
|
||
|
|
"loss": 5.7986,
|
||
|
|
"mean_token_accuracy": 0.12715880945324898,
|
||
|
|
"num_tokens": 4757060.0,
|
||
|
|
"step": 2110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9879505157470705,
|
||
|
|
"epoch": 0.13953948670581248,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0003634925306279376,
|
||
|
|
"loss": 5.7561,
|
||
|
|
"mean_token_accuracy": 0.13249528855085374,
|
||
|
|
"num_tokens": 4769029.0,
|
||
|
|
"step": 2115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.018679618835449,
|
||
|
|
"epoch": 0.13986936728904137,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0003624081679920574,
|
||
|
|
"loss": 5.8149,
|
||
|
|
"mean_token_accuracy": 0.13416093364357948,
|
||
|
|
"num_tokens": 4779451.0,
|
||
|
|
"step": 2120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.920935106277466,
|
||
|
|
"epoch": 0.14019924787227023,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0003613214090170977,
|
||
|
|
"loss": 5.7599,
|
||
|
|
"mean_token_accuracy": 0.13627765849232673,
|
||
|
|
"num_tokens": 4791350.0,
|
||
|
|
"step": 2125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.003325128555298,
|
||
|
|
"epoch": 0.1405291284554991,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0003602322834971048,
|
||
|
|
"loss": 5.7446,
|
||
|
|
"mean_token_accuracy": 0.13855525851249695,
|
||
|
|
"num_tokens": 4802117.0,
|
||
|
|
"step": 2130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.030262470245361,
|
||
|
|
"epoch": 0.14085900903872797,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0003591408212910051,
|
||
|
|
"loss": 5.7574,
|
||
|
|
"mean_token_accuracy": 0.13873222917318345,
|
||
|
|
"num_tokens": 4812966.0,
|
||
|
|
"step": 2135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.038935852050781,
|
||
|
|
"epoch": 0.14118888962195686,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0003580470523217863,
|
||
|
|
"loss": 5.8236,
|
||
|
|
"mean_token_accuracy": 0.13563399836421014,
|
||
|
|
"num_tokens": 4825228.0,
|
||
|
|
"step": 2140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.031043529510498,
|
||
|
|
"epoch": 0.14151877020518572,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0003569510065756771,
|
||
|
|
"loss": 5.8276,
|
||
|
|
"mean_token_accuracy": 0.13363277837634085,
|
||
|
|
"num_tokens": 4837282.0,
|
||
|
|
"step": 2145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.976261377334595,
|
||
|
|
"epoch": 0.1418486507884146,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0003558527141013254,
|
||
|
|
"loss": 5.7133,
|
||
|
|
"mean_token_accuracy": 0.14040677696466447,
|
||
|
|
"num_tokens": 4848882.0,
|
||
|
|
"step": 2150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.953822278976441,
|
||
|
|
"epoch": 0.14217853137164346,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0003547522050089742,
|
||
|
|
"loss": 5.7321,
|
||
|
|
"mean_token_accuracy": 0.13586447685956954,
|
||
|
|
"num_tokens": 4858963.0,
|
||
|
|
"step": 2155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.987196159362793,
|
||
|
|
"epoch": 0.14250841195487235,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00035364950946963606,
|
||
|
|
"loss": 5.8111,
|
||
|
|
"mean_token_accuracy": 0.1297604463994503,
|
||
|
|
"num_tokens": 4870055.0,
|
||
|
|
"step": 2160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.039496755599975,
|
||
|
|
"epoch": 0.1428382925381012,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0003525446577142663,
|
||
|
|
"loss": 5.7991,
|
||
|
|
"mean_token_accuracy": 0.13666038811206818,
|
||
|
|
"num_tokens": 4881840.0,
|
||
|
|
"step": 2165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.027910757064819,
|
||
|
|
"epoch": 0.14316817312133007,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.00035143768003293395,
|
||
|
|
"loss": 5.7918,
|
||
|
|
"mean_token_accuracy": 0.13733214884996414,
|
||
|
|
"num_tokens": 4894108.0,
|
||
|
|
"step": 2170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.990892362594605,
|
||
|
|
"epoch": 0.14349805370455895,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0003503286067739913,
|
||
|
|
"loss": 5.8143,
|
||
|
|
"mean_token_accuracy": 0.1337997905910015,
|
||
|
|
"num_tokens": 4906495.0,
|
||
|
|
"step": 2175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.989019823074341,
|
||
|
|
"epoch": 0.1438279342877878,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00034921746834324193,
|
||
|
|
"loss": 5.7671,
|
||
|
|
"mean_token_accuracy": 0.1328294411301613,
|
||
|
|
"num_tokens": 4917701.0,
|
||
|
|
"step": 2180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.951587677001953,
|
||
|
|
"epoch": 0.1441578148710167,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0003481042952031072,
|
||
|
|
"loss": 5.8062,
|
||
|
|
"mean_token_accuracy": 0.12987686842679977,
|
||
|
|
"num_tokens": 4930697.0,
|
||
|
|
"step": 2185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.993644952774048,
|
||
|
|
"epoch": 0.14448769545424556,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0003469891178717911,
|
||
|
|
"loss": 5.7682,
|
||
|
|
"mean_token_accuracy": 0.14051052331924438,
|
||
|
|
"num_tokens": 4942197.0,
|
||
|
|
"step": 2190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.048940134048462,
|
||
|
|
"epoch": 0.14481757603747444,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0003458719669224436,
|
||
|
|
"loss": 5.7923,
|
||
|
|
"mean_token_accuracy": 0.1344756856560707,
|
||
|
|
"num_tokens": 4953963.0,
|
||
|
|
"step": 2195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.956955623626709,
|
||
|
|
"epoch": 0.1451474566207033,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0003447528729823221,
|
||
|
|
"loss": 5.6837,
|
||
|
|
"mean_token_accuracy": 0.14405391812324525,
|
||
|
|
"num_tokens": 4965878.0,
|
||
|
|
"step": 2200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.96135630607605,
|
||
|
|
"epoch": 0.1454773372039322,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0003436318667319525,
|
||
|
|
"loss": 5.7945,
|
||
|
|
"mean_token_accuracy": 0.1385580815374851,
|
||
|
|
"num_tokens": 4977421.0,
|
||
|
|
"step": 2205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.991558361053467,
|
||
|
|
"epoch": 0.14580721778716105,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.00034250897890428716,
|
||
|
|
"loss": 5.736,
|
||
|
|
"mean_token_accuracy": 0.13585484623908997,
|
||
|
|
"num_tokens": 4989018.0,
|
||
|
|
"step": 2210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0171167850494385,
|
||
|
|
"epoch": 0.1461370983703899,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0003413842402838633,
|
||
|
|
"loss": 5.8079,
|
||
|
|
"mean_token_accuracy": 0.13656753972172736,
|
||
|
|
"num_tokens": 5000800.0,
|
||
|
|
"step": 2215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.006067180633545,
|
||
|
|
"epoch": 0.1464669789536188,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.00034025768170595834,
|
||
|
|
"loss": 5.8074,
|
||
|
|
"mean_token_accuracy": 0.1327499806880951,
|
||
|
|
"num_tokens": 5012229.0,
|
||
|
|
