4079 lines
110 KiB
JSON
4079 lines
110 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 2.016137165910237,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 2000,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 10.742588329315186,
|
||
|
|
"epoch": 0.005042864346949067,
|
||
|
|
"grad_norm": 4.78125,
|
||
|
|
"learning_rate": 2e-06,
|
||
|
|
"loss": 10.7888,
|
||
|
|
"mean_token_accuracy": 6.958942394703626e-05,
|
||
|
|
"num_tokens": 11445.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742593383789062,
|
||
|
|
"epoch": 0.010085728693898134,
|
||
|
|
"grad_norm": 5.25,
|
||
|
|
"learning_rate": 4.5e-06,
|
||
|
|
"loss": 10.7696,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 22095.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742596626281738,
|
||
|
|
"epoch": 0.015128593040847202,
|
||
|
|
"grad_norm": 4.5625,
|
||
|
|
"learning_rate": 7e-06,
|
||
|
|
"loss": 10.7579,
|
||
|
|
"mean_token_accuracy": 0.00017376195173710585,
|
||
|
|
"num_tokens": 33847.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742617321014404,
|
||
|
|
"epoch": 0.020171457387796268,
|
||
|
|
"grad_norm": 4.53125,
|
||
|
|
"learning_rate": 9.5e-06,
|
||
|
|
"loss": 10.7022,
|
||
|
|
"mean_token_accuracy": 0.0003061072085984051,
|
||
|
|
"num_tokens": 44495.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742618179321289,
|
||
|
|
"epoch": 0.025214321734745335,
|
||
|
|
"grad_norm": 4.0625,
|
||
|
|
"learning_rate": 1.2e-05,
|
||
|
|
"loss": 10.6161,
|
||
|
|
"mean_token_accuracy": 0.0038310963835101576,
|
||
|
|
"num_tokens": 55298.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742384719848634,
|
||
|
|
"epoch": 0.030257186081694403,
|
||
|
|
"grad_norm": 3.859375,
|
||
|
|
"learning_rate": 1.4500000000000002e-05,
|
||
|
|
"loss": 10.4928,
|
||
|
|
"mean_token_accuracy": 0.023839639127254487,
|
||
|
|
"num_tokens": 66391.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.741421985626221,
|
||
|
|
"epoch": 0.03530005042864347,
|
||
|
|
"grad_norm": 3.125,
|
||
|
|
"learning_rate": 1.7000000000000003e-05,
|
||
|
|
"loss": 10.3446,
|
||
|
|
"mean_token_accuracy": 0.037043477036058904,
|
||
|
|
"num_tokens": 77624.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.738873195648193,
|
||
|
|
"epoch": 0.040342914775592535,
|
||
|
|
"grad_norm": 2.578125,
|
||
|
|
"learning_rate": 1.95e-05,
|
||
|
|
"loss": 10.2004,
|
||
|
|
"mean_token_accuracy": 0.04290186390280724,
|
||
|
|
"num_tokens": 89426.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.734352970123291,
|
||
|
|
"epoch": 0.0453857791225416,
|
||
|
|
"grad_norm": 2.1875,
|
||
|
|
"learning_rate": 2.2e-05,
|
||
|
|
"loss": 10.1008,
|
||
|
|
"mean_token_accuracy": 0.04177976287901401,
|
||
|
|
"num_tokens": 100252.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.731473350524903,
|
||
|
|
"epoch": 0.05042864346949067,
|
||
|
|
"grad_norm": 2.0625,
|
||
|
|
"learning_rate": 2.4500000000000003e-05,
|
||
|
|
"loss": 10.0294,
|
||
|
|
"mean_token_accuracy": 0.035502530820667746,
|
||
|
|
"num_tokens": 110578.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.731419467926026,
|
||
|
|
"epoch": 0.05547150781643974,
|
||
|
|
"grad_norm": 1.9453125,
|
||
|
|
"learning_rate": 2.7e-05,
|
||
|
|
"loss": 9.9893,
|
||
|
|
"mean_token_accuracy": 0.03719575461000204,
|
||
|
|
"num_tokens": 121631.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.730601024627685,
|
||
|
|
"epoch": 0.060514372163388806,
|
||
|
|
"grad_norm": 1.96875,
|
||
|
|
"learning_rate": 2.95e-05,
|
||
|
|
"loss": 9.9237,
|
||
|
|
"mean_token_accuracy": 0.043491701036691664,
|
||
|
|
"num_tokens": 134254.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.727654361724854,
|
||
|
|
"epoch": 0.06555723651033787,
|
||
|
|
"grad_norm": 1.734375,
|
||
|
|
"learning_rate": 3.2e-05,
|
||
|
|
"loss": 9.8843,
|
||
|
|
"mean_token_accuracy": 0.03803328052163124,
|
||
|
|
"num_tokens": 144928.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.724302101135255,
|
||
|
|
"epoch": 0.07060010085728693,
|
||
|
|
"grad_norm": 1.8203125,
|
||
|
|
"learning_rate": 3.4500000000000005e-05,
|
||
|
|
"loss": 9.7798,
|
||
|
|
"mean_token_accuracy": 0.039696192182600495,
|
||
|
|
"num_tokens": 155518.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.720338535308837,
|
||
|
|
"epoch": 0.07564296520423601,
|
||
|
|
"grad_norm": 1.9375,
|
||
|
|
"learning_rate": 3.7e-05,
|
||
|
|
"loss": 9.7038,
|
||
|
|
"mean_token_accuracy": 0.04226764794439077,
|
||
|
|
"num_tokens": 165850.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.71519594192505,
|
||
|
|
"epoch": 0.08068582955118507,
|
||
|
|
"grad_norm": 1.8828125,
|
||
|
|
"learning_rate": 3.95e-05,
|
||
|
|
"loss": 9.6932,
|
||
|
|
"mean_token_accuracy": 0.04092370942234993,
|
||
|
|
"num_tokens": 176787.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.709799861907959,
|
||
|
|
"epoch": 0.08572869389813415,
|
||
|
|
"grad_norm": 1.7578125,
|
||
|
|
"learning_rate": 4.2000000000000004e-05,
|
||
|
|
"loss": 9.6293,
|
||
|
|
"mean_token_accuracy": 0.03919961098581552,
|
||
|
|
"num_tokens": 188345.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.706261253356933,
|
||
|
|
"epoch": 0.0907715582450832,
|
||
|
|
"grad_norm": 1.78125,
|
||
|
|
"learning_rate": 4.45e-05,
|
||
|
|
"loss": 9.5833,
|
||
|
|
"mean_token_accuracy": 0.03263202589005232,
|
||
|
|
"num_tokens": 199315.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.702005004882812,
|
||
|
|
"epoch": 0.09581442259203228,
|
||
|
|
"grad_norm": 1.7578125,
|
||
|
|
"learning_rate": 4.7000000000000004e-05,
|
||
|
|
"loss": 9.4401,
|
||
|
|
"mean_token_accuracy": 0.04271471928805113,
|
||
|
|
"num_tokens": 209627.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.688950729370116,
|
||
|
|
"epoch": 0.10085728693898134,
|
||
|
|
"grad_norm": 1.8125,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"loss": 9.3648,
|
||
|
|
"mean_token_accuracy": 0.04892551712691784,
|
||
|
|
"num_tokens": 220872.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.666452217102051,
|
||
|
|
"epoch": 0.1059001512859304,
|
||
|
|
"grad_norm": 1.8125,
|
||
|
|
"learning_rate": 5.2e-05,
|
||
|
|
"loss": 9.2706,
|
||
|
|
"mean_token_accuracy": 0.04733602069318295,
|
||
|
|
"num_tokens": 233272.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.643214797973632,
|
||
|
|
"epoch": 0.11094301563287948,
|
||
|
|
"grad_norm": 1.8125,
|
||
|
|
"learning_rate": 5.45e-05,
|
||
|
|
"loss": 9.1724,
|
||
|
|
"mean_token_accuracy": 0.05065925419330597,
|
||
|
|
"num_tokens": 243529.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.622024440765381,
|
||
|
|
"epoch": 0.11598587997982854,
|
||
|
|
"grad_norm": 1.640625,
|
||
|
|
"learning_rate": 5.7e-05,
|
||
|
|
"loss": 9.0982,
|
||
|
|
"mean_token_accuracy": 0.04518871679902077,
|
||
|
|
"num_tokens": 254942.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.591822242736816,
|
||
|
|
"epoch": 0.12102874432677761,
|
||
|
|
"grad_norm": 1.7421875,
|
||
|
|
"learning_rate": 5.9499999999999996e-05,
|
||
|
|
"loss": 8.9746,
|
||
|
|
"mean_token_accuracy": 0.05078088715672493,
|
||
|
|
"num_tokens": 266552.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.53172492980957,
|
||
|
|
"epoch": 0.1260716086737267,
|
||
|
|
"grad_norm": 1.59375,
|
||
|
|
"learning_rate": 6.2e-05,
|
||
|
|
"loss": 8.8367,
|
||
|
|
"mean_token_accuracy": 0.049286961928009985,
|
||
|
|
"num_tokens": 277906.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.461231136322022,
|
||
|
|
"epoch": 0.13111447302067575,
|
||
|
|
"grad_norm": 1.6328125,
|
||
|
|
"learning_rate": 6.450000000000001e-05,
|
||
|
|
"loss": 8.7177,
|
||
|
|
"mean_token_accuracy": 0.05140590891242027,
|
||
|
|
"num_tokens": 289079.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.385406398773194,
|
||
|
|
"epoch": 0.1361573373676248,
|
||
|
|
"grad_norm": 1.5,
|
||
|
|
"learning_rate": 6.7e-05,
|
||
|
|
"loss": 8.6441,
|
||
|
|
"mean_token_accuracy": 0.04429629724472761,
|
||
|
|
"num_tokens": 300107.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.312572288513184,
|
||
|
|
"epoch": 0.14120020171457387,
|
||
|
|
"grad_norm": 1.5234375,
|
||
|
|
"learning_rate": 6.950000000000001e-05,
|
||
|
|
"loss": 8.4806,
|
||
|
|
"mean_token_accuracy": 0.05319313518702984,
|
||
|
|
"num_tokens": 310779.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.203822803497314,
|
||
|
|
"epoch": 0.14624306606152296,
|
||
|
|
"grad_norm": 1.453125,
|
||
|
|
"learning_rate": 7.2e-05,
|
||
|
|
"loss": 8.4202,
|
||
|
|
"mean_token_accuracy": 0.051876432821154596,
|
||
|
|
"num_tokens": 323478.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.096873664855957,
|
||
|
|
"epoch": 0.15128593040847202,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 7.45e-05,
|
||
|
|
"loss": 8.2552,
|
||
|
|
"mean_token_accuracy": 0.05630794763565063,
|
||
|
|
"num_tokens": 335255.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.960623264312744,
|
||
|
|
"epoch": 0.15632879475542108,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 7.7e-05,
|
||
|
|
"loss": 8.1385,
|
||
|
|
"mean_token_accuracy": 0.05476163513958454,
|
||
|
|
"num_tokens": 344824.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.771032524108886,
|
||
|
|
"epoch": 0.16137165910237014,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 7.950000000000001e-05,
|
||
|
|
"loss": 8.0754,
|
||
|
|
"mean_token_accuracy": 0.05333587229251861,
|
||
|
|
"num_tokens": 356283.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.623997592926026,
|
||
|
|
"epoch": 0.1664145234493192,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 8.2e-05,
|
||
|
|
"loss": 7.996,
|
||
|
|
"mean_token_accuracy": 0.05669583305716515,
|
||
|
|
"num_tokens": 368098.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.383370685577393,
|
||
|
|
"epoch": 0.1714573877962683,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 8.450000000000001e-05,
|
||
|
|
"loss": 7.8796,
|
||
|
|
"mean_token_accuracy": 0.059235493466258046,
|
||
|
|
"num_tokens": 380948.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.174373054504395,
|
||
|
|
"epoch": 0.17650025214321735,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 8.7e-05,
|
||
|
|
"loss": 7.7633,
|
||
|
|
"mean_token_accuracy": 0.05942847430706024,
|
||
|
|
"num_tokens": 390392.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.980836009979248,
|
||
|
|
"epoch": 0.1815431164901664,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 8.95e-05,
|
||
|
|
"loss": 7.7496,
|
||
|
|
"mean_token_accuracy": 0.06362583562731743,
|
||
|
|
"num_tokens": 400328.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.7655029296875,
|
||
|
|
"epoch": 0.18658598083711547,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 9.2e-05,
|
||
|
|
"loss": 7.7544,
|
||
|
|
"mean_token_accuracy": 0.06182343065738678,
|
||
|
|
"num_tokens": 410909.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.639219570159913,
|
||
|
|
"epoch": 0.19162884518406456,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 9.45e-05,
|
||
|
|
"loss": 7.691,
|
||
|
|
"mean_token_accuracy": 0.06425628773868083,
|
||
|
|
"num_tokens": 422726.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.559172058105469,
|
||
|
|
"epoch": 0.19667170953101362,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 9.7e-05,
|
||
|
|
"loss": 7.5594,
|
||
|
|
"mean_token_accuracy": 0.07219541147351265,
|
||
|
|
"num_tokens": 433376.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.397376251220702,
|
||
|
|
"epoch": 0.20171457387796268,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 9.95e-05,
|
||
|
|
"loss": 7.6275,
|
||
|
|
"mean_token_accuracy": 0.06337097361683845,
|
||
|
|
"num_tokens": 443940.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.361763286590577,
|
||
|
|
"epoch": 0.20675743822491174,
|
||
|
|
"grad_norm": 0.78125,
|
||
|
|
"learning_rate": 0.000102,
|
||
|
|
"loss": 7.5213,
|
||
|
|
"mean_token_accuracy": 0.06769266054034233,
|
||
|
|
"num_tokens": 455016.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.303247165679931,
|
||
|
|
"epoch": 0.2118003025718608,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.00010449999999999999,
|
||
|
|
"loss": 7.553,
|
||
|
|
"mean_token_accuracy": 0.06669275388121605,
|
||
|
|
"num_tokens": 466380.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.23162612915039,
|
||
|
|
"epoch": 0.2168431669188099,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000107,
|
||
|
|
"loss": 7.4065,
|
||
|
|
"mean_token_accuracy": 0.07161542177200317,
|
||
|
|
"num_tokens": 476915.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.226816177368164,
|
||
|
|
"epoch": 0.22188603126575895,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0001095,
|
||
|
|
"loss": 7.4817,
|
||
|
|
"mean_token_accuracy": 0.07145784981548786,
|
||
|
|
"num_tokens": 488924.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.18234987258911,
|
||
|
|
"epoch": 0.22692889561270801,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.000112,
|
||
|
|
"loss": 7.4263,
|
||
|
|
"mean_token_accuracy": 0.07183554545044898,
|
||
|
|
"num_tokens": 498965.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.137568473815918,
|
||
|
|
"epoch": 0.23197175995965708,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0001145,
|
||
|
|
"loss": 7.4409,
|
||
|
|
"mean_token_accuracy": 0.07232684977352619,
|
||
|
|
"num_tokens": 509755.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.12470645904541,
|
||
|
|
"epoch": 0.23701462430660616,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.00011700000000000001,
|
||
|
|
"loss": 7.4064,
|
||
|
|
"mean_token_accuracy": 0.07139695808291435,
|
||
|
|
"num_tokens": 521221.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.080301761627197,
|
||
|
|
"epoch": 0.24205748865355523,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.00011949999999999999,
|
||
|
|
"loss": 7.503,
|
||
|
|
"mean_token_accuracy": 0.06776785589754582,
|
||
|
|
"num_tokens": 533595.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.111075401306152,
|
||
|
|
"epoch": 0.24710035300050429,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.000122,
|
||
|
|
"loss": 7.4348,
|
||
|
|
"mean_token_accuracy": 0.07060522697865963,
|
||
|
|
"num_tokens": 543672.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.046464586257935,
|
||
|
|
"epoch": 0.2521432173474534,
|
||
|
|
"grad_norm": 0.7734375,
|
||
|
|
"learning_rate": 0.0001245,
|
||
|
|
"loss": 7.3208,
|
||
|
|
"mean_token_accuracy": 0.07489579617977142,
|
||
|
|
"num_tokens": 554906.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.984986257553101,
|
||
|
|
"epoch": 0.25718608169440244,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.000127,
|
||
|
|
"loss": 7.3941,
|
||
|
|
"mean_token_accuracy": 0.07390029206871987,
|
||
|
|
"num_tokens": 566419.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.038315868377685,
|
||
|
|
"epoch": 0.2622289460413515,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0001295,
|
||
|
|
"loss": 7.3625,
|
||
|
|
"mean_token_accuracy": 0.07229974381625652,
|
||
|
|
"num_tokens": 578848.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.896354866027832,
|
||
|
|
"epoch": 0.26727181038830056,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.000132,
|
||
|
|
"loss": 7.305,
|
||
|
|
