10045 lines
275 KiB
JSON
10045 lines
275 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.0,
|
|
"eval_steps": 500,
|
|
"global_step": 5000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.002,
|
|
"grad_norm": 3.529070725879476,
|
|
"learning_rate": 9.999984208641271e-06,
|
|
"loss": 0.4748,
|
|
"num_input_tokens_seen": 396688,
|
|
"step": 5,
|
|
"train_runtime": 75.1268,
|
|
"train_tokens_per_second": 5280.244
|
|
},
|
|
{
|
|
"epoch": 0.004,
|
|
"grad_norm": 1.1725318777053566,
|
|
"learning_rate": 9.999920056417385e-06,
|
|
"loss": 0.3853,
|
|
"num_input_tokens_seen": 780032,
|
|
"step": 10,
|
|
"train_runtime": 138.2073,
|
|
"train_tokens_per_second": 5643.926
|
|
},
|
|
{
|
|
"epoch": 0.006,
|
|
"grad_norm": 1.050069609189703,
|
|
"learning_rate": 9.999806557001092e-06,
|
|
"loss": 0.3416,
|
|
"num_input_tokens_seen": 1239888,
|
|
"step": 15,
|
|
"train_runtime": 205.0125,
|
|
"train_tokens_per_second": 6047.864
|
|
},
|
|
{
|
|
"epoch": 0.008,
|
|
"grad_norm": 1.0659218188772097,
|
|
"learning_rate": 9.999643711512586e-06,
|
|
"loss": 0.3701,
|
|
"num_input_tokens_seen": 1603472,
|
|
"step": 20,
|
|
"train_runtime": 265.8186,
|
|
"train_tokens_per_second": 6032.204
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"grad_norm": 0.820657214467373,
|
|
"learning_rate": 9.999431521559081e-06,
|
|
"loss": 0.3371,
|
|
"num_input_tokens_seen": 1963184,
|
|
"step": 25,
|
|
"train_runtime": 325.7553,
|
|
"train_tokens_per_second": 6026.56
|
|
},
|
|
{
|
|
"epoch": 0.012,
|
|
"grad_norm": 1.1800961461261863,
|
|
"learning_rate": 9.999169989234815e-06,
|
|
"loss": 0.3436,
|
|
"num_input_tokens_seen": 2326256,
|
|
"step": 30,
|
|
"train_runtime": 387.5961,
|
|
"train_tokens_per_second": 6001.753
|
|
},
|
|
{
|
|
"epoch": 0.014,
|
|
"grad_norm": 1.231264145354163,
|
|
"learning_rate": 9.998859117121e-06,
|
|
"loss": 0.3498,
|
|
"num_input_tokens_seen": 2713648,
|
|
"step": 35,
|
|
"train_runtime": 444.7317,
|
|
"train_tokens_per_second": 6101.765
|
|
},
|
|
{
|
|
"epoch": 0.016,
|
|
"grad_norm": 0.9000852106140734,
|
|
"learning_rate": 9.99849890828582e-06,
|
|
"loss": 0.3205,
|
|
"num_input_tokens_seen": 3106864,
|
|
"step": 40,
|
|
"train_runtime": 510.8204,
|
|
"train_tokens_per_second": 6082.106
|
|
},
|
|
{
|
|
"epoch": 0.018,
|
|
"grad_norm": 0.8813007763453813,
|
|
"learning_rate": 9.998089366284392e-06,
|
|
"loss": 0.3272,
|
|
"num_input_tokens_seen": 3513728,
|
|
"step": 45,
|
|
"train_runtime": 573.2378,
|
|
"train_tokens_per_second": 6129.617
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"grad_norm": 0.842498340169096,
|
|
"learning_rate": 9.997630495158728e-06,
|
|
"loss": 0.3279,
|
|
"num_input_tokens_seen": 3950720,
|
|
"step": 50,
|
|
"train_runtime": 651.4821,
|
|
"train_tokens_per_second": 6064.203
|
|
},
|
|
{
|
|
"epoch": 0.022,
|
|
"grad_norm": 0.7406379773223285,
|
|
"learning_rate": 9.9971222994377e-06,
|
|
"loss": 0.304,
|
|
"num_input_tokens_seen": 4341968,
|
|
"step": 55,
|
|
"train_runtime": 723.0612,
|
|
"train_tokens_per_second": 6004.98
|
|
},
|
|
{
|
|
"epoch": 0.024,
|
|
"grad_norm": 0.9246450042837577,
|
|
"learning_rate": 9.996564784137e-06,
|
|
"loss": 0.2791,
|
|
"num_input_tokens_seen": 4716832,
|
|
"step": 60,
|
|
"train_runtime": 789.7507,
|
|
"train_tokens_per_second": 5972.558
|
|
},
|
|
{
|
|
"epoch": 0.026,
|
|
"grad_norm": 0.6813867833298154,
|
|
"learning_rate": 9.995957954759073e-06,
|
|
"loss": 0.3242,
|
|
"num_input_tokens_seen": 5190560,
|
|
"step": 65,
|
|
"train_runtime": 868.1415,
|
|
"train_tokens_per_second": 5978.933
|
|
},
|
|
{
|
|
"epoch": 0.028,
|
|
"grad_norm": 0.958297020853992,
|
|
"learning_rate": 9.995301817293084e-06,
|
|
"loss": 0.3044,
|
|
"num_input_tokens_seen": 5563120,
|
|
"step": 70,
|
|
"train_runtime": 931.2634,
|
|
"train_tokens_per_second": 5973.734
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"grad_norm": 0.8856568117076815,
|
|
"learning_rate": 9.99459637821484e-06,
|
|
"loss": 0.3096,
|
|
"num_input_tokens_seen": 5970768,
|
|
"step": 75,
|
|
"train_runtime": 998.4455,
|
|
"train_tokens_per_second": 5980.064
|
|
},
|
|
{
|
|
"epoch": 0.032,
|
|
"grad_norm": 1.1073162962080754,
|
|
"learning_rate": 9.993841644486747e-06,
|
|
"loss": 0.3166,
|
|
"num_input_tokens_seen": 6259376,
|
|
"step": 80,
|
|
"train_runtime": 1039.407,
|
|
"train_tokens_per_second": 6022.065
|
|
},
|
|
{
|
|
"epoch": 0.034,
|
|
"grad_norm": 0.9231847695523737,
|
|
"learning_rate": 9.993037623557716e-06,
|
|
"loss": 0.3017,
|
|
"num_input_tokens_seen": 6654464,
|
|
"step": 85,
|
|
"train_runtime": 1110.0658,
|
|
"train_tokens_per_second": 5994.657
|
|
},
|
|
{
|
|
"epoch": 0.036,
|
|
"grad_norm": 0.8821941113621354,
|
|
"learning_rate": 9.992184323363112e-06,
|
|
"loss": 0.2731,
|
|
"num_input_tokens_seen": 7023760,
|
|
"step": 90,
|
|
"train_runtime": 1183.6772,
|
|
"train_tokens_per_second": 5933.848
|
|
},
|
|
{
|
|
"epoch": 0.038,
|
|
"grad_norm": 1.0797634407658638,
|
|
"learning_rate": 9.991281752324664e-06,
|
|
"loss": 0.3023,
|
|
"num_input_tokens_seen": 7436112,
|
|
"step": 95,
|
|
"train_runtime": 1257.9906,
|
|
"train_tokens_per_second": 5911.103
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"grad_norm": 1.103353756296292,
|
|
"learning_rate": 9.990329919350382e-06,
|
|
"loss": 0.2834,
|
|
"num_input_tokens_seen": 7791888,
|
|
"step": 100,
|
|
"train_runtime": 1322.6092,
|
|
"train_tokens_per_second": 5891.301
|
|
},
|
|
{
|
|
"epoch": 0.042,
|
|
"grad_norm": 0.8278175812097224,
|
|
"learning_rate": 9.989328833834472e-06,
|
|
"loss": 0.3008,
|
|
"num_input_tokens_seen": 8185936,
|
|
"step": 105,
|
|
"train_runtime": 1380.3591,
|
|
"train_tokens_per_second": 5930.294
|
|
},
|
|
{
|
|
"epoch": 0.044,
|
|
"grad_norm": 0.7830140246513998,
|
|
"learning_rate": 9.988278505657247e-06,
|
|
"loss": 0.2933,
|
|
"num_input_tokens_seen": 8598768,
|
|
"step": 110,
|
|
"train_runtime": 1447.4638,
|
|
"train_tokens_per_second": 5940.576
|
|
},
|
|
{
|
|
"epoch": 0.046,
|
|
"grad_norm": 0.6319254381860551,
|
|
"learning_rate": 9.987178945185019e-06,
|
|
"loss": 0.2986,
|
|
"num_input_tokens_seen": 9017264,
|
|
"step": 115,
|
|
"train_runtime": 1515.8302,
|
|
"train_tokens_per_second": 5948.73
|
|
},
|
|
{
|
|
"epoch": 0.048,
|
|
"grad_norm": 0.7754207741241279,
|
|
"learning_rate": 9.986030163270011e-06,
|
|
"loss": 0.3024,
|
|
"num_input_tokens_seen": 9449872,
|
|
"step": 120,
|
|
"train_runtime": 1593.8688,
|
|
"train_tokens_per_second": 5928.889
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"grad_norm": 0.6941365154998115,
|
|
"learning_rate": 9.98483217125023e-06,
|
|
"loss": 0.2553,
|
|
"num_input_tokens_seen": 9874192,
|
|
"step": 125,
|
|
"train_runtime": 1663.0592,
|
|
"train_tokens_per_second": 5937.366
|
|
},
|
|
{
|
|
"epoch": 0.052,
|
|
"grad_norm": 0.8267427353263731,
|
|
"learning_rate": 9.98358498094938e-06,
|
|
"loss": 0.3012,
|
|
"num_input_tokens_seen": 10278272,
|
|
"step": 130,
|
|
"train_runtime": 1727.2891,
|
|
"train_tokens_per_second": 5950.522
|
|
},
|
|
{
|
|
"epoch": 0.054,
|
|
"grad_norm": 2.1153588465265982,
|
|
"learning_rate": 9.982288604676719e-06,
|
|
"loss": 0.2758,
|
|
"num_input_tokens_seen": 10695136,
|
|
"step": 135,
|
|
"train_runtime": 1793.2202,
|
|
"train_tokens_per_second": 5964.207
|
|
},
|
|
{
|
|
"epoch": 0.056,
|
|
"grad_norm": 0.8604952494397087,
|
|
"learning_rate": 9.980943055226964e-06,
|
|
"loss": 0.3056,
|
|
"num_input_tokens_seen": 11039680,
|
|
"step": 140,
|
|
"train_runtime": 1854.7104,
|
|
"train_tokens_per_second": 5952.239
|
|
},
|
|
{
|
|
"epoch": 0.058,
|
|
"grad_norm": 0.8382901602209842,
|
|
"learning_rate": 9.979548345880142e-06,
|
|
"loss": 0.2943,
|
|
"num_input_tokens_seen": 11454128,
|
|
"step": 145,
|
|
"train_runtime": 1926.181,
|
|
"train_tokens_per_second": 5946.548
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"grad_norm": 0.8875123598888999,
|
|
"learning_rate": 9.978104490401468e-06,
|
|
"loss": 0.2913,
|
|
"num_input_tokens_seen": 11794496,
|
|
"step": 150,
|
|
"train_runtime": 1978.6218,
|
|
"train_tokens_per_second": 5960.965
|
|
},
|
|
{
|
|
"epoch": 0.062,
|
|
"grad_norm": 1.0539384040695126,
|
|
"learning_rate": 9.976611503041218e-06,
|
|
"loss": 0.3153,
|
|
"num_input_tokens_seen": 12169264,
|
|
"step": 155,
|
|
"train_runtime": 2051.3054,
|
|
"train_tokens_per_second": 5932.449
|
|
},
|
|
{
|
|
"epoch": 0.064,
|
|
"grad_norm": 0.8524180493974752,
|
|
"learning_rate": 9.975069398534574e-06,
|
|
"loss": 0.2993,
|
|
"num_input_tokens_seen": 12515168,
|
|
"step": 160,
|
|
"train_runtime": 2113.3806,
|
|
"train_tokens_per_second": 5921.871
|
|
},
|
|
{
|
|
"epoch": 0.066,
|
|
"grad_norm": 1.0205477764931508,
|
|
"learning_rate": 9.97347819210148e-06,
|
|
"loss": 0.2946,
|
|
"num_input_tokens_seen": 12905488,
|
|
"step": 165,
|
|
"train_runtime": 2174.4797,
|
|
"train_tokens_per_second": 5934.978
|
|
},
|
|
{
|
|
"epoch": 0.068,
|
|
"grad_norm": 0.7838766165442029,
|
|
"learning_rate": 9.971837899446505e-06,
|
|
"loss": 0.3075,
|
|
"num_input_tokens_seen": 13358672,
|
|
"step": 170,
|
|
"train_runtime": 2252.5741,
|
|
"train_tokens_per_second": 5930.403
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"grad_norm": 0.8892411786342892,
|
|
"learning_rate": 9.970148536758678e-06,
|
|
"loss": 0.2952,
|
|
"num_input_tokens_seen": 13779472,
|
|
"step": 175,
|
|
"train_runtime": 2315.3569,
|
|
"train_tokens_per_second": 5951.338
|
|
},
|
|
{
|
|
"epoch": 0.072,
|
|
"grad_norm": 1.0296532392116329,
|
|
"learning_rate": 9.968410120711321e-06,
|
|
"loss": 0.2709,
|
|
"num_input_tokens_seen": 14093728,
|
|
"step": 180,
|
|
"train_runtime": 2371.6187,
|
|
"train_tokens_per_second": 5942.662
|
|
},
|
|
{
|
|
"epoch": 0.074,
|
|
"grad_norm": 0.8880922770210048,
|
|
"learning_rate": 9.966622668461899e-06,
|
|
"loss": 0.2928,
|
|
"num_input_tokens_seen": 14595840,
|
|
"step": 185,
|
|
"train_runtime": 2444.1035,
|
|
"train_tokens_per_second": 5971.858
|
|
},
|
|
{
|
|
"epoch": 0.076,
|
|
"grad_norm": 0.9979494314336124,
|
|
"learning_rate": 9.964786197651848e-06,
|
|
"loss": 0.2898,
|
|
"num_input_tokens_seen": 14919280,
|
|
"step": 190,
|
|
"train_runtime": 2497.4922,
|
|
"train_tokens_per_second": 5973.704
|
|
},
|
|
{
|
|
"epoch": 0.078,
|
|
"grad_norm": 0.9769457891685653,
|
|
"learning_rate": 9.96290072640639e-06,
|
|
"loss": 0.2992,
|
|
"num_input_tokens_seen": 15268256,
|
|
"step": 195,
|
|
"train_runtime": 2567.8553,
|
|
"train_tokens_per_second": 5945.918
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"grad_norm": 0.9296142727078585,
|
|
"learning_rate": 9.96096627333437e-06,
|
|
"loss": 0.3001,
|
|
"num_input_tokens_seen": 15678432,
|
|
"step": 200,
|
|
"train_runtime": 2635.5512,
|
|
"train_tokens_per_second": 5948.825
|
|
},
|
|
{
|
|
"epoch": 0.082,
|
|
"grad_norm": 1.2434185369871753,
|
|
"learning_rate": 9.958982857528053e-06,
|
|
"loss": 0.2888,
|
|
"num_input_tokens_seen": 16161600,
|
|
"step": 205,
|
|
"train_runtime": 2714.3312,
|
|
"train_tokens_per_second": 5954.174
|
|
},
|
|
{
|
|
"epoch": 0.084,
|
|
"grad_norm": 0.7574454494180245,
|
|
"learning_rate": 9.956950498562954e-06,
|
|
"loss": 0.2696,
|
|
"num_input_tokens_seen": 16572832,
|
|
"step": 210,
|
|
"train_runtime": 2789.5683,
|
|
"train_tokens_per_second": 5941.002
|
|
},
|
|
{
|
|
"epoch": 0.086,
|
|
"grad_norm": 1.0339850849304288,
|
|
"learning_rate": 9.954869216497636e-06,
|
|
"loss": 0.298,
|
|
"num_input_tokens_seen": 16966064,
|
|
"step": 215,
|
|
"train_runtime": 2858.0332,
|
|
"train_tokens_per_second": 5936.272
|
|
},
|
|
{
|
|
"epoch": 0.088,
|
|
"grad_norm": 0.9072760950057258,
|
|
"learning_rate": 9.952739031873513e-06,
|
|
"loss": 0.2919,
|
|
"num_input_tokens_seen": 17326464,
|
|
"step": 220,
|
|
"train_runtime": 2923.5635,
|
|
"train_tokens_per_second": 5926.488
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"grad_norm": 0.9033068608878783,
|
|
"learning_rate": 9.950559965714647e-06,
|
|
"loss": 0.29,
|
|
"num_input_tokens_seen": 17798944,
|
|
"step": 225,
|
|
"train_runtime": 2998.1702,
|
|
"train_tokens_per_second": 5936.602
|
|
},
|
|
{
|
|