"step": 2220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.998569822311401,
|
||
|
|
"epoch": 0.14679685953684765,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0003391293340557446,
|
||
|
|
"loss": 5.8149,
|
||
|
|
"mean_token_accuracy": 0.13783595487475395,
|
||
|
|
"num_tokens": 5022606.0,
|
||
|
|
"step": 2225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.959091663360596,
|
||
|
|
"epoch": 0.14712674012007654,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0003379992282674431,
|
||
|
|
"loss": 5.6329,
|
||
|
|
"mean_token_accuracy": 0.1467166393995285,
|
||
|
|
"num_tokens": 5033238.0,
|
||
|
|
"step": 2230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.014291000366211,
|
||
|
|
"epoch": 0.1474566207033054,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0003368673953234749,
|
||
|
|
"loss": 5.7302,
|
||
|
|
"mean_token_accuracy": 0.13859887793660164,
|
||
|
|
"num_tokens": 5043847.0,
|
||
|
|
"step": 2235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.985012483596802,
|
||
|
|
"epoch": 0.14778650128653428,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00033573386625361176,
|
||
|
|
"loss": 5.7556,
|
||
|
|
"mean_token_accuracy": 0.14404344484210013,
|
||
|
|
"num_tokens": 5055709.0,
|
||
|
|
"step": 2240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.955406570434571,
|
||
|
|
"epoch": 0.14811638186976314,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.00033459867213412567,
|
||
|
|
"loss": 5.7068,
|
||
|
|
"mean_token_accuracy": 0.13526695519685744,
|
||
|
|
"num_tokens": 5068465.0,
|
||
|
|
"step": 2245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.995353746414184,
|
||
|
|
"epoch": 0.14844626245299203,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000333461844086937,
|
||
|
|
"loss": 5.8169,
|
||
|
|
"mean_token_accuracy": 0.13264559879899024,
|
||
|
|
"num_tokens": 5078044.0,
|
||
|
|
"step": 2250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9070898532867435,
|
||
|
|
"epoch": 0.1487761430362209,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00033232341327876097,
|
||
|
|
"loss": 5.6827,
|
||
|
|
"mean_token_accuracy": 0.1389334961771965,
|
||
|
|
"num_tokens": 5089419.0,
|
||
|
|
"step": 2255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9418010234832765,
|
||
|
|
"epoch": 0.14910602361944975,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0003311834109202531,
|
||
|
|
"loss": 5.7642,
|
||
|
|
"mean_token_accuracy": 0.13794886991381644,
|
||
|
|
"num_tokens": 5100949.0,
|
||
|
|
"step": 2260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.026254034042358,
|
||
|
|
"epoch": 0.14943590420267863,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00033004186826515416,
|
||
|
|
"loss": 5.7815,
|
||
|
|
"mean_token_accuracy": 0.1351143829524517,
|
||
|
|
"num_tokens": 5111339.0,
|
||
|
|
"step": 2265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.973840999603271,
|
||
|
|
"epoch": 0.1497657847859075,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0003288988166094324,
|
||
|
|
"loss": 5.7589,
|
||
|
|
"mean_token_accuracy": 0.14394627138972282,
|
||
|
|
"num_tokens": 5121090.0,
|
||
|
|
"step": 2270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.976790094375611,
|
||
|
|
"epoch": 0.15009566536913638,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00032775428729042656,
|
||
|
|
"loss": 5.7954,
|
||
|
|
"mean_token_accuracy": 0.1333276942372322,
|
||
|
|
"num_tokens": 5133413.0,
|
||
|
|
"step": 2275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9762529850006105,
|
||
|
|
"epoch": 0.15042554595236524,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.000326608311685986,
|
||
|
|
"loss": 5.7192,
|
||
|
|
"mean_token_accuracy": 0.1380014419555664,
|
||
|
|
"num_tokens": 5144011.0,
|
||
|
|
"step": 2280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.971281099319458,
|
||
|
|
"epoch": 0.15075542653559412,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0003254609212136108,
|
||
|
|
"loss": 5.7417,
|
||
|
|
"mean_token_accuracy": 0.13871914893388748,
|
||
|
|
"num_tokens": 5154766.0,
|
||
|
|
"step": 2285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.012048959732056,
|
||
|
|
"epoch": 0.15108530711882298,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00032431214732959036,
|
||
|
|
"loss": 5.7721,
|
||
|
|
"mean_token_accuracy": 0.1379425346851349,
|
||
|
|
"num_tokens": 5166092.0,
|
||
|
|
"step": 2290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.936145496368408,
|
||
|
|
"epoch": 0.15141518770205187,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.000323162021528141,
|
||
|
|
"loss": 5.6581,
|
||
|
|
"mean_token_accuracy": 0.14484875351190568,
|
||
|
|
"num_tokens": 5176533.0,
|
||
|
|
"step": 2295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.001963329315186,
|
||
|
|
"epoch": 0.15174506828528073,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00032201057534054264,
|
||
|
|
"loss": 5.7897,
|
||
|
|
"mean_token_accuracy": 0.13622895777225494,
|
||
|
|
"num_tokens": 5186647.0,
|
||
|
|
"step": 2300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0021404266357425,
|
||
|
|
"epoch": 0.1520749488685096,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00032085784033427414,
|
||
|
|
"loss": 5.7298,
|
||
|
|
"mean_token_accuracy": 0.14511198028922082,
|
||
|
|
"num_tokens": 5197785.0,
|
||
|
|
"step": 2305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.878802728652954,
|
||
|
|
"epoch": 0.15240482945173847,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0003197038481121478,
|
||
|
|
"loss": 5.7573,
|
||
|
|
"mean_token_accuracy": 0.1323046825826168,
|
||
|
|
"num_tokens": 5208557.0,
|
||
|
|
"step": 2310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.061697292327881,
|
||
|
|
"epoch": 0.15273471003496733,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0003185486303114436,
|
||
|
|
"loss": 5.8037,
|
||
|
|
"mean_token_accuracy": 0.13767401725053788,
|
||
|
|
"num_tokens": 5220243.0,
|
||
|
|
"step": 2315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.062685108184814,
|
||
|
|
"epoch": 0.15306459061819622,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0003173922186030409,
|
||
|
|
"loss": 5.7995,
|
||
|
|
"mean_token_accuracy": 0.13269810676574706,
|
||
|
|
"num_tokens": 5230426.0,
|
||
|
|
"step": 2320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.911227226257324,
|
||
|
|
"epoch": 0.15339447120142508,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.000316234644690551,
|
||
|
|
"loss": 5.7424,
|
||
|
|
"mean_token_accuracy": 0.1366793282330036,
|
||
|
|
"num_tokens": 5241425.0,
|
||
|
|
"step": 2325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0411840915679935,
|
||
|
|
"epoch": 0.15372435178465396,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0003150759403094473,
|
||
|
|
"loss": 5.8166,
|
||
|
|
"mean_token_accuracy": 0.1355382539331913,
|
||
|
|
"num_tokens": 5252620.0,
|
||
|
|
"step": 2330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.995370149612427,
|
||
|
|