"mean_token_accuracy": 0.07605222910642624,
|
||
|
|
"num_tokens": 590601.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.9424131393432615,
|
||
|
|
"epoch": 0.2723146747352496,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.00013450000000000002,
|
||
|
|
"loss": 7.3548,
|
||
|
|
"mean_token_accuracy": 0.07202886901795864,
|
||
|
|
"num_tokens": 602021.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.004773712158203,
|
||
|
|
"epoch": 0.2773575390821987,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.00013700000000000002,
|
||
|
|
"loss": 7.4443,
|
||
|
|
"mean_token_accuracy": 0.06653593964874745,
|
||
|
|
"num_tokens": 613966.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.990764474868774,
|
||
|
|
"epoch": 0.28240040342914774,
|
||
|
|
"grad_norm": 1.5390625,
|
||
|
|
"learning_rate": 0.0001395,
|
||
|
|
"loss": 7.2762,
|
||
|
|
"mean_token_accuracy": 0.07293831780552865,
|
||
|
|
"num_tokens": 624851.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.808479070663452,
|
||
|
|
"epoch": 0.2874432677760968,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.00014199999999999998,
|
||
|
|
"loss": 7.3518,
|
||
|
|
"mean_token_accuracy": 0.07462373450398445,
|
||
|
|
"num_tokens": 635580.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.965742826461792,
|
||
|
|
"epoch": 0.2924861321230459,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0001445,
|
||
|
|
"loss": 7.4071,
|
||
|
|
"mean_token_accuracy": 0.0715030949562788,
|
||
|
|
"num_tokens": 646927.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.943162631988526,
|
||
|
|
"epoch": 0.297528996469995,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000147,
|
||
|
|
"loss": 7.2414,
|
||
|
|
"mean_token_accuracy": 0.07769636139273643,
|
||
|
|
"num_tokens": 658116.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.861419916152954,
|
||
|
|
"epoch": 0.30257186081694404,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0001495,
|
||
|
|
"loss": 7.2404,
|
||
|
|
"mean_token_accuracy": 0.07680558413267136,
|
||
|
|
"num_tokens": 669054.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.859039735794068,
|
||
|
|
"epoch": 0.3076147251638931,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.000152,
|
||
|
|
"loss": 7.2846,
|
||
|
|
"mean_token_accuracy": 0.07930284813046455,
|
||
|
|
"num_tokens": 680439.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.81926383972168,
|
||
|
|
"epoch": 0.31265758951084216,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00015450000000000001,
|
||
|
|
"loss": 7.2209,
|
||
|
|
"mean_token_accuracy": 0.0794371448457241,
|
||
|
|
"num_tokens": 690909.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.75442066192627,
|
||
|
|
"epoch": 0.3177004538577912,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000157,
|
||
|
|
"loss": 7.209,
|
||
|
|
"mean_token_accuracy": 0.07925689667463302,
|
||
|
|
"num_tokens": 701744.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.746679449081421,
|
||
|
|
"epoch": 0.3227433182047403,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0001595,
|
||
|
|
"loss": 7.2338,
|
||
|
|
"mean_token_accuracy": 0.08032149039208888,
|
||
|
|
"num_tokens": 712268.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.765822124481201,
|
||
|
|
"epoch": 0.32778618255168934,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000162,
|
||
|
|
"loss": 7.2609,
|
||
|
|
"mean_token_accuracy": 0.07947171069681644,
|
||
|
|
"num_tokens": 722978.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.870586299896241,
|
||
|
|
"epoch": 0.3328290468986384,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.00016450000000000001,
|
||
|
|
"loss": 7.253,
|
||
|
|
"mean_token_accuracy": 0.07748774662613869,
|
||
|
|
"num_tokens": 734278.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.8009439468383786,
|
||
|
|
"epoch": 0.3378719112455875,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.00016700000000000002,
|
||
|
|
"loss": 7.1867,
|
||
|
|
"mean_token_accuracy": 0.07406368069350719,
|
||
|
|
"num_tokens": 746109.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.751057529449463,
|
||
|
|
"epoch": 0.3429147755925366,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00016950000000000003,
|
||
|
|
"loss": 7.1104,
|
||
|
|
"mean_token_accuracy": 0.07908297292888164,
|
||
|
|
"num_tokens": 757519.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.711837816238403,
|
||
|
|
"epoch": 0.34795763993948564,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00017199999999999998,
|
||
|
|
"loss": 7.0784,
|
||
|
|
"mean_token_accuracy": 0.08319444209337234,
|
||
|
|
"num_tokens": 767665.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.729198932647705,
|
||
|
|
"epoch": 0.3530005042864347,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00017449999999999999,
|
||
|
|
"loss": 7.118,
|
||
|
|
"mean_token_accuracy": 0.08570092767477036,
|
||
|
|
"num_tokens": 778880.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.589126014709473,
|
||
|
|
"epoch": 0.35804336863338376,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.000177,
|
||
|
|
"loss": 7.1275,
|
||
|
|
"mean_token_accuracy": 0.08408626839518547,
|
||
|
|
"num_tokens": 790360.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.650224447250366,
|
||
|
|
"epoch": 0.3630862329803328,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0001795,
|
||
|
|
"loss": 7.0884,
|
||
|
|
"mean_token_accuracy": 0.08589479774236679,
|
||
|
|
"num_tokens": 800889.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.698587417602539,
|
||
|
|
"epoch": 0.3681290973272819,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000182,
|
||
|
|
"loss": 7.0774,
|
||
|
|
"mean_token_accuracy": 0.08224210813641548,
|
||
|
|
"num_tokens": 811414.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.551970529556274,
|
||
|
|
"epoch": 0.37317196167423095,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0001845,
|
||
|
|
"loss": 7.0729,
|
||
|
|
"mean_token_accuracy": 0.08361641615629196,
|
||
|
|
"num_tokens": 822822.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.61205792427063,
|
||
|
|
"epoch": 0.37821482602118,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000187,
|
||
|
|
"loss": 6.9949,
|
||
|
|
"mean_token_accuracy": 0.09048431143164634,
|
||
|
|
"num_tokens": 833145.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.606620168685913,
|
||
|
|
"epoch": 0.3832576903681291,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0001895,
|
||
|
|
"loss": 7.1067,
|
||
|
|
"mean_token_accuracy": 0.08064279481768608,
|
||
|
|
"num_tokens": 844015.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.537594938278199,
|
||
|
|
"epoch": 0.3883005547150782,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.000192,
|
||
|
|
"loss": 7.0227,
|
||
|
|
"mean_token_accuracy": 0.08781845718622208,
|
||
|
|
"num_tokens": 855806.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.601389598846436,
|
||
|
|
"epoch": 0.39334341906202724,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0001945,
|
||
|
|
"loss": 6.952,
|
||
|
|
"mean_token_accuracy": 0.08714486509561539,
|
||
|
|
"num_tokens": 865750.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.603587245941162,
|
||
|
|
"epoch": 0.3983862834089763,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.00019700000000000002,
|
||
|
|
"loss": 7.0798,
|
||
|
|
"mean_token_accuracy": 0.08171837627887726,
|
||
|
|
"num_tokens": 877630.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.46077446937561,
|
||
|
|
"epoch": 0.40342914775592537,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.00019950000000000002,
|
||
|
|
"loss": 6.9621,
|
||
|
|
"mean_token_accuracy": 0.08956382796168327,
|
||
|
|
"num_tokens": 888667.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.612736940383911,
|
||
|
|
"epoch": 0.4084720121028744,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000202,
|
||
|
|
"loss": 7.0383,
|
||
|
|
"mean_token_accuracy": 0.0815612755715847,
|
||
|
|
"num_tokens": 900989.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4917103290557865,
|
||
|
|
"epoch": 0.4135148764498235,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.00020449999999999998,
|
||
|
|
"loss": 6.9247,
|
||
|
|
"mean_token_accuracy": 0.08268933743238449,
|
||
|
|
"num_tokens": 911479.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.538983345031738,
|
||
|
|
"epoch": 0.41855774079677255,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000207,
|
||
|
|
"loss": 6.9579,
|
||
|
|
"mean_token_accuracy": 0.0860539086163044,
|
||
|
|
"num_tokens": 922434.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.502885150909424,
|
||
|
|
"epoch": 0.4236006051437216,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0002095,
|
||
|
|
"loss": 6.9417,
|
||
|
|
"mean_token_accuracy": 0.08750939816236496,
|
||
|
|
"num_tokens": 933405.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.503132390975952,
|
||
|
|
"epoch": 0.4286434694906707,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000212,
|
||
|
|
"loss": 6.9414,
|
||
|
|
"mean_token_accuracy": 0.0863698624074459,
|
||
|
|
"num_tokens": 943567.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.433593511581421,
|
||
|
|
"epoch": 0.4336863338376198,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0002145,
|
||
|
|
"loss": 6.9729,
|
||
|
|
"mean_token_accuracy": 0.08398969918489456,
|
||
|
|
"num_tokens": 955123.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4864178657531735,
|
||
|
|
"epoch": 0.43872919818456885,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.00021700000000000002,
|
||
|
|
"loss": 6.9878,
|
||
|
|
"mean_token_accuracy": 0.08637007214128971,
|
||
|
|
"num_tokens": 965565.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.533525228500366,
|
||
|
|
"epoch": 0.4437720625315179,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0002195,
|
||
|
|
"loss": 6.9331,
|
||
|
|
"mean_token_accuracy": 0.09186888933181762,
|
||
|
|
"num_tokens": 977101.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.447479343414306,
|
||
|
|
"epoch": 0.44881492687846697,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.000222,
|
||
|
|
"loss": 6.9676,
|
||
|
|
"mean_token_accuracy": 0.08773500472307205,
|
||
|
|
"num_tokens": 987445.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.413919162750244,
|
||
|
|
"epoch": 0.45385779122541603,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0002245,
|
||
|
|
"loss": 6.8527,
|
||
|
|
"mean_token_accuracy": 0.0943599946796894,
|
||
|
|
"num_tokens": 999379.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.366581916809082,
|
||
|
|
"epoch": 0.4589006555723651,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00022700000000000002,
|
||
|
|
"loss": 6.7887,
|
||
|
|
"mean_token_accuracy": 0.09886589571833611,
|
||
|
|
"num_tokens": 1010744.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.395628499984741,
|
||
|
|
"epoch": 0.46394351991931415,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00022950000000000002,
|
||
|
|
"loss": 6.8751,
|
||
|
|
"mean_token_accuracy": 0.09002586975693702,
|
||
|
|
"num_tokens": 1021808.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.436336374282837,
|
||
|
|
"epoch": 0.4689863842662632,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00023200000000000003,
|
||
|
|
"loss": 6.9197,
|
||
|
|
"mean_token_accuracy": 0.08965835645794869,
|
||
|
|
"num_tokens": 1033694.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.366260051727295,
|
||
|
|
"epoch": 0.47402924861321233,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00023449999999999998,
|
||
|
|
"loss": 6.8866,
|
||
|
|
"mean_token_accuracy": 0.08940717950463295,
|
||
|
|
"num_tokens": 1044690.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3759284019470215,
|
||
|
|
"epoch": 0.4790721129601614,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.000237,
|
||
|
|
"loss": 6.883,
|
||
|
|
"mean_token_accuracy": 0.09023785665631294,
|
||
|
|
"num_tokens": 1055557.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.412348127365112,
|
||
|
|
"epoch": 0.48411497730711045,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0002395,
|
||
|
|
"loss": 6.8225,
|
||
|
|
"mean_token_accuracy": 0.09234220460057259,
|
||
|
|
"num_tokens": 1067304.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.280447006225586,
|
||
|
|
"epoch": 0.4891578416540595,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000242,
|
||
|
|
"loss": 6.8498,
|
||
|
|
"mean_token_accuracy": 0.09138206690549851,
|
||
|
|
"num_tokens": 1078955.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.339125728607177,
|
||
|
|
"epoch": 0.49420070600100857,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0002445,
|
||
|
|
"loss": 6.8907,
|
||
|
|
"mean_token_accuracy": 0.09167812019586563,
|
||
|
|
"num_tokens": 1091405.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.334241151809692,
|
||
|
|
"epoch": 0.49924357034795763,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000247,
|
||
|
|
"loss": 6.8625,
|
||
|
|
"mean_token_accuracy": 0.09363722130656242,
|
||
|
|
"num_tokens": 1103227.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.351650381088257,
|
||
|
|
"epoch": 0.5042864346949067,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0002495,
|
||
|
|
"loss": 6.7968,
|
||
|
|
"mean_token_accuracy": 0.09819836765527726,
|
||
|
|
"num_tokens": 1114485.0,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5042864346949067,
|
||
|
|
"eval_entropy": 7.210145644559205,
|
||
|
|
"eval_loss": 6.899664402008057,
|
||
|
|
"eval_mean_token_accuracy": 0.09479910408267538,
|
||
|
|
"eval_num_tokens": 1114485.0,
|
||
|
|
"eval_runtime": 2.1175,
|
||
|
|
"eval_samples_per_second": 1481.964,
|
||
|
|
"eval_steps_per_second": 185.6,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.260896873474121,
|
||
|
|
"epoch": 0.5093292990418558,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.000252,
|
||
|
|
"loss": 6.8181,
|
||
|
|
"mean_token_accuracy": 0.09441837519407273,
|
||
|
|
"num_tokens": 1126789.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.352414274215699,
|
||
|
|
"epoch": 0.5143721633888049,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0002545,
|
||
|
|
"loss": 6.7989,
|
||
|
|
"mean_token_accuracy": 0.09330016896128654,
|
||
|
|
"num_tokens": 1138192.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2082147121429445,
|
||
|
|
"epoch": 0.5194150277357539,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000257,
|
||
|
|
"loss": 6.7411,
|
||
|
|
"mean_token_accuracy": 0.09130406081676483,
|
||
|
|
"num_tokens": 1148526.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.369548559188843,
|
||
|
|
"epoch": 0.524457892082703,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0002595,
|
||
|
|
"loss": 6.8496,
|
||
|
|
"mean_token_accuracy": 0.08768555521965027,
|
||
|
|
"num_tokens": 1159194.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.23188009262085,
|
||
|
|
"epoch": 0.529500756429652,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.000262,
|
||
|
|
"loss": 6.7433,
|
||
|
|
"mean_token_accuracy": 0.1001415841281414,
|
||
|
|
"num_tokens": 1170601.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.288579416275025,
|
||
|
|