"epoch": 0.092,
|
|
"grad_norm": 0.7265860170186728,
|
|
"learning_rate": 9.948332039527541e-06,
|
|
"loss": 0.281,
|
|
"num_input_tokens_seen": 18203216,
|
|
"step": 230,
|
|
"train_runtime": 3064.0023,
|
|
"train_tokens_per_second": 5940.993
|
|
},
|
|
{
|
|
"epoch": 0.094,
|
|
"grad_norm": 0.7719043892731912,
|
|
"learning_rate": 9.946055275300929e-06,
|
|
"loss": 0.2857,
|
|
"num_input_tokens_seen": 18595600,
|
|
"step": 235,
|
|
"train_runtime": 3122.8974,
|
|
"train_tokens_per_second": 5954.598
|
|
},
|
|
{
|
|
"epoch": 0.096,
|
|
"grad_norm": 0.684701998859407,
|
|
"learning_rate": 9.943729695505552e-06,
|
|
"loss": 0.276,
|
|
"num_input_tokens_seen": 19005936,
|
|
"step": 240,
|
|
"train_runtime": 3188.4373,
|
|
"train_tokens_per_second": 5960.894
|
|
},
|
|
{
|
|
"epoch": 0.098,
|
|
"grad_norm": 0.946898379784884,
|
|
"learning_rate": 9.941355323093944e-06,
|
|
"loss": 0.297,
|
|
"num_input_tokens_seen": 19412496,
|
|
"step": 245,
|
|
"train_runtime": 3255.2016,
|
|
"train_tokens_per_second": 5963.531
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"grad_norm": 0.9553375335195206,
|
|
"learning_rate": 9.938932181500206e-06,
|
|
"loss": 0.2649,
|
|
"num_input_tokens_seen": 19830960,
|
|
"step": 250,
|
|
"train_runtime": 3333.374,
|
|
"train_tokens_per_second": 5949.215
|
|
},
|
|
{
|
|
"epoch": 0.102,
|
|
"grad_norm": 0.8135687801680254,
|
|
"learning_rate": 9.93646029463976e-06,
|
|
"loss": 0.252,
|
|
"num_input_tokens_seen": 20210288,
|
|
"step": 255,
|
|
"train_runtime": 3401.5027,
|
|
"train_tokens_per_second": 5941.576
|
|
},
|
|
{
|
|
"epoch": 0.104,
|
|
"grad_norm": 0.7875655466453482,
|
|
"learning_rate": 9.933939686909137e-06,
|
|
"loss": 0.2986,
|
|
"num_input_tokens_seen": 20651728,
|
|
"step": 260,
|
|
"train_runtime": 3475.6609,
|
|
"train_tokens_per_second": 5941.813
|
|
},
|
|
{
|
|
"epoch": 0.106,
|
|
"grad_norm": 1.270712900867129,
|
|
"learning_rate": 9.931370383185717e-06,
|
|
"loss": 0.2679,
|
|
"num_input_tokens_seen": 21084048,
|
|
"step": 265,
|
|
"train_runtime": 3549.0279,
|
|
"train_tokens_per_second": 5940.795
|
|
},
|
|
{
|
|
"epoch": 0.108,
|
|
"grad_norm": 0.9393845827359342,
|
|
"learning_rate": 9.92875240882749e-06,
|
|
"loss": 0.2861,
|
|
"num_input_tokens_seen": 21420560,
|
|
"step": 270,
|
|
"train_runtime": 3601.2535,
|
|
"train_tokens_per_second": 5948.084
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"grad_norm": 0.7444755169661749,
|
|
"learning_rate": 9.926085789672806e-06,
|
|
"loss": 0.2649,
|
|
"num_input_tokens_seen": 21794608,
|
|
"step": 275,
|
|
"train_runtime": 3667.1267,
|
|
"train_tokens_per_second": 5943.238
|
|
},
|
|
{
|
|
"epoch": 0.112,
|
|
"grad_norm": 0.7145025641256342,
|
|
"learning_rate": 9.923370552040117e-06,
|
|
"loss": 0.3103,
|
|
"num_input_tokens_seen": 22200176,
|
|
"step": 280,
|
|
"train_runtime": 3735.5676,
|
|
"train_tokens_per_second": 5942.919
|
|
},
|
|
{
|
|
"epoch": 0.114,
|
|
"grad_norm": 0.8512241574919769,
|
|
"learning_rate": 9.920606722727726e-06,
|
|
"loss": 0.2771,
|
|
"num_input_tokens_seen": 22588416,
|
|
"step": 285,
|
|
"train_runtime": 3792.0445,
|
|
"train_tokens_per_second": 5956.791
|
|
},
|
|
{
|
|
"epoch": 0.116,
|
|
"grad_norm": 0.6266092029054396,
|
|
"learning_rate": 9.917794329013511e-06,
|
|
"loss": 0.2872,
|
|
"num_input_tokens_seen": 22996016,
|
|
"step": 290,
|
|
"train_runtime": 3857.7998,
|
|
"train_tokens_per_second": 5960.915
|
|
},
|
|
{
|
|
"epoch": 0.118,
|
|
"grad_norm": 0.751809560103108,
|
|
"learning_rate": 9.914933398654663e-06,
|
|
"loss": 0.2847,
|
|
"num_input_tokens_seen": 23433456,
|
|
"step": 295,
|
|
"train_runtime": 3927.9056,
|
|
"train_tokens_per_second": 5965.891
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"grad_norm": 0.6755889847224258,
|
|
"learning_rate": 9.912023959887408e-06,
|
|
"loss": 0.2537,
|
|
"num_input_tokens_seen": 23781600,
|
|
"step": 300,
|
|
"train_runtime": 3982.1935,
|
|
"train_tokens_per_second": 5971.985
|
|
},
|
|
{
|
|
"epoch": 0.122,
|
|
"grad_norm": 0.943323280572443,
|
|
"learning_rate": 9.909066041426733e-06,
|
|
"loss": 0.2843,
|
|
"num_input_tokens_seen": 24225024,
|
|
"step": 305,
|
|
"train_runtime": 4055.2554,
|
|
"train_tokens_per_second": 5973.736
|
|
},
|
|
{
|
|
"epoch": 0.124,
|
|
"grad_norm": 1.2175580370359331,
|
|
"learning_rate": 9.9060596724661e-06,
|
|
"loss": 0.2864,
|
|
"num_input_tokens_seen": 24592480,
|
|
"step": 310,
|
|
"train_runtime": 4115.2286,
|
|
"train_tokens_per_second": 5975.969
|
|
},
|
|
{
|
|
"epoch": 0.126,
|
|
"grad_norm": 1.0147370785297811,
|
|
"learning_rate": 9.903004882677157e-06,
|
|
"loss": 0.2892,
|
|
"num_input_tokens_seen": 24957024,
|
|
"step": 315,
|
|
"train_runtime": 4168.4655,
|
|
"train_tokens_per_second": 5987.101
|
|
},
|
|
{
|
|
"epoch": 0.128,
|
|
"grad_norm": 0.7344408173379581,
|
|
"learning_rate": 9.899901702209445e-06,
|
|
"loss": 0.2789,
|
|
"num_input_tokens_seen": 25374832,
|
|
"step": 320,
|
|
"train_runtime": 4244.2432,
|
|
"train_tokens_per_second": 5978.647
|
|
},
|
|
{
|
|
"epoch": 0.13,
|
|
"grad_norm": 1.3103019223544174,
|
|
"learning_rate": 9.8967501616901e-06,
|
|
"loss": 0.2766,
|
|
"num_input_tokens_seen": 25810848,
|
|
"step": 325,
|
|
"train_runtime": 4317.4147,
|
|
"train_tokens_per_second": 5978.311
|
|
},
|
|
{
|
|
"epoch": 0.132,
|
|
"grad_norm": 0.8685597289161924,
|
|
"learning_rate": 9.89355029222356e-06,
|
|
"loss": 0.293,
|
|
"num_input_tokens_seen": 26237024,
|
|
"step": 330,
|
|
"train_runtime": 4380.5436,
|
|
"train_tokens_per_second": 5989.445
|
|
},
|
|
{
|
|
"epoch": 0.134,
|
|
"grad_norm": 0.8404098804337911,
|
|
"learning_rate": 9.89030212539124e-06,
|
|
"loss": 0.286,
|
|
"num_input_tokens_seen": 26629216,
|
|
"step": 335,
|
|
"train_runtime": 4437.1469,
|
|
"train_tokens_per_second": 6001.428
|
|
},
|
|
{
|
|
"epoch": 0.136,
|
|
"grad_norm": 0.7386985305075902,
|
|
"learning_rate": 9.88700569325124e-06,
|
|
"loss": 0.3048,
|
|
"num_input_tokens_seen": 27042592,
|
|
"step": 340,
|
|
"train_runtime": 4503.3805,
|
|
"train_tokens_per_second": 6004.954
|
|
},
|
|
{
|
|
"epoch": 0.138,
|
|
"grad_norm": 0.8859553305112097,
|
|
"learning_rate": 9.883661028338009e-06,
|
|
"loss": 0.2555,
|
|
"num_input_tokens_seen": 27433280,
|
|
"step": 345,
|
|
"train_runtime": 4577.0851,
|
|
"train_tokens_per_second": 5993.614
|
|
},
|
|
{
|
|
"epoch": 0.14,
|
|
"grad_norm": 0.7480812603367697,
|
|
"learning_rate": 9.880268163662043e-06,
|
|
"loss": 0.2678,
|
|
"num_input_tokens_seen": 27796240,
|
|
"step": 350,
|
|
"train_runtime": 4640.6632,
|
|
"train_tokens_per_second": 5989.713
|
|
},
|
|
{
|
|
"epoch": 0.142,
|
|
"grad_norm": 1.1794465477248353,
|
|
"learning_rate": 9.876827132709545e-06,
|
|
"loss": 0.2818,
|
|
"num_input_tokens_seen": 28242816,
|
|
"step": 355,
|
|
"train_runtime": 4716.0159,
|
|
"train_tokens_per_second": 5988.702
|
|
},
|
|
{
|
|
"epoch": 0.144,
|
|
"grad_norm": 0.8608826793810502,
|
|
"learning_rate": 9.873337969442102e-06,
|
|
"loss": 0.2624,
|
|
"num_input_tokens_seen": 28623824,
|
|
"step": 360,
|
|
"train_runtime": 4784.382,
|
|
"train_tokens_per_second": 5982.763
|
|
},
|
|
{
|
|
"epoch": 0.146,
|
|
"grad_norm": 0.842112418190514,
|
|
"learning_rate": 9.869800708296347e-06,
|
|
"loss": 0.2888,
|
|
"num_input_tokens_seen": 29059536,
|
|
"step": 365,
|
|
"train_runtime": 4860.2713,
|
|
"train_tokens_per_second": 5978.995
|
|
},
|
|
{
|
|
"epoch": 0.148,
|
|
"grad_norm": 0.7582805292047462,
|
|
"learning_rate": 9.86621538418362e-06,
|
|
"loss": 0.2907,
|
|
"num_input_tokens_seen": 29474832,
|
|
"step": 370,
|
|
"train_runtime": 4921.9495,
|
|
"train_tokens_per_second": 5988.447
|
|
},
|
|
{
|
|
"epoch": 0.15,
|
|
"grad_norm": 0.7906066031029222,
|
|
"learning_rate": 9.862582032489621e-06,
|
|
"loss": 0.2706,
|
|
"num_input_tokens_seen": 29872512,
|
|
"step": 375,
|
|
"train_runtime": 4981.8012,
|
|
"train_tokens_per_second": 5996.328
|
|
},
|
|
{
|
|
"epoch": 0.152,
|
|
"grad_norm": 0.7636592190389889,
|
|
"learning_rate": 9.858900689074065e-06,
|
|
"loss": 0.2743,
|
|
"num_input_tokens_seen": 30343872,
|
|
"step": 380,
|
|
"train_runtime": 5056.2219,
|
|
"train_tokens_per_second": 6001.294
|
|
},
|
|
{
|
|
"epoch": 0.154,
|
|
"grad_norm": 0.7503467243251319,
|
|
"learning_rate": 9.855171390270325e-06,
|
|
"loss": 0.2688,
|
|
"num_input_tokens_seen": 30848768,
|
|
"step": 385,
|
|
"train_runtime": 5131.3151,
|
|
"train_tokens_per_second": 6011.864
|
|
},
|
|
{
|
|
"epoch": 0.156,
|
|
"grad_norm": 2.8570072621011606,
|
|
"learning_rate": 9.851394172885075e-06,
|
|
"loss": 0.2894,
|
|
"num_input_tokens_seen": 31282352,
|
|
"step": 390,
|
|
"train_runtime": 5203.7543,
|
|
"train_tokens_per_second": 6011.497
|
|
},
|
|
{
|
|
"epoch": 0.158,
|
|
"grad_norm": 0.8255350410433486,
|
|
"learning_rate": 9.847569074197927e-06,
|
|
"loss": 0.2886,
|
|
"num_input_tokens_seen": 31685040,
|
|
"step": 395,
|
|
"train_runtime": 5273.3386,
|
|
"train_tokens_per_second": 6008.535
|
|
},
|
|
{
|
|
"epoch": 0.16,
|
|
"grad_norm": 0.7055444954194724,
|
|
"learning_rate": 9.843696131961058e-06,
|
|
"loss": 0.273,
|
|
"num_input_tokens_seen": 32051808,
|
|
"step": 400,
|
|
"train_runtime": 5349.3981,
|
|
"train_tokens_per_second": 5991.666
|
|
},
|
|
{
|
|
"epoch": 0.162,
|
|
"grad_norm": 0.7738430122073711,
|
|
"learning_rate": 9.839775384398846e-06,
|
|
"loss": 0.2698,
|
|
"num_input_tokens_seen": 32439248,
|
|
"step": 405,
|
|
"train_runtime": 5424.8322,
|
|
"train_tokens_per_second": 5979.77
|
|
},
|
|
{
|
|
"epoch": 0.164,
|
|
"grad_norm": 0.8597473971332746,
|
|
"learning_rate": 9.835806870207487e-06,
|
|
"loss": 0.2574,
|
|
"num_input_tokens_seen": 32860528,
|
|
"step": 410,
|
|
"train_runtime": 5488.1995,
|
|
"train_tokens_per_second": 5987.488
|
|
},
|
|
{
|
|
"epoch": 0.166,
|
|
"grad_norm": 0.9548490042158907,
|
|
"learning_rate": 9.831790628554613e-06,
|
|
"loss": 0.2709,
|
|
"num_input_tokens_seen": 33238192,
|
|
"step": 415,
|
|
"train_runtime": 5558.4847,
|
|
"train_tokens_per_second": 5979.722
|
|
},
|
|
{
|
|
"epoch": 0.168,
|
|
"grad_norm": 0.6176099320311793,
|
|
"learning_rate": 9.827726699078907e-06,
|
|
"loss": 0.2656,
|
|
"num_input_tokens_seen": 33690160,
|
|
"step": 420,
|
|
"train_runtime": 5625.9505,
|
|
"train_tokens_per_second": 5988.35
|
|
},
|
|
{
|
|
"epoch": 0.17,
|
|
"grad_norm": 0.8127343411925148,
|
|
"learning_rate": 9.823615121889716e-06,
|
|
"loss": 0.29,
|
|
"num_input_tokens_seen": 34073536,
|
|
"step": 425,
|
|
"train_runtime": 5692.2387,
|
|
"train_tokens_per_second": 5985.964
|
|
},
|
|
{
|
|
"epoch": 0.172,
|
|
"grad_norm": 0.7691896317723499,
|
|
"learning_rate": 9.819455937566642e-06,
|
|
"loss": 0.2823,
|
|
"num_input_tokens_seen": 34424192,
|
|
"step": 430,
|
|
"train_runtime": 5754.8576,
|
|
"train_tokens_per_second": 5981.763
|
|
},
|
|
{
|
|
"epoch": 0.174,
|
|
"grad_norm": 1.0082130619949137,
|
|
"learning_rate": 9.815249187159158e-06,
|
|
"loss": 0.2496,
|
|
"num_input_tokens_seen": 34809680,
|
|
"step": 435,
|
|
"train_runtime": 5832.4698,
|
|
"train_tokens_per_second": 5968.257
|
|
},
|
|
{
|
|
"epoch": 0.176,
|
|
"grad_norm": 0.7539701356352378,
|
|
"learning_rate": 9.81099491218619e-06,
|
|
"loss": 0.2627,
|
|
"num_input_tokens_seen": 35219808,
|
|
"step": 440,
|
|
"train_runtime": 5895.6451,
|
|
"train_tokens_per_second": 5973.868
|
|
},
|
|
{
|
|
"epoch": 0.178,
|
|
"grad_norm": 0.8592295102624296,
|
|
"learning_rate": 9.806693154635719e-06,
|
|
"loss": 0.2774,
|
|
"num_input_tokens_seen": 35565248,
|
|
"step": 445,
|
|
"train_runtime": 5941.5778,
|
|
"train_tokens_per_second": 5985.826
|
|
},
|
|
{
|
|
"epoch": 0.18,
|
|
"grad_norm": 0.6582951154075225,
|
|
"learning_rate": 9.802343956964348e-06,
|
|
"loss": 0.2588,
|
|
"num_input_tokens_seen": 36022288,
|
|
"step": 450,
|
|
"train_runtime": 6003.9751,
|
|
"train_tokens_per_second": 5999.74
|
|
},
|
|
{
|
|
"epoch": 0.182,
|
|
"grad_norm": 0.9061477622621547,
|
|
"learning_rate": 9.797947362096909e-06,
|
|
"loss": 0.2588,
|
|
"num_input_tokens_seen": 36379920,
|
|
"step": 455,
|
|
"train_runtime": 6055.0509,
|
|
"train_tokens_per_second": 6008.194