"epoch": 0.15405423236788282,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00031391613722619587,
|
||
|
|
"loss": 5.7665,
|
||
|
|
"mean_token_accuracy": 0.13599780797958375,
|
||
|
|
"num_tokens": 5264284.0,
|
||
|
|
"step": 2335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.965780735015869,
|
||
|
|
"epoch": 0.1543841129511117,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000312755267237384,
|
||
|
|
"loss": 5.7581,
|
||
|
|
"mean_token_accuracy": 0.14127838015556335,
|
||
|
|
"num_tokens": 5274382.0,
|
||
|
|
"step": 2340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.991366386413574,
|
||
|
|
"epoch": 0.15471399353434057,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0003115933621688488,
|
||
|
|
"loss": 5.789,
|
||
|
|
"mean_token_accuracy": 0.13329199850559234,
|
||
|
|
"num_tokens": 5286116.0,
|
||
|
|
"step": 2345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.931483221054077,
|
||
|
|
"epoch": 0.15504387411756945,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00031043045387480487,
|
||
|
|
"loss": 5.7038,
|
||
|
|
"mean_token_accuracy": 0.14397905617952347,
|
||
|
|
"num_tokens": 5295918.0,
|
||
|
|
"step": 2350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.96733775138855,
|
||
|
|
"epoch": 0.1553737547007983,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0003092665742369703,
|
||
|
|
"loss": 5.7361,
|
||
|
|
"mean_token_accuracy": 0.1403938911855221,
|
||
|
|
"num_tokens": 5306529.0,
|
||
|
|
"step": 2355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.028081035614013,
|
||
|
|
"epoch": 0.15570363528402717,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00030810175516369343,
|
||
|
|
"loss": 5.7661,
|
||
|
|
"mean_token_accuracy": 0.13846702873706818,
|
||
|
|
"num_tokens": 5318089.0,
|
||
|
|
"step": 2360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.990221786499023,
|
||
|
|
"epoch": 0.15603351586725606,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0003069360285890775,
|
||
|
|
"loss": 5.7621,
|
||
|
|
"mean_token_accuracy": 0.13685602098703384,
|
||
|
|
"num_tokens": 5329563.0,
|
||
|
|
"step": 2365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.976520681381226,
|
||
|
|
"epoch": 0.15636339645048491,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00030576942647210547,
|
||
|
|
"loss": 5.6692,
|
||
|
|
"mean_token_accuracy": 0.14305319339036943,
|
||
|
|
"num_tokens": 5341100.0,
|
||
|
|
"step": 2370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.953386306762695,
|
||
|
|
"epoch": 0.1566932770337138,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.00030460198079576355,
|
||
|
|
"loss": 5.7091,
|
||
|
|
"mean_token_accuracy": 0.1394743949174881,
|
||
|
|
"num_tokens": 5351150.0,
|
||
|
|
"step": 2375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.892103052139282,
|
||
|
|
"epoch": 0.15702315761694266,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0003034337235661648,
|
||
|
|
"loss": 5.7101,
|
||
|
|
"mean_token_accuracy": 0.1376820407807827,
|
||
|
|
"num_tokens": 5362481.0,
|
||
|
|
"step": 2380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.913623666763305,
|
||
|
|
"epoch": 0.15735303820017155,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0003022646868116714,
|
||
|
|
"loss": 5.6801,
|
||
|
|
"mean_token_accuracy": 0.14595198184251784,
|
||
|
|
"num_tokens": 5372869.0,
|
||
|
|
"step": 2385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.96872239112854,
|
||
|
|
"epoch": 0.1576829187834004,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0003010949025820163,
|
||
|
|
"loss": 5.7009,
|
||
|
|
"mean_token_accuracy": 0.1381881281733513,
|
||
|
|
"num_tokens": 5382804.0,
|
||
|
|
"step": 2390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.999673080444336,
|
||
|
|
"epoch": 0.1580127993666293,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0002999244029474252,
|
||
|
|
"loss": 5.6598,
|
||
|
|
"mean_token_accuracy": 0.14963865131139756,
|
||
|
|
"num_tokens": 5393682.0,
|
||
|
|
"step": 2395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.943587112426758,
|
||
|
|
"epoch": 0.15834267994985815,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.00029875321999773684,
|
||
|
|
"loss": 5.767,
|
||
|
|
"mean_token_accuracy": 0.13558961153030397,
|
||
|
|
"num_tokens": 5406709.0,
|
||
|
|
"step": 2400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9357071876525875,
|
||
|
|
"epoch": 0.158672560533087,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.00029758138584152333,
|
||
|
|
"loss": 5.6921,
|
||
|
|
"mean_token_accuracy": 0.1386982724070549,
|
||
|
|
"num_tokens": 5418103.0,
|
||
|
|
"step": 2405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.99927339553833,
|
||
|
|
"epoch": 0.1590024411163159,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0002964089326052102,
|
||
|
|
"loss": 5.7388,
|
||
|
|
"mean_token_accuracy": 0.13509734869003295,
|
||
|
|
"num_tokens": 5428210.0,
|
||
|
|
"step": 2410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.922349071502685,
|
||
|
|
"epoch": 0.15933232169954475,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0002952358924321949,
|
||
|
|
"loss": 5.7079,
|
||
|
|
"mean_token_accuracy": 0.13836478739976882,
|
||
|
|
"num_tokens": 5440270.0,
|
||
|
|
"step": 2415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.979345512390137,
|
||
|
|
"epoch": 0.15966220228277364,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.00029406229748196657,
|
||
|
|
"loss": 5.6728,
|
||
|
|
"mean_token_accuracy": 0.14294909536838532,
|
||
|
|
"num_tokens": 5450757.0,
|
||
|
|
"step": 2420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.944041109085083,
|
||
|
|
"epoch": 0.1599920828660025,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0002928881799292235,
|
||
|
|
"loss": 5.711,
|
||
|
|
"mean_token_accuracy": 0.1462253138422966,
|
||
|
|
"num_tokens": 5461022.0,
|
||
|
|
"step": 2425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.969419050216675,
|
||
|
|
"epoch": 0.16032196344923139,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.00029171357196299154,
|
||
|
|
"loss": 5.6766,
|
||
|
|
"mean_token_accuracy": 0.13884125649929047,
|
||
|
|
"num_tokens": 5472135.0,
|
||
|
|
"step": 2430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9739738464355465,
|
||
|
|
"epoch": 0.16065184403246024,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0002905385057857414,
|
||
|
|
"loss": 5.7457,
|
||
|
|
"mean_token_accuracy": 0.13374390602111816,
|
||
|
|
"num_tokens": 5483948.0,
|
||
|
|
"step": 2435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.006627130508423,
|
||
|
|
"epoch": 0.16098172461568913,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0002893630136125058,
|
||
|
|
"loss": 5.7302,
|
||
|
|
"mean_token_accuracy": 0.13958463966846466,
|
||
|
|
"num_tokens": 5495668.0,
|
||
|
|
"step": 2440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.973841428756714,
|
||
|
|
"epoch": 0.161311605198918,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0002881871276699967,
|
||
|
|
"loss": 5.7866,
|
||
|
|
"mean_token_accuracy": 0.13569992035627365,
|
||
|