"epoch": 0.5345436207766011,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00026450000000000003,
|
||
|
|
"loss": 6.7419,
|
||
|
|
"mean_token_accuracy": 0.0954306311905384,
|
||
|
|
"num_tokens": 1182441.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.17895131111145,
|
||
|
|
"epoch": 0.5395864851235502,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00026700000000000004,
|
||
|
|
"loss": 6.6349,
|
||
|
|
"mean_token_accuracy": 0.10441381633281707,
|
||
|
|
"num_tokens": 1192530.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.13337082862854,
|
||
|
|
"epoch": 0.5446293494704992,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00026950000000000005,
|
||
|
|
"loss": 6.7521,
|
||
|
|
"mean_token_accuracy": 0.0956033818423748,
|
||
|
|
"num_tokens": 1203831.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2454320907592775,
|
||
|
|
"epoch": 0.5496722138174484,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00027200000000000005,
|
||
|
|
"loss": 6.6923,
|
||
|
|
"mean_token_accuracy": 0.0969244122505188,
|
||
|
|
"num_tokens": 1214164.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.150829601287842,
|
||
|
|
"epoch": 0.5547150781643974,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0002745,
|
||
|
|
"loss": 6.7235,
|
||
|
|
"mean_token_accuracy": 0.09548334404826164,
|
||
|
|
"num_tokens": 1226932.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.283726549148559,
|
||
|
|
"epoch": 0.5597579425113465,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000277,
|
||
|
|
"loss": 6.79,
|
||
|
|
"mean_token_accuracy": 0.08873454928398132,
|
||
|
|
"num_tokens": 1237212.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.143116188049317,
|
||
|
|
"epoch": 0.5648008068582955,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0002795,
|
||
|
|
"loss": 6.6907,
|
||
|
|
"mean_token_accuracy": 0.09660674557089806,
|
||
|
|
"num_tokens": 1249340.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.123078393936157,
|
||
|
|
"epoch": 0.5698436712052446,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00028199999999999997,
|
||
|
|
"loss": 6.6907,
|
||
|
|
"mean_token_accuracy": 0.09954180717468261,
|
||
|
|
"num_tokens": 1260778.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1541259765625,
|
||
|
|
"epoch": 0.5748865355521936,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0002845,
|
||
|
|
"loss": 6.6986,
|
||
|
|
"mean_token_accuracy": 0.09604307189583779,
|
||
|
|
"num_tokens": 1272216.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.223128890991211,
|
||
|
|
"epoch": 0.5799293998991427,
|
||
|
|
"grad_norm": 1.46875,
|
||
|
|
"learning_rate": 0.000287,
|
||
|
|
"loss": 6.7725,
|
||
|
|
"mean_token_accuracy": 0.09934922829270362,
|
||
|
|
"num_tokens": 1283558.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.209529066085816,
|
||
|
|
"epoch": 0.5849722642460918,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0002895,
|
||
|
|
"loss": 6.834,
|
||
|
|
"mean_token_accuracy": 0.08799525387585164,
|
||
|
|
"num_tokens": 1294638.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.27526068687439,
|
||
|
|
"epoch": 0.5900151285930408,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000292,
|
||
|
|
"loss": 6.7472,
|
||
|
|
"mean_token_accuracy": 0.09616359025239944,
|
||
|
|
"num_tokens": 1304697.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.173431634902954,
|
||
|
|
"epoch": 0.59505799293999,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0002945,
|
||
|
|
"loss": 6.7033,
|
||
|
|
"mean_token_accuracy": 0.09485772103071213,
|
||
|
|
"num_tokens": 1316618.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.151233100891114,
|
||
|
|
"epoch": 0.600100857286939,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.000297,
|
||
|
|
"loss": 6.8116,
|
||
|
|
"mean_token_accuracy": 0.08478758260607719,
|
||
|
|
"num_tokens": 1328134.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.242454576492309,
|
||
|
|
"epoch": 0.6051437216338881,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0002995,
|
||
|
|
"loss": 6.7227,
|
||
|
|
"mean_token_accuracy": 0.0935085467994213,
|
||
|
|
"num_tokens": 1339101.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.143788623809814,
|
||
|
|
"epoch": 0.6101865859808371,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.000302,
|
||
|
|
"loss": 6.5973,
|
||
|
|
"mean_token_accuracy": 0.09975283592939377,
|
||
|
|
"num_tokens": 1349181.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0980949878692625,
|
||
|
|
"epoch": 0.6152294503277862,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0003045,
|
||
|
|
"loss": 6.7221,
|
||
|
|
"mean_token_accuracy": 0.09565178751945495,
|
||
|
|
"num_tokens": 1361443.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.098438501358032,
|
||
|
|
"epoch": 0.6202723146747352,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000307,
|
||
|
|
"loss": 6.6778,
|
||
|
|
"mean_token_accuracy": 0.10161929428577424,
|
||
|
|
"num_tokens": 1372807.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.160452890396118,
|
||
|
|
"epoch": 0.6253151790216843,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0003095,
|
||
|
|
"loss": 6.7426,
|
||
|
|
"mean_token_accuracy": 0.09811687916517257,
|
||
|
|
"num_tokens": 1385509.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.133578205108643,
|
||
|
|
"epoch": 0.6303580433686334,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000312,
|
||
|
|
"loss": 6.6405,
|
||
|
|
"mean_token_accuracy": 0.0968807429075241,
|
||
|
|
"num_tokens": 1396035.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.047602128982544,
|
||
|
|
"epoch": 0.6354009077155824,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0003145,
|
||
|
|
"loss": 6.5876,
|
||
|
|
"mean_token_accuracy": 0.10460086688399314,
|
||
|
|
"num_tokens": 1406839.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.976920652389526,
|
||
|
|
"epoch": 0.6404437720625316,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.000317,
|
||
|
|
"loss": 6.559,
|
||
|
|
"mean_token_accuracy": 0.09928513914346696,
|
||
|
|
"num_tokens": 1417708.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.116953611373901,
|
||
|
|
"epoch": 0.6454866364094806,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0003195,
|
||
|
|
"loss": 6.6878,
|
||
|
|
"mean_token_accuracy": 0.0931871697306633,
|
||
|
|
"num_tokens": 1428985.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.110161256790161,
|
||
|
|
"epoch": 0.6505295007564297,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.000322,
|
||
|
|
"loss": 6.7068,
|
||
|
|
"mean_token_accuracy": 0.10163840278983116,
|
||
|
|
"num_tokens": 1440232.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.962800979614258,
|
||
|
|
"epoch": 0.6555723651033787,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00032450000000000003,
|
||
|
|
"loss": 6.4498,
|
||
|
|
"mean_token_accuracy": 0.1053794801235199,
|
||
|
|
"num_tokens": 1451735.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.015639686584473,
|
||
|
|
"epoch": 0.6606152294503278,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00032700000000000003,
|
||
|
|
"loss": 6.6221,
|
||
|
|
"mean_token_accuracy": 0.09871228262782097,
|
||
|
|
"num_tokens": 1463477.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.01046838760376,
|
||
|
|
"epoch": 0.6656580937972768,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00032950000000000004,
|
||
|
|
"loss": 6.6263,
|
||
|
|
"mean_token_accuracy": 0.09373534545302391,
|
||
|
|
"num_tokens": 1473802.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.009602022171021,
|
||
|
|
"epoch": 0.6707009581442259,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00033200000000000005,
|
||
|
|
"loss": 6.6264,
|
||
|
|
"mean_token_accuracy": 0.09858302772045135,
|
||
|
|
"num_tokens": 1485519.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.069497060775757,
|
||
|
|
"epoch": 0.675743822491175,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00033450000000000005,
|
||
|
|
"loss": 6.6323,
|
||
|
|
"mean_token_accuracy": 0.09767952933907509,
|
||
|
|
"num_tokens": 1496957.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0134529113769535,
|
||
|
|
"epoch": 0.680786686838124,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000337,
|
||
|
|
"loss": 6.6387,
|
||
|
|
"mean_token_accuracy": 0.10315296724438668,
|
||
|
|
"num_tokens": 1508336.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.98244080543518,
|
||
|
|
"epoch": 0.6858295511850732,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0003395,
|
||
|
|
"loss": 6.6118,
|
||
|
|
"mean_token_accuracy": 0.09836572855710983,
|
||
|
|
"num_tokens": 1520016.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9399433612823485,
|
||
|
|
"epoch": 0.6908724155320222,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.000342,
|
||
|
|
"loss": 6.4545,
|
||
|
|
"mean_token_accuracy": 0.10555818825960159,
|
||
|
|
"num_tokens": 1531877.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.861659812927246,
|
||
|
|
"epoch": 0.6959152798789713,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00034449999999999997,
|
||
|
|
"loss": 6.4507,
|
||
|
|
"mean_token_accuracy": 0.10879426971077918,
|
||
|
|
"num_tokens": 1541553.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.983822345733643,
|
||
|
|
"epoch": 0.7009581442259203,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000347,
|
||
|
|
"loss": 6.6146,
|
||
|
|
"mean_token_accuracy": 0.10361509844660759,
|
||
|
|
"num_tokens": 1552491.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.899546098709107,
|
||
|
|
"epoch": 0.7060010085728694,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0003495,
|
||
|
|
"loss": 6.5076,
|
||
|
|
"mean_token_accuracy": 0.10220511853694916,
|
||
|
|
"num_tokens": 1563695.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.986747407913208,
|
||
|
|
"epoch": 0.7110438729198184,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000352,
|
||
|
|
"loss": 6.5457,
|
||
|
|
"mean_token_accuracy": 0.1040324755012989,
|
||
|
|
"num_tokens": 1573467.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.899123620986939,
|
||
|
|
"epoch": 0.7160867372667675,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0003545,
|
||
|
|
"loss": 6.523,
|
||
|
|
"mean_token_accuracy": 0.1107451319694519,
|
||
|
|
"num_tokens": 1584367.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.902140855789185,
|
||
|
|
"epoch": 0.7211296016137166,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000357,
|
||
|
|
"loss": 6.4647,
|
||
|
|
"mean_token_accuracy": 0.11195559501647949,
|
||
|
|
"num_tokens": 1595301.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.908828496932983,
|
||
|
|
"epoch": 0.7261724659606656,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0003595,
|
||
|
|
"loss": 6.5362,
|
||
|
|
"mean_token_accuracy": 0.10281007215380669,
|
||
|
|
"num_tokens": 1605916.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.960860681533814,
|
||
|
|
"epoch": 0.7312153303076148,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000362,
|
||
|
|
"loss": 6.5308,
|
||
|
|
"mean_token_accuracy": 0.10332813784480095,
|
||
|
|
"num_tokens": 1616455.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.853022289276123,
|
||
|
|
"epoch": 0.7362581946545638,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0003645,
|
||
|
|
"loss": 6.4979,
|
||
|
|
"mean_token_accuracy": 0.10751453042030334,
|
||
|
|
"num_tokens": 1627396.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0525219440460205,
|
||
|
|
"epoch": 0.7413010590015129,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000367,
|
||
|
|
"loss": 6.6317,
|
||
|
|
"mean_token_accuracy": 0.09941819235682488,
|
||
|
|
"num_tokens": 1639073.0,
|
||
|
|
"step": 735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.803125476837158,
|
||
|
|
"epoch": 0.7463439233484619,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0003695,
|
||
|
|
"loss": 6.4978,
|
||
|
|
"mean_token_accuracy": 0.10190683454275132,
|
||
|
|
"num_tokens": 1649787.0,
|
||
|
|
"step": 740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.935564804077148,
|
||
|
|
"epoch": 0.751386787695411,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000372,
|
||
|
|
"loss": 6.4383,
|
||
|
|
"mean_token_accuracy": 0.10585329979658127,
|
||
|
|
"num_tokens": 1658883.0,
|
||
|
|
"step": 745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7616808891296385,
|
||
|
|
"epoch": 0.75642965204236,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0003745,
|
||
|
|
"loss": 6.4186,
|
||
|
|
"mean_token_accuracy": 0.11256190687417984,
|
||
|
|
"num_tokens": 1669099.0,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.824008131027222,
|
||
|
|
"epoch": 0.7614725163893091,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.000377,
|
||
|
|
"loss": 6.4199,
|
||
|
|
"mean_token_accuracy": 0.10491297394037247,
|
||
|
|
"num_tokens": 1680227.0,
|
||
|
|
"step": 755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.830388927459717,
|
||
|
|
"epoch": 0.7665153807362582,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0003795,
|
||
|
|
"loss": 6.4178,
|
||
|
|
"mean_token_accuracy": 0.10797212198376656,
|
||
|
|
"num_tokens": 1689901.0,
|
||
|
|
"step": 760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.790120553970337,
|
||
|
|
"epoch": 0.7715582450832073,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000382,
|
||
|
|
"loss": 6.4932,
|
||
|
|
"mean_token_accuracy": 0.10378503128886223,
|
||
|
|
"num_tokens": 1700498.0,
|
||
|
|
"step": 765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.854589986801147,
|
||
|
|
"epoch": 0.7766011094301564,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0003845,
|
||
|
|
"loss": 6.3993,
|
||
|
|
"mean_token_accuracy": 0.1122807152569294,
|
||
|
|
"num_tokens": 1710715.0,
|
||
|
|
"step": 770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.860204267501831,
|
||
|
|
"epoch": 0.7816439737771054,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00038700000000000003,
|
||
|
|
"loss": 6.5261,
|
||
|
|
"mean_token_accuracy": 0.106892429292202,
|
||
|
|
"num_tokens": 1723858.0,
|
||
|
|
"step": 775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.753562068939209,
|
||
|
|
"epoch": 0.7866868381240545,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00038950000000000003,
|
||
|
|
"loss": 6.491,
|
||
|
|
"mean_token_accuracy": 0.10414958521723747,
|
||
|
|
"num_tokens": 1734678.0,
|
||
|
|
"step": 780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.837999296188355,
|
||
|
|
"epoch": 0.7917297024710035,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00039200000000000004,
|
||
|
|
"loss": 6.3922,
|
||
|
|
"mean_token_accuracy": 0.11342072263360023,
|
||
|
|
"num_tokens": 1743869.0,
|
||
|
|
"step": 785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.905572748184204,
|
||
|
|
"epoch": 0.7967725668179526,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.00039450000000000005,
|
||
|
|
"loss": 6.4633,
|
||
|
|
"mean_token_accuracy": 0.10736536532640457,
|
||
|
|
"num_tokens": 1755266.0,
|
||
|
|
"step": 790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.693229627609253,
|
||
|
|
"epoch": 0.8018154311649016,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00039700000000000005,