|
|
},
|
|
{
|
|
"epoch": 0.184,
|
|
"grad_norm": 0.8275916426654469,
|
|
"learning_rate": 9.793503413426016e-06,
|
|
"loss": 0.283,
|
|
"num_input_tokens_seen": 36772016,
|
|
"step": 460,
|
|
"train_runtime": 6126.2574,
|
|
"train_tokens_per_second": 6002.362
|
|
},
|
|
{
|
|
"epoch": 0.186,
|
|
"grad_norm": 0.666351274255967,
|
|
"learning_rate": 9.789012154811648e-06,
|
|
"loss": 0.2506,
|
|
"num_input_tokens_seen": 37179920,
|
|
"step": 465,
|
|
"train_runtime": 6201.0957,
|
|
"train_tokens_per_second": 5995.702
|
|
},
|
|
{
|
|
"epoch": 0.188,
|
|
"grad_norm": 0.7350566549608656,
|
|
"learning_rate": 9.784473630580713e-06,
|
|
"loss": 0.2597,
|
|
"num_input_tokens_seen": 37564736,
|
|
"step": 470,
|
|
"train_runtime": 6266.0186,
|
|
"train_tokens_per_second": 5994.993
|
|
},
|
|
{
|
|
"epoch": 0.19,
|
|
"grad_norm": 0.8759339634430292,
|
|
"learning_rate": 9.779887885526616e-06,
|
|
"loss": 0.2517,
|
|
"num_input_tokens_seen": 37917184,
|
|
"step": 475,
|
|
"train_runtime": 6331.4411,
|
|
"train_tokens_per_second": 5988.713
|
|
},
|
|
{
|
|
"epoch": 0.192,
|
|
"grad_norm": 0.7821815325835307,
|
|
"learning_rate": 9.775254964908807e-06,
|
|
"loss": 0.2538,
|
|
"num_input_tokens_seen": 38358080,
|
|
"step": 480,
|
|
"train_runtime": 6403.8247,
|
|
"train_tokens_per_second": 5989.87
|
|
},
|
|
{
|
|
"epoch": 0.194,
|
|
"grad_norm": 0.7670902572150325,
|
|
"learning_rate": 9.770574914452343e-06,
|
|
"loss": 0.26,
|
|
"num_input_tokens_seen": 38766496,
|
|
"step": 485,
|
|
"train_runtime": 6470.9129,
|
|
"train_tokens_per_second": 5990.885
|
|
},
|
|
{
|
|
"epoch": 0.196,
|
|
"grad_norm": 0.7521204078415982,
|
|
"learning_rate": 9.765847780347433e-06,
|
|
"loss": 0.3009,
|
|
"num_input_tokens_seen": 39138720,
|
|
"step": 490,
|
|
"train_runtime": 6532.3628,
|
|
"train_tokens_per_second": 5991.51
|
|
},
|
|
{
|
|
"epoch": 0.198,
|
|
"grad_norm": 0.8185418550494987,
|
|
"learning_rate": 9.761073609248981e-06,
|
|
"loss": 0.268,
|
|
"num_input_tokens_seen": 39469344,
|
|
"step": 495,
|
|
"train_runtime": 6593.0053,
|
|
"train_tokens_per_second": 5986.548
|
|
},
|
|
{
|
|
"epoch": 0.2,
|
|
"grad_norm": 0.65232833162797,
|
|
"learning_rate": 9.756252448276128e-06,
|
|
"loss": 0.2887,
|
|
"num_input_tokens_seen": 39864896,
|
|
"step": 500,
|
|
"train_runtime": 6658.7107,
|
|
"train_tokens_per_second": 5986.879
|
|
},
|
|
{
|
|
"epoch": 0.202,
|
|
"grad_norm": 0.8062005254862974,
|
|
"learning_rate": 9.751384345011787e-06,
|
|
"loss": 0.2467,
|
|
"num_input_tokens_seen": 40238784,
|
|
"step": 505,
|
|
"train_runtime": 6729.641,
|
|
"train_tokens_per_second": 5979.336
|
|
},
|
|
{
|
|
"epoch": 0.204,
|
|
"grad_norm": 0.8767149003459634,
|
|
"learning_rate": 9.746469347502174e-06,
|
|
"loss": 0.2698,
|
|
"num_input_tokens_seen": 40666368,
|
|
"step": 510,
|
|
"train_runtime": 6799.6733,
|
|
"train_tokens_per_second": 5980.636
|
|
},
|
|
{
|
|
"epoch": 0.206,
|
|
"grad_norm": 0.8711260304261372,
|
|
"learning_rate": 9.741507504256327e-06,
|
|
"loss": 0.2785,
|
|
"num_input_tokens_seen": 41071520,
|
|
"step": 515,
|
|
"train_runtime": 6866.2851,
|
|
"train_tokens_per_second": 5981.622
|
|
},
|
|
{
|
|
"epoch": 0.208,
|
|
"grad_norm": 0.6363360313886239,
|
|
"learning_rate": 9.736498864245638e-06,
|
|
"loss": 0.2527,
|
|
"num_input_tokens_seen": 41512256,
|
|
"step": 520,
|
|
"train_runtime": 6939.7657,
|
|
"train_tokens_per_second": 5981.795
|
|
},
|
|
{
|
|
"epoch": 0.21,
|
|
"grad_norm": 0.8109179802915915,
|
|
"learning_rate": 9.73144347690336e-06,
|
|
"loss": 0.29,
|
|
"num_input_tokens_seen": 41873264,
|
|
"step": 525,
|
|
"train_runtime": 6999.3465,
|
|
"train_tokens_per_second": 5982.453
|
|
},
|
|
{
|
|
"epoch": 0.212,
|
|
"grad_norm": 0.8539497377334406,
|
|
"learning_rate": 9.726341392124127e-06,
|
|
"loss": 0.2566,
|
|
"num_input_tokens_seen": 42217568,
|
|
"step": 530,
|
|
"train_runtime": 7053.5565,
|
|
"train_tokens_per_second": 5985.288
|
|
},
|
|
{
|
|
"epoch": 0.214,
|
|
"grad_norm": 0.7599514956902396,
|
|
"learning_rate": 9.721192660263454e-06,
|
|
"loss": 0.2762,
|
|
"num_input_tokens_seen": 42533184,
|
|
"step": 535,
|
|
"train_runtime": 7107.1623,
|
|
"train_tokens_per_second": 5984.552
|
|
},
|
|
{
|
|
"epoch": 0.216,
|
|
"grad_norm": 0.7228195853216592,
|
|
"learning_rate": 9.715997332137248e-06,
|
|
"loss": 0.2783,
|
|
"num_input_tokens_seen": 42919952,
|
|
"step": 540,
|
|
"train_runtime": 7177.2775,
|
|
"train_tokens_per_second": 5979.977
|
|
},
|
|
{
|
|
"epoch": 0.218,
|
|
"grad_norm": 0.8834406791399088,
|
|
"learning_rate": 9.710755459021297e-06,
|
|
"loss": 0.2809,
|
|
"num_input_tokens_seen": 43338336,
|
|
"step": 545,
|
|
"train_runtime": 7248.3874,
|
|
"train_tokens_per_second": 5979.031
|
|
},
|
|
{
|
|
"epoch": 0.22,
|
|
"grad_norm": 0.8666526531262357,
|
|
"learning_rate": 9.705467092650775e-06,
|
|
"loss": 0.2603,
|
|
"num_input_tokens_seen": 43671568,
|
|
"step": 550,
|
|
"train_runtime": 7301.6838,
|
|
"train_tokens_per_second": 5981.027
|
|
},
|
|
{
|
|
"epoch": 0.222,
|
|
"grad_norm": 1.3601258560189031,
|
|
"learning_rate": 9.700132285219724e-06,
|
|
"loss": 0.2591,
|
|
"num_input_tokens_seen": 44031712,
|
|
"step": 555,
|
|
"train_runtime": 7371.2006,
|
|
"train_tokens_per_second": 5973.479
|
|
},
|
|
{
|
|
"epoch": 0.224,
|
|
"grad_norm": 0.7394669684887641,
|
|
"learning_rate": 9.694751089380536e-06,
|
|
"loss": 0.2417,
|
|
"num_input_tokens_seen": 44454032,
|
|
"step": 560,
|
|
"train_runtime": 7434.7623,
|
|
"train_tokens_per_second": 5979.214
|
|
},
|
|
{
|
|
"epoch": 0.226,
|
|
"grad_norm": 0.9392531588494222,
|
|
"learning_rate": 9.689323558243446e-06,
|
|
"loss": 0.2764,
|
|
"num_input_tokens_seen": 44824640,
|
|
"step": 565,
|
|
"train_runtime": 7492.0783,
|
|
"train_tokens_per_second": 5982.938
|
|
},
|
|
{
|
|
"epoch": 0.228,
|
|
"grad_norm": 0.9030061133696439,
|
|
"learning_rate": 9.683849745375991e-06,
|
|
"loss": 0.2747,
|
|
"num_input_tokens_seen": 45255888,
|
|
"step": 570,
|
|
"train_runtime": 7561.0701,
|
|
"train_tokens_per_second": 5985.381
|
|
},
|
|
{
|
|
"epoch": 0.23,
|
|
"grad_norm": 0.7295413257969424,
|
|
"learning_rate": 9.678329704802495e-06,
|
|
"loss": 0.2908,
|
|
"num_input_tokens_seen": 45694304,
|
|
"step": 575,
|
|
"train_runtime": 7636.2571,
|
|
"train_tokens_per_second": 5983.861
|
|
},
|
|
{
|
|
"epoch": 0.232,
|
|
"grad_norm": 0.7831225605388562,
|
|
"learning_rate": 9.672763491003531e-06,
|
|
"loss": 0.2688,
|
|
"num_input_tokens_seen": 46114448,
|
|
"step": 580,
|
|
"train_runtime": 7706.713,
|
|
"train_tokens_per_second": 5983.673
|
|
},
|
|
{
|
|
"epoch": 0.234,
|
|
"grad_norm": 0.7815429105705216,
|
|
"learning_rate": 9.667151158915382e-06,
|
|
"loss": 0.2664,
|
|
"num_input_tokens_seen": 46491280,
|
|
"step": 585,
|
|
"train_runtime": 7768.7784,
|
|
"train_tokens_per_second": 5984.375
|
|
},
|
|
{
|
|
"epoch": 0.236,
|
|
"grad_norm": 0.8060541161386678,
|
|
"learning_rate": 9.661492763929502e-06,
|
|
"loss": 0.2569,
|
|
"num_input_tokens_seen": 46979712,
|
|
"step": 590,
|
|
"train_runtime": 7846.7326,
|
|
"train_tokens_per_second": 5987.169
|
|
},
|
|
{
|
|
"epoch": 0.238,
|
|
"grad_norm": 1.152392275434152,
|
|
"learning_rate": 9.65578836189196e-06,
|
|
"loss": 0.2726,
|
|
"num_input_tokens_seen": 47322192,
|
|
"step": 595,
|
|
"train_runtime": 7910.5668,
|
|
"train_tokens_per_second": 5982.149
|
|
},
|
|
{
|
|
"epoch": 0.24,
|
|
"grad_norm": 0.6887772490533477,
|
|
"learning_rate": 9.650038009102905e-06,
|
|
"loss": 0.2834,
|
|
"num_input_tokens_seen": 47679712,
|
|
"step": 600,
|
|
"train_runtime": 7966.1483,
|
|
"train_tokens_per_second": 5985.291
|
|
},
|
|
{
|
|
"epoch": 0.242,
|
|
"grad_norm": 0.6130384062661248,
|
|
"learning_rate": 9.644241762315995e-06,
|
|
"loss": 0.2423,
|
|
"num_input_tokens_seen": 48067456,
|
|
"step": 605,
|
|
"train_runtime": 8031.7985,
|
|
"train_tokens_per_second": 5984.644
|
|
},
|
|
{
|
|
"epoch": 0.244,
|
|
"grad_norm": 1.2446167359065596,
|
|
"learning_rate": 9.63839967873785e-06,
|
|
"loss": 0.2658,
|
|
"num_input_tokens_seen": 48471152,
|
|
"step": 610,
|
|
"train_runtime": 8102.9608,
|
|
"train_tokens_per_second": 5981.906
|
|
},
|
|
{
|
|
"epoch": 0.246,
|
|
"grad_norm": 0.7294863740740954,
|
|
"learning_rate": 9.63251181602747e-06,
|
|
"loss": 0.2777,
|
|
"num_input_tokens_seen": 48821504,
|
|
"step": 615,
|
|
"train_runtime": 8163.5213,
|
|
"train_tokens_per_second": 5980.447
|
|
},
|
|
{
|
|
"epoch": 0.248,
|
|
"grad_norm": 0.7657155324916852,
|
|
"learning_rate": 9.626578232295689e-06,
|
|
"loss": 0.2731,
|
|
"num_input_tokens_seen": 49249872,
|
|
"step": 620,
|
|
"train_runtime": 8238.4067,
|
|
"train_tokens_per_second": 5978.082
|
|
},
|
|
{
|
|
"epoch": 0.25,
|
|
"grad_norm": 0.8492612505753264,
|
|
"learning_rate": 9.620598986104578e-06,
|
|
"loss": 0.2416,
|
|
"num_input_tokens_seen": 49722272,
|
|
"step": 625,
|
|
"train_runtime": 8312.1519,
|
|
"train_tokens_per_second": 5981.877
|
|
},
|
|
{
|
|
"epoch": 0.252,
|
|
"grad_norm": 0.5904583667356289,
|
|
"learning_rate": 9.61457413646689e-06,
|
|
"loss": 0.2351,
|
|
"num_input_tokens_seen": 50162672,
|
|
"step": 630,
|
|
"train_runtime": 8385.8082,
|
|
"train_tokens_per_second": 5981.853
|
|
},
|
|
{
|
|
"epoch": 0.254,
|
|
"grad_norm": 0.8152781635195294,
|
|
"learning_rate": 9.60850374284545e-06,
|
|
"loss": 0.2645,
|
|
"num_input_tokens_seen": 50561280,
|
|
"step": 635,
|
|
"train_runtime": 8456.8003,
|
|
"train_tokens_per_second": 5978.772
|
|
},
|
|
{
|
|
"epoch": 0.256,
|
|
"grad_norm": 0.8578030045027673,
|
|
"learning_rate": 9.602387865152597e-06,
|
|
"loss": 0.2591,
|
|
"num_input_tokens_seen": 50972256,
|
|
"step": 640,
|
|
"train_runtime": 8523.5289,
|
|
"train_tokens_per_second": 5980.182
|
|
},
|
|
{
|
|
"epoch": 0.258,
|
|
"grad_norm": 0.6780597416159073,
|
|
"learning_rate": 9.596226563749575e-06,
|
|
"loss": 0.2685,
|
|
"num_input_tokens_seen": 51396304,
|
|
"step": 645,
|
|
"train_runtime": 8597.0686,
|
|
"train_tokens_per_second": 5978.352
|
|
},
|
|
{
|
|
"epoch": 0.26,
|
|
"grad_norm": 1.102448723613161,
|
|
"learning_rate": 9.59001989944594e-06,
|
|
"loss": 0.2784,
|
|
"num_input_tokens_seen": 51798816,
|
|
"step": 650,
|
|
"train_runtime": 8668.8465,
|
|
"train_tokens_per_second": 5975.284
|
|
},
|
|
{
|
|
"epoch": 0.262,
|
|
"grad_norm": 0.8841959640928475,
|
|
"learning_rate": 9.583767933498964e-06,
|
|
"loss": 0.2514,
|
|
"num_input_tokens_seen": 52139568,
|
|
"step": 655,
|
|
"train_runtime": 8710.9548,
|
|
"train_tokens_per_second": 5985.517
|
|
},
|
|
{
|
|
"epoch": 0.264,
|
|
"grad_norm": 1.037638223962085,
|
|
"learning_rate": 9.577470727613025e-06,
|
|
"loss": 0.2774,
|
|
"num_input_tokens_seen": 52493312,
|
|
"step": 660,
|
|
"train_runtime": 8765.6718,
|
|
"train_tokens_per_second": 5988.51
|
|
},
|
|
{
|
|
"epoch": 0.266,
|
|
"grad_norm": 0.8858274237729105,
|
|
"learning_rate": 9.571128343939006e-06,
|
|
"loss": 0.2814,
|
|
"num_input_tokens_seen": 52863632,
|
|
"step": 665,
|
|
"train_runtime": 8843.4286,
|
|
"train_tokens_per_second": 5977.73
|
|
},
|
|
{
|
|
"epoch": 0.268,
|
|
"grad_norm": 0.8391980666108796,
|
|
"learning_rate": 9.56474084507367e-06,
|
|
"loss": 0.261,
|
|
"num_input_tokens_seen": 53215856,
|
|
"step": 670,
|
|
"train_runtime": 8907.6923,
|
|
"train_tokens_per_second": 5974.146
|
|
},
|
|
{
|
|
"epoch": 0.27,
|
|
"grad_norm": 0.8495736711346393,
|
|
"learning_rate": 9.558308294059055e-06,
|
|
"loss": 0.2676,
|
|
"num_input_tokens_seen": 53562768,
|
|
"step": 675,
|
|
"train_runtime": 8965.163,
|
|
"train_tokens_per_second": 5974.545
|
|
},
|
|
{
|
|
"epoch": 0.272,
|
|
"grad_norm": 0.941473355481309,
|
|
"learning_rate": 9.55183075438184e-06,
|
|
"loss": 0.2357,
|
|
"num_input_tokens_seen": 54030624,
|
|
"step": 680,
|
|
"train_runtime": 9040.6249,
|
|
"train_tokens_per_second": 5976.426
|
|
},
|
|
{
|
|
"epoch": 0.274,
|
|
"grad_norm": 0.7012350033428856,
|
|
"learning_rate": 9.545308289972727e-06,
|
|
"loss": 0.2402,
|
|
"num_input_tokens_seen": 54343888,
|
|
"step": 685,
|
|
"train_runtime": 9086.5654,
|
|
"train_tokens_per_second": 5980.685
|
|
},
|
|
{
|