|
"num_tokens": 5506798.0,
|
||
|
|
"step": 2445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.966570329666138,
|
||
|
|
"epoch": 0.16164148578214688,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00028701088019572114,
|
||
|
|
"loss": 5.6757,
|
||
|
|
"mean_token_accuracy": 0.14030151069164276,
|
||
|
|
"num_tokens": 5516519.0,
|
||
|
|
"step": 2450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.879304504394531,
|
||
|
|
"epoch": 0.16197136636537574,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0002858343034370977,
|
||
|
|
"loss": 5.5763,
|
||
|
|
"mean_token_accuracy": 0.14370452463626862,
|
||
|
|
"num_tokens": 5526177.0,
|
||
|
|
"step": 2455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.936300039291382,
|
||
|
|
"epoch": 0.1623012469486046,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.00028465742965057267,
|
||
|
|
"loss": 5.7663,
|
||
|
|
"mean_token_accuracy": 0.1424056202173233,
|
||
|
|
"num_tokens": 5538006.0,
|
||
|
|
"step": 2460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.979116535186767,
|
||
|
|
"epoch": 0.16263112753183348,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00028348029110073533,
|
||
|
|
"loss": 5.6799,
|
||
|
|
"mean_token_accuracy": 0.14178653806447983,
|
||
|
|
"num_tokens": 5548270.0,
|
||
|
|
"step": 2465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9398942470550535,
|
||
|
|
"epoch": 0.16296100811506234,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.00028230292005943365,
|
||
|
|
"loss": 5.7433,
|
||
|
|
"mean_token_accuracy": 0.14213079810142518,
|
||
|
|
"num_tokens": 5560101.0,
|
||
|
|
"step": 2470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.042861032485962,
|
||
|
|
"epoch": 0.16329088869829123,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00028112534880488945,
|
||
|
|
"loss": 5.7177,
|
||
|
|
"mean_token_accuracy": 0.13882540464401244,
|
||
|
|
"num_tokens": 5570572.0,
|
||
|
|
"step": 2475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0429705619812015,
|
||
|
|
"epoch": 0.16362076928152008,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0002799476096208137,
|
||
|
|
"loss": 5.7364,
|
||
|
|
"mean_token_accuracy": 0.14288759976625443,
|
||
|
|
"num_tokens": 5581067.0,
|
||
|
|
"step": 2480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.911858415603637,
|
||
|
|
"epoch": 0.16395064986474897,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00027876973479552087,
|
||
|
|
"loss": 5.6209,
|
||
|
|
"mean_token_accuracy": 0.13597656562924385,
|
||
|
|
"num_tokens": 5591818.0,
|
||
|
|
"step": 2485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.848461866378784,
|
||
|
|
"epoch": 0.16428053044797783,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.00027759175662104424,
|
||
|
|
"loss": 5.6971,
|
||
|
|
"mean_token_accuracy": 0.14237040653824806,
|
||
|
|
"num_tokens": 5604533.0,
|
||
|
|
"step": 2490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.00955638885498,
|
||
|
|
"epoch": 0.16461041103120672,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0002764137073922508,
|
||
|
|
"loss": 5.7646,
|
||
|
|
"mean_token_accuracy": 0.13329966589808465,
|
||
|
|
"num_tokens": 5615379.0,
|
||
|
|
"step": 2495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.005825424194336,
|
||
|
|
"epoch": 0.16494029161443557,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.00027523561940595505,
|
||
|
|
"loss": 5.6881,
|
||
|
|
"mean_token_accuracy": 0.14149803146719933,
|
||
|
|
"num_tokens": 5627467.0,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.970895290374756,
|
||
|
|
"epoch": 0.16527017219766443,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0002740575249600342,
|
||
|
|
"loss": 5.7826,
|
||
|
|
"mean_token_accuracy": 0.13751427754759787,
|
||
|
|
"num_tokens": 5639177.0,
|
||
|
|
"step": 2505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.945276689529419,
|
||
|
|
"epoch": 0.16560005278089332,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.00027287945635254263,
|
||
|
|
"loss": 5.6966,
|
||
|
|
"mean_token_accuracy": 0.13551856055855752,
|
||
|
|
"num_tokens": 5651465.0,
|
||
|
|
"step": 2510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.928407669067383,
|
||
|
|
"epoch": 0.16592993336412218,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00027170144588082635,
|
||
|
|
"loss": 5.693,
|
||
|
|
"mean_token_accuracy": 0.14488657414913178,
|
||
|
|
"num_tokens": 5662940.0,
|
||
|
|
"step": 2515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.005222463607788,
|
||
|
|
"epoch": 0.16625981394735106,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.00027052352584063763,
|
||
|
|
"loss": 5.7156,
|
||
|
|
"mean_token_accuracy": 0.1372163861989975,
|
||
|
|
"num_tokens": 5674774.0,
|
||
|
|
"step": 2520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.916850662231445,
|
||
|
|
"epoch": 0.16658969453057992,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00026934572852524907,
|
||
|
|
"loss": 5.6283,
|
||
|
|
"mean_token_accuracy": 0.14093754664063454,
|
||
|
|
"num_tokens": 5686838.0,
|
||
|
|
"step": 2525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.88103404045105,
|
||
|
|
"epoch": 0.1669195751138088,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00026816808622456937,
|
||
|
|
"loss": 5.6563,
|
||
|
|
"mean_token_accuracy": 0.1439339816570282,
|
||
|
|
"num_tokens": 5697711.0,
|
||
|
|
"step": 2530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9629110336303714,
|
||
|
|
"epoch": 0.16724945569703767,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0002669906312242569,
|
||
|
|
"loss": 5.6787,
|
||
|
|
"mean_token_accuracy": 0.1483391985297203,
|
||
|
|
"num_tokens": 5708627.0,
|
||
|
|
"step": 2535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.918844413757324,
|
||
|
|
"epoch": 0.16757933628026656,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.00026581339580483525,
|
||
|
|
"loss": 5.764,
|
||
|
|
"mean_token_accuracy": 0.14220132678747177,
|
||
|
|
"num_tokens": 5719822.0,
|
||
|
|
"step": 2540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.980520582199096,
|
||
|
|
"epoch": 0.16790921686349541,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0002646364122408082,
|
||
|
|
"loss": 5.6431,
|
||
|
|
"mean_token_accuracy": 0.14504677653312684,
|
||
|
|
"num_tokens": 5730392.0,
|
||
|
|
"step": 2545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.019266414642334,
|
||
|
|
"epoch": 0.16823909744672427,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0002634597127997749,
|
||
|
|
"loss": 5.7094,
|
||
|
|
"mean_token_accuracy": 0.14131525456905364,
|
||
|
|
"num_tokens": 5742923.0,
|
||
|
|
"step": 2550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.924505949020386,
|
||
|
|
"epoch": 0.16856897802995316,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0002622833297415445,
|
||
|
|
"loss": 5.7103,
|
||
|
|
"mean_token_accuracy": 0.14125737696886062,
|
||
|
|
"num_tokens": 5753787.0,
|
||
|
|
"step": 2555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.921623563766479,
|
||
|
|