|
||
|
|
"loss": 6.4254,
|
||
|
|
"mean_token_accuracy": 0.1047304928302765,
|
||
|
|
"num_tokens": 1766089.0,
|
||
|
|
"step": 795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.800949335098267,
|
||
|
|
"epoch": 0.8068582955118507,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0003995,
|
||
|
|
"loss": 6.441,
|
||
|
|
"mean_token_accuracy": 0.10456803143024444,
|
||
|
|
"num_tokens": 1776057.0,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.839222145080567,
|
||
|
|
"epoch": 0.8119011598587998,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000402,
|
||
|
|
"loss": 6.4781,
|
||
|
|
"mean_token_accuracy": 0.10709379687905311,
|
||
|
|
"num_tokens": 1786729.0,
|
||
|
|
"step": 805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.80726170539856,
|
||
|
|
"epoch": 0.8169440242057489,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004045,
|
||
|
|
"loss": 6.408,
|
||
|
|
"mean_token_accuracy": 0.10803752541542053,
|
||
|
|
"num_tokens": 1797708.0,
|
||
|
|
"step": 810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7316183090209964,
|
||
|
|
"epoch": 0.821986888552698,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00040699999999999997,
|
||
|
|
"loss": 6.4408,
|
||
|
|
"mean_token_accuracy": 0.11508865803480148,
|
||
|
|
"num_tokens": 1807326.0,
|
||
|
|
"step": 815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7365195751190186,
|
||
|
|
"epoch": 0.827029752899647,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004095,
|
||
|
|
"loss": 6.3771,
|
||
|
|
"mean_token_accuracy": 0.11316760107874871,
|
||
|
|
"num_tokens": 1817266.0,
|
||
|
|
"step": 820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.765561532974243,
|
||
|
|
"epoch": 0.8320726172465961,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.000412,
|
||
|
|
"loss": 6.3975,
|
||
|
|
"mean_token_accuracy": 0.11348253637552261,
|
||
|
|
"num_tokens": 1827840.0,
|
||
|
|
"step": 825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.61966724395752,
|
||
|
|
"epoch": 0.8371154815935451,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004145,
|
||
|
|
"loss": 6.3751,
|
||
|
|
"mean_token_accuracy": 0.10820141658186913,
|
||
|
|
"num_tokens": 1838158.0,
|
||
|
|
"step": 830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.799835348129273,
|
||
|
|
"epoch": 0.8421583459404942,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000417,
|
||
|
|
"loss": 6.4544,
|
||
|
|
"mean_token_accuracy": 0.10612540319561958,
|
||
|
|
"num_tokens": 1848317.0,
|
||
|
|
"step": 835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.711783790588379,
|
||
|
|
"epoch": 0.8472012102874432,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004195,
|
||
|
|
"loss": 6.3855,
|
||
|
|
"mean_token_accuracy": 0.10564651787281036,
|
||
|
|
"num_tokens": 1858751.0,
|
||
|
|
"step": 840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7946678638458256,
|
||
|
|
"epoch": 0.8522440746343923,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000422,
|
||
|
|
"loss": 6.3903,
|
||
|
|
"mean_token_accuracy": 0.1101529210805893,
|
||
|
|
"num_tokens": 1870739.0,
|
||
|
|
"step": 845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8033802032470705,
|
||
|
|
"epoch": 0.8572869389813415,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004245,
|
||
|
|
"loss": 6.5132,
|
||
|
|
"mean_token_accuracy": 0.11032365560531616,
|
||
|
|
"num_tokens": 1880995.0,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.705736064910889,
|
||
|
|
"epoch": 0.8623298033282905,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000427,
|
||
|
|
"loss": 6.4509,
|
||
|
|
"mean_token_accuracy": 0.10846404731273651,
|
||
|
|
"num_tokens": 1892633.0,
|
||
|
|
"step": 855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8639147758483885,
|
||
|
|
"epoch": 0.8673726676752396,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004295,
|
||
|
|
"loss": 6.5176,
|
||
|
|
"mean_token_accuracy": 0.10401368141174316,
|
||
|
|
"num_tokens": 1904802.0,
|
||
|
|
"step": 860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.778040790557862,
|
||
|
|
"epoch": 0.8724155320221886,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.000432,
|
||
|
|
"loss": 6.5199,
|
||
|
|
"mean_token_accuracy": 0.10730656683444977,
|
||
|
|
"num_tokens": 1915755.0,
|
||
|
|
"step": 865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.688451814651489,
|
||
|
|
"epoch": 0.8774583963691377,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004345,
|
||
|
|
"loss": 6.2652,
|
||
|
|
"mean_token_accuracy": 0.11115367412567138,
|
||
|
|
"num_tokens": 1926098.0,
|
||
|
|
"step": 870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.744540882110596,
|
||
|
|
"epoch": 0.8825012607160867,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000437,
|
||
|
|
"loss": 6.4883,
|
||
|
|
"mean_token_accuracy": 0.11085206493735314,
|
||
|
|
"num_tokens": 1936607.0,
|
||
|
|
"step": 875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.703429174423218,
|
||
|
|
"epoch": 0.8875441250630358,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004395,
|
||
|
|
"loss": 6.377,
|
||
|
|
"mean_token_accuracy": 0.10893332436680794,
|
||
|
|
"num_tokens": 1948596.0,
|
||
|
|
"step": 880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.669404411315918,
|
||
|
|
"epoch": 0.8925869894099848,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000442,
|
||
|
|
"loss": 6.4526,
|
||
|
|
"mean_token_accuracy": 0.11500444263219833,
|
||
|
|
"num_tokens": 1960322.0,
|
||
|
|
"step": 885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.710722208023071,
|
||
|
|
"epoch": 0.8976298537569339,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004445,
|
||
|
|
"loss": 6.379,
|
||
|
|
"mean_token_accuracy": 0.11063228026032448,
|
||
|
|
"num_tokens": 1971052.0,
|
||
|
|
"step": 890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.781415891647339,
|
||
|
|
"epoch": 0.902672718103883,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000447,
|
||
|
|
"loss": 6.3932,
|
||
|
|
"mean_token_accuracy": 0.10573994740843773,
|
||
|
|
"num_tokens": 1980917.0,
|
||
|
|
"step": 895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.649546766281128,
|
||
|
|
"epoch": 0.9077155824508321,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.00044950000000000003,
|
||
|
|
"loss": 6.3419,
|
||
|
|
"mean_token_accuracy": 0.11238374263048172,
|
||
|
|
"num_tokens": 1991035.0,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.629901695251465,
|
||
|
|
"epoch": 0.9127584467977812,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00045200000000000004,
|
||
|
|
"loss": 6.3659,
|
||
|
|
"mean_token_accuracy": 0.11216280534863472,
|
||
|
|
"num_tokens": 2000587.0,
|
||
|
|
"step": 905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.720604801177979,
|
||
|
|
"epoch": 0.9178013111447302,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00045450000000000004,
|
||
|
|
"loss": 6.3292,
|
||
|
|
"mean_token_accuracy": 0.11438163220882416,
|
||
|
|
"num_tokens": 2011087.0,
|
||
|
|
"step": 910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.651438570022583,
|
||
|
|
"epoch": 0.9228441754916793,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00045700000000000005,
|
||
|
|
"loss": 6.3782,
|
||
|
|
"mean_token_accuracy": 0.10697766989469529,
|
||
|
|
"num_tokens": 2023472.0,
|
||
|
|
"step": 915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.697429943084717,
|
||
|
|
"epoch": 0.9278870398386283,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00045950000000000006,
|
||
|
|
"loss": 6.3639,
|
||
|
|
"mean_token_accuracy": 0.11164266243577003,
|
||
|
|
"num_tokens": 2033783.0,
|
||
|
|
"step": 920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.520638275146484,
|
||
|
|
"epoch": 0.9329299041855774,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.000462,
|
||
|
|
"loss": 6.3795,
|
||
|
|
"mean_token_accuracy": 0.11479249447584153,
|
||
|
|
"num_tokens": 2045882.0,
|
||
|
|
"step": 925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7621557235717775,
|
||
|
|
"epoch": 0.9379727685325264,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004645,
|
||
|
|
"loss": 6.3894,
|
||
|
|
"mean_token_accuracy": 0.10624322891235352,
|
||
|
|
"num_tokens": 2056549.0,
|
||
|
|
"step": 930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.654461240768432,
|
||
|
|
"epoch": 0.9430156328794755,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000467,
|
||
|
|
"loss": 6.3845,
|
||
|
|
"mean_token_accuracy": 0.11624199599027633,
|
||
|
|
"num_tokens": 2067540.0,
|
||
|
|
"step": 935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.602401876449585,
|
||
|
|
"epoch": 0.9480584972264247,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004695,
|
||
|
|
"loss": 6.2956,
|
||
|
|
"mean_token_accuracy": 0.11275828555226326,
|
||
|
|
"num_tokens": 2077386.0,
|
||
|
|
"step": 940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.646829652786255,
|
||
|
|
"epoch": 0.9531013615733737,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000472,
|
||
|
|
"loss": 6.2697,
|
||
|
|
"mean_token_accuracy": 0.11356851384043694,
|
||
|
|
"num_tokens": 2087777.0,
|
||
|
|
"step": 945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.494188833236694,
|
||
|
|
"epoch": 0.9581442259203228,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004745,
|
||
|
|
"loss": 6.2604,
|
||
|
|
"mean_token_accuracy": 0.11282371133565902,
|
||
|
|
"num_tokens": 2099071.0,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.53692774772644,
|
||
|
|
"epoch": 0.9631870902672718,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000477,
|
||
|
|
"loss": 6.3258,
|
||
|
|
"mean_token_accuracy": 0.1121332198381424,
|
||
|
|
"num_tokens": 2109168.0,
|
||
|
|
"step": 955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.835064029693603,
|
||
|
|
"epoch": 0.9682299546142209,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004795,
|
||
|
|
"loss": 6.425,
|
||
|
|
"mean_token_accuracy": 0.10913640931248665,
|
||
|
|
"num_tokens": 2120696.0,
|
||
|
|
"step": 960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.537368297576904,
|
||
|
|
"epoch": 0.9732728189611699,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000482,
|
||
|
|
"loss": 6.371,
|
||
|
|
"mean_token_accuracy": 0.10968417152762414,
|
||
|
|
"num_tokens": 2132427.0,
|
||
|
|
"step": 965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.598920631408691,
|
||
|
|
"epoch": 0.978315683308119,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004845,
|
||
|
|
"loss": 6.3618,
|
||
|
|
"mean_token_accuracy": 0.11373768299818039,
|
||
|
|
"num_tokens": 2143120.0,
|
||
|
|
"step": 970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.740956020355225,
|
||
|
|
"epoch": 0.983358547655068,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.000487,
|
||
|
|
"loss": 6.349,
|
||
|
|
"mean_token_accuracy": 0.10921334773302079,
|
||
|
|
"num_tokens": 2154154.0,
|
||
|
|
"step": 975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.541984796524048,
|
||
|
|
"epoch": 0.9884014120020171,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004895,
|
||
|
|
"loss": 6.4499,
|
||
|
|
"mean_token_accuracy": 0.10598269626498222,
|
||
|
|
"num_tokens": 2167000.0,
|
||
|
|
"step": 980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.663674449920654,
|
||
|
|
"epoch": 0.9934442763489663,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000492,
|
||
|
|
"loss": 6.3823,
|
||
|
|
"mean_token_accuracy": 0.11338229328393937,
|
||
|
|
"num_tokens": 2178100.0,
|
||
|
|
"step": 985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6093058586120605,
|
||
|
|
"epoch": 0.9984871406959153,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004945,
|
||
|
|
"loss": 6.331,
|
||
|
|
"mean_token_accuracy": 0.10886227712035179,
|
||
|
|
"num_tokens": 2189063.0,
|
||
|
|
"step": 990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.706958293914795,
|
||
|
|
"epoch": 1.0030257186081695,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000497,
|
||
|
|
"loss": 6.2723,
|
||
|
|
"mean_token_accuracy": 0.11505810419718425,
|
||
|
|
"num_tokens": 2198302.0,
|
||
|
|
"step": 995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.57634973526001,
|
||
|
|
"epoch": 1.0080685829551186,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004995,
|
||
|
|
"loss": 6.2311,
|
||
|
|
"mean_token_accuracy": 0.1161844253540039,
|
||
|
|
"num_tokens": 2209648.0,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0080685829551186,
|
||
|
|
"eval_entropy": 6.5141722082181746,
|
||
|
|
"eval_loss": 6.3961334228515625,
|
||
|
|
"eval_mean_token_accuracy": 0.11549569743166443,
|
||
|
|
"eval_num_tokens": 2209648.0,
|
||
|
|
"eval_runtime": 2.054,
|
||
|
|
"eval_samples_per_second": 1527.74,
|
||
|
|
"eval_steps_per_second": 191.333,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.522863817214966,
|
||
|
|
"epoch": 1.0131114473020675,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999997762223182,
|
||
|
|
"loss": 6.1663,
|
||
|
|
"mean_token_accuracy": 0.12039870694279671,
|
||
|
|
"num_tokens": 2220806.0,
|
||
|
|
"step": 1005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.48839225769043,
|
||
|
|
"epoch": 1.0181543116490166,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999988671262489,
|
||
|
|
"loss": 6.1552,
|
||
|
|
"mean_token_accuracy": 0.11676756143569947,
|
||
|
|
"num_tokens": 2231806.0,
|
||
|
|
"step": 1010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5846107006073,
|
||
|
|
"epoch": 1.0231971759959657,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999972587285105,
|
||
|
|
"loss": 6.2079,
|
||
|
|
"mean_token_accuracy": 0.12164777219295501,
|
||
|
|
"num_tokens": 2243835.0,
|
||
|
|
"step": 1015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.374717426300049,
|
||
|
|
"epoch": 1.0282400403429148,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999949510341015,
|
||
|
|
"loss": 6.1189,
|
||
|
|
"mean_token_accuracy": 0.11811361014842987,
|
||
|
|
"num_tokens": 2254722.0,
|
||
|
|
"step": 1020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.500878429412841,
|
||
|
|
"epoch": 1.033282904689864,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004999919440501947,
|
||
|
|
"loss": 6.077,
|
||
|
|
"mean_token_accuracy": 0.12784491255879402,
|
||
|
|
"num_tokens": 2264806.0,
|
||
|
|
"step": 1025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.599410104751587,
|
||
|
|
"epoch": 1.0383257690368128,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999882377861355,
|
||
|
|
"loss": 6.259,
|
||
|
|
"mean_token_accuracy": 0.11469498798251151,
|
||
|
|
"num_tokens": 2277037.0,
|
||
|
|
"step": 1030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.523988580703735,
|
||
|
|
"epoch": 1.043368633383762,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004999838322534433,
|
||
|
|
"loss": 6.2056,
|
||
|
|
"mean_token_accuracy": 0.10915817320346832,
|
||
|
|
"num_tokens": 2289829.0,
|
||
|
|
"step": 1035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.515505409240722,
|
||
|
|
"epoch": 1.048411497730711,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999787274658107,
|
||
|
|
"loss": 6.1,
|
||
|
|
"mean_token_accuracy": 0.11675480157136917,