|
"epoch": 0.276,
|
|
"grad_norm": 0.626498976221356,
|
|
"learning_rate": 9.538740965205809e-06,
|
|
"loss": 0.2372,
|
|
"num_input_tokens_seen": 54668576,
|
|
"step": 690,
|
|
"train_runtime": 9140.102,
|
|
"train_tokens_per_second": 5981.178
|
|
},
|
|
{
|
|
"epoch": 0.278,
|
|
"grad_norm": 0.6826557552174048,
|
|
"learning_rate": 9.532128844897928e-06,
|
|
"loss": 0.2741,
|
|
"num_input_tokens_seen": 55095472,
|
|
"step": 695,
|
|
"train_runtime": 9209.0632,
|
|
"train_tokens_per_second": 5982.744
|
|
},
|
|
{
|
|
"epoch": 0.28,
|
|
"grad_norm": 0.8107331496725793,
|
|
"learning_rate": 9.52547199430804e-06,
|
|
"loss": 0.2364,
|
|
"num_input_tokens_seen": 55413664,
|
|
"step": 700,
|
|
"train_runtime": 9262.2508,
|
|
"train_tokens_per_second": 5982.743
|
|
},
|
|
{
|
|
"epoch": 0.282,
|
|
"grad_norm": 0.7874944184568773,
|
|
"learning_rate": 9.51877047913658e-06,
|
|
"loss": 0.2586,
|
|
"num_input_tokens_seen": 55779360,
|
|
"step": 705,
|
|
"train_runtime": 9320.6217,
|
|
"train_tokens_per_second": 5984.511
|
|
},
|
|
{
|
|
"epoch": 0.284,
|
|
"grad_norm": 1.8567686550412206,
|
|
"learning_rate": 9.512024365524788e-06,
|
|
"loss": 0.2655,
|
|
"num_input_tokens_seen": 56130272,
|
|
"step": 710,
|
|
"train_runtime": 9375.9114,
|
|
"train_tokens_per_second": 5986.647
|
|
},
|
|
{
|
|
"epoch": 0.286,
|
|
"grad_norm": 0.7851630152910232,
|
|
"learning_rate": 9.505233720054086e-06,
|
|
"loss": 0.2579,
|
|
"num_input_tokens_seen": 56500464,
|
|
"step": 715,
|
|
"train_runtime": 9440.7193,
|
|
"train_tokens_per_second": 5984.763
|
|
},
|
|
{
|
|
"epoch": 0.288,
|
|
"grad_norm": 0.8612089302332713,
|
|
"learning_rate": 9.498398609745405e-06,
|
|
"loss": 0.2478,
|
|
"num_input_tokens_seen": 56844928,
|
|
"step": 720,
|
|
"train_runtime": 9500.9395,
|
|
"train_tokens_per_second": 5983.085
|
|
},
|
|
{
|
|
"epoch": 0.29,
|
|
"grad_norm": 0.7600175238797224,
|
|
"learning_rate": 9.491519102058523e-06,
|
|
"loss": 0.2765,
|
|
"num_input_tokens_seen": 57261328,
|
|
"step": 725,
|
|
"train_runtime": 9573.8278,
|
|
"train_tokens_per_second": 5981.028
|
|
},
|
|
{
|
|
"epoch": 0.292,
|
|
"grad_norm": 0.9375851471978519,
|
|
"learning_rate": 9.484595264891403e-06,
|
|
"loss": 0.2419,
|
|
"num_input_tokens_seen": 57632624,
|
|
"step": 730,
|
|
"train_runtime": 9644.209,
|
|
"train_tokens_per_second": 5975.879
|
|
},
|
|
{
|
|
"epoch": 0.294,
|
|
"grad_norm": 0.9027653994149234,
|
|
"learning_rate": 9.477627166579523e-06,
|
|
"loss": 0.271,
|
|
"num_input_tokens_seen": 58025408,
|
|
"step": 735,
|
|
"train_runtime": 9710.5708,
|
|
"train_tokens_per_second": 5975.489
|
|
},
|
|
{
|
|
"epoch": 0.296,
|
|
"grad_norm": 0.8578883410124413,
|
|
"learning_rate": 9.4706148758952e-06,
|
|
"loss": 0.2637,
|
|
"num_input_tokens_seen": 58396208,
|
|
"step": 740,
|
|
"train_runtime": 9777.666,
|
|
"train_tokens_per_second": 5972.408
|
|
},
|
|
{
|
|
"epoch": 0.298,
|
|
"grad_norm": 0.8776112915445362,
|
|
"learning_rate": 9.463558462046912e-06,
|
|
"loss": 0.2727,
|
|
"num_input_tokens_seen": 58707376,
|
|
"step": 745,
|
|
"train_runtime": 9819.0785,
|
|
"train_tokens_per_second": 5978.909
|
|
},
|
|
{
|
|
"epoch": 0.3,
|
|
"grad_norm": 0.5840963430287371,
|
|
"learning_rate": 9.456457994678616e-06,
|
|
"loss": 0.2322,
|
|
"num_input_tokens_seen": 59145392,
|
|
"step": 750,
|
|
"train_runtime": 9890.3227,
|
|
"train_tokens_per_second": 5980.128
|
|
},
|
|
{
|
|
"epoch": 0.302,
|
|
"grad_norm": 0.7317905873414259,
|
|
"learning_rate": 9.449313543869056e-06,
|
|
"loss": 0.2846,
|
|
"num_input_tokens_seen": 59450400,
|
|
"step": 755,
|
|
"train_runtime": 9940.4488,
|
|
"train_tokens_per_second": 5980.656
|
|
},
|
|
{
|
|
"epoch": 0.304,
|
|
"grad_norm": 0.7403200227430362,
|
|
"learning_rate": 9.44212518013108e-06,
|
|
"loss": 0.2741,
|
|
"num_input_tokens_seen": 59840944,
|
|
"step": 760,
|
|
"train_runtime": 10013.8692,
|
|
"train_tokens_per_second": 5975.806
|
|
},
|
|
{
|
|
"epoch": 0.306,
|
|
"grad_norm": 0.7622642170344124,
|
|
"learning_rate": 9.434892974410932e-06,
|
|
"loss": 0.2604,
|
|
"num_input_tokens_seen": 60216688,
|
|
"step": 765,
|
|
"train_runtime": 10074.7344,
|
|
"train_tokens_per_second": 5977.0
|
|
},
|
|
{
|
|
"epoch": 0.308,
|
|
"grad_norm": 0.8785789117135203,
|
|
"learning_rate": 9.427616998087568e-06,
|
|
"loss": 0.2431,
|
|
"num_input_tokens_seen": 60638976,
|
|
"step": 770,
|
|
"train_runtime": 10146.9679,
|
|
"train_tokens_per_second": 5976.069
|
|
},
|
|
{
|
|
"epoch": 0.31,
|
|
"grad_norm": 0.8249894805799513,
|
|
"learning_rate": 9.420297322971934e-06,
|
|
"loss": 0.2526,
|
|
"num_input_tokens_seen": 61134256,
|
|
"step": 775,
|
|
"train_runtime": 10225.8927,
|
|
"train_tokens_per_second": 5978.378
|
|
},
|
|
{
|
|
"epoch": 0.312,
|
|
"grad_norm": 0.6744756944455406,
|
|
"learning_rate": 9.412934021306267e-06,
|
|
"loss": 0.2512,
|
|
"num_input_tokens_seen": 61553648,
|
|
"step": 780,
|
|
"train_runtime": 10286.5901,
|
|
"train_tokens_per_second": 5983.873
|
|
},
|
|
{
|
|
"epoch": 0.314,
|
|
"grad_norm": 0.8062812974951873,
|
|
"learning_rate": 9.405527165763384e-06,
|
|
"loss": 0.286,
|
|
"num_input_tokens_seen": 61957648,
|
|
"step": 785,
|
|
"train_runtime": 10352.746,
|
|
"train_tokens_per_second": 5984.658
|
|
},
|
|
{
|
|
"epoch": 0.316,
|
|
"grad_norm": 0.7356106568881381,
|
|
"learning_rate": 9.398076829445958e-06,
|
|
"loss": 0.2711,
|
|
"num_input_tokens_seen": 62288880,
|
|
"step": 790,
|
|
"train_runtime": 10408.5909,
|
|
"train_tokens_per_second": 5984.372
|
|
},
|
|
{
|
|
"epoch": 0.318,
|
|
"grad_norm": 0.7610857265233825,
|
|
"learning_rate": 9.3905830858858e-06,
|
|
"loss": 0.2685,
|
|
"num_input_tokens_seen": 62663632,
|
|
"step": 795,
|
|
"train_runtime": 10467.9413,
|
|
"train_tokens_per_second": 5986.242
|
|
},
|
|
{
|
|
"epoch": 0.32,
|
|
"grad_norm": 0.7966898610801778,
|
|
"learning_rate": 9.383046009043134e-06,
|
|
"loss": 0.2693,
|
|
"num_input_tokens_seen": 63057792,
|
|
"step": 800,
|
|
"train_runtime": 10539.3948,
|
|
"train_tokens_per_second": 5983.056
|
|
},
|
|
{
|
|
"epoch": 0.322,
|
|
"grad_norm": 0.7289146876069654,
|
|
"learning_rate": 9.37546567330587e-06,
|
|
"loss": 0.2542,
|
|
"num_input_tokens_seen": 63428432,
|
|
"step": 805,
|
|
"train_runtime": 10606.3414,
|
|
"train_tokens_per_second": 5980.237
|
|
},
|
|
{
|
|
"epoch": 0.324,
|
|
"grad_norm": 0.7123973284012891,
|
|
"learning_rate": 9.367842153488853e-06,
|
|
"loss": 0.2482,
|
|
"num_input_tokens_seen": 63837776,
|
|
"step": 810,
|
|
"train_runtime": 10684.1996,
|
|
"train_tokens_per_second": 5974.97
|
|
},
|
|
{
|
|
"epoch": 0.326,
|
|
"grad_norm": 0.6116848677069046,
|
|
"learning_rate": 9.360175524833153e-06,
|
|
"loss": 0.2393,
|
|
"num_input_tokens_seen": 64207744,
|
|
"step": 815,
|
|
"train_runtime": 10746.2594,
|
|
"train_tokens_per_second": 5974.892
|
|
},
|
|
{
|
|
"epoch": 0.328,
|
|
"grad_norm": 0.7090177624564499,
|
|
"learning_rate": 9.352465863005295e-06,
|
|
"loss": 0.2464,
|
|
"num_input_tokens_seen": 64527552,
|
|
"step": 820,
|
|
"train_runtime": 10794.1158,
|
|
"train_tokens_per_second": 5978.03
|
|
},
|
|
{
|
|
"epoch": 0.33,
|
|
"grad_norm": 0.9228460888788435,
|
|
"learning_rate": 9.344713244096533e-06,
|
|
"loss": 0.2576,
|
|
"num_input_tokens_seen": 64870000,
|
|
"step": 825,
|
|
"train_runtime": 10861.5895,
|
|
"train_tokens_per_second": 5972.422
|
|
},
|
|
{
|
|
"epoch": 0.332,
|
|
"grad_norm": 0.7749537888998517,
|
|
"learning_rate": 9.336917744622083e-06,
|
|
"loss": 0.255,
|
|
"num_input_tokens_seen": 65269280,
|
|
"step": 830,
|
|
"train_runtime": 10929.169,
|
|
"train_tokens_per_second": 5972.026
|
|
},
|
|
{
|
|
"epoch": 0.334,
|
|
"grad_norm": 0.7288672113983271,
|
|
"learning_rate": 9.329079441520377e-06,
|
|
"loss": 0.2511,
|
|
"num_input_tokens_seen": 65627792,
|
|
"step": 835,
|
|
"train_runtime": 10988.928,
|
|
"train_tokens_per_second": 5972.174
|
|
},
|
|
{
|
|
"epoch": 0.336,
|
|
"grad_norm": 0.601500012457241,
|
|
"learning_rate": 9.321198412152303e-06,
|
|
"loss": 0.2454,
|
|
"num_input_tokens_seen": 66037840,
|
|
"step": 840,
|
|
"train_runtime": 11058.4902,
|
|
"train_tokens_per_second": 5971.687
|
|
},
|
|
{
|
|
"epoch": 0.338,
|
|
"grad_norm": 0.8144980181728814,
|
|
"learning_rate": 9.31327473430044e-06,
|
|
"loss": 0.2629,
|
|
"num_input_tokens_seen": 66426768,
|
|
"step": 845,
|
|
"train_runtime": 11133.0882,
|
|
"train_tokens_per_second": 5966.608
|
|
},
|
|
{
|
|
"epoch": 0.34,
|
|
"grad_norm": 0.7166518808881578,
|
|
"learning_rate": 9.305308486168288e-06,
|
|
"loss": 0.2955,
|
|
"num_input_tokens_seen": 66772240,
|
|
"step": 850,
|
|
"train_runtime": 11191.3696,
|
|
"train_tokens_per_second": 5966.405
|
|
},
|
|
{
|
|
"epoch": 0.342,
|
|
"grad_norm": 0.7897465503734388,
|
|
"learning_rate": 9.297299746379503e-06,
|
|
"loss": 0.2835,
|
|
"num_input_tokens_seen": 67111024,
|
|
"step": 855,
|
|
"train_runtime": 11250.8182,
|
|
"train_tokens_per_second": 5964.991
|
|
},
|
|
{
|
|
"epoch": 0.344,
|
|
"grad_norm": 0.7396912203991731,
|
|
"learning_rate": 9.28924859397711e-06,
|
|
"loss": 0.2637,
|
|
"num_input_tokens_seen": 67482144,
|
|
"step": 860,
|
|
"train_runtime": 11318.7263,
|
|
"train_tokens_per_second": 5961.991
|
|
},
|
|
{
|
|
"epoch": 0.346,
|
|
"grad_norm": 0.6992972676350053,
|
|
"learning_rate": 9.281155108422732e-06,
|
|
"loss": 0.237,
|
|
"num_input_tokens_seen": 67876032,
|
|
"step": 865,
|
|
"train_runtime": 11382.7481,
|
|
"train_tokens_per_second": 5963.062
|
|
},
|
|
{
|
|
"epoch": 0.348,
|
|
"grad_norm": 0.6948771027671538,
|
|
"learning_rate": 9.27301936959581e-06,
|
|
"loss": 0.2797,
|
|
"num_input_tokens_seen": 68282368,
|
|
"step": 870,
|
|
"train_runtime": 11454.6041,
|
|
"train_tokens_per_second": 5961.129
|
|
},
|
|
{
|
|
"epoch": 0.35,
|
|
"grad_norm": 0.7539839679695668,
|
|
"learning_rate": 9.264841457792795e-06,
|
|
"loss": 0.2602,
|
|
"num_input_tokens_seen": 68701008,
|
|
"step": 875,
|
|
"train_runtime": 11524.7372,
|
|
"train_tokens_per_second": 5961.178
|
|
},
|
|
{
|
|
"epoch": 0.352,
|
|
"grad_norm": 0.7952906428828391,
|
|
"learning_rate": 9.25662145372638e-06,
|
|
"loss": 0.2757,
|
|
"num_input_tokens_seen": 69139648,
|
|
"step": 880,
|
|
"train_runtime": 11594.0901,
|
|
"train_tokens_per_second": 5963.353
|
|
},
|
|
{
|
|
"epoch": 0.354,
|
|
"grad_norm": 0.5875437368411229,
|
|
"learning_rate": 9.248359438524683e-06,
|
|
"loss": 0.2738,
|
|
"num_input_tokens_seen": 69591040,
|
|
"step": 885,
|
|
"train_runtime": 11669.2233,
|
|
"train_tokens_per_second": 5963.639
|
|
},
|
|
{
|
|
"epoch": 0.356,
|
|
"grad_norm": 0.8362276418870209,
|
|
"learning_rate": 9.24005549373046e-06,
|
|
"loss": 0.2693,
|
|
"num_input_tokens_seen": 69919248,
|
|
"step": 890,
|
|
"train_runtime": 11720.5537,
|
|
"train_tokens_per_second": 5965.524
|
|
},
|
|
{
|
|
"epoch": 0.358,
|
|
"grad_norm": 0.8689160927298022,
|
|
"learning_rate": 9.231709701300293e-06,
|
|
"loss": 0.2522,
|
|
"num_input_tokens_seen": 70352544,
|
|
"step": 895,
|
|
"train_runtime": 11791.7221,
|
|
"train_tokens_per_second": 5966.265
|
|
},
|
|
{
|
|
"epoch": 0.36,
|
|
"grad_norm": 0.7199820818597936,
|
|
"learning_rate": 9.223322143603786e-06,
|
|
"loss": 0.2546,
|
|
"num_input_tokens_seen": 70743040,
|
|
"step": 900,
|
|
"train_runtime": 11864.5227,
|
|
"train_tokens_per_second": 5962.569
|
|
},
|
|
{
|
|
"epoch": 0.362,
|
|
"grad_norm": 0.6472872435071626,
|
|
"learning_rate": 9.214892903422745e-06,
|
|
"loss": 0.2453,
|
|
"num_input_tokens_seen": 71217216,
|
|
"step": 905,
|
|
"train_runtime": 11942.6153,
|
|
"train_tokens_per_second": 5963.285
|
|
},
|
|
{
|
|
"epoch": 0.364,
|
|
"grad_norm": 0.6936535531088693,
|
|
"learning_rate": 9.206422063950368e-06,
|
|
"loss": 0.27,
|
|
"num_input_tokens_seen": 71603280,
|
|
"step": 910,
|
|
"train_runtime": 12014.7541,
|
|
"train_tokens_per_second": 5959.613
|
|
},
|
|
{
|
|
"epoch": 0.366,
|
|
"grad_norm": 0.7343273673132791,
|
|
"learning_rate": 9.19790970879042e-06,
|
|
"loss": 0.2542,
|
|
"num_input_tokens_seen": 72051488,
|
|
"step": 915,
|
|
"train_runtime": 12090.529,
|
|
"train_tokens_per_second": 5959.333
|
|
},