"epoch": 0.16889885861318202,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0002611072953172531,
|
||
|
|
"loss": 5.672,
|
||
|
|
"mean_token_accuracy": 0.14091814309358597,
|
||
|
|
"num_tokens": 5766449.0,
|
||
|
|
"step": 2560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.927491331100464,
|
||
|
|
"epoch": 0.1692287391964109,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.00025993164176847845,
|
||
|
|
"loss": 5.6475,
|
||
|
|
"mean_token_accuracy": 0.14647908508777618,
|
||
|
|
"num_tokens": 5779102.0,
|
||
|
|
"step": 2565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.988221931457519,
|
||
|
|
"epoch": 0.16955861977963976,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0002587564013263564,
|
||
|
|
"loss": 5.7551,
|
||
|
|
"mean_token_accuracy": 0.13622020855545997,
|
||
|
|
"num_tokens": 5790072.0,
|
||
|
|
"step": 2570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9031391620635985,
|
||
|
|
"epoch": 0.16988850036286865,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0002575816062106974,
|
||
|
|
"loss": 5.644,
|
||
|
|
"mean_token_accuracy": 0.14085342809557916,
|
||
|
|
"num_tokens": 5800896.0,
|
||
|
|
"step": 2575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.913019132614136,
|
||
|
|
"epoch": 0.1702183809460975,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00025640728862910293,
|
||
|
|
"loss": 5.7345,
|
||
|
|
"mean_token_accuracy": 0.14141321703791618,
|
||
|
|
"num_tokens": 5811897.0,
|
||
|
|
"step": 2580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.969927263259888,
|
||
|
|
"epoch": 0.1705482615293264,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.00025523348077608285,
|
||
|
|
"loss": 5.6883,
|
||
|
|
"mean_token_accuracy": 0.1466064840555191,
|
||
|
|
"num_tokens": 5823999.0,
|
||
|
|
"step": 2585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9573136329650875,
|
||
|
|
"epoch": 0.17087814211255525,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00025406021483217225,
|
||
|
|
"loss": 5.7232,
|
||
|
|
"mean_token_accuracy": 0.1421687975525856,
|
||
|
|
"num_tokens": 5836490.0,
|
||
|
|
"step": 2590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.948178720474243,
|
||
|
|
"epoch": 0.17120802269578414,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00025288752296304963,
|
||
|
|
"loss": 5.6773,
|
||
|
|
"mean_token_accuracy": 0.14576417207717896,
|
||
|
|
"num_tokens": 5847674.0,
|
||
|
|
"step": 2595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9269232749938965,
|
||
|
|
"epoch": 0.171537903279013,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000251715437318655,
|
||
|
|
"loss": 5.6193,
|
||
|
|
"mean_token_accuracy": 0.1481877937912941,
|
||
|
|
"num_tokens": 5858585.0,
|
||
|
|
"step": 2600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9234230518341064,
|
||
|
|
"epoch": 0.17186778386224186,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0002505439900323084,
|
||
|
|
"loss": 5.6047,
|
||
|
|
"mean_token_accuracy": 0.14109234884381294,
|
||
|
|
"num_tokens": 5868679.0,
|
||
|
|
"step": 2605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9644920349121096,
|
||
|
|
"epoch": 0.17219766444547074,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00024937321321982894,
|
||
|
|
"loss": 5.7521,
|
||
|
|
"mean_token_accuracy": 0.13143511787056922,
|
||
|
|
"num_tokens": 5879662.0,
|
||
|
|
"step": 2610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.907003784179688,
|
||
|
|
"epoch": 0.1725275450286996,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00024820313897865433,
|
||
|
|
"loss": 5.6976,
|
||
|
|
"mean_token_accuracy": 0.1399913303554058,
|
||
|
|
"num_tokens": 5891948.0,
|
||
|
|
"step": 2615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.99510760307312,
|
||
|
|
"epoch": 0.1728574256119285,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00024703379938696105,
|
||
|
|
"loss": 5.6088,
|
||
|
|
"mean_token_accuracy": 0.14399268627166747,
|
||
|
|
"num_tokens": 5902994.0,
|
||
|
|
"step": 2620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.943341398239136,
|
||
|
|
"epoch": 0.17318730619515735,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00024586522650278447,
|
||
|
|
"loss": 5.6756,
|
||
|
|
"mean_token_accuracy": 0.13893972635269164,
|
||
|
|
"num_tokens": 5913708.0,
|
||
|
|
"step": 2625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.891685914993286,
|
||
|
|
"epoch": 0.17351718677838623,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.00024469745236314064,
|
||
|
|
"loss": 5.7092,
|
||
|
|
"mean_token_accuracy": 0.14240608364343643,
|
||
|
|
"num_tokens": 5926093.0,
|
||
|
|
"step": 2630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.906329727172851,
|
||
|
|
"epoch": 0.1738470673616151,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.00024353050898314767,
|
||
|
|
"loss": 5.6651,
|
||
|
|
"mean_token_accuracy": 0.14397929310798646,
|
||
|
|
"num_tokens": 5936664.0,
|
||
|
|
"step": 2635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.942281103134155,
|
||
|
|
"epoch": 0.17417694794484398,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00024236442835514743,
|
||
|
|
"loss": 5.636,
|
||
|
|
"mean_token_accuracy": 0.14072627127170562,
|
||
|
|
"num_tokens": 5946713.0,
|
||
|
|
"step": 2640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.002525758743286,
|
||
|
|
"epoch": 0.17450682852807284,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00024119924244782965,
|
||
|
|
"loss": 5.7382,
|
||
|
|
"mean_token_accuracy": 0.1348221018910408,
|
||
|
|
"num_tokens": 5957671.0,
|
||
|
|
"step": 2645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.944177579879761,
|
||
|
|
"epoch": 0.1748367091113017,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00024003498320535462,
|
||
|
|
"loss": 5.6241,
|
||
|
|
"mean_token_accuracy": 0.14416669309139252,
|
||
|
|
"num_tokens": 5967555.0,
|
||
|
|
"step": 2650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.970792293548584,
|
||
|
|
"epoch": 0.17516658969453058,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.00023887168254647727,
|
||
|
|
"loss": 5.7316,
|
||
|
|
"mean_token_accuracy": 0.14033383131027222,
|
||
|
|
"num_tokens": 5979210.0,
|
||
|
|
"step": 2655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9564353942871096,
|
||
|
|
"epoch": 0.17549647027775944,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00023770937236367308,
|
||
|
|
"loss": 5.6816,
|
||
|
|
"mean_token_accuracy": 0.13913488686084746,
|
||
|
|
"num_tokens": 5990501.0,
|
||
|
|
"step": 2660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.916724109649659,
|
||
|
|
"epoch": 0.17582635086098833,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00023654808452226278,
|
||
|
|
"loss": 5.7497,
|
||
|
|
"mean_token_accuracy": 0.13746197149157524,
|
||
|
|
"num_tokens": 6003520.0,
|
||
|
|
"step": 2665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9751975536346436,
|
||
|
|
"epoch": 0.1761562314442172,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00023538785085953912,
|
||
|
|
"loss": 5.7253,
|