|
||
|
|
"num_tokens": 2300340.0,
|
||
|
|
"step": 1040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.47110800743103,
|
||
|
|
"epoch": 1.0534543620776602,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999729234391032,
|
||
|
|
"loss": 6.1279,
|
||
|
|
"mean_token_accuracy": 0.1232002280652523,
|
||
|
|
"num_tokens": 2310009.0,
|
||
|
|
"step": 1045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.43739595413208,
|
||
|
|
"epoch": 1.058497226424609,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.00049996642019136,
|
||
|
|
"loss": 6.1581,
|
||
|
|
"mean_token_accuracy": 0.11546300202608109,
|
||
|
|
"num_tokens": 2319290.0,
|
||
|
|
"step": 1050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.552343559265137,
|
||
|
|
"epoch": 1.0635400907715582,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999592177427933,
|
||
|
|
"loss": 6.1181,
|
||
|
|
"mean_token_accuracy": 0.12222910076379775,
|
||
|
|
"num_tokens": 2329170.0,
|
||
|
|
"step": 1055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.407629442214966,
|
||
|
|
"epoch": 1.0685829551185073,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004999513161157885,
|
||
|
|
"loss": 6.119,
|
||
|
|
"mean_token_accuracy": 0.11926354318857194,
|
||
|
|
"num_tokens": 2339617.0,
|
||
|
|
"step": 1060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.497067499160766,
|
||
|
|
"epoch": 1.0736258194654564,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999427153349041,
|
||
|
|
"loss": 6.1083,
|
||
|
|
"mean_token_accuracy": 0.12506095916032792,
|
||
|
|
"num_tokens": 2349548.0,
|
||
|
|
"step": 1065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.351389837265015,
|
||
|
|
"epoch": 1.0786686838124055,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999334154268714,
|
||
|
|
"loss": 6.1019,
|
||
|
|
"mean_token_accuracy": 0.11952552795410157,
|
||
|
|
"num_tokens": 2359116.0,
|
||
|
|
"step": 1070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.541378593444824,
|
||
|
|
"epoch": 1.0837115481593544,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004999234164205949,
|
||
|
|
"loss": 6.1649,
|
||
|
|
"mean_token_accuracy": 0.12546638995409012,
|
||
|
|
"num_tokens": 2369412.0,
|
||
|
|
"step": 1075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.466941499710083,
|
||
|
|
"epoch": 1.0887544125063036,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999127183471517,
|
||
|
|
"loss": 6.222,
|
||
|
|
"mean_token_accuracy": 0.11774109154939652,
|
||
|
|
"num_tokens": 2381276.0,
|
||
|
|
"step": 1080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.495827722549438,
|
||
|
|
"epoch": 1.0937972768532527,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004999013212397915,
|
||
|
|
"loss": 6.1256,
|
||
|
|
"mean_token_accuracy": 0.12179253101348878,
|
||
|
|
"num_tokens": 2392135.0,
|
||
|
|
"step": 1085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.338582515716553,
|
||
|
|
"epoch": 1.0988401412002018,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004998892251339368,
|
||
|
|
"loss": 6.0403,
|
||
|
|
"mean_token_accuracy": 0.13191248327493668,
|
||
|
|
"num_tokens": 2402957.0,
|
||
|
|
"step": 1090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.49658522605896,
|
||
|
|
"epoch": 1.1038830055471507,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998764300671827,
|
||
|
|
"loss": 6.1791,
|
||
|
|
"mean_token_accuracy": 0.12375712767243385,
|
||
|
|
"num_tokens": 2413386.0,
|
||
|
|
"step": 1095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.396690225601196,
|
||
|
|
"epoch": 1.1089258698940998,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004998629360792965,
|
||
|
|
"loss": 6.1582,
|
||
|
|
"mean_token_accuracy": 0.11660370007157325,
|
||
|
|
"num_tokens": 2424441.0,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.422626638412476,
|
||
|
|
"epoch": 1.113968734241049,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004998487432122179,
|
||
|
|
"loss": 6.1819,
|
||
|
|
"mean_token_accuracy": 0.11399172693490982,
|
||
|
|
"num_tokens": 2436144.0,
|
||
|
|
"step": 1105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.488900423049927,
|
||
|
|
"epoch": 1.119011598587998,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004998338515100585,
|
||
|
|
"loss": 6.0988,
|
||
|
|
"mean_token_accuracy": 0.1264061599969864,
|
||
|
|
"num_tokens": 2447393.0,
|
||
|
|
"step": 1110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.347085332870483,
|
||
|
|
"epoch": 1.1240544629349472,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998182610191022,
|
||
|
|
"loss": 6.0551,
|
||
|
|
"mean_token_accuracy": 0.12492778077721596,
|
||
|
|
"num_tokens": 2458632.0,
|
||
|
|
"step": 1115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4905647277832035,
|
||
|
|
"epoch": 1.129097327281896,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004998019717878047,
|
||
|
|
"loss": 6.135,
|
||
|
|
"mean_token_accuracy": 0.11796133294701576,
|
||
|
|
"num_tokens": 2469331.0,
|
||
|
|
"step": 1120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.457821035385132,
|
||
|
|
"epoch": 1.1341401916288452,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.000499784983866793,
|
||
|
|
"loss": 6.1834,
|
||
|
|
"mean_token_accuracy": 0.11562436521053314,
|
||
|
|
"num_tokens": 2479501.0,
|
||
|
|
"step": 1125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3564197540283205,
|
||
|
|
"epoch": 1.1391830559757943,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004997672973088661,
|
||
|
|
"loss": 6.052,
|
||
|
|
"mean_token_accuracy": 0.126077089458704,
|
||
|
|
"num_tokens": 2490087.0,
|
||
|
|
"step": 1130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.441509485244751,
|
||
|
|
"epoch": 1.1442259203227434,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004997489121689944,
|
||
|
|
"loss": 6.1185,
|
||
|
|
"mean_token_accuracy": 0.1169286049902439,
|
||
|
|
"num_tokens": 2501130.0,
|
||
|
|
"step": 1135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.476033449172974,
|
||
|
|
"epoch": 1.1492687846696923,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004997298285043189,
|
||
|
|
"loss": 6.2252,
|
||
|
|
"mean_token_accuracy": 0.11470448672771454,
|
||
|
|
"num_tokens": 2513999.0,
|
||
|
|
"step": 1140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4647002696990965,
|
||
|
|
"epoch": 1.1543116490166414,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004997100463741527,
|
||
|
|
"loss": 6.1458,
|
||
|
|
"mean_token_accuracy": 0.11966953650116921,
|
||
|
|
"num_tokens": 2525579.0,
|
||
|
|
"step": 1145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.375444412231445,
|
||
|
|
"epoch": 1.1593545133635905,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004996895658399785,
|
||
|
|
"loss": 6.1188,
|
||
|
|
"mean_token_accuracy": 0.12094511762261391,
|
||
|
|
"num_tokens": 2536091.0,
|
||
|
|
"step": 1150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.43728551864624,
|
||
|
|
"epoch": 1.1643973777105396,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004996683869654507,
|
||
|
|
"loss": 6.1577,
|
||
|
|
"mean_token_accuracy": 0.12777142524719237,
|
||
|
|
"num_tokens": 2546073.0,
|
||
|
|
"step": 1155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.448345422744751,
|
||
|
|
"epoch": 1.1694402420574885,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004996465098163934,
|
||
|
|
"loss": 6.108,
|
||
|
|
"mean_token_accuracy": 0.11881096065044403,
|
||
|
|
"num_tokens": 2556626.0,
|
||
|
|
"step": 1160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.405810403823852,
|
||
|
|
"epoch": 1.1744831064044376,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004996239344608015,
|
||
|
|
"loss": 6.1156,
|
||
|
|
"mean_token_accuracy": 0.12832853496074675,
|
||
|
|
"num_tokens": 2567304.0,
|
||
|
|
"step": 1165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.377554607391358,
|
||
|
|
"epoch": 1.1795259707513868,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004996006609688398,
|
||
|
|
"loss": 6.001,
|
||
|
|
"mean_token_accuracy": 0.1183304913341999,
|
||
|
|
"num_tokens": 2577242.0,
|
||
|
|
"step": 1170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.341175317764282,
|
||
|
|
"epoch": 1.1845688350983359,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004995766894128426,
|
||
|
|
"loss": 6.0978,
|
||
|
|
"mean_token_accuracy": 0.11528865247964859,
|
||
|
|
"num_tokens": 2588330.0,
|
||
|
|
"step": 1175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.347274208068848,
|
||
|
|
"epoch": 1.189611699445285,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004995520198673143,
|
||
|
|
"loss": 6.1208,
|
||
|
|
"mean_token_accuracy": 0.1222249336540699,
|
||
|
|
"num_tokens": 2598471.0,
|
||
|
|
"step": 1180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.476546859741211,
|
||
|
|
"epoch": 1.194654563792234,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004995266524089283,
|
||
|
|
"loss": 6.1917,
|
||
|
|
"mean_token_accuracy": 0.11832692325115204,
|
||
|
|
"num_tokens": 2610238.0,
|
||
|
|
"step": 1185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.360067367553711,
|
||
|
|
"epoch": 1.199697428139183,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004995005871165271,
|
||
|
|
"loss": 6.0669,
|
||
|
|
"mean_token_accuracy": 0.11930153965950012,
|
||
|
|
"num_tokens": 2619870.0,
|
||
|
|
"step": 1190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.458434772491455,
|
||
|
|
"epoch": 1.2047402924861321,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004994738240711225,
|
||
|
|
"loss": 6.1989,
|
||
|
|
"mean_token_accuracy": 0.11891994774341583,
|
||
|
|
"num_tokens": 2631541.0,
|
||
|
|
"step": 1195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.346074151992798,
|
||
|
|
"epoch": 1.2097831568330812,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004994463633558945,
|
||
|
|
"loss": 6.0434,
|
||
|
|
"mean_token_accuracy": 0.12345149591565133,
|
||
|
|
"num_tokens": 2641896.0,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.380703020095825,
|
||
|
|
"epoch": 1.2148260211800301,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004994182050561917,
|
||
|
|
"loss": 6.1134,
|
||
|
|
"mean_token_accuracy": 0.11929800137877464,
|
||
|
|
"num_tokens": 2654208.0,
|
||
|
|
"step": 1205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.355344963073731,
|
||
|
|
"epoch": 1.2198688855269793,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004993893492595306,
|
||
|
|
"loss": 6.0965,
|
||
|
|
"mean_token_accuracy": 0.12326192557811737,
|
||
|
|
"num_tokens": 2665115.0,
|
||
|
|
"step": 1210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.437494277954102,
|
||
|
|
"epoch": 1.2249117498739284,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004993597960555959,
|
||
|
|
"loss": 6.1801,
|
||
|
|
"mean_token_accuracy": 0.11685346364974976,
|
||
|
|
"num_tokens": 2676093.0,
|
||
|
|
"step": 1215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.38605375289917,
|
||
|
|
"epoch": 1.2299546142208775,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004993295455362395,
|
||
|
|
"loss": 6.1218,
|
||
|
|
"mean_token_accuracy": 0.12748127356171607,
|
||
|
|
"num_tokens": 2687866.0,
|
||
|
|
"step": 1220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.403005504608155,
|
||
|
|
"epoch": 1.2349974785678266,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004992985977954808,
|
||
|
|
"loss": 6.1404,
|
||
|
|
"mean_token_accuracy": 0.12012984082102776,
|
||
|
|
"num_tokens": 2699814.0,
|
||
|
|
"step": 1225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.36786527633667,
|
||
|
|
"epoch": 1.2400403429147757,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000499266952929506,
|
||
|
|
"loss": 6.1101,
|
||
|
|
"mean_token_accuracy": 0.13033016249537469,
|
||
|
|
"num_tokens": 2710384.0,
|
||
|
|
"step": 1230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3866376876831055,
|
||
|
|
"epoch": 1.2450832072617246,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004992346110366682,
|
||
|
|
"loss": 6.0859,
|
||
|
|
"mean_token_accuracy": 0.12090532258152961,
|
||
|
|
"num_tokens": 2721442.0,
|
||
|
|
"step": 1235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.362185049057007,
|
||
|
|
"epoch": 1.2501260716086737,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.0004992015722174865,
|
||
|
|
"loss": 6.1027,
|
||
|
|
"mean_token_accuracy": 0.11984567195177079,
|
||
|
|
"num_tokens": 2733605.0,
|
||
|
|
"step": 1240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.381150722503662,
|
||
|
|
"epoch": 1.2551689359556228,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004991678365746466,
|
||
|
|
"loss": 6.1376,
|
||
|
|
"mean_token_accuracy": 0.12807665169239044,
|
||
|
|
"num_tokens": 2744853.0,
|
||
|
|
"step": 1245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.278868913650513,
|
||
|
|
"epoch": 1.2602118003025717,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004991334042129996,
|
||
|
|
"loss": 6.0394,
|
||
|
|
"mean_token_accuracy": 0.12930434346199035,
|
||
|
|
"num_tokens": 2754477.0,
|
||
|
|
"step": 1250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3861668586730955,
|
||
|
|
"epoch": 1.2652546646495209,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004990982752395618,
|
||
|
|
"loss": 6.062,
|
||
|
|
"mean_token_accuracy": 0.12282699942588807,
|
||
|
|
"num_tokens": 2765895.0,
|
||
|
|
"step": 1255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3185412883758545,
|
||
|
|
"epoch": 1.27029752899647,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004990624497635152,
|
||
|
|
"loss": 6.0955,
|
||
|
|
"mean_token_accuracy": 0.12333361357450486,
|
||
|
|
"num_tokens": 2776897.0,
|
||
|
|
"step": 1260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4460615634918215,
|
||
|
|
"epoch": 1.275340393343419,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.000499025927896206,
|
||
|
|
"loss": 6.1191,
|
||
|
|
"mean_token_accuracy": 0.12341732308268547,
|
||
|
|
"num_tokens": 2788666.0,
|
||
|
|
"step": 1265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.285901021957398,
|
||
|
|
"epoch": 1.2803832576903682,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004989887097511451,
|
||
|
|
"loss": 6.0122,
|
||
|
|
"mean_token_accuracy": 0.12529174312949182,
|
||
|
|
"num_tokens": 2799167.0,
|
||
|
|
"step": 1270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.281661653518677,
|
||
|
|
"epoch": 1.2854261220373173,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004989507954440074,
|
||
|
|
"loss": 6.0129,
|
||
|
|
"mean_token_accuracy": 0.11882785484194755,
|
||
|
|
"num_tokens": 2809774.0,
|
||
|
|
"step": 1275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.318780517578125,
|
||
|
|
"epoch": 1.2904689863842662,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004989121850926313,
|
||
|
|
"loss": 6.1337,
|
||
|
|
"mean_token_accuracy": 0.11986329406499863,
|
||
|
|
"num_tokens": 2820515.0,
|
||
|
|
"step": 1280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.336706733703613,
|
||
|
|
"epoch": 1.2955118507312153,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004988728788170188,
|
||
|
|
"loss": 6.0786,
|
||
|
|