|
|
{
|
|
"epoch": 0.368,
|
|
"grad_norm": 0.917360247584837,
|
|
"learning_rate": 9.189355921956414e-06,
|
|
"loss": 0.2589,
|
|
"num_input_tokens_seen": 72527008,
|
|
"step": 920,
|
|
"train_runtime": 12168.4904,
|
|
"train_tokens_per_second": 5960.231
|
|
},
|
|
{
|
|
"epoch": 0.37,
|
|
"grad_norm": 0.7350510206851814,
|
|
"learning_rate": 9.180760787870766e-06,
|
|
"loss": 0.2867,
|
|
"num_input_tokens_seen": 72948304,
|
|
"step": 925,
|
|
"train_runtime": 12242.6135,
|
|
"train_tokens_per_second": 5958.556
|
|
},
|
|
{
|
|
"epoch": 0.372,
|
|
"grad_norm": 0.7541549801390238,
|
|
"learning_rate": 9.172124391363986e-06,
|
|
"loss": 0.2782,
|
|
"num_input_tokens_seen": 73288864,
|
|
"step": 930,
|
|
"train_runtime": 12299.826,
|
|
"train_tokens_per_second": 5958.529
|
|
},
|
|
{
|
|
"epoch": 0.374,
|
|
"grad_norm": 0.8317564298674665,
|
|
"learning_rate": 9.163446817673817e-06,
|
|
"loss": 0.2686,
|
|
"num_input_tokens_seen": 73737984,
|
|
"step": 935,
|
|
"train_runtime": 12370.4346,
|
|
"train_tokens_per_second": 5960.824
|
|
},
|
|
{
|
|
"epoch": 0.376,
|
|
"grad_norm": 0.6607759087260642,
|
|
"learning_rate": 9.154728152444408e-06,
|
|
"loss": 0.2233,
|
|
"num_input_tokens_seen": 74213840,
|
|
"step": 940,
|
|
"train_runtime": 12443.1991,
|
|
"train_tokens_per_second": 5964.209
|
|
},
|
|
{
|
|
"epoch": 0.378,
|
|
"grad_norm": 0.6062097980101698,
|
|
"learning_rate": 9.145968481725466e-06,
|
|
"loss": 0.2441,
|
|
"num_input_tokens_seen": 74626672,
|
|
"step": 945,
|
|
"train_runtime": 12519.7182,
|
|
"train_tokens_per_second": 5960.731
|
|
},
|
|
{
|
|
"epoch": 0.38,
|
|
"grad_norm": 0.6654792002985258,
|
|
"learning_rate": 9.137167891971407e-06,
|
|
"loss": 0.2461,
|
|
"num_input_tokens_seen": 75031472,
|
|
"step": 950,
|
|
"train_runtime": 12593.3703,
|
|
"train_tokens_per_second": 5958.014
|
|
},
|
|
{
|
|
"epoch": 0.382,
|
|
"grad_norm": 0.8388912617650379,
|
|
"learning_rate": 9.128326470040495e-06,
|
|
"loss": 0.2524,
|
|
"num_input_tokens_seen": 75420768,
|
|
"step": 955,
|
|
"train_runtime": 12664.1715,
|
|
"train_tokens_per_second": 5955.444
|
|
},
|
|
{
|
|
"epoch": 0.384,
|
|
"grad_norm": 0.6889457837790466,
|
|
"learning_rate": 9.119444303193997e-06,
|
|
"loss": 0.2614,
|
|
"num_input_tokens_seen": 75773776,
|
|
"step": 960,
|
|
"train_runtime": 12727.9061,
|
|
"train_tokens_per_second": 5953.358
|
|
},
|
|
{
|
|
"epoch": 0.386,
|
|
"grad_norm": 0.8297814546544214,
|
|
"learning_rate": 9.110521479095314e-06,
|
|
"loss": 0.2407,
|
|
"num_input_tokens_seen": 76196496,
|
|
"step": 965,
|
|
"train_runtime": 12791.1909,
|
|
"train_tokens_per_second": 5956.951
|
|
},
|
|
{
|
|
"epoch": 0.388,
|
|
"grad_norm": 0.6413044681177218,
|
|
"learning_rate": 9.101558085809114e-06,
|
|
"loss": 0.2573,
|
|
"num_input_tokens_seen": 76591056,
|
|
"step": 970,
|
|
"train_runtime": 12855.6204,
|
|
"train_tokens_per_second": 5957.788
|
|
},
|
|
{
|
|
"epoch": 0.39,
|
|
"grad_norm": 0.7210732824974905,
|
|
"learning_rate": 9.092554211800476e-06,
|
|
"loss": 0.2697,
|
|
"num_input_tokens_seen": 76955088,
|
|
"step": 975,
|
|
"train_runtime": 12909.069,
|
|
"train_tokens_per_second": 5961.32
|
|
},
|
|
{
|
|
"epoch": 0.392,
|
|
"grad_norm": 0.7245964043841143,
|
|
"learning_rate": 9.083509945933996e-06,
|
|
"loss": 0.2575,
|
|
"num_input_tokens_seen": 77376480,
|
|
"step": 980,
|
|
"train_runtime": 12984.986,
|
|
"train_tokens_per_second": 5958.919
|
|
},
|
|
{
|
|
"epoch": 0.394,
|
|
"grad_norm": 0.9126407724225012,
|
|
"learning_rate": 9.074425377472932e-06,
|
|
"loss": 0.2609,
|
|
"num_input_tokens_seen": 77724816,
|
|
"step": 985,
|
|
"train_runtime": 13042.6743,
|
|
"train_tokens_per_second": 5959.27
|
|
},
|
|
{
|
|
"epoch": 0.396,
|
|
"grad_norm": 0.7128423265110231,
|
|
"learning_rate": 9.065300596078304e-06,
|
|
"loss": 0.2565,
|
|
"num_input_tokens_seen": 78153632,
|
|
"step": 990,
|
|
"train_runtime": 13120.8794,
|
|
"train_tokens_per_second": 5956.432
|
|
},
|
|
{
|
|
"epoch": 0.398,
|
|
"grad_norm": 0.6067421606247867,
|
|
"learning_rate": 9.056135691808019e-06,
|
|
"loss": 0.2617,
|
|
"num_input_tokens_seen": 78580512,
|
|
"step": 995,
|
|
"train_runtime": 13191.8231,
|
|
"train_tokens_per_second": 5956.759
|
|
},
|
|
{
|
|
"epoch": 0.4,
|
|
"grad_norm": 1.0171109792998725,
|
|
"learning_rate": 9.046930755115986e-06,
|
|
"loss": 0.2443,
|
|
"num_input_tokens_seen": 79016832,
|
|
"step": 1000,
|
|
"train_runtime": 13262.4875,
|
|
"train_tokens_per_second": 5957.919
|
|
},
|
|
{
|
|
"epoch": 0.402,
|
|
"grad_norm": 0.624788109000857,
|
|
"learning_rate": 9.037685876851211e-06,
|
|
"loss": 0.2496,
|
|
"num_input_tokens_seen": 79339488,
|
|
"step": 1005,
|
|
"train_runtime": 13317.1987,
|
|
"train_tokens_per_second": 5957.671
|
|
},
|
|
{
|
|
"epoch": 0.404,
|
|
"grad_norm": 1.3437666934516999,
|
|
"learning_rate": 9.028401148256911e-06,
|
|
"loss": 0.2595,
|
|
"num_input_tokens_seen": 79734112,
|
|
"step": 1010,
|
|
"train_runtime": 13384.2845,
|
|
"train_tokens_per_second": 5957.294
|
|
},
|
|
{
|
|
"epoch": 0.406,
|
|
"grad_norm": 0.9331183492160343,
|
|
"learning_rate": 9.01907666096961e-06,
|
|
"loss": 0.2649,
|
|
"num_input_tokens_seen": 80113424,
|
|
"step": 1015,
|
|
"train_runtime": 13448.7587,
|
|
"train_tokens_per_second": 5956.938
|
|
},
|
|
{
|
|
"epoch": 0.408,
|
|
"grad_norm": 0.8916393321532121,
|
|
"learning_rate": 9.00971250701823e-06,
|
|
"loss": 0.2566,
|
|
"num_input_tokens_seen": 80485408,
|
|
"step": 1020,
|
|
"train_runtime": 13514.594,
|
|
"train_tokens_per_second": 5955.444
|
|
},
|
|
{
|
|
"epoch": 0.41,
|
|
"grad_norm": 0.6466488488459519,
|
|
"learning_rate": 9.000308778823196e-06,
|
|
"loss": 0.2335,
|
|
"num_input_tokens_seen": 80804000,
|
|
"step": 1025,
|
|
"train_runtime": 13566.7577,
|
|
"train_tokens_per_second": 5956.029
|
|
},
|
|
{
|
|
"epoch": 0.412,
|
|
"grad_norm": 0.7558803329595326,
|
|
"learning_rate": 8.990865569195502e-06,
|
|
"loss": 0.27,
|
|
"num_input_tokens_seen": 81218816,
|
|
"step": 1030,
|
|
"train_runtime": 13639.7747,
|
|
"train_tokens_per_second": 5954.557
|
|
},
|
|
{
|
|
"epoch": 0.414,
|
|
"grad_norm": 0.7131746675468659,
|
|
"learning_rate": 8.98138297133582e-06,
|
|
"loss": 0.2453,
|
|
"num_input_tokens_seen": 81613792,
|
|
"step": 1035,
|
|
"train_runtime": 13706.1897,
|
|
"train_tokens_per_second": 5954.521
|
|
},
|
|
{
|
|
"epoch": 0.416,
|
|
"grad_norm": 0.6901488903873247,
|
|
"learning_rate": 8.971861078833558e-06,
|
|
"loss": 0.2493,
|
|
"num_input_tokens_seen": 82060224,
|
|
"step": 1040,
|
|
"train_runtime": 13784.5271,
|
|
"train_tokens_per_second": 5953.068
|
|
},
|
|
{
|
|
"epoch": 0.418,
|
|
"grad_norm": 0.6646198187655422,
|
|
"learning_rate": 8.962299985665955e-06,
|
|
"loss": 0.2342,
|
|
"num_input_tokens_seen": 82494944,
|
|
"step": 1045,
|
|
"train_runtime": 13849.5372,
|
|
"train_tokens_per_second": 5956.513
|
|
},
|
|
{
|
|
"epoch": 0.42,
|
|
"grad_norm": 0.6253491898077594,
|
|
"learning_rate": 8.952699786197137e-06,
|
|
"loss": 0.2373,
|
|
"num_input_tokens_seen": 82808768,
|
|
"step": 1050,
|
|
"train_runtime": 13914.8709,
|
|
"train_tokens_per_second": 5951.099
|
|
},
|
|
{
|
|
"epoch": 0.422,
|
|
"grad_norm": 0.7708996437720635,
|
|
"learning_rate": 8.943060575177197e-06,
|
|
"loss": 0.243,
|
|
"num_input_tokens_seen": 83196256,
|
|
"step": 1055,
|
|
"train_runtime": 13976.3704,
|
|
"train_tokens_per_second": 5952.637
|
|
},
|
|
{
|
|
"epoch": 0.424,
|
|
"grad_norm": 0.9176135630737275,
|
|
"learning_rate": 8.93338244774126e-06,
|
|
"loss": 0.2866,
|
|
"num_input_tokens_seen": 83661872,
|
|
"step": 1060,
|
|
"train_runtime": 14050.0901,
|
|
"train_tokens_per_second": 5954.543
|
|
},
|
|
{
|
|
"epoch": 0.426,
|
|
"grad_norm": 0.7219954539715555,
|
|
"learning_rate": 8.923665499408535e-06,
|
|
"loss": 0.2466,
|
|
"num_input_tokens_seen": 84013360,
|
|
"step": 1065,
|
|
"train_runtime": 14119.6235,
|
|
"train_tokens_per_second": 5950.113
|
|
},
|
|
{
|
|
"epoch": 0.428,
|
|
"grad_norm": 0.7629186621884477,
|
|
"learning_rate": 8.91390982608138e-06,
|
|
"loss": 0.2593,
|
|
"num_input_tokens_seen": 84398000,
|
|
"step": 1070,
|
|
"train_runtime": 14195.2042,
|
|
"train_tokens_per_second": 5945.529
|
|
},
|
|
{
|
|
"epoch": 0.43,
|
|
"grad_norm": 0.7305819771780363,
|
|
"learning_rate": 8.904115524044349e-06,
|
|
"loss": 0.2553,
|
|
"num_input_tokens_seen": 84711792,
|
|
"step": 1075,
|
|
"train_runtime": 14240.4426,
|
|
"train_tokens_per_second": 5948.677
|
|
},
|
|
{
|
|
"epoch": 0.432,
|
|
"grad_norm": 0.8171300968987977,
|
|
"learning_rate": 8.894282689963252e-06,
|
|
"loss": 0.2611,
|
|
"num_input_tokens_seen": 85117264,
|
|
"step": 1080,
|
|
"train_runtime": 14298.5417,
|
|
"train_tokens_per_second": 5952.863
|
|
},
|
|
{
|
|
"epoch": 0.434,
|
|
"grad_norm": 0.7999063479153911,
|
|
"learning_rate": 8.88441142088419e-06,
|
|
"loss": 0.2605,
|
|
"num_input_tokens_seen": 85480624,
|
|
"step": 1085,
|
|
"train_runtime": 14353.0025,
|
|
"train_tokens_per_second": 5955.592
|
|
},
|
|
{
|
|
"epoch": 0.436,
|
|
"grad_norm": 0.6760703286202087,
|
|
"learning_rate": 8.874501814232603e-06,
|
|
"loss": 0.2476,
|
|
"num_input_tokens_seen": 85832000,
|
|
"step": 1090,
|
|
"train_runtime": 14408.823,
|
|
"train_tokens_per_second": 5956.906
|
|
},
|
|
{
|
|
"epoch": 0.438,
|
|
"grad_norm": 0.6222891384021169,
|
|
"learning_rate": 8.86455396781231e-06,
|
|
"loss": 0.24,
|
|
"num_input_tokens_seen": 86208160,
|
|
"step": 1095,
|
|
"train_runtime": 14471.0092,
|
|
"train_tokens_per_second": 5957.301
|
|
},
|
|
{
|
|
"epoch": 0.44,
|
|
"grad_norm": 0.8225171871864566,
|
|
"learning_rate": 8.854567979804538e-06,
|
|
"loss": 0.2628,
|
|
"num_input_tokens_seen": 86613904,
|
|
"step": 1100,
|
|
"train_runtime": 14541.9038,
|
|
"train_tokens_per_second": 5956.16
|
|
},
|
|
{
|
|
"epoch": 0.442,
|
|
"grad_norm": 0.7386320533997327,
|
|
"learning_rate": 8.844543948766958e-06,
|
|
"loss": 0.2561,
|
|
"num_input_tokens_seen": 87012032,
|
|
"step": 1105,
|
|
"train_runtime": 14616.3222,
|
|
"train_tokens_per_second": 5953.073
|
|
},
|
|
{
|
|
"epoch": 0.444,
|
|
"grad_norm": 0.8014432527357591,
|
|
"learning_rate": 8.834481973632709e-06,
|
|
"loss": 0.2612,
|
|
"num_input_tokens_seen": 87397408,
|
|
"step": 1110,
|
|
"train_runtime": 14677.529,
|
|
"train_tokens_per_second": 5954.504
|
|
},
|
|
{
|
|
"epoch": 0.446,
|
|
"grad_norm": 0.930443798550076,
|
|
"learning_rate": 8.824382153709423e-06,
|
|
"loss": 0.2647,
|
|
"num_input_tokens_seen": 87762928,
|
|
"step": 1115,
|
|
"train_runtime": 14750.6792,
|
|
"train_tokens_per_second": 5949.755
|
|
},
|
|
{
|
|
"epoch": 0.448,
|
|
"grad_norm": 0.6435095826798272,
|
|
"learning_rate": 8.814244588678245e-06,
|
|
"loss": 0.242,
|
|
"num_input_tokens_seen": 88121120,
|
|
"step": 1120,
|
|
"train_runtime": 14807.3984,
|
|
"train_tokens_per_second": 5951.155
|
|
},
|
|
{
|
|
"epoch": 0.45,
|
|
"grad_norm": 0.7653907584800824,
|
|
"learning_rate": 8.80406937859285e-06,
|
|
"loss": 0.2395,
|
|
"num_input_tokens_seen": 88525008,
|
|
"step": 1125,
|
|
"train_runtime": 14870.9967,
|
|
"train_tokens_per_second": 5952.863
|
|
},
|
|
{
|
|
"epoch": 0.452,
|
|
"grad_norm": 0.7573515883491185,
|
|
"learning_rate": 8.793856623878453e-06,
|
|
"loss": 0.2401,
|
|
"num_input_tokens_seen": 88958160,
|
|
"step": 1130,
|
|
"train_runtime": 14945.3854,
|
|
"train_tokens_per_second": 5952.216
|
|
},
|
|
{
|
|
"epoch": 0.454,
|
|
"grad_norm": 1.1357409156529634,
|
|
"learning_rate": 8.78360642533082e-06,
|
|
"loss": 0.2585,
|
|
"num_input_tokens_seen": 89252000,
|
|
"step": 1135,
|
|
"train_runtime": 14990.5393,
|
|
"train_tokens_per_second": 5953.889
|
|
},
|
|
{
|
|
"epoch": 0.456,
|
|
"grad_norm": 0.8644413546151707,
|
|
"learning_rate": 8.773318884115273e-06,
|
|
"loss": 0.2189,
|
|
"num_input_tokens_seen": 89628016,
|
|
"step": 1140,
|
|
"train_runtime": 15058.5277,
|
|
"train_tokens_per_second": 5951.977
|
|
},
|
|
{
|
|
"epoch": 0.458,
|
|
"grad_norm": 0.7389022088863988,
|
|
"learning_rate": 8.76299410176569e-06,
|
|
"loss": 0.2649,
|
|
"num_input_tokens_seen": 90034128,
|
|
"step": 1145,
|
|
"train_runtime": 15122.4941,