||
|
|
"mean_token_accuracy": 0.1436193160712719,
|
||
|
|
"num_tokens": 6013404.0,
|
||
|
|
"step": 2670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.90507869720459,
|
||
|
|
"epoch": 0.17648611202744607,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00023422870318389404,
|
||
|
|
"loss": 5.5561,
|
||
|
|
"mean_token_accuracy": 0.1554765984416008,
|
||
|
|
"num_tokens": 6024275.0,
|
||
|
|
"step": 2675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.944999074935913,
|
||
|
|
"epoch": 0.17681599261067493,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0002330706732739468,
|
||
|
|
"loss": 5.6921,
|
||
|
|
"mean_token_accuracy": 0.14285095930099487,
|
||
|
|
"num_tokens": 6036693.0,
|
||
|
|
"step": 2680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9724428176879885,
|
||
|
|
"epoch": 0.17714587319390382,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00023191379287767211,
|
||
|
|
"loss": 5.6804,
|
||
|
|
"mean_token_accuracy": 0.1420604482293129,
|
||
|
|
"num_tokens": 6046984.0,
|
||
|
|
"step": 2685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.096405506134033,
|
||
|
|
"epoch": 0.17747575377713268,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0002307580937115305,
|
||
|
|
"loss": 5.8265,
|
||
|
|
"mean_token_accuracy": 0.13556594848632814,
|
||
|
|
"num_tokens": 6059435.0,
|
||
|
|
"step": 2690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.985703706741333,
|
||
|
|
"epoch": 0.17780563436036154,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00022960360745959846,
|
||
|
|
"loss": 5.5735,
|
||
|
|
"mean_token_accuracy": 0.14474853575229646,
|
||
|
|
"num_tokens": 6069800.0,
|
||
|
|
"step": 2695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9838399410247805,
|
||
|
|
"epoch": 0.17813551494359042,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.00022845036577269972,
|
||
|
|
"loss": 5.7525,
|
||
|
|
"mean_token_accuracy": 0.1397376090288162,
|
||
|
|
"num_tokens": 6081438.0,
|
||
|
|
"step": 2700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.95524525642395,
|
||
|
|
"epoch": 0.17846539552681928,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00022729840026753777,
|
||
|
|
"loss": 5.755,
|
||
|
|
"mean_token_accuracy": 0.1396619848906994,
|
||
|
|
"num_tokens": 6094507.0,
|
||
|
|
"step": 2705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.98814287185669,
|
||
|
|
"epoch": 0.17879527611004817,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0002261477425258287,
|
||
|
|
"loss": 5.6631,
|
||
|
|
"mean_token_accuracy": 0.14468785226345063,
|
||
|
|
"num_tokens": 6104406.0,
|
||
|
|
"step": 2710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.910196542739868,
|
||
|
|
"epoch": 0.17912515669327703,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0002249984240934358,
|
||
|
|
"loss": 5.7207,
|
||
|
|
"mean_token_accuracy": 0.13494618535041808,
|
||
|
|
"num_tokens": 6116970.0,
|
||
|
|
"step": 2715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9692315578460695,
|
||
|
|
"epoch": 0.1794550372765059,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.00022385047647950464,
|
||
|
|
"loss": 5.7061,
|
||
|
|
"mean_token_accuracy": 0.13399825170636176,
|
||
|
|
"num_tokens": 6127418.0,
|
||
|
|
"step": 2720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.93900351524353,
|
||
|
|
"epoch": 0.17978491785973477,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0002227039311555986,
|
||
|
|
"loss": 5.6411,
|
||
|
|
"mean_token_accuracy": 0.1496211126446724,
|
||
|
|
"num_tokens": 6138575.0,
|
||
|
|
"step": 2725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.990826797485352,
|
||
|
|
"epoch": 0.18011479844296366,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0002215588195548372,
|
||
|
|
"loss": 5.7249,
|
||
|
|
"mean_token_accuracy": 0.13931261524558067,
|
||
|
|
"num_tokens": 6148888.0,
|
||
|
|
"step": 2730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8738728046417235,
|
||
|
|
"epoch": 0.18044467902619252,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.00022041517307103337,
|
||
|
|
"loss": 5.629,
|
||
|
|
"mean_token_accuracy": 0.14270053207874298,
|
||
|
|
"num_tokens": 6160482.0,
|
||
|
|
"step": 2735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.943509769439697,
|
||
|
|
"epoch": 0.18077455960942138,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0002192730230578331,
|
||
|
|
"loss": 5.6295,
|
||
|
|
"mean_token_accuracy": 0.13954010009765624,
|
||
|
|
"num_tokens": 6172290.0,
|
||
|
|
"step": 2740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9307451248168945,
|
||
|
|
"epoch": 0.18110444019265026,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.0002181324008278559,
|
||
|
|
"loss": 5.6948,
|
||
|
|
"mean_token_accuracy": 0.14874305874109267,
|
||
|
|
"num_tokens": 6183144.0,
|
||
|
|
"step": 2745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.891363286972046,
|
||
|
|
"epoch": 0.18143432077587912,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00021699333765183655,
|
||
|
|
"loss": 5.6871,
|
||
|
|
"mean_token_accuracy": 0.14649532735347748,
|
||
|
|
"num_tokens": 6193976.0,
|
||
|
|
"step": 2750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9374219417572025,
|
||
|
|
"epoch": 0.181764201359108,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0002158558647577673,
|
||
|
|
"loss": 5.6161,
|
||
|
|
"mean_token_accuracy": 0.14469706416130065,
|
||
|
|
"num_tokens": 6203953.0,
|
||
|
|
"step": 2755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.868966865539551,
|
||
|
|
"epoch": 0.18209408194233687,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.00021472001333004215,
|
||
|
|
"loss": 5.5935,
|
||
|
|
"mean_token_accuracy": 0.14960595667362214,
|
||
|
|
"num_tokens": 6214858.0,
|
||
|
|
"step": 2760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.974717521667481,
|
||
|
|
"epoch": 0.18242396252556575,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.00021358581450860186,
|
||
|
|
"loss": 5.6986,
|
||
|
|
"mean_token_accuracy": 0.15034186020493506,
|
||
|
|
"num_tokens": 6225934.0,
|
||
|
|
"step": 2765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.942675685882568,
|
||
|
|
"epoch": 0.1827538431087946,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0002124532993880799,
|
||
|
|
"loss": 5.686,
|
||
|
|
"mean_token_accuracy": 0.1463989183306694,
|
||
|
|
"num_tokens": 6237381.0,
|
||
|
|
"step": 2770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.987509298324585,
|
||
|
|
"epoch": 0.1830837236920235,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.00021132249901695044,
|
||
|
|
"loss": 5.7483,
|
||
|
|
"mean_token_accuracy": 0.13539374321699144,
|
||
|
|
"num_tokens": 6250303.0,
|
||
|
|
"step": 2775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.957989025115967,
|
||
|
|
"epoch": 0.18341360427525236,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.00021019344439667705,
|
||
|
|
"loss": 5.618,
|
||
|
|
"mean_token_accuracy": 0.14666351974010466,
|
||
|
|
"num_tokens": 6261840.0,
|
||
|
|