"mean_token_accuracy": 0.1216197930276394,
|
||
|
|
"num_tokens": 2832163.0,
|
||
|
|
"step": 1285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.311708307266235,
|
||
|
|
"epoch": 1.3005547150781644,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004988328767393346,
|
||
|
|
"loss": 6.0644,
|
||
|
|
"mean_token_accuracy": 0.1252337910234928,
|
||
|
|
"num_tokens": 2843717.0,
|
||
|
|
"step": 1290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.23866548538208,
|
||
|
|
"epoch": 1.3055975794251133,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004987921789839061,
|
||
|
|
"loss": 6.0187,
|
||
|
|
"mean_token_accuracy": 0.12154641002416611,
|
||
|
|
"num_tokens": 2854489.0,
|
||
|
|
"step": 1295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.304507398605347,
|
||
|
|
"epoch": 1.3106404437720625,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004987507856772229,
|
||
|
|
"loss": 6.0674,
|
||
|
|
"mean_token_accuracy": 0.12463115528225899,
|
||
|
|
"num_tokens": 2865317.0,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.30941219329834,
|
||
|
|
"epoch": 1.3156833081190116,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004987086969479364,
|
||
|
|
"loss": 5.9961,
|
||
|
|
"mean_token_accuracy": 0.12587646394968033,
|
||
|
|
"num_tokens": 2877466.0,
|
||
|
|
"step": 1305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2870680809021,
|
||
|
|
"epoch": 1.3207261724659607,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004986659129268592,
|
||
|
|
"loss": 6.018,
|
||
|
|
"mean_token_accuracy": 0.1252691850066185,
|
||
|
|
"num_tokens": 2887698.0,
|
||
|
|
"step": 1310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.190779304504394,
|
||
|
|
"epoch": 1.3257690368129098,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004986224337469652,
|
||
|
|
"loss": 5.9728,
|
||
|
|
"mean_token_accuracy": 0.13109618574380874,
|
||
|
|
"num_tokens": 2899339.0,
|
||
|
|
"step": 1315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.250626802444458,
|
||
|
|
"epoch": 1.330811901159859,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004985782595433886,
|
||
|
|
"loss": 6.0246,
|
||
|
|
"mean_token_accuracy": 0.12930653765797614,
|
||
|
|
"num_tokens": 2908340.0,
|
||
|
|
"step": 1320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.36276421546936,
|
||
|
|
"epoch": 1.3358547655068078,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004985333904534237,
|
||
|
|
"loss": 6.1153,
|
||
|
|
"mean_token_accuracy": 0.12473672702908516,
|
||
|
|
"num_tokens": 2920432.0,
|
||
|
|
"step": 1325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.318589591979981,
|
||
|
|
"epoch": 1.340897629853757,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000498487826616525,
|
||
|
|
"loss": 6.0603,
|
||
|
|
"mean_token_accuracy": 0.12252447828650474,
|
||
|
|
"num_tokens": 2930385.0,
|
||
|
|
"step": 1330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.31836199760437,
|
||
|
|
"epoch": 1.345940494200706,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004984415681743056,
|
||
|
|
"loss": 6.0133,
|
||
|
|
"mean_token_accuracy": 0.1288218967616558,
|
||
|
|
"num_tokens": 2940760.0,
|
||
|
|
"step": 1335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.281600284576416,
|
||
|
|
"epoch": 1.350983358547655,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004983946152705382,
|
||
|
|
"loss": 6.0344,
|
||
|
|
"mean_token_accuracy": 0.13234889060258864,
|
||
|
|
"num_tokens": 2952441.0,
|
||
|
|
"step": 1340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.320213270187378,
|
||
|
|
"epoch": 1.356026222894604,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004983469680511531,
|
||
|
|
"loss": 6.0584,
|
||
|
|
"mean_token_accuracy": 0.125762165337801,
|
||
|
|
"num_tokens": 2962766.0,
|
||
|
|
"step": 1345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2049356460571286,
|
||
|
|
"epoch": 1.3610690872415532,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004982986266642393,
|
||
|
|
"loss": 5.9448,
|
||
|
|
"mean_token_accuracy": 0.13519371226429938,
|
||
|
|
"num_tokens": 2974239.0,
|
||
|
|
"step": 1350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.304392290115357,
|
||
|
|
"epoch": 1.3661119515885023,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004982495912600426,
|
||
|
|
"loss": 5.9836,
|
||
|
|
"mean_token_accuracy": 0.12600109577178956,
|
||
|
|
"num_tokens": 2984497.0,
|
||
|
|
"step": 1355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.244618892669678,
|
||
|
|
"epoch": 1.3711548159354514,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004981998619909664,
|
||
|
|
"loss": 5.9772,
|
||
|
|
"mean_token_accuracy": 0.12882400155067444,
|
||
|
|
"num_tokens": 2995367.0,
|
||
|
|
"step": 1360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.267851448059082,
|
||
|
|
"epoch": 1.3761976802824005,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004981494390115704,
|
||
|
|
"loss": 6.0067,
|
||
|
|
"mean_token_accuracy": 0.1295331373810768,
|
||
|
|
"num_tokens": 3007687.0,
|
||
|
|
"step": 1365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.281758832931518,
|
||
|
|
"epoch": 1.3812405446293494,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004980983224785704,
|
||
|
|
"loss": 6.0025,
|
||
|
|
"mean_token_accuracy": 0.1259416989982128,
|
||
|
|
"num_tokens": 3017505.0,
|
||
|
|
"step": 1370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1590625762939455,
|
||
|
|
"epoch": 1.3862834089762985,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004980465125508376,
|
||
|
|
"loss": 5.9409,
|
||
|
|
"mean_token_accuracy": 0.12704395055770873,
|
||
|
|
"num_tokens": 3028271.0,
|
||
|
|
"step": 1375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.286492538452149,
|
||
|
|
"epoch": 1.3913262733232477,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004979940093893986,
|
||
|
|
"loss": 5.9927,
|
||
|
|
"mean_token_accuracy": 0.12936830893158913,
|
||
|
|
"num_tokens": 3040440.0,
|
||
|
|
"step": 1380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.132359313964844,
|
||
|
|
"epoch": 1.3963691376701965,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004979408131574345,
|
||
|
|
"loss": 5.9758,
|
||
|
|
"mean_token_accuracy": 0.12391475141048432,
|
||
|
|
"num_tokens": 3050999.0,
|
||
|
|
"step": 1385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.337554454803467,
|
||
|
|
"epoch": 1.4014120020171457,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004978869240202802,
|
||
|
|
"loss": 6.027,
|
||
|
|
"mean_token_accuracy": 0.12895868942141533,
|
||
|
|
"num_tokens": 3063374.0,
|
||
|
|
"step": 1390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.267091894149781,
|
||
|
|
"epoch": 1.4064548663640948,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004978323421454246,
|
||
|
|
"loss": 6.0622,
|
||
|
|
"mean_token_accuracy": 0.12893708497285844,
|
||
|
|
"num_tokens": 3075464.0,
|
||
|
|
"step": 1395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.185108709335327,
|
||
|
|
"epoch": 1.411497730711044,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004977770677025092,
|
||
|
|
"loss": 5.9221,
|
||
|
|
"mean_token_accuracy": 0.1268825463950634,
|
||
|
|
"num_tokens": 3086398.0,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.22553391456604,
|
||
|
|
"epoch": 1.416540595057993,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004977211008633284,
|
||
|
|
"loss": 6.0521,
|
||
|
|
"mean_token_accuracy": 0.11881259009242058,
|
||
|
|
"num_tokens": 3097777.0,
|
||
|
|
"step": 1405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.272607231140137,
|
||
|
|
"epoch": 1.4215834594049421,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004976644418018285,
|
||
|
|
"loss": 6.0208,
|
||
|
|
"mean_token_accuracy": 0.13160417675971986,
|
||
|
|
"num_tokens": 3108711.0,
|
||
|
|
"step": 1410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2519410133361815,
|
||
|
|
"epoch": 1.426626323751891,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000497607090694107,
|
||
|
|
"loss": 6.0407,
|
||
|
|
"mean_token_accuracy": 0.12776092514395715,
|
||
|
|
"num_tokens": 3119589.0,
|
||
|
|
"step": 1415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.209818506240845,
|
||
|
|
"epoch": 1.4316691880988401,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0004975490477184126,
|
||
|
|
"loss": 5.973,
|
||
|
|
"mean_token_accuracy": 0.13335097581148148,
|
||
|
|
"num_tokens": 3131744.0,
|
||
|
|
"step": 1420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2790721416473385,
|
||
|
|
"epoch": 1.4367120524457893,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.000497490313055144,
|
||
|
|
"loss": 6.0089,
|
||
|
|
"mean_token_accuracy": 0.12579527944326402,
|
||
|
|
"num_tokens": 3143526.0,
|
||
|
|
"step": 1425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.256898641586304,
|
||
|
|
"epoch": 1.4417549167927382,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004974308868868501,
|
||
|
|
"loss": 5.9551,
|
||
|
|
"mean_token_accuracy": 0.12504913732409478,
|
||
|
|
"num_tokens": 3154561.0,
|
||
|
|
"step": 1430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.238351345062256,
|
||
|
|
"epoch": 1.4467977811396873,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004973707693982287,
|
||
|
|
"loss": 6.1168,
|
||
|
|
"mean_token_accuracy": 0.12133650034666062,
|
||
|
|
"num_tokens": 3166052.0,
|
||
|
|
"step": 1435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.357213068008423,
|
||
|
|
"epoch": 1.4518406454866364,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004973099607761264,
|
||
|
|
"loss": 6.0734,
|
||
|
|
"mean_token_accuracy": 0.12326012775301934,
|
||
|
|
"num_tokens": 3179335.0,
|
||
|
|
"step": 1440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.196079301834106,
|
||
|
|
"epoch": 1.4568835098335855,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004972484612095378,
|
||
|
|
"loss": 5.9556,
|
||
|
|
"mean_token_accuracy": 0.12705831453204156,
|
||
|
|
"num_tokens": 3192129.0,
|
||
|
|
"step": 1445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.309902286529541,
|
||
|
|
"epoch": 1.4619263741805346,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000497186270889605,
|
||
|
|
"loss": 6.0646,
|
||
|
|
"mean_token_accuracy": 0.12445836812257767,
|
||
|
|
"num_tokens": 3202792.0,
|
||
|
|
"step": 1450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.250305843353272,
|
||
|
|
"epoch": 1.4669692385274837,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004971233900096169,
|
||
|
|
"loss": 6.0093,
|
||
|
|
"mean_token_accuracy": 0.12253658324480057,
|
||
|
|
"num_tokens": 3213707.0,
|
||
|
|
"step": 1455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.325912141799927,
|
||
|
|
"epoch": 1.4720121028744326,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004970598187650085,
|
||
|
|
"loss": 5.9955,
|
||
|
|
"mean_token_accuracy": 0.13006001710891724,
|
||
|
|
"num_tokens": 3224531.0,
|
||
|
|
"step": 1460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.210040140151977,
|
||
|
|
"epoch": 1.4770549672213817,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000496995557353361,
|
||
|
|
"loss": 5.9749,
|
||
|
|
"mean_token_accuracy": 0.1309881828725338,
|
||
|
|
"num_tokens": 3234656.0,
|
||
|
|
"step": 1465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.212216138839722,
|
||
|
|
"epoch": 1.4820978315683309,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004969306059744004,
|
||
|
|
"loss": 6.0054,
|
||
|
|
"mean_token_accuracy": 0.13170277923345566,
|
||
|
|
"num_tokens": 3246745.0,
|
||
|
|
"step": 1470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.162950563430786,
|
||
|
|
"epoch": 1.4871406959152798,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004968649648299968,
|
||
|
|
"loss": 5.9935,
|
||
|
|
"mean_token_accuracy": 0.12871679663658142,
|
||
|
|
"num_tokens": 3257277.0,
|
||
|
|
"step": 1475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.304571056365967,
|
||
|
|
"epoch": 1.4921835602622289,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004967986341241646,
|
||
|
|
"loss": 5.9564,
|
||
|
|
"mean_token_accuracy": 0.13108997642993928,
|
||
|
|
"num_tokens": 3267704.0,
|
||
|
|
"step": 1480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.211066675186157,
|
||
|
|
"epoch": 1.497226424609178,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004967316140630611,
|
||
|
|
"loss": 6.0263,
|
||
|
|
"mean_token_accuracy": 0.1284073054790497,
|
||
|
|
"num_tokens": 3279772.0,
|
||
|
|
"step": 1485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.19977822303772,
|
||
|
|
"epoch": 1.502269288956127,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004966639048549862,
|
||
|
|
"loss": 5.9248,
|
||
|
|
"mean_token_accuracy": 0.13373203277587892,
|
||
|
|
"num_tokens": 3290536.0,
|
||
|
|
"step": 1490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.163003826141358,
|
||
|
|
"epoch": 1.5073121533030762,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004965955067103816,
|
||
|
|
"loss": 6.0015,
|
||
|
|
"mean_token_accuracy": 0.13202472701668738,
|
||
|
|
"num_tokens": 3302051.0,
|
||
|
|
"step": 1495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.216978979110718,
|
||
|
|
"epoch": 1.5123550176500253,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004965264198418305,
|
||
|
|
"loss": 5.9805,
|
||
|
|
"mean_token_accuracy": 0.11812185272574424,
|
||
|
|
"num_tokens": 3314324.0,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.5123550176500253,
|
||
|
|
"eval_entropy": 5.988947841047331,
|
||
|
|
"eval_loss": 6.126096725463867,
|
||
|
|
"eval_mean_token_accuracy": 0.12609033783276877,
|
||
|
|
"eval_num_tokens": 3314324.0,
|
||
|
|
"eval_runtime": 2.0434,
|
||
|
|
"eval_samples_per_second": 1535.706,
|
||
|
|
"eval_steps_per_second": 192.33,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.162470149993896,
|
||
|
|
"epoch": 1.5173978819969742,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004964566444640564,
|
||
|
|
"loss": 5.9764,
|
||
|
|
"mean_token_accuracy": 0.12956623807549478,
|
||
|
|
"num_tokens": 3326246.0,
|
||
|
|
"step": 1505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1691357612609865,
|
||
|
|
"epoch": 1.5224407463439233,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004963861807939227,
|
||
|
|
"loss": 5.9697,
|
||
|
|
"mean_token_accuracy": 0.13050643503665924,
|
||
|
|
"num_tokens": 3336308.0,
|
||
|
|
"step": 1510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.113428115844727,
|
||
|
|
"epoch": 1.5274836106908725,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004963150290504321,
|
||
|
|
"loss": 5.9096,
|
||
|
|
"mean_token_accuracy": 0.1319293461740017,
|
||
|
|
"num_tokens": 3347596.0,
|
||
|
|
"step": 1515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.130649662017822,
|
||
|
|
"epoch": 1.5325264750378214,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004962431894547259,
|
||
|
|
"loss": 5.8863,
|
||
|
|
"mean_token_accuracy": 0.13102136179804802,
|
||
|
|
"num_tokens": 3358370.0,
|
||
|
|
"step": 1520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.282006025314331,
|
||
|
|