|
|
"train_tokens_per_second": 5953.656
|
|
},
|
|
{
|
|
"epoch": 0.46,
|
|
"grad_norm": 0.7710676631866474,
|
|
"learning_rate": 8.752632180183504e-06,
|
|
"loss": 0.2562,
|
|
"num_input_tokens_seen": 90366512,
|
|
"step": 1150,
|
|
"train_runtime": 15178.7113,
|
|
"train_tokens_per_second": 5953.504
|
|
},
|
|
{
|
|
"epoch": 0.462,
|
|
"grad_norm": 0.9633116613760667,
|
|
"learning_rate": 8.7422332216367e-06,
|
|
"loss": 0.2366,
|
|
"num_input_tokens_seen": 90739280,
|
|
"step": 1155,
|
|
"train_runtime": 15251.2362,
|
|
"train_tokens_per_second": 5949.634
|
|
},
|
|
{
|
|
"epoch": 0.464,
|
|
"grad_norm": 0.8014531807399391,
|
|
"learning_rate": 8.7317973287588e-06,
|
|
"loss": 0.2465,
|
|
"num_input_tokens_seen": 91111104,
|
|
"step": 1160,
|
|
"train_runtime": 15326.9003,
|
|
"train_tokens_per_second": 5944.523
|
|
},
|
|
{
|
|
"epoch": 0.466,
|
|
"grad_norm": 0.8222390185564179,
|
|
"learning_rate": 8.721324604547851e-06,
|
|
"loss": 0.2689,
|
|
"num_input_tokens_seen": 91526176,
|
|
"step": 1165,
|
|
"train_runtime": 15404.9048,
|
|
"train_tokens_per_second": 5941.366
|
|
},
|
|
{
|
|
"epoch": 0.468,
|
|
"grad_norm": 1.0652869678290553,
|
|
"learning_rate": 8.710815152365416e-06,
|
|
"loss": 0.2943,
|
|
"num_input_tokens_seen": 91904368,
|
|
"step": 1170,
|
|
"train_runtime": 15478.9534,
|
|
"train_tokens_per_second": 5937.376
|
|
},
|
|
{
|
|
"epoch": 0.47,
|
|
"grad_norm": 0.6030089904636131,
|
|
"learning_rate": 8.700269075935542e-06,
|
|
"loss": 0.2485,
|
|
"num_input_tokens_seen": 92358160,
|
|
"step": 1175,
|
|
"train_runtime": 15556.3907,
|
|
"train_tokens_per_second": 5936.992
|
|
},
|
|
{
|
|
"epoch": 0.472,
|
|
"grad_norm": 0.9092828633416254,
|
|
"learning_rate": 8.689686479343747e-06,
|
|
"loss": 0.2464,
|
|
"num_input_tokens_seen": 92821904,
|
|
"step": 1180,
|
|
"train_runtime": 15632.5857,
|
|
"train_tokens_per_second": 5937.719
|
|
},
|
|
{
|
|
"epoch": 0.474,
|
|
"grad_norm": 0.7894642154049413,
|
|
"learning_rate": 8.679067467035989e-06,
|
|
"loss": 0.2504,
|
|
"num_input_tokens_seen": 93187600,
|
|
"step": 1185,
|
|
"train_runtime": 15697.5108,
|
|
"train_tokens_per_second": 5936.457
|
|
},
|
|
{
|
|
"epoch": 0.476,
|
|
"grad_norm": 0.8786028772279872,
|
|
"learning_rate": 8.66841214381763e-06,
|
|
"loss": 0.2568,
|
|
"num_input_tokens_seen": 93487696,
|
|
"step": 1190,
|
|
"train_runtime": 15741.8142,
|
|
"train_tokens_per_second": 5938.813
|
|
},
|
|
{
|
|
"epoch": 0.478,
|
|
"grad_norm": 0.7893669505556468,
|
|
"learning_rate": 8.657720614852412e-06,
|
|
"loss": 0.2278,
|
|
"num_input_tokens_seen": 93876672,
|
|
"step": 1195,
|
|
"train_runtime": 15806.9191,
|
|
"train_tokens_per_second": 5938.961
|
|
},
|
|
{
|
|
"epoch": 0.48,
|
|
"grad_norm": 0.8565601256929846,
|
|
"learning_rate": 8.646992985661404e-06,
|
|
"loss": 0.2417,
|
|
"num_input_tokens_seen": 94238000,
|
|
"step": 1200,
|
|
"train_runtime": 15871.1761,
|
|
"train_tokens_per_second": 5937.682
|
|
},
|
|
{
|
|
"epoch": 0.482,
|
|
"grad_norm": 0.9164857605094122,
|
|
"learning_rate": 8.636229362121979e-06,
|
|
"loss": 0.2496,
|
|
"num_input_tokens_seen": 94567520,
|
|
"step": 1205,
|
|
"train_runtime": 15931.6796,
|
|
"train_tokens_per_second": 5935.816
|
|
},
|
|
{
|
|
"epoch": 0.484,
|
|
"grad_norm": 0.7077259117523806,
|
|
"learning_rate": 8.625429850466756e-06,
|
|
"loss": 0.2244,
|
|
"num_input_tokens_seen": 94893184,
|
|
"step": 1210,
|
|
"train_runtime": 15990.0473,
|
|
"train_tokens_per_second": 5934.516
|
|
},
|
|
{
|
|
"epoch": 0.486,
|
|
"grad_norm": 0.6485501307737555,
|
|
"learning_rate": 8.614594557282553e-06,
|
|
"loss": 0.2397,
|
|
"num_input_tokens_seen": 95276080,
|
|
"step": 1215,
|
|
"train_runtime": 16055.5553,
|
|
"train_tokens_per_second": 5934.15
|
|
},
|
|
{
|
|
"epoch": 0.488,
|
|
"grad_norm": 0.6447256273387733,
|
|
"learning_rate": 8.603723589509342e-06,
|
|
"loss": 0.2477,
|
|
"num_input_tokens_seen": 95722112,
|
|
"step": 1220,
|
|
"train_runtime": 16124.7208,
|
|
"train_tokens_per_second": 5936.358
|
|
},
|
|
{
|
|
"epoch": 0.49,
|
|
"grad_norm": 0.7012472368965309,
|
|
"learning_rate": 8.592817054439184e-06,
|
|
"loss": 0.2625,
|
|
"num_input_tokens_seen": 96141024,
|
|
"step": 1225,
|
|
"train_runtime": 16196.1707,
|
|
"train_tokens_per_second": 5936.034
|
|
},
|
|
{
|
|
"epoch": 0.492,
|
|
"grad_norm": 0.6324888494194018,
|
|
"learning_rate": 8.581875059715177e-06,
|
|
"loss": 0.2503,
|
|
"num_input_tokens_seen": 96587392,
|
|
"step": 1230,
|
|
"train_runtime": 16262.1697,
|
|
"train_tokens_per_second": 5939.391
|
|
},
|
|
{
|
|
"epoch": 0.494,
|
|
"grad_norm": 0.7054612824038707,
|
|
"learning_rate": 8.570897713330392e-06,
|
|
"loss": 0.2599,
|
|
"num_input_tokens_seen": 97023264,
|
|
"step": 1235,
|
|
"train_runtime": 16336.3737,
|
|
"train_tokens_per_second": 5939.094
|
|
},
|
|
{
|
|
"epoch": 0.496,
|
|
"grad_norm": 0.8286039820576346,
|
|
"learning_rate": 8.559885123626806e-06,
|
|
"loss": 0.2513,
|
|
"num_input_tokens_seen": 97430560,
|
|
"step": 1240,
|
|
"train_runtime": 16397.8473,
|
|
"train_tokens_per_second": 5941.668
|
|
},
|
|
{
|
|
"epoch": 0.498,
|
|
"grad_norm": 0.564446015093804,
|
|
"learning_rate": 8.548837399294235e-06,
|
|
"loss": 0.2637,
|
|
"num_input_tokens_seen": 97827472,
|
|
"step": 1245,
|
|
"train_runtime": 16455.0469,
|
|
"train_tokens_per_second": 5945.135
|
|
},
|
|
{
|
|
"epoch": 0.5,
|
|
"grad_norm": 0.7169858114687652,
|
|
"learning_rate": 8.537754649369256e-06,
|
|
"loss": 0.2419,
|
|
"num_input_tokens_seen": 98229376,
|
|
"step": 1250,
|
|
"train_runtime": 16532.9815,
|
|
"train_tokens_per_second": 5941.419
|
|
},
|
|
{
|
|
"epoch": 0.502,
|
|
"grad_norm": 0.753834648508727,
|
|
"learning_rate": 8.526636983234135e-06,
|
|
"loss": 0.2418,
|
|
"num_input_tokens_seen": 98599872,
|
|
"step": 1255,
|
|
"train_runtime": 16586.3065,
|
|
"train_tokens_per_second": 5944.655
|
|
},
|
|
{
|
|
"epoch": 0.504,
|
|
"grad_norm": 0.6582526707978466,
|
|
"learning_rate": 8.515484510615753e-06,
|
|
"loss": 0.2554,
|
|
"num_input_tokens_seen": 99026864,
|
|
"step": 1260,
|
|
"train_runtime": 16653.3937,
|
|
"train_tokens_per_second": 5946.347
|
|
},
|
|
{
|
|
"epoch": 0.506,
|
|
"grad_norm": 0.6945432775129547,
|
|
"learning_rate": 8.504297341584509e-06,
|
|
"loss": 0.2658,
|
|
"num_input_tokens_seen": 99395904,
|
|
"step": 1265,
|
|
"train_runtime": 16722.2133,
|
|
"train_tokens_per_second": 5943.944
|
|
},
|
|
{
|
|
"epoch": 0.508,
|
|
"grad_norm": 0.7918732739548086,
|
|
"learning_rate": 8.493075586553245e-06,
|
|
"loss": 0.2281,
|
|
"num_input_tokens_seen": 99825616,
|
|
"step": 1270,
|
|
"train_runtime": 16787.7864,
|
|
"train_tokens_per_second": 5946.324
|
|
},
|
|
{
|
|
"epoch": 0.51,
|
|
"grad_norm": 0.7696512289103038,
|
|
"learning_rate": 8.481819356276155e-06,
|
|
"loss": 0.2434,
|
|
"num_input_tokens_seen": 100220256,
|
|
"step": 1275,
|
|
"train_runtime": 16855.7722,
|
|
"train_tokens_per_second": 5945.753
|
|
},
|
|
{
|
|
"epoch": 0.512,
|
|
"grad_norm": 0.7508764829190959,
|
|
"learning_rate": 8.470528761847684e-06,
|
|
"loss": 0.2503,
|
|
"num_input_tokens_seen": 100620576,
|
|
"step": 1280,
|
|
"train_runtime": 16926.3709,
|
|
"train_tokens_per_second": 5944.604
|
|
},
|
|
{
|
|
"epoch": 0.514,
|
|
"grad_norm": 0.9707421200986698,
|
|
"learning_rate": 8.459203914701444e-06,
|
|
"loss": 0.2738,
|
|
"num_input_tokens_seen": 101019904,
|
|
"step": 1285,
|
|
"train_runtime": 16986.4734,
|
|
"train_tokens_per_second": 5947.079
|
|
},
|
|
{
|
|
"epoch": 0.516,
|
|
"grad_norm": 0.8459354981861116,
|
|
"learning_rate": 8.447844926609103e-06,
|
|
"loss": 0.2742,
|
|
"num_input_tokens_seen": 101476336,
|
|
"step": 1290,
|
|
"train_runtime": 17064.6621,
|
|
"train_tokens_per_second": 5946.578
|
|
},
|
|
{
|
|
"epoch": 0.518,
|
|
"grad_norm": 0.6264057337370963,
|
|
"learning_rate": 8.436451909679286e-06,
|
|
"loss": 0.2436,
|
|
"num_input_tokens_seen": 101840464,
|
|
"step": 1295,
|
|
"train_runtime": 17121.8045,
|
|
"train_tokens_per_second": 5947.998
|
|
},
|
|
{
|
|
"epoch": 0.52,
|
|
"grad_norm": 0.8953106899143487,
|
|
"learning_rate": 8.425024976356474e-06,
|
|
"loss": 0.2449,
|
|
"num_input_tokens_seen": 102215776,
|
|
"step": 1300,
|
|
"train_runtime": 17186.2906,
|
|
"train_tokens_per_second": 5947.518
|
|
},
|
|
{
|
|
"epoch": 0.522,
|
|
"grad_norm": 0.9429866958899052,
|
|
"learning_rate": 8.413564239419883e-06,
|
|
"loss": 0.2516,
|
|
"num_input_tokens_seen": 102620256,
|
|
"step": 1305,
|
|
"train_runtime": 17260.7388,
|
|
"train_tokens_per_second": 5945.299
|
|
},
|
|
{
|
|
"epoch": 0.524,
|
|
"grad_norm": 0.7083743370162111,
|
|
"learning_rate": 8.40206981198236e-06,
|
|
"loss": 0.2496,
|
|
"num_input_tokens_seen": 102981744,
|
|
"step": 1310,
|
|
"train_runtime": 17315.691,
|
|
"train_tokens_per_second": 5947.308
|
|
},
|
|
{
|
|
"epoch": 0.526,
|
|
"grad_norm": 0.7049439211819539,
|
|
"learning_rate": 8.390541807489266e-06,
|
|
"loss": 0.2612,
|
|
"num_input_tokens_seen": 103420880,
|
|
"step": 1315,
|
|
"train_runtime": 17394.0332,
|
|
"train_tokens_per_second": 5945.768
|
|
},
|
|
{
|
|
"epoch": 0.528,
|
|
"grad_norm": 0.6884521726121087,
|
|
"learning_rate": 8.378980339717348e-06,
|
|
"loss": 0.2544,
|
|
"num_input_tokens_seen": 103881808,
|
|
"step": 1320,
|
|
"train_runtime": 17469.4075,
|
|
"train_tokens_per_second": 5946.499
|
|
},
|
|
{
|
|
"epoch": 0.53,
|
|
"grad_norm": 1.0516635133353769,
|
|
"learning_rate": 8.367385522773625e-06,
|
|
"loss": 0.2626,
|
|
"num_input_tokens_seen": 104250576,
|
|
"step": 1325,
|
|
"train_runtime": 17525.1657,
|
|
"train_tokens_per_second": 5948.621
|
|
},
|
|
{
|
|
"epoch": 0.532,
|
|
"grad_norm": 0.7098039380682222,
|
|
"learning_rate": 8.355757471094263e-06,
|
|
"loss": 0.2524,
|
|
"num_input_tokens_seen": 104591808,
|
|
"step": 1330,
|
|
"train_runtime": 17586.521,
|
|
"train_tokens_per_second": 5947.271
|
|
},
|
|
{
|
|
"epoch": 0.534,
|
|
"grad_norm": 0.5159589865497483,
|
|
"learning_rate": 8.344096299443434e-06,
|
|
"loss": 0.2493,
|
|
"num_input_tokens_seen": 104999392,
|
|
"step": 1335,
|
|
"train_runtime": 17651.5705,
|
|
"train_tokens_per_second": 5948.445
|
|
},
|
|
{
|
|
"epoch": 0.536,
|
|
"grad_norm": 0.904008052443577,
|
|
"learning_rate": 8.332402122912198e-06,
|
|
"loss": 0.2369,
|
|
"num_input_tokens_seen": 105360928,
|
|
"step": 1340,
|
|
"train_runtime": 17714.3169,
|
|
"train_tokens_per_second": 5947.784
|
|
},
|
|
{
|
|
"epoch": 0.538,
|
|
"grad_norm": 0.6651472179253896,
|
|
"learning_rate": 8.320675056917353e-06,
|
|
"loss": 0.2566,
|
|
"num_input_tokens_seen": 105742624,
|
|
"step": 1345,
|
|
"train_runtime": 17778.4474,
|
|
"train_tokens_per_second": 5947.799
|
|
},
|
|
{
|
|
"epoch": 0.54,
|
|
"grad_norm": 0.7927826502831012,
|
|
"learning_rate": 8.308915217200305e-06,
|
|
"loss": 0.2643,
|
|
"num_input_tokens_seen": 106120016,
|
|
"step": 1350,
|
|
"train_runtime": 17837.0793,
|
|
"train_tokens_per_second": 5949.405
|
|
},
|
|
{
|
|
"epoch": 0.542,
|
|
"grad_norm": 0.8565986406816929,
|
|
"learning_rate": 8.297122719825928e-06,
|
|
"loss": 0.2274,
|
|
"num_input_tokens_seen": 106498992,
|
|
"step": 1355,
|
|
"train_runtime": 17911.1244,
|
|
"train_tokens_per_second": 5945.969
|
|
},
|
|
{
|
|
"epoch": 0.544,
|
|
"grad_norm": 0.6638912658832349,
|
|
"learning_rate": 8.285297681181408e-06,
|
|
"loss": 0.233,
|
|
"num_input_tokens_seen": 106906656,
|
|
"step": 1360,
|
|
"train_runtime": 17973.95,
|
|
"train_tokens_per_second": 5947.867
|
|
},
|
|
{
|
|
"epoch": 0.546,
|
|
"grad_norm": 0.8715953996990423,
|
|
"learning_rate": 8.273440217975103e-06,
|
|
"loss": 0.2527,
|
|
"num_input_tokens_seen": 107212272,
|
|
"step": 1365,
|
|
"train_runtime": 18023.9906,
|
|
"train_tokens_per_second": 5948.309
|
|
},
|
|
{
|
|
"epoch": 0.548,
|
|
"grad_norm": 0.7473907734015952,
|
|
"learning_rate": 8.261550447235389e-06,
|
|
"loss": 0.2356,
|
|
"num_input_tokens_seen": 107567200,
|
|
"step": 1370,
|
|
"train_runtime": 18080.5797,
|
|
"train_tokens_per_second": 5949.323
|
|
},
|
|
{
|
|
"epoch": 0.55,
|
|
"grad_norm": 0.7915564307590499,
|
|
"learning_rate": 8.2496284863095e-06,