"step": 2780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.011433029174805,
|
||
|
|
"epoch": 0.18374348485848124,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00020906616648086213,
|
||
|
|
"loss": 5.748,
|
||
|
|
"mean_token_accuracy": 0.13503013625741006,
|
||
|
|
"num_tokens": 6273598.0,
|
||
|
|
"step": 2785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.949694967269897,
|
||
|
|
"epoch": 0.1840733654417101,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00020794069617439942,
|
||
|
|
"loss": 5.6412,
|
||
|
|
"mean_token_accuracy": 0.15156308114528655,
|
||
|
|
"num_tokens": 6284449.0,
|
||
|
|
"step": 2790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.960120677947998,
|
||
|
|
"epoch": 0.18440324602493896,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00020681706433262593,
|
||
|
|
"loss": 5.7501,
|
||
|
|
"mean_token_accuracy": 0.1441426917910576,
|
||
|
|
"num_tokens": 6297659.0,
|
||
|
|
"step": 2795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9029364585876465,
|
||
|
|
"epoch": 0.18473312660816785,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00020569530176047602,
|
||
|
|
"loss": 5.6721,
|
||
|
|
"mean_token_accuracy": 0.14518202245235443,
|
||
|
|
"num_tokens": 6309173.0,
|
||
|
|
"step": 2800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9200451374053955,
|
||
|
|
"epoch": 0.1850630071913967,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0002045754392116374,
|
||
|
|
"loss": 5.5883,
|
||
|
|
"mean_token_accuracy": 0.14563190713524818,
|
||
|
|
"num_tokens": 6320819.0,
|
||
|
|
"step": 2805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.893794679641724,
|
||
|
|
"epoch": 0.1853928877746256,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.00020345750738770757,
|
||
|
|
"loss": 5.5815,
|
||
|
|
"mean_token_accuracy": 0.14634376019239426,
|
||
|
|
"num_tokens": 6333224.0,
|
||
|
|
"step": 2810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.919555425643921,
|
||
|
|
"epoch": 0.18572276835785445,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00020234153693735214,
|
||
|
|
"loss": 5.6035,
|
||
|
|
"mean_token_accuracy": 0.14678714871406556,
|
||
|
|
"num_tokens": 6343603.0,
|
||
|
|
"step": 2815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.855648612976074,
|
||
|
|
"epoch": 0.18605264894108334,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0002012275584554647,
|
||
|
|
"loss": 5.551,
|
||
|
|
"mean_token_accuracy": 0.15018419325351715,
|
||
|
|
"num_tokens": 6354478.0,
|
||
|
|
"step": 2820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.865906476974487,
|
||
|
|
"epoch": 0.1863825295243122,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00020011560248232803,
|
||
|
|
"loss": 5.6023,
|
||
|
|
"mean_token_accuracy": 0.14977008551359178,
|
||
|
|
"num_tokens": 6364947.0,
|
||
|
|
"step": 2825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.92622742652893,
|
||
|
|
"epoch": 0.18671241010754108,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00019900569950277692,
|
||
|
|
"loss": 5.6129,
|
||
|
|
"mean_token_accuracy": 0.14615447223186492,
|
||
|
|
"num_tokens": 6377153.0,
|
||
|
|
"step": 2830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9444808006286625,
|
||
|
|
"epoch": 0.18704229069076994,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00019789787994536228,
|
||
|
|
"loss": 5.8004,
|
||
|
|
"mean_token_accuracy": 0.13469668328762055,
|
||
|
|
"num_tokens": 6389476.0,
|
||
|
|
"step": 2835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.99590048789978,
|
||
|
|
"epoch": 0.1873721712739988,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00019679217418151667,
|
||
|
|
"loss": 5.7321,
|
||
|
|
"mean_token_accuracy": 0.1374764196574688,
|
||
|
|
"num_tokens": 6401723.0,
|
||
|
|
"step": 2840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9844255447387695,
|
||
|
|
"epoch": 0.1877020518572277,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00019568861252472236,
|
||
|
|
"loss": 5.584,
|
||
|
|
"mean_token_accuracy": 0.14757253751158714,
|
||
|
|
"num_tokens": 6411224.0,
|
||
|
|
"step": 2845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.976707649230957,
|
||
|
|
"epoch": 0.18803193244045655,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00019458722522967952,
|
||
|
|
"loss": 5.7056,
|
||
|
|
"mean_token_accuracy": 0.13817794024944305,
|
||
|
|
"num_tokens": 6422281.0,
|
||
|
|
"step": 2850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.948973989486694,
|
||
|
|
"epoch": 0.18836181302368543,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00019348804249147723,
|
||
|
|
"loss": 5.6386,
|
||
|
|
"mean_token_accuracy": 0.14388069361448289,
|
||
|
|
"num_tokens": 6432698.0,
|
||
|
|
"step": 2855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.943766403198242,
|
||
|
|
"epoch": 0.1886916936069143,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0001923910944447655,
|
||
|
|
"loss": 5.5526,
|
||
|
|
"mean_token_accuracy": 0.14603390768170357,
|
||
|
|
"num_tokens": 6442626.0,
|
||
|
|
"step": 2860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.883777809143067,
|
||
|
|
"epoch": 0.18902157419014318,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00019129641116292928,
|
||
|
|
"loss": 5.6112,
|
||
|
|
"mean_token_accuracy": 0.14786824882030486,
|
||
|
|
"num_tokens": 6454868.0,
|
||
|
|
"step": 2865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.90051965713501,
|
||
|
|
"epoch": 0.18935145477337204,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00019020402265726343,
|
||
|
|
"loss": 5.6609,
|
||
|
|
"mean_token_accuracy": 0.14203333109617233,
|
||
|
|
"num_tokens": 6467088.0,
|
||
|
|
"step": 2870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9010449886322025,
|
||
|
|
"epoch": 0.18968133535660092,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0001891139588761509,
|
||
|
|
"loss": 5.5919,
|
||
|
|
"mean_token_accuracy": 0.1448397234082222,
|
||
|
|
"num_tokens": 6477767.0,
|
||
|
|
"step": 2875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.94102783203125,
|
||
|
|
"epoch": 0.19001121593982978,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00018802624970424076,
|
||
|
|
"loss": 5.6538,
|
||
|
|
"mean_token_accuracy": 0.14244230836629868,
|
||
|
|
"num_tokens": 6488815.0,
|
||
|
|
"step": 2880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.871285486221313,
|
||
|
|
"epoch": 0.19034109652305864,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.00018694092496162945,
|
||
|
|
"loss": 5.5211,
|
||
|
|
"mean_token_accuracy": 0.14842878729104997,
|
||
|
|
"num_tokens": 6499928.0,
|
||
|
|
"step": 2885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.910442543029785,
|
||
|
|
"epoch": 0.19067097710628753,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00018585801440304306,
|
||
|
|
"loss": 5.649,
|
||
|
|
"mean_token_accuracy": 0.14074429944157602,
|
||
|
|
"num_tokens": 6510164.0,
|
||
|
|
"step": 2890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.965809154510498,
|
||
|
|
"epoch": 0.19100085768951638,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.00018477754771702165,