"epoch": 1.5375693393847705,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004961706622300834,
|
||
|
|
"loss": 5.9189,
|
||
|
|
"mean_token_accuracy": 0.12766351029276848,
|
||
|
|
"num_tokens": 3368630.0,
|
||
|
|
"step": 1525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.164436769485474,
|
||
|
|
"epoch": 1.5426122037317196,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004960974476019206,
|
||
|
|
"loss": 5.9346,
|
||
|
|
"mean_token_accuracy": 0.13147821873426438,
|
||
|
|
"num_tokens": 3379952.0,
|
||
|
|
"step": 1530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.137597465515137,
|
||
|
|
"epoch": 1.5476550680786687,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004960235457977905,
|
||
|
|
"loss": 5.8684,
|
||
|
|
"mean_token_accuracy": 0.13159159570932388,
|
||
|
|
"num_tokens": 3390097.0,
|
||
|
|
"step": 1535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.087500667572021,
|
||
|
|
"epoch": 1.5526979324256178,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004959489570473814,
|
||
|
|
"loss": 5.8595,
|
||
|
|
"mean_token_accuracy": 0.1370345577597618,
|
||
|
|
"num_tokens": 3399778.0,
|
||
|
|
"step": 1540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.216370344161987,
|
||
|
|
"epoch": 1.557740796772567,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.000495873681582517,
|
||
|
|
"loss": 6.0103,
|
||
|
|
"mean_token_accuracy": 0.12765116170048713,
|
||
|
|
"num_tokens": 3410213.0,
|
||
|
|
"step": 1545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.172270250320435,
|
||
|
|
"epoch": 1.5627836611195158,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004957977196371552,
|
||
|
|
"loss": 6.0277,
|
||
|
|
"mean_token_accuracy": 0.13068305626511573,
|
||
|
|
"num_tokens": 3422071.0,
|
||
|
|
"step": 1550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.241772222518921,
|
||
|
|
"epoch": 1.567826525466465,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004957210714473873,
|
||
|
|
"loss": 5.9931,
|
||
|
|
"mean_token_accuracy": 0.13293333649635314,
|
||
|
|
"num_tokens": 3432102.0,
|
||
|
|
"step": 1555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.157260370254517,
|
||
|
|
"epoch": 1.572869389813414,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004956437372514378,
|
||
|
|
"loss": 5.962,
|
||
|
|
"mean_token_accuracy": 0.12790244817733765,
|
||
|
|
"num_tokens": 3442821.0,
|
||
|
|
"step": 1560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1026246547698975,
|
||
|
|
"epoch": 1.577912254160363,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004955657172896631,
|
||
|
|
"loss": 5.9231,
|
||
|
|
"mean_token_accuracy": 0.1324974425137043,
|
||
|
|
"num_tokens": 3454378.0,
|
||
|
|
"step": 1565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.163491344451904,
|
||
|
|
"epoch": 1.582955118507312,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004954870118045511,
|
||
|
|
"loss": 5.9412,
|
||
|
|
"mean_token_accuracy": 0.13418091386556624,
|
||
|
|
"num_tokens": 3463933.0,
|
||
|
|
"step": 1570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.149846458435059,
|
||
|
|
"epoch": 1.5879979828542612,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004954076210407203,
|
||
|
|
"loss": 5.8842,
|
||
|
|
"mean_token_accuracy": 0.12891194969415665,
|
||
|
|
"num_tokens": 3473993.0,
|
||
|
|
"step": 1575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.184996604919434,
|
||
|
|
"epoch": 1.5930408472012103,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004953275452449188,
|
||
|
|
"loss": 6.0255,
|
||
|
|
"mean_token_accuracy": 0.12238797843456269,
|
||
|
|
"num_tokens": 3484882.0,
|
||
|
|
"step": 1580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.172972679138184,
|
||
|
|
"epoch": 1.5980837115481594,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004952467846660243,
|
||
|
|
"loss": 5.9429,
|
||
|
|
"mean_token_accuracy": 0.13000317960977553,
|
||
|
|
"num_tokens": 3496503.0,
|
||
|
|
"step": 1585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.168394422531128,
|
||
|
|
"epoch": 1.6031265758951085,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004951653395550423,
|
||
|
|
"loss": 6.0277,
|
||
|
|
"mean_token_accuracy": 0.13080177530646325,
|
||
|
|
"num_tokens": 3508696.0,
|
||
|
|
"step": 1590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.255574321746826,
|
||
|
|
"epoch": 1.6081694402420574,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004950832101651062,
|
||
|
|
"loss": 5.9399,
|
||
|
|
"mean_token_accuracy": 0.13680166453123094,
|
||
|
|
"num_tokens": 3519542.0,
|
||
|
|
"step": 1595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.162024974822998,
|
||
|
|
"epoch": 1.6132123045890066,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004950003967514762,
|
||
|
|
"loss": 5.9039,
|
||
|
|
"mean_token_accuracy": 0.13319480940699577,
|
||
|
|
"num_tokens": 3531576.0,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.168517971038819,
|
||
|
|
"epoch": 1.6182551689359557,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.000494916899571538,
|
||
|
|
"loss": 5.8714,
|
||
|
|
"mean_token_accuracy": 0.13608561530709268,
|
||
|
|
"num_tokens": 3542816.0,
|
||
|
|
"step": 1605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.182320785522461,
|
||
|
|
"epoch": 1.6232980332829046,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004948327188848029,
|
||
|
|
"loss": 6.0066,
|
||
|
|
"mean_token_accuracy": 0.12684836611151695,
|
||
|
|
"num_tokens": 3554100.0,
|
||
|
|
"step": 1610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.230264568328858,
|
||
|
|
"epoch": 1.6283408976298537,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004947478549529065,
|
||
|
|
"loss": 5.8562,
|
||
|
|
"mean_token_accuracy": 0.12772923931479455,
|
||
|
|
"num_tokens": 3565048.0,
|
||
|
|
"step": 1615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.198247385025025,
|
||
|
|
"epoch": 1.6333837619768028,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004946623080396077,
|
||
|
|
"loss": 5.9378,
|
||
|
|
"mean_token_accuracy": 0.1336819685995579,
|
||
|
|
"num_tokens": 3575587.0,
|
||
|
|
"step": 1620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.148627471923828,
|
||
|
|
"epoch": 1.638426626323752,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004945760784107884,
|
||
|
|
"loss": 6.0094,
|
||
|
|
"mean_token_accuracy": 0.12861310243606566,
|
||
|
|
"num_tokens": 3587059.0,
|
||
|
|
"step": 1625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1220705032348635,
|
||
|
|
"epoch": 1.643469490670701,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004944891663344522,
|
||
|
|
"loss": 5.8406,
|
||
|
|
"mean_token_accuracy": 0.13324351757764816,
|
||
|
|
"num_tokens": 3598492.0,
|
||
|
|
"step": 1630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.100050592422486,
|
||
|
|
"epoch": 1.6485123550176501,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004944015720807239,
|
||
|
|
"loss": 5.9125,
|
||
|
|
"mean_token_accuracy": 0.1337079659104347,
|
||
|
|
"num_tokens": 3609513.0,
|
||
|
|
"step": 1635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.179864168167114,
|
||
|
|
"epoch": 1.653555219364599,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004943132959218484,
|
||
|
|
"loss": 5.9377,
|
||
|
|
"mean_token_accuracy": 0.13239555582404136,
|
||
|
|
"num_tokens": 3621327.0,
|
||
|
|
"step": 1640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.07295184135437,
|
||
|
|
"epoch": 1.6585980837115482,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00049422433813219,
|
||
|
|
"loss": 5.8455,
|
||
|
|
"mean_token_accuracy": 0.1334436446428299,
|
||
|
|
"num_tokens": 3632136.0,
|
||
|
|
"step": 1645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.140309047698975,
|
||
|
|
"epoch": 1.6636409480584973,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004941346989882318,
|
||
|
|
"loss": 5.8253,
|
||
|
|
"mean_token_accuracy": 0.13711320981383324,
|
||
|
|
"num_tokens": 3642271.0,
|
||
|
|
"step": 1650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.994101095199585,
|
||
|
|
"epoch": 1.6686838124054462,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004940443787685739,
|
||
|
|
"loss": 5.9454,
|
||
|
|
"mean_token_accuracy": 0.12989369183778762,
|
||
|
|
"num_tokens": 3652355.0,
|
||
|
|
"step": 1655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.283844423294068,
|
||
|
|
"epoch": 1.6737266767523953,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004939533777539341,
|
||
|
|
"loss": 5.9346,
|
||
|
|
"mean_token_accuracy": 0.12859864830970763,
|
||
|
|
"num_tokens": 3663714.0,
|
||
|
|
"step": 1660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0334240913391115,
|
||
|
|
"epoch": 1.6787695410993444,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004938616962271453,
|
||
|
|
"loss": 5.8808,
|
||
|
|
"mean_token_accuracy": 0.12998360991477967,
|
||
|
|
"num_tokens": 3674675.0,
|
||
|
|
"step": 1665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.12380805015564,
|
||
|
|
"epoch": 1.6838124054462935,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004937693344731561,
|
||
|
|
"loss": 5.954,
|
||
|
|
"mean_token_accuracy": 0.1350781202316284,
|
||
|
|
"num_tokens": 3686403.0,
|
||
|
|
"step": 1670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.118779897689819,
|
||
|
|
"epoch": 1.6888552697932426,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004936762927790286,
|
||
|
|
"loss": 5.8456,
|
||
|
|
"mean_token_accuracy": 0.1421683058142662,
|
||
|
|
"num_tokens": 3697259.0,
|
||
|
|
"step": 1675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.124578905105591,
|
||
|
|
"epoch": 1.6938981341401917,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004935825714339389,
|
||
|
|
"loss": 5.9011,
|
||
|
|
"mean_token_accuracy": 0.1348792150616646,
|
||
|
|
"num_tokens": 3708536.0,
|
||
|
|
"step": 1680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.220402526855469,
|
||
|
|
"epoch": 1.6989409984871406,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004934881707291748,
|
||
|
|
"loss": 5.9122,
|
||
|
|
"mean_token_accuracy": 0.1309715911746025,
|
||
|
|
"num_tokens": 3719181.0,
|
||
|
|
"step": 1685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.012847232818603,
|
||
|
|
"epoch": 1.7039838628340898,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004933930909581362,
|
||
|
|
"loss": 5.7549,
|
||
|
|
"mean_token_accuracy": 0.13449717462062835,
|
||
|
|
"num_tokens": 3729325.0,
|
||
|
|
"step": 1690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.101225805282593,
|
||
|
|
"epoch": 1.7090267271810389,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004932973324163328,
|
||
|
|
"loss": 5.9008,
|
||
|
|
"mean_token_accuracy": 0.13119059279561043,
|
||
|
|
"num_tokens": 3740462.0,
|
||
|
|
"step": 1695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.210686779022216,
|
||
|
|
"epoch": 1.7140695915279878,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004932008954013846,
|
||
|
|
"loss": 5.9776,
|
||
|
|
"mean_token_accuracy": 0.13249426260590552,
|
||
|
|
"num_tokens": 3752523.0,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.021712589263916,
|
||
|
|
"epoch": 1.7191124558749369,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004931037802130201,
|
||
|
|
"loss": 5.8401,
|
||
|
|
"mean_token_accuracy": 0.13165827840566635,
|
||
|
|
"num_tokens": 3764120.0,
|
||
|
|
"step": 1705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.134450483322143,
|
||
|
|
"epoch": 1.724155320221886,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004930059871530755,
|
||
|
|
"loss": 5.9728,
|
||
|
|
"mean_token_accuracy": 0.13011515960097314,
|
||
|
|
"num_tokens": 3776733.0,
|
||
|
|
"step": 1710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.178735971450806,
|
||
|
|
"epoch": 1.7291981845688351,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004929075165254938,
|
||
|
|
"loss": 5.9398,
|
||
|
|
"mean_token_accuracy": 0.126145376265049,
|
||
|
|
"num_tokens": 3787799.0,
|
||
|
|
"step": 1715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.030863428115845,
|
||
|
|
"epoch": 1.7342410489157842,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004928083686363241,
|
||
|
|
"loss": 5.863,
|
||
|
|
"mean_token_accuracy": 0.13384964913129807,
|
||
|
|
"num_tokens": 3797995.0,
|
||
|
|
"step": 1720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.203894710540771,
|
||
|
|
"epoch": 1.7392839132627333,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004927085437937204,
|
||
|
|
"loss": 5.9367,
|
||
|
|
"mean_token_accuracy": 0.13228645250201226,
|
||
|
|
"num_tokens": 3809580.0,
|
||
|
|
"step": 1725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.146491956710816,
|
||
|
|
"epoch": 1.7443267776096822,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004926080423079404,
|
||
|
|
"loss": 5.9601,
|
||
|
|
"mean_token_accuracy": 0.13396261408925056,
|
||
|
|
"num_tokens": 3820150.0,
|
||
|
|
"step": 1730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.114956378936768,
|
||
|
|
"epoch": 1.7493696419566314,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000492506864491345,
|
||
|
|
"loss": 5.8223,
|
||
|
|
"mean_token_accuracy": 0.1336710497736931,
|
||
|
|
"num_tokens": 3830391.0,
|
||
|
|
"step": 1735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.977906370162964,
|
||
|
|
"epoch": 1.7544125063035805,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004924050106583976,
|
||
|
|
"loss": 5.8382,
|
||
|
|
"mean_token_accuracy": 0.13849121034145356,
|
||
|
|
"num_tokens": 3842773.0,
|
||
|
|
"step": 1740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.199583864212036,
|
||
|
|
"epoch": 1.7594553706505294,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004923024811256618,
|
||
|
|
"loss": 5.8795,
|
||
|
|
"mean_token_accuracy": 0.13239177986979483,
|
||
|
|
"num_tokens": 3853646.0,
|
||
|
|
"step": 1745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.085389232635498,
|
||
|
|
"epoch": 1.7644982349974785,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.000492199276211802,
|
||
|
|
"loss": 5.8426,
|
||
|
|
"mean_token_accuracy": 0.13615378588438035,
|
||
|
|
"num_tokens": 3865319.0,
|
||
|
|
"step": 1750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.044885206222534,
|
||
|
|
"epoch": 1.7695410993444276,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004920953962375813,
|
||
|
|
"loss": 5.8977,
|
||
|
|
"mean_token_accuracy": 0.13141547441482543,
|
||
|
|
"num_tokens": 3877107.0,
|
||
|
|
"step": 1755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.093702268600464,
|
||
|
|
"epoch": 1.7745839636913767,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004919908415258612,
|
||
|
|
"loss": 5.9368,
|
||
|
|
"mean_token_accuracy": 0.13592029139399528,
|
||
|
|
"num_tokens": 3889334.0,
|
||
|
|
"step": 1760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.16692967414856,
|
||
|
|
"epoch": 1.7796268280383258,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004918856124016002,
|
||
|
|
"loss": 5.8309,
|
||
|
|
"mean_token_accuracy": 0.13962946012616156,
|
||
|
|
"num_tokens": 3899482.0,
|
||
|
|
"step": 1765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.017588901519775,