|
|
"loss": 0.2204,
|
|
"num_input_tokens_seen": 108001632,
|
|
"step": 1375,
|
|
"train_runtime": 18151.1849,
|
|
"train_tokens_per_second": 5950.115
|
|
},
|
|
{
|
|
"epoch": 0.552,
|
|
"grad_norm": 0.690764307158169,
|
|
"learning_rate": 8.23767445286238e-06,
|
|
"loss": 0.2518,
|
|
"num_input_tokens_seen": 108400032,
|
|
"step": 1380,
|
|
"train_runtime": 18216.9813,
|
|
"train_tokens_per_second": 5950.494
|
|
},
|
|
{
|
|
"epoch": 0.554,
|
|
"grad_norm": 0.6612957959493211,
|
|
"learning_rate": 8.225688464875514e-06,
|
|
"loss": 0.254,
|
|
"num_input_tokens_seen": 108793600,
|
|
"step": 1385,
|
|
"train_runtime": 18294.9254,
|
|
"train_tokens_per_second": 5946.654
|
|
},
|
|
{
|
|
"epoch": 0.556,
|
|
"grad_norm": 0.8146239119318059,
|
|
"learning_rate": 8.213670640645762e-06,
|
|
"loss": 0.2616,
|
|
"num_input_tokens_seen": 109239856,
|
|
"step": 1390,
|
|
"train_runtime": 18361.5892,
|
|
"train_tokens_per_second": 5949.368
|
|
},
|
|
{
|
|
"epoch": 0.558,
|
|
"grad_norm": 0.9407259867063503,
|
|
"learning_rate": 8.201621098784198e-06,
|
|
"loss": 0.2497,
|
|
"num_input_tokens_seen": 109586848,
|
|
"step": 1395,
|
|
"train_runtime": 18423.9904,
|
|
"train_tokens_per_second": 5948.052
|
|
},
|
|
{
|
|
"epoch": 0.56,
|
|
"grad_norm": 0.6787557953668363,
|
|
"learning_rate": 8.189539958214934e-06,
|
|
"loss": 0.2422,
|
|
"num_input_tokens_seen": 110004576,
|
|
"step": 1400,
|
|
"train_runtime": 18486.0657,
|
|
"train_tokens_per_second": 5950.675
|
|
},
|
|
{
|
|
"epoch": 0.562,
|
|
"grad_norm": 0.6738263355281091,
|
|
"learning_rate": 8.177427338173955e-06,
|
|
"loss": 0.2511,
|
|
"num_input_tokens_seen": 110425520,
|
|
"step": 1405,
|
|
"train_runtime": 18556.9515,
|
|
"train_tokens_per_second": 5950.628
|
|
},
|
|
{
|
|
"epoch": 0.564,
|
|
"grad_norm": 0.6654146458771333,
|
|
"learning_rate": 8.165283358207924e-06,
|
|
"loss": 0.2545,
|
|
"num_input_tokens_seen": 110798416,
|
|
"step": 1410,
|
|
"train_runtime": 18617.3657,
|
|
"train_tokens_per_second": 5951.348
|
|
},
|
|
{
|
|
"epoch": 0.566,
|
|
"grad_norm": 0.7124097479742371,
|
|
"learning_rate": 8.153108138173027e-06,
|
|
"loss": 0.243,
|
|
"num_input_tokens_seen": 111221456,
|
|
"step": 1415,
|
|
"train_runtime": 18693.9621,
|
|
"train_tokens_per_second": 5949.592
|
|
},
|
|
{
|
|
"epoch": 0.568,
|
|
"grad_norm": 0.7722193156964303,
|
|
"learning_rate": 8.140901798233766e-06,
|
|
"loss": 0.2481,
|
|
"num_input_tokens_seen": 111584784,
|
|
"step": 1420,
|
|
"train_runtime": 18761.6948,
|
|
"train_tokens_per_second": 5947.479
|
|
},
|
|
{
|
|
"epoch": 0.57,
|
|
"grad_norm": 0.708503545830723,
|
|
"learning_rate": 8.12866445886179e-06,
|
|
"loss": 0.2444,
|
|
"num_input_tokens_seen": 111922640,
|
|
"step": 1425,
|
|
"train_runtime": 18826.1559,
|
|
"train_tokens_per_second": 5945.061
|
|
},
|
|
{
|
|
"epoch": 0.572,
|
|
"grad_norm": 0.858693182825798,
|
|
"learning_rate": 8.116396240834699e-06,
|
|
"loss": 0.2414,
|
|
"num_input_tokens_seen": 112287760,
|
|
"step": 1430,
|
|
"train_runtime": 18895.7567,
|
|
"train_tokens_per_second": 5942.485
|
|
},
|
|
{
|
|
"epoch": 0.574,
|
|
"grad_norm": 0.6950450411170785,
|
|
"learning_rate": 8.10409726523485e-06,
|
|
"loss": 0.2424,
|
|
"num_input_tokens_seen": 112661728,
|
|
"step": 1435,
|
|
"train_runtime": 18947.4324,
|
|
"train_tokens_per_second": 5946.016
|
|
},
|
|
{
|
|
"epoch": 0.576,
|
|
"grad_norm": 0.9025950371365907,
|
|
"learning_rate": 8.091767653448169e-06,
|
|
"loss": 0.2563,
|
|
"num_input_tokens_seen": 113064880,
|
|
"step": 1440,
|
|
"train_runtime": 19013.0998,
|
|
"train_tokens_per_second": 5946.683
|
|
},
|
|
{
|
|
"epoch": 0.578,
|
|
"grad_norm": 0.783582958375125,
|
|
"learning_rate": 8.079407527162944e-06,
|
|
"loss": 0.2386,
|
|
"num_input_tokens_seen": 113464160,
|
|
"step": 1445,
|
|
"train_runtime": 19080.6528,
|
|
"train_tokens_per_second": 5946.555
|
|
},
|
|
{
|
|
"epoch": 0.58,
|
|
"grad_norm": 0.6682602674979189,
|
|
"learning_rate": 8.067017008368632e-06,
|
|
"loss": 0.2558,
|
|
"num_input_tokens_seen": 113867952,
|
|
"step": 1450,
|
|
"train_runtime": 19145.0648,
|
|
"train_tokens_per_second": 5947.64
|
|
},
|
|
{
|
|
"epoch": 0.582,
|
|
"grad_norm": 0.707706565040942,
|
|
"learning_rate": 8.054596219354655e-06,
|
|
"loss": 0.2554,
|
|
"num_input_tokens_seen": 114273424,
|
|
"step": 1455,
|
|
"train_runtime": 19222.6331,
|
|
"train_tokens_per_second": 5944.733
|
|
},
|
|
{
|
|
"epoch": 0.584,
|
|
"grad_norm": 0.7233732054254851,
|
|
"learning_rate": 8.042145282709181e-06,
|
|
"loss": 0.2601,
|
|
"num_input_tokens_seen": 114717424,
|
|
"step": 1460,
|
|
"train_runtime": 19289.3055,
|
|
"train_tokens_per_second": 5947.203
|
|
},
|
|
{
|
|
"epoch": 0.586,
|
|
"grad_norm": 0.6422217738433834,
|
|
"learning_rate": 8.029664321317932e-06,
|
|
"loss": 0.2601,
|
|
"num_input_tokens_seen": 115135984,
|
|
"step": 1465,
|
|
"train_runtime": 19354.3487,
|
|
"train_tokens_per_second": 5948.843
|
|
},
|
|
{
|
|
"epoch": 0.588,
|
|
"grad_norm": 0.7333788682022774,
|
|
"learning_rate": 8.017153458362957e-06,
|
|
"loss": 0.2652,
|
|
"num_input_tokens_seen": 115545440,
|
|
"step": 1470,
|
|
"train_runtime": 19414.5638,
|
|
"train_tokens_per_second": 5951.483
|
|
},
|
|
{
|
|
"epoch": 0.59,
|
|
"grad_norm": 0.6290152315681616,
|
|
"learning_rate": 8.004612817321419e-06,
|
|
"loss": 0.2579,
|
|
"num_input_tokens_seen": 115943440,
|
|
"step": 1475,
|
|
"train_runtime": 19481.8184,
|
|
"train_tokens_per_second": 5951.366
|
|
},
|
|
{
|
|
"epoch": 0.592,
|
|
"grad_norm": 0.7113000835362475,
|
|
"learning_rate": 7.99204252196439e-06,
|
|
"loss": 0.2586,
|
|
"num_input_tokens_seen": 116366400,
|
|
"step": 1480,
|
|
"train_runtime": 19550.9137,
|
|
"train_tokens_per_second": 5951.967
|
|
},
|
|
{
|
|
"epoch": 0.594,
|
|
"grad_norm": 0.676866820935986,
|
|
"learning_rate": 7.979442696355601e-06,
|
|
"loss": 0.2324,
|
|
"num_input_tokens_seen": 116736672,
|
|
"step": 1485,
|
|
"train_runtime": 19619.6574,
|
|
"train_tokens_per_second": 5949.985
|
|
},
|
|
{
|
|
"epoch": 0.596,
|
|
"grad_norm": 0.63597242705262,
|
|
"learning_rate": 7.966813464850252e-06,
|
|
"loss": 0.2577,
|
|
"num_input_tokens_seen": 117116064,
|
|
"step": 1490,
|
|
"train_runtime": 19679.1949,
|
|
"train_tokens_per_second": 5951.263
|
|
},
|
|
{
|
|
"epoch": 0.598,
|
|
"grad_norm": 0.5934642312626544,
|
|
"learning_rate": 7.954154952093754e-06,
|
|
"loss": 0.2366,
|
|
"num_input_tokens_seen": 117565696,
|
|
"step": 1495,
|
|
"train_runtime": 19754.6802,
|
|
"train_tokens_per_second": 5951.283
|
|
},
|
|
{
|
|
"epoch": 0.6,
|
|
"grad_norm": 0.8246530677768509,
|
|
"learning_rate": 7.941467283020521e-06,
|
|
"loss": 0.2458,
|
|
"num_input_tokens_seen": 117980528,
|
|
"step": 1500,
|
|
"train_runtime": 19825.7152,
|
|
"train_tokens_per_second": 5950.884
|
|
},
|
|
{
|
|
"epoch": 0.602,
|
|
"grad_norm": 0.6803775472920268,
|
|
"learning_rate": 7.928750582852722e-06,
|
|
"loss": 0.2354,
|
|
"num_input_tokens_seen": 118392000,
|
|
"step": 1505,
|
|
"train_runtime": 19894.375,
|
|
"train_tokens_per_second": 5951.029
|
|
},
|
|
{
|
|
"epoch": 0.604,
|
|
"grad_norm": 0.6829702832729062,
|
|
"learning_rate": 7.916004977099054e-06,
|
|
"loss": 0.2437,
|
|
"num_input_tokens_seen": 118773680,
|
|
"step": 1510,
|
|
"train_runtime": 19959.575,
|
|
"train_tokens_per_second": 5950.712
|
|
},
|
|
{
|
|
"epoch": 0.606,
|
|
"grad_norm": 0.5796988428999044,
|
|
"learning_rate": 7.903230591553504e-06,
|
|
"loss": 0.2312,
|
|
"num_input_tokens_seen": 119115104,
|
|
"step": 1515,
|
|
"train_runtime": 20011.3737,
|
|
"train_tokens_per_second": 5952.37
|
|
},
|
|
{
|
|
"epoch": 0.608,
|
|
"grad_norm": 0.7848124831820052,
|
|
"learning_rate": 7.890427552294093e-06,
|
|
"loss": 0.2591,
|
|
"num_input_tokens_seen": 119460384,
|
|
"step": 1520,
|
|
"train_runtime": 20074.942,
|
|
"train_tokens_per_second": 5950.721
|
|
},
|
|
{
|
|
"epoch": 0.61,
|
|
"grad_norm": 0.7615681932253368,
|
|
"learning_rate": 7.877595985681656e-06,
|
|
"loss": 0.2653,
|
|
"num_input_tokens_seen": 119858560,
|
|
"step": 1525,
|
|
"train_runtime": 20141.7147,
|
|
"train_tokens_per_second": 5950.762
|
|
},
|
|
{
|
|
"epoch": 0.612,
|
|
"grad_norm": 0.6772425523098504,
|
|
"learning_rate": 7.864736018358571e-06,
|
|
"loss": 0.2344,
|
|
"num_input_tokens_seen": 120298352,
|
|
"step": 1530,
|
|
"train_runtime": 20211.3072,
|
|
"train_tokens_per_second": 5952.032
|
|
},
|
|
{
|
|
"epoch": 0.614,
|
|
"grad_norm": 0.7585007734797548,
|
|
"learning_rate": 7.851847777247528e-06,
|
|
"loss": 0.2657,
|
|
"num_input_tokens_seen": 120735536,
|
|
"step": 1535,
|
|
"train_runtime": 20289.6603,
|
|
"train_tokens_per_second": 5950.594
|
|
},
|
|
{
|
|
"epoch": 0.616,
|
|
"grad_norm": 0.9257964242960042,
|
|
"learning_rate": 7.83893138955026e-06,
|
|
"loss": 0.2744,
|
|
"num_input_tokens_seen": 121111328,
|
|
"step": 1540,
|
|
"train_runtime": 20354.3359,
|
|
"train_tokens_per_second": 5950.149
|
|
},
|
|
{
|
|
"epoch": 0.618,
|
|
"grad_norm": 0.7584226438302087,
|
|
"learning_rate": 7.8259869827463e-06,
|
|
"loss": 0.2471,
|
|
"num_input_tokens_seen": 121505792,
|
|
"step": 1545,
|
|
"train_runtime": 20414.9433,
|
|
"train_tokens_per_second": 5951.806
|
|
},
|
|
{
|
|
"epoch": 0.62,
|
|
"grad_norm": 0.7804373473000645,
|
|
"learning_rate": 7.813014684591718e-06,
|
|
"loss": 0.2406,
|
|
"num_input_tokens_seen": 121888000,
|
|
"step": 1550,
|
|
"train_runtime": 20492.5707,
|
|
"train_tokens_per_second": 5947.912
|
|
},
|
|
{
|
|
"epoch": 0.622,
|
|
"grad_norm": 0.6855534375843669,
|
|
"learning_rate": 7.800014623117858e-06,
|
|
"loss": 0.2424,
|
|
"num_input_tokens_seen": 122302912,
|
|
"step": 1555,
|
|
"train_runtime": 20566.4692,
|
|
"train_tokens_per_second": 5946.714
|
|
},
|
|
{
|
|
"epoch": 0.624,
|
|
"grad_norm": 0.7810986327996574,
|
|
"learning_rate": 7.786986926630079e-06,
|
|
"loss": 0.2585,
|
|
"num_input_tokens_seen": 122677712,
|
|
"step": 1560,
|
|
"train_runtime": 20618.1097,
|
|
"train_tokens_per_second": 5949.998
|
|
},
|
|
{
|
|
"epoch": 0.626,
|
|
"grad_norm": 0.7759520825635546,
|
|
"learning_rate": 7.773931723706487e-06,
|
|
"loss": 0.2532,
|
|
"num_input_tokens_seen": 123054656,
|
|
"step": 1565,
|
|
"train_runtime": 20678.9508,
|
|
"train_tokens_per_second": 5950.72
|
|
},
|
|
{
|
|
"epoch": 0.628,
|
|
"grad_norm": 0.7987781132107461,
|
|
"learning_rate": 7.760849143196664e-06,
|
|
"loss": 0.2555,
|
|
"num_input_tokens_seen": 123475648,
|
|
"step": 1570,
|
|
"train_runtime": 20756.4498,
|
|
"train_tokens_per_second": 5948.785
|
|
},
|
|
{
|
|
"epoch": 0.63,
|
|
"grad_norm": 0.7418203966884972,
|
|
"learning_rate": 7.747739314220398e-06,
|
|
"loss": 0.2416,
|
|
"num_input_tokens_seen": 123922816,
|
|
"step": 1575,
|
|
"train_runtime": 20831.9196,
|
|
"train_tokens_per_second": 5948.699
|
|
},
|
|
{
|
|
"epoch": 0.632,
|
|
"grad_norm": 0.6174717984031014,
|
|
"learning_rate": 7.734602366166406e-06,
|
|
"loss": 0.2552,
|
|
"num_input_tokens_seen": 124277408,
|
|
"step": 1580,
|
|
"train_runtime": 20888.719,
|
|
"train_tokens_per_second": 5949.499
|
|
},
|
|
{
|
|
"epoch": 0.634,
|
|
"grad_norm": 0.587009610351487,
|
|
"learning_rate": 7.721438428691065e-06,
|
|
"loss": 0.2438,
|
|
"num_input_tokens_seen": 124687888,
|
|
"step": 1585,
|
|
"train_runtime": 20962.2577,
|
|
"train_tokens_per_second": 5948.209
|
|
},
|
|
{
|
|
"epoch": 0.636,
|
|
"grad_norm": 0.7006930473267186,
|
|
"learning_rate": 7.708247631717122e-06,
|
|
"loss": 0.2349,
|
|
"num_input_tokens_seen": 125035328,
|
|
"step": 1590,
|
|
"train_runtime": 21019.6479,
|
|
"train_tokens_per_second": 5948.498
|
|
},
|
|
{
|
|
"epoch": 0.638,
|
|
"grad_norm": 0.7599865290838017,
|
|
"learning_rate": 7.695030105432417e-06,
|
|
"loss": 0.2621,
|
|
"num_input_tokens_seen": 125398688,
|
|
"step": 1595,
|
|
"train_runtime": 21076.0616,
|
|
"train_tokens_per_second": 5949.816
|
|
},
|
|
{
|
|
"epoch": 0.64,
|
|
"grad_norm": 0.6599089458820105,
|
|
"learning_rate": 7.681785980288601e-06,
|
|
"loss": 0.2424,
|
|
"num_input_tokens_seen": 125792304,
|
|
"step": 1600,
|
|
"train_runtime": 21138.3773,
|
|
"train_tokens_per_second": 5950.897