|
||
|
|
"loss": 5.6869,
|
||
|
|
"mean_token_accuracy": 0.14213037192821504,
|
||
|
|
"num_tokens": 6521088.0,
|
||
|
|
"step": 2895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.895754671096801,
|
||
|
|
"epoch": 0.19133073827274527,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00018369955452510506,
|
||
|
|
"loss": 5.6016,
|
||
|
|
"mean_token_accuracy": 0.15054157227277756,
|
||
|
|
"num_tokens": 6531481.0,
|
||
|
|
"step": 2900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.982218790054321,
|
||
|
|
"epoch": 0.19166061885597413,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0001826240643810212,
|
||
|
|
"loss": 5.6079,
|
||
|
|
"mean_token_accuracy": 0.1519411064684391,
|
||
|
|
"num_tokens": 6541548.0,
|
||
|
|
"step": 2905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.944736194610596,
|
||
|
|
"epoch": 0.19199049943920302,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0001815511067698758,
|
||
|
|
"loss": 5.752,
|
||
|
|
"mean_token_accuracy": 0.14090781956911086,
|
||
|
|
"num_tokens": 6553587.0,
|
||
|
|
"step": 2910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.937925195693969,
|
||
|
|
"epoch": 0.19232038002243187,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0001804807111073436,
|
||
|
|
"loss": 5.6054,
|
||
|
|
"mean_token_accuracy": 0.14230228438973427,
|
||
|
|
"num_tokens": 6565321.0,
|
||
|
|
"step": 2915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.920470905303955,
|
||
|
|
"epoch": 0.19265026060566076,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0001794129067388625,
|
||
|
|
"loss": 5.5536,
|
||
|
|
"mean_token_accuracy": 0.15099060237407685,
|
||
|
|
"num_tokens": 6576844.0,
|
||
|
|
"step": 2920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9754081726074215,
|
||
|
|
"epoch": 0.19298014118888962,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.00017834772293882868,
|
||
|
|
"loss": 5.6913,
|
||
|
|
"mean_token_accuracy": 0.14374057054519654,
|
||
|
|
"num_tokens": 6588455.0,
|
||
|
|
"step": 2925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.953689050674439,
|
||
|
|
"epoch": 0.1933100217721185,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000177285188909794,
|
||
|
|
"loss": 5.7106,
|
||
|
|
"mean_token_accuracy": 0.14074183255434036,
|
||
|
|
"num_tokens": 6599408.0,
|
||
|
|
"step": 2930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.898287439346314,
|
||
|
|
"epoch": 0.19363990235534737,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0001762253337816656,
|
||
|
|
"loss": 5.6004,
|
||
|
|
"mean_token_accuracy": 0.1480652391910553,
|
||
|
|
"num_tokens": 6610208.0,
|
||
|
|
"step": 2935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.894304513931274,
|
||
|
|
"epoch": 0.19396978293857622,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00017516818661090738,
|
||
|
|
"loss": 5.5487,
|
||
|
|
"mean_token_accuracy": 0.14810549467802048,
|
||
|
|
"num_tokens": 6620762.0,
|
||
|
|
"step": 2940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.898684692382813,
|
||
|
|
"epoch": 0.1942996635218051,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0001741137763797428,
|
||
|
|
"loss": 5.5613,
|
||
|
|
"mean_token_accuracy": 0.14752606004476548,
|
||
|
|
"num_tokens": 6633051.0,
|
||
|
|
"step": 2945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8875751972198485,
|
||
|
|
"epoch": 0.19462954410503397,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00017306213199536115,
|
||
|
|
"loss": 5.6154,
|
||
|
|
"mean_token_accuracy": 0.14497639536857604,
|
||
|
|
"num_tokens": 6643665.0,
|
||
|
|
"step": 2950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.892143249511719,
|
||
|
|
"epoch": 0.19495942468826286,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0001720132822891243,
|
||
|
|
"loss": 5.5554,
|
||
|
|
"mean_token_accuracy": 0.1472393974661827,
|
||
|
|
"num_tokens": 6654814.0,
|
||
|
|
"step": 2955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.934198999404908,
|
||
|
|
"epoch": 0.19528930527149171,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0001709672560157769,
|
||
|
|
"loss": 5.5671,
|
||
|
|
"mean_token_accuracy": 0.15178595781326293,
|
||
|
|
"num_tokens": 6665865.0,
|
||
|
|
"step": 2960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.978811454772949,
|
||
|
|
"epoch": 0.1956191858547206,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.00016992408185265758,
|
||
|
|
"loss": 5.6294,
|
||
|
|
"mean_token_accuracy": 0.14344705939292907,
|
||
|
|
"num_tokens": 6676980.0,
|
||
|
|
"step": 2965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.906698322296142,
|
||
|
|
"epoch": 0.19594906643794946,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00016888378839891298,
|
||
|
|
"loss": 5.5682,
|
||
|
|
"mean_token_accuracy": 0.15274428576231003,
|
||
|
|
"num_tokens": 6688301.0,
|
||
|
|
"step": 2970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.871945238113403,
|
||
|
|
"epoch": 0.19627894702117835,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0001678464041747137,
|
||
|
|
"loss": 5.5877,
|
||
|
|
"mean_token_accuracy": 0.1440347522497177,
|
||
|
|
"num_tokens": 6699076.0,
|
||
|
|
"step": 2975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.952255010604858,
|
||
|
|
"epoch": 0.1966088276044072,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.00016681195762047223,
|
||
|
|
"loss": 5.7032,
|
||
|
|
"mean_token_accuracy": 0.13876561149954797,
|
||
|
|
"num_tokens": 6711229.0,
|
||
|
|
"step": 2980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.967507553100586,
|
||
|
|
"epoch": 0.19693870818763606,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00016578047709606337,
|
||
|
|
"loss": 5.6068,
|
||
|
|
"mean_token_accuracy": 0.14666555374860762,
|
||
|
|
"num_tokens": 6723384.0,
|
||
|
|
"step": 2985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.963400077819824,
|
||
|
|
"epoch": 0.19726858877086495,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.00016475199088004678,
|
||
|
|
"loss": 5.6425,
|
||
|
|
"mean_token_accuracy": 0.14739813208580016,
|
||
|
|
"num_tokens": 6735310.0,
|
||
|
|
"step": 2990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.871047449111939,
|
||
|
|
"epoch": 0.1975984693540938,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00016372652716889163,
|
||
|
|
"loss": 5.5903,
|
||
|
|
"mean_token_accuracy": 0.1471934512257576,
|
||
|
|
"num_tokens": 6745268.0,
|
||
|
|
"step": 2995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.90426082611084,
|
||
|
|
"epoch": 0.1979283499373227,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0001627041140762035,
|
||
|
|
"loss": 5.6573,
|
||
|
|
"mean_token_accuracy": 0.14316656887531282,
|
||
|
|
"num_tokens": 6755062.0,
|
||
|
|
"step": 3000
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 4000,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 1,
|
||
|
|
"save_steps": 500,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 1676549941493760.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|