|
||
|
|
"epoch": 1.784669692385275,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004917797091918526,
|
||
|
|
"loss": 5.7533,
|
||
|
|
"mean_token_accuracy": 0.14028869047760964,
|
||
|
|
"num_tokens": 3910216.0,
|
||
|
|
"step": 1770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.108081436157226,
|
||
|
|
"epoch": 1.789712556732224,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004916731322257683,
|
||
|
|
"loss": 5.9182,
|
||
|
|
"mean_token_accuracy": 0.13611244261264802,
|
||
|
|
"num_tokens": 3922246.0,
|
||
|
|
"step": 1775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.097801351547242,
|
||
|
|
"epoch": 1.794755421079173,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004915658818345908,
|
||
|
|
"loss": 5.8098,
|
||
|
|
"mean_token_accuracy": 0.14234220013022422,
|
||
|
|
"num_tokens": 3933688.0,
|
||
|
|
"step": 1780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0966685771942135,
|
||
|
|
"epoch": 1.799798285426122,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004914579583516568,
|
||
|
|
"loss": 5.9188,
|
||
|
|
"mean_token_accuracy": 0.1313386917114258,
|
||
|
|
"num_tokens": 3944168.0,
|
||
|
|
"step": 1785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.024723100662231,
|
||
|
|
"epoch": 1.804841149773071,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000491349362112395,
|
||
|
|
"loss": 5.8244,
|
||
|
|
"mean_token_accuracy": 0.13950928971171378,
|
||
|
|
"num_tokens": 3954346.0,
|
||
|
|
"step": 1790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.133016967773438,
|
||
|
|
"epoch": 1.80988401412002,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.000491240093454325,
|
||
|
|
"loss": 5.9441,
|
||
|
|
"mean_token_accuracy": 0.13316622376441956,
|
||
|
|
"num_tokens": 3966375.0,
|
||
|
|
"step": 1795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1298604011535645,
|
||
|
|
"epoch": 1.8149268784669692,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004911301527170563,
|
||
|
|
"loss": 5.91,
|
||
|
|
"mean_token_accuracy": 0.13569873794913292,
|
||
|
|
"num_tokens": 3977030.0,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.000961494445801,
|
||
|
|
"epoch": 1.8199697428139183,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004910195402422873,
|
||
|
|
"loss": 5.8183,
|
||
|
|
"mean_token_accuracy": 0.13428226485848427,
|
||
|
|
"num_tokens": 3988064.0,
|
||
|
|
"step": 1805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.15083794593811,
|
||
|
|
"epoch": 1.8250126071608674,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004909082563738042,
|
||
|
|
"loss": 5.8778,
|
||
|
|
"mean_token_accuracy": 0.13448215946555137,
|
||
|
|
"num_tokens": 3997994.0,
|
||
|
|
"step": 1810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.131000089645386,
|
||
|
|
"epoch": 1.8300554715078166,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004907963014574797,
|
||
|
|
"loss": 5.9245,
|
||
|
|
"mean_token_accuracy": 0.13084746673703193,
|
||
|
|
"num_tokens": 4008645.0,
|
||
|
|
"step": 1815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.088234567642212,
|
||
|
|
"epoch": 1.8350983358547657,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004906836758412722,
|
||
|
|
"loss": 5.8739,
|
||
|
|
"mean_token_accuracy": 0.1310124434530735,
|
||
|
|
"num_tokens": 4020387.0,
|
||
|
|
"step": 1820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.93744158744812,
|
||
|
|
"epoch": 1.8401412002017146,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004905703798752248,
|
||
|
|
"loss": 5.7445,
|
||
|
|
"mean_token_accuracy": 0.138221687823534,
|
||
|
|
"num_tokens": 4032720.0,
|
||
|
|
"step": 1825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.048615217208862,
|
||
|
|
"epoch": 1.8451840645486637,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.000490456413911464,
|
||
|
|
"loss": 5.8111,
|
||
|
|
"mean_token_accuracy": 0.1402272567152977,
|
||
|
|
"num_tokens": 4043438.0,
|
||
|
|
"step": 1830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0049676418304445,
|
||
|
|
"epoch": 1.8502269288956126,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004903417783041987,
|
||
|
|
"loss": 5.8002,
|
||
|
|
"mean_token_accuracy": 0.14097705483436584,
|
||
|
|
"num_tokens": 4054467.0,
|
||
|
|
"step": 1835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.081655836105346,
|
||
|
|
"epoch": 1.8552697932425617,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004902264734097188,
|
||
|
|
"loss": 5.797,
|
||
|
|
"mean_token_accuracy": 0.13625596538186074,
|
||
|
|
"num_tokens": 4066418.0,
|
||
|
|
"step": 1840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.121115112304688,
|
||
|
|
"epoch": 1.8603126575895108,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004901104995863948,
|
||
|
|
"loss": 5.8976,
|
||
|
|
"mean_token_accuracy": 0.1304987095296383,
|
||
|
|
"num_tokens": 4078770.0,
|
||
|
|
"step": 1845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.036437129974365,
|
||
|
|
"epoch": 1.86535552193646,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004899938571946759,
|
||
|
|
"loss": 5.9277,
|
||
|
|
"mean_token_accuracy": 0.1331052951514721,
|
||
|
|
"num_tokens": 4089998.0,
|
||
|
|
"step": 1850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.108745002746582,
|
||
|
|
"epoch": 1.870398386283409,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004898765465970894,
|
||
|
|
"loss": 5.84,
|
||
|
|
"mean_token_accuracy": 0.140093395113945,
|
||
|
|
"num_tokens": 4101409.0,
|
||
|
|
"step": 1855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.08279275894165,
|
||
|
|
"epoch": 1.8754412506303582,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004897585681582393,
|
||
|
|
"loss": 5.9562,
|
||
|
|
"mean_token_accuracy": 0.13204566687345504,
|
||
|
|
"num_tokens": 4113598.0,
|
||
|
|
"step": 1860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0311401844024655,
|
||
|
|
"epoch": 1.8804841149773073,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004896399222448053,
|
||
|
|
"loss": 5.8903,
|
||
|
|
"mean_token_accuracy": 0.13502624183893203,
|
||
|
|
"num_tokens": 4124639.0,
|
||
|
|
"step": 1865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1842851638793945,
|
||
|
|
"epoch": 1.8855269793242562,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004895206092255417,
|
||
|
|
"loss": 5.9528,
|
||
|
|
"mean_token_accuracy": 0.1261625297367573,
|
||
|
|
"num_tokens": 4136280.0,
|
||
|
|
"step": 1870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0394891738891605,
|
||
|
|
"epoch": 1.8905698436712053,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004894006294712761,
|
||
|
|
"loss": 5.798,
|
||
|
|
"mean_token_accuracy": 0.13385596573352815,
|
||
|
|
"num_tokens": 4148251.0,
|
||
|
|
"step": 1875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.066561222076416,
|
||
|
|
"epoch": 1.8956127080181542,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004892799833549083,
|
||
|
|
"loss": 5.8793,
|
||
|
|
"mean_token_accuracy": 0.13789762407541276,
|
||
|
|
"num_tokens": 4159298.0,
|
||
|
|
"step": 1880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.094835710525513,
|
||
|
|
"epoch": 1.9006555723651033,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004891586712514091,
|
||
|
|
"loss": 5.7976,
|
||
|
|
"mean_token_accuracy": 0.13934613019227982,
|
||
|
|
"num_tokens": 4169974.0,
|
||
|
|
"step": 1885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.004667186737061,
|
||
|
|
"epoch": 1.9056984367120524,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004890366935378196,
|
||
|
|
"loss": 5.7951,
|
||
|
|
"mean_token_accuracy": 0.1426852449774742,
|
||
|
|
"num_tokens": 4181442.0,
|
||
|
|
"step": 1890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.072988843917846,
|
||
|
|
"epoch": 1.9107413010590015,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004889140505932492,
|
||
|
|
"loss": 5.8431,
|
||
|
|
"mean_token_accuracy": 0.1416805826127529,
|
||
|
|
"num_tokens": 4191535.0,
|
||
|
|
"step": 1895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.028358507156372,
|
||
|
|
"epoch": 1.9157841654059506,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004887907427988749,
|
||
|
|
"loss": 5.8658,
|
||
|
|
"mean_token_accuracy": 0.13532739132642746,
|
||
|
|
"num_tokens": 4201741.0,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.012132596969605,
|
||
|
|
"epoch": 1.9208270297528998,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004886667705379403,
|
||
|
|
"loss": 5.7607,
|
||
|
|
"mean_token_accuracy": 0.1425751641392708,
|
||
|
|
"num_tokens": 4211762.0,
|
||
|
|
"step": 1905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.053383636474609,
|
||
|
|
"epoch": 1.9258698940998489,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004885421341957541,
|
||
|
|
"loss": 5.8402,
|
||
|
|
"mean_token_accuracy": 0.13849018067121505,
|
||
|
|
"num_tokens": 4222322.0,
|
||
|
|
"step": 1910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.139491748809815,
|
||
|
|
"epoch": 1.9309127584467978,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004884168341596888,
|
||
|
|
"loss": 5.9232,
|
||
|
|
"mean_token_accuracy": 0.13450294807553292,
|
||
|
|
"num_tokens": 4232166.0,
|
||
|
|
"step": 1915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.027013111114502,
|
||
|
|
"epoch": 1.9359556227937469,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004882908708191797,
|
||
|
|
"loss": 5.8756,
|
||
|
|
"mean_token_accuracy": 0.13291192501783372,
|
||
|
|
"num_tokens": 4243651.0,
|
||
|
|
"step": 1920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.078602075576782,
|
||
|
|
"epoch": 1.9409984871406958,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.00048816424456572403,
|
||
|
|
"loss": 5.8051,
|
||
|
|
"mean_token_accuracy": 0.14046954810619355,
|
||
|
|
"num_tokens": 4255137.0,
|
||
|
|
"step": 1925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.943156766891479,
|
||
|
|
"epoch": 1.946041351487645,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00048803695579287905,
|
||
|
|
"loss": 5.804,
|
||
|
|
"mean_token_accuracy": 0.13446772545576097,
|
||
|
|
"num_tokens": 4264904.0,
|
||
|
|
"step": 1930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.996735715866089,
|
||
|
|
"epoch": 1.951084215834594,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00048790900489626104,
|
||
|
|
"loss": 5.7651,
|
||
|
|
"mean_token_accuracy": 0.1391440138220787,
|
||
|
|
"num_tokens": 4275305.0,
|
||
|
|
"step": 1935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.009812355041504,
|
||
|
|
"epoch": 1.9561270801815431,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004877803922735445,
|
||
|
|
"loss": 5.8517,
|
||
|
|
"mean_token_accuracy": 0.13518264666199684,
|
||
|
|
"num_tokens": 4287038.0,
|
||
|
|
"step": 1940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1983202457427975,
|
||
|
|
"epoch": 1.9611699445284922,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004876511183244603,
|
||
|
|
"loss": 5.9598,
|
||
|
|
"mean_token_accuracy": 0.12747678980231286,
|
||
|
|
"num_tokens": 4298668.0,
|
||
|
|
"step": 1945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.964114427566528,
|
||
|
|
"epoch": 1.9662128088754414,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00048752118345079496,
|
||
|
|
"loss": 5.7317,
|
||
|
|
"mean_token_accuracy": 0.1404605582356453,
|
||
|
|
"num_tokens": 4309429.0,
|
||
|
|
"step": 1950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.004175186157227,
|
||
|
|
"epoch": 1.9712556732223905,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00048739058805638905,
|
||
|
|
"loss": 5.8295,
|
||
|
|
"mean_token_accuracy": 0.13574060425162315,
|
||
|
|
"num_tokens": 4321137.0,
|
||
|
|
"step": 1955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.061343431472778,
|
||
|
|
"epoch": 1.9762985375693394,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.000487259332547136,
|
||
|
|
"loss": 5.8552,
|
||
|
|
"mean_token_accuracy": 0.1286994807422161,
|
||
|
|
"num_tokens": 4331249.0,
|
||
|
|
"step": 1960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.057663679122925,
|
||
|
|
"epoch": 1.9813414019162885,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.000487127417330981,
|
||
|
|
"loss": 5.8436,
|
||
|
|
"mean_token_accuracy": 0.1318496935069561,
|
||
|
|
"num_tokens": 4342154.0,
|
||
|
|
"step": 1965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.129978799819947,
|
||
|
|
"epoch": 1.9863842662632374,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004869948428179196,
|
||
|
|
"loss": 5.878,
|
||
|
|
"mean_token_accuracy": 0.13126063123345375,
|
||
|
|
"num_tokens": 4353906.0,
|
||
|
|
"step": 1970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.023782205581665,
|
||
|
|
"epoch": 1.9914271306101865,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004868616094199964,
|
||
|
|
"loss": 5.9263,
|
||
|
|
"mean_token_accuracy": 0.13177506774663925,
|
||
|
|
"num_tokens": 4366416.0,
|
||
|
|
"step": 1975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.075288438796997,
|
||
|
|
"epoch": 1.9964699949571356,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000486727717551304,
|
||
|
|
"loss": 5.8269,
|
||
|
|
"mean_token_accuracy": 0.1384887605905533,
|
||
|
|
"num_tokens": 4376743.0,
|
||
|
|
"step": 1980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.952099906073676,
|
||
|
|
"epoch": 2.00100857286939,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004865931676279813,
|
||
|
|
"loss": 5.6221,
|
||
|
|
"mean_token_accuracy": 0.15006235241889954,
|
||
|
|
"num_tokens": 4385379.0,
|
||
|
|
"step": 1985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.009042406082154,
|
||
|
|
"epoch": 2.006051437216339,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004864579600682125,
|
||
|
|
"loss": 5.5673,
|
||
|
|
"mean_token_accuracy": 0.14534694105386733,
|
||
|
|
"num_tokens": 4396872.0,
|
||
|
|
"step": 1990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.029089117050171,
|
||
|
|
"epoch": 2.011094301563288,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.00048632209529222607,
|
||
|
|
"loss": 5.493,
|
||
|
|
"mean_token_accuracy": 0.15098107904195784,
|
||
|
|
"num_tokens": 4407075.0,
|
||
|
|
"step": 1995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.954484272003174,
|
||
|
|
"epoch": 2.016137165910237,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00048618557372229253,
|
||
|
|
"loss": 5.528,
|
||
|
|
"mean_token_accuracy": 0.15284537971019746,
|
||
|
|
"num_tokens": 4418020.0,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.016137165910237,
|
||
|
|
"eval_entropy": 5.739924000116401,
|
||
|
|
"eval_loss": 5.955663204193115,
|
||
|
|
"eval_mean_token_accuracy": 0.13522450197440675,
|
||
|
|
"eval_num_tokens": 4418020.0,
|
||
|
|
"eval_runtime": 2.0884,
|
||
|
|
"eval_samples_per_second": 1502.568,
|
||
|
|
"eval_steps_per_second": 188.18,
|
||
|
|
"step": 2000
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 9910,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 10,
|
||
|
|
"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": 1095357125652480.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|