|
|
},
|
|
{
|
|
"epoch": 0.642,
|
|
"grad_norm": 0.6818631558687155,
|
|
"learning_rate": 7.668515386999837e-06,
|
|
"loss": 0.2416,
|
|
"num_input_tokens_seen": 126242176,
|
|
"step": 1605,
|
|
"train_runtime": 21213.8268,
|
|
"train_tokens_per_second": 5950.938
|
|
},
|
|
{
|
|
"epoch": 0.644,
|
|
"grad_norm": 0.6131556907902158,
|
|
"learning_rate": 7.65521845654153e-06,
|
|
"loss": 0.2298,
|
|
"num_input_tokens_seen": 126620048,
|
|
"step": 1610,
|
|
"train_runtime": 21289.2762,
|
|
"train_tokens_per_second": 5947.598
|
|
},
|
|
{
|
|
"epoch": 0.646,
|
|
"grad_norm": 0.7008878416577765,
|
|
"learning_rate": 7.641895320149008e-06,
|
|
"loss": 0.2582,
|
|
"num_input_tokens_seen": 127024944,
|
|
"step": 1615,
|
|
"train_runtime": 21353.3578,
|
|
"train_tokens_per_second": 5948.711
|
|
},
|
|
{
|
|
"epoch": 0.648,
|
|
"grad_norm": 0.7032794542013124,
|
|
"learning_rate": 7.628546109316257e-06,
|
|
"loss": 0.2617,
|
|
"num_input_tokens_seen": 127455024,
|
|
"step": 1620,
|
|
"train_runtime": 21427.4186,
|
|
"train_tokens_per_second": 5948.221
|
|
},
|
|
{
|
|
"epoch": 0.65,
|
|
"grad_norm": 0.9036139861758402,
|
|
"learning_rate": 7.615170955794592e-06,
|
|
"loss": 0.2782,
|
|
"num_input_tokens_seen": 127834640,
|
|
"step": 1625,
|
|
"train_runtime": 21504.2807,
|
|
"train_tokens_per_second": 5944.614
|
|
},
|
|
{
|
|
"epoch": 0.652,
|
|
"grad_norm": 0.8227192501807431,
|
|
"learning_rate": 7.60176999159138e-06,
|
|
"loss": 0.25,
|
|
"num_input_tokens_seen": 128188304,
|
|
"step": 1630,
|
|
"train_runtime": 21559.1839,
|
|
"train_tokens_per_second": 5945.879
|
|
},
|
|
{
|
|
"epoch": 0.654,
|
|
"grad_norm": 0.6968370902757749,
|
|
"learning_rate": 7.588343348968728e-06,
|
|
"loss": 0.2343,
|
|
"num_input_tokens_seen": 128624560,
|
|
"step": 1635,
|
|
"train_runtime": 21637.7464,
|
|
"train_tokens_per_second": 5944.453
|
|
},
|
|
{
|
|
"epoch": 0.656,
|
|
"grad_norm": 0.6928512624740695,
|
|
"learning_rate": 7.574891160442179e-06,
|
|
"loss": 0.2391,
|
|
"num_input_tokens_seen": 128979536,
|
|
"step": 1640,
|
|
"train_runtime": 21696.0196,
|
|
"train_tokens_per_second": 5944.848
|
|
},
|
|
{
|
|
"epoch": 0.658,
|
|
"grad_norm": 0.6282910568416581,
|
|
"learning_rate": 7.561413558779401e-06,
|
|
"loss": 0.2453,
|
|
"num_input_tokens_seen": 129395280,
|
|
"step": 1645,
|
|
"train_runtime": 21773.3461,
|
|
"train_tokens_per_second": 5942.829
|
|
},
|
|
{
|
|
"epoch": 0.66,
|
|
"grad_norm": 0.5387647591500422,
|
|
"learning_rate": 7.547910676998883e-06,
|
|
"loss": 0.2445,
|
|
"num_input_tokens_seen": 129790480,
|
|
"step": 1650,
|
|
"train_runtime": 21839.9147,
|
|
"train_tokens_per_second": 5942.811
|
|
},
|
|
{
|
|
"epoch": 0.662,
|
|
"grad_norm": 0.7777098347909889,
|
|
"learning_rate": 7.534382648368617e-06,
|
|
"loss": 0.2519,
|
|
"num_input_tokens_seen": 130179568,
|
|
"step": 1655,
|
|
"train_runtime": 21901.6622,
|
|
"train_tokens_per_second": 5943.821
|
|
},
|
|
{
|
|
"epoch": 0.664,
|
|
"grad_norm": 0.769633021051581,
|
|
"learning_rate": 7.520829606404781e-06,
|
|
"loss": 0.2464,
|
|
"num_input_tokens_seen": 130546960,
|
|
"step": 1660,
|
|
"train_runtime": 21956.2789,
|
|
"train_tokens_per_second": 5945.769
|
|
},
|
|
{
|
|
"epoch": 0.666,
|
|
"grad_norm": 0.798499009796827,
|
|
"learning_rate": 7.507251684870433e-06,
|
|
"loss": 0.2613,
|
|
"num_input_tokens_seen": 131000944,
|
|
"step": 1665,
|
|
"train_runtime": 22027.5074,
|
|
"train_tokens_per_second": 5947.152
|
|
},
|
|
{
|
|
"epoch": 0.668,
|
|
"grad_norm": 0.7054809636104681,
|
|
"learning_rate": 7.493649017774172e-06,
|
|
"loss": 0.2391,
|
|
"num_input_tokens_seen": 131408096,
|
|
"step": 1670,
|
|
"train_runtime": 22092.0472,
|
|
"train_tokens_per_second": 5948.208
|
|
},
|
|
{
|
|
"epoch": 0.67,
|
|
"grad_norm": 0.7480944347369234,
|
|
"learning_rate": 7.480021739368831e-06,
|
|
"loss": 0.238,
|
|
"num_input_tokens_seen": 131842384,
|
|
"step": 1675,
|
|
"train_runtime": 22165.098,
|
|
"train_tokens_per_second": 5948.198
|
|
},
|
|
{
|
|
"epoch": 0.672,
|
|
"grad_norm": 0.7749303371068519,
|
|
"learning_rate": 7.46636998415015e-06,
|
|
"loss": 0.2482,
|
|
"num_input_tokens_seen": 132275008,
|
|
"step": 1680,
|
|
"train_runtime": 22241.2007,
|
|
"train_tokens_per_second": 5947.296
|
|
},
|
|
{
|
|
"epoch": 0.674,
|
|
"grad_norm": 0.5451444378369477,
|
|
"learning_rate": 7.452693886855438e-06,
|
|
"loss": 0.2456,
|
|
"num_input_tokens_seen": 132563520,
|
|
"step": 1685,
|
|
"train_runtime": 22282.3979,
|
|
"train_tokens_per_second": 5949.248
|
|
},
|
|
{
|
|
"epoch": 0.676,
|
|
"grad_norm": 0.7569897610310852,
|
|
"learning_rate": 7.438993582462255e-06,
|
|
"loss": 0.2424,
|
|
"num_input_tokens_seen": 132997392,
|
|
"step": 1690,
|
|
"train_runtime": 22352.6253,
|
|
"train_tokens_per_second": 5949.967
|
|
},
|
|
{
|
|
"epoch": 0.678,
|
|
"grad_norm": 1.0505987211800965,
|
|
"learning_rate": 7.425269206187076e-06,
|
|
"loss": 0.2544,
|
|
"num_input_tokens_seen": 133426496,
|
|
"step": 1695,
|
|
"train_runtime": 22430.7241,
|
|
"train_tokens_per_second": 5948.381
|
|
},
|
|
{
|
|
"epoch": 0.68,
|
|
"grad_norm": 0.9802178584484053,
|
|
"learning_rate": 7.411520893483952e-06,
|
|
"loss": 0.2391,
|
|
"num_input_tokens_seen": 133870544,
|
|
"step": 1700,
|
|
"train_runtime": 22509.2718,
|
|
"train_tokens_per_second": 5947.351
|
|
},
|
|
{
|
|
"epoch": 0.682,
|
|
"grad_norm": 0.6878690951367751,
|
|
"learning_rate": 7.397748780043179e-06,
|
|
"loss": 0.2578,
|
|
"num_input_tokens_seen": 134297232,
|
|
"step": 1705,
|
|
"train_runtime": 22573.9014,
|
|
"train_tokens_per_second": 5949.226
|
|
},
|
|
{
|
|
"epoch": 0.684,
|
|
"grad_norm": 0.5834750130153558,
|
|
"learning_rate": 7.38395300178996e-06,
|
|
"loss": 0.2515,
|
|
"num_input_tokens_seen": 134663632,
|
|
"step": 1710,
|
|
"train_runtime": 22644.4422,
|
|
"train_tokens_per_second": 5946.873
|
|
},
|
|
{
|
|
"epoch": 0.686,
|
|
"grad_norm": 0.9249623959814148,
|
|
"learning_rate": 7.370133694883052e-06,
|
|
"loss": 0.2333,
|
|
"num_input_tokens_seen": 135047920,
|
|
"step": 1715,
|
|
"train_runtime": 22705.4724,
|
|
"train_tokens_per_second": 5947.814
|
|
},
|
|
{
|
|
"epoch": 0.688,
|
|
"grad_norm": 0.6098108074100824,
|
|
"learning_rate": 7.356290995713436e-06,
|
|
"loss": 0.2569,
|
|
"num_input_tokens_seen": 135533312,
|
|
"step": 1720,
|
|
"train_runtime": 22783.9238,
|
|
"train_tokens_per_second": 5948.638
|
|
},
|
|
{
|
|
"epoch": 0.69,
|
|
"grad_norm": 0.7622642918846533,
|
|
"learning_rate": 7.342425040902967e-06,
|
|
"loss": 0.2587,
|
|
"num_input_tokens_seen": 135924224,
|
|
"step": 1725,
|
|
"train_runtime": 22851.1503,
|
|
"train_tokens_per_second": 5948.244
|
|
},
|
|
{
|
|
"epoch": 0.692,
|
|
"grad_norm": 0.7997119352799948,
|
|
"learning_rate": 7.32853596730302e-06,
|
|
"loss": 0.2396,
|
|
"num_input_tokens_seen": 136269040,
|
|
"step": 1730,
|
|
"train_runtime": 22918.3706,
|
|
"train_tokens_per_second": 5945.843
|
|
},
|
|
{
|
|
"epoch": 0.694,
|
|
"grad_norm": 0.617079296944827,
|
|
"learning_rate": 7.314623911993143e-06,
|
|
"loss": 0.2483,
|
|
"num_input_tokens_seen": 136639296,
|
|
"step": 1735,
|
|
"train_runtime": 22978.1982,
|
|
"train_tokens_per_second": 5946.476
|
|
},
|
|
{
|
|
"epoch": 0.696,
|
|
"grad_norm": 0.7038872747532084,
|
|
"learning_rate": 7.300689012279706e-06,
|
|
"loss": 0.2255,
|
|
"num_input_tokens_seen": 137049552,
|
|
"step": 1740,
|
|
"train_runtime": 23047.5997,
|
|
"train_tokens_per_second": 5946.37
|
|
},
|
|
{
|
|
"epoch": 0.698,
|
|
"grad_norm": 0.700125410633313,
|
|
"learning_rate": 7.286731405694544e-06,
|
|
"loss": 0.2147,
|
|
"num_input_tokens_seen": 137441952,
|
|
"step": 1745,
|
|
"train_runtime": 23110.0137,
|
|
"train_tokens_per_second": 5947.29
|
|
},
|
|
{
|
|
"epoch": 0.7,
|
|
"grad_norm": 0.7270805438257301,
|
|
"learning_rate": 7.272751229993598e-06,
|
|
"loss": 0.2395,
|
|
"num_input_tokens_seen": 137846304,
|
|
"step": 1750,
|
|
"train_runtime": 23172.4464,
|
|
"train_tokens_per_second": 5948.716
|
|
},
|
|
{
|
|
"epoch": 0.702,
|
|
"grad_norm": 0.9542369589000788,
|
|
"learning_rate": 7.258748623155558e-06,
|
|
"loss": 0.2618,
|
|
"num_input_tokens_seen": 138221600,
|
|
"step": 1755,
|
|
"train_runtime": 23231.6747,
|
|
"train_tokens_per_second": 5949.705
|
|
},
|
|
{
|
|
"epoch": 0.704,
|
|
"grad_norm": 0.7708838947852765,
|
|
"learning_rate": 7.244723723380504e-06,
|
|
"loss": 0.2495,
|
|
"num_input_tokens_seen": 138551408,
|
|
"step": 1760,
|
|
"train_runtime": 23285.9836,
|
|
"train_tokens_per_second": 5949.992
|
|
},
|
|
{
|
|
"epoch": 0.706,
|
|
"grad_norm": 0.7712799091118461,
|
|
"learning_rate": 7.23067666908853e-06,
|
|
"loss": 0.2567,
|
|
"num_input_tokens_seen": 138961472,
|
|
"step": 1765,
|
|
"train_runtime": 23355.8988,
|
|
"train_tokens_per_second": 5949.738
|
|
},
|
|
{
|
|
"epoch": 0.708,
|
|
"grad_norm": 0.7569151862311946,
|
|
"learning_rate": 7.216607598918392e-06,
|
|
"loss": 0.2481,
|
|
"num_input_tokens_seen": 139357456,
|
|
"step": 1770,
|
|
"train_runtime": 23423.3842,
|
|
"train_tokens_per_second": 5949.501
|
|
},
|
|
{
|
|
"epoch": 0.71,
|
|
"grad_norm": 0.6715017049823879,
|
|
"learning_rate": 7.202516651726135e-06,
|
|
"loss": 0.2582,
|
|
"num_input_tokens_seen": 139772704,
|
|
"step": 1775,
|
|
"train_runtime": 23495.5051,
|
|
"train_tokens_per_second": 5948.912
|
|
},
|
|
{
|
|
"epoch": 0.712,
|
|
"grad_norm": 0.7171565711417337,
|
|
"learning_rate": 7.1884039665837165e-06,
|
|
"loss": 0.2319,
|
|
"num_input_tokens_seen": 140175600,
|
|
"step": 1780,
|
|
"train_runtime": 23566.3719,
|
|
"train_tokens_per_second": 5948.12
|
|
},
|
|
{
|
|
"epoch": 0.714,
|
|
"grad_norm": 0.7456884832299608,
|
|
"learning_rate": 7.1742696827776415e-06,
|
|
"loss": 0.2401,
|
|
"num_input_tokens_seen": 140581648,
|
|
"step": 1785,
|
|
"train_runtime": 23637.9719,
|
|
"train_tokens_per_second": 5947.28
|
|
},
|
|
{
|
|
"epoch": 0.716,
|
|
"grad_norm": 0.7525544880376253,
|
|
"learning_rate": 7.160113939807587e-06,
|
|
"loss": 0.239,
|
|
"num_input_tokens_seen": 140968624,
|
|
"step": 1790,
|
|
"train_runtime": 23704.7362,
|
|
"train_tokens_per_second": 5946.855
|
|
},
|
|
{
|
|
"epoch": 0.718,
|
|
"grad_norm": 0.7879553824914558,
|
|
"learning_rate": 7.145936877385019e-06,
|
|
"loss": 0.2254,
|
|
"num_input_tokens_seen": 141456880,
|
|
"step": 1795,
|
|
"train_runtime": 23780.4742,
|
|
"train_tokens_per_second": 5948.447
|
|
},
|
|
{
|
|
"epoch": 0.72,
|
|
"grad_norm": 0.6311955732363271,
|
|
"learning_rate": 7.131738635431822e-06,
|
|
"loss": 0.2468,
|
|
"num_input_tokens_seen": 141757984,
|
|
"step": 1800,
|
|
"train_runtime": 23831.672,
|
|
"train_tokens_per_second": 5948.302
|
|
},
|
|
{
|
|
"epoch": 0.722,
|
|
"grad_norm": 0.6989839986980433,
|
|
"learning_rate": 7.11751935407891e-06,
|
|
"loss": 0.2488,
|
|
"num_input_tokens_seen": 142217936,
|
|
"step": 1805,
|
|
"train_runtime": 23894.4573,
|
|
"train_tokens_per_second": 5951.922
|
|
},
|
|
{
|
|
"epoch": 0.724,
|
|
"grad_norm": 0.7097400213735673,
|
|
"learning_rate": 7.103279173664851e-06,
|
|
"loss": 0.2444,
|
|
"num_input_tokens_seen": 142634320,
|
|
"step": 1810,
|
|
"train_runtime": 23967.6077,
|
|
"train_tokens_per_second": 5951.129
|
|
},
|
|
{
|
|
"epoch": 0.726,
|
|
"grad_norm": 0.8803147982554296,
|
|
"learning_rate": 7.089018234734476e-06,
|
|
"loss": 0.2165,
|
|
"num_input_tokens_seen": 142950304,
|
|
"step": 1815,
|
|
"train_runtime": 24025.9246,
|
|
"train_tokens_per_second": 5949.836
|
|
},
|
|
{
|
|
"epoch": 0.728,
|
|
"grad_norm": 0.7666276980489303,
|
|
"learning_rate": 7.074736678037495e-06,
|
|
"loss": 0.2464,
|
|
"num_input_tokens_seen": 143344704,
|
|
"step": 1820,
|
|
"train_runtime": 24103.6543,
|
|
"train_tokens_per_second": 5947.011
|
|
},
|
|
{
|
|
"epoch": 0.73,
|
|
"grad_norm": 0.7010307195980472,
|
|
"learning_rate": 7.060434644527105e-06,
|
|
"loss": 0.2115,
|
|
"num_input_tokens_seen": 143742144,
|
|
"step": 1825,
|
|
"train_runtime": 24177.3942,
|
|
"train_tokens_per_second": 5945.312
|
|
},
|
|
{
|
|
"epoch": 0.732,
|
|
"grad_norm": 0.6425733515884736,
|
|
"learning_rate": 7.046112275358607e-06,
|
|
"loss": 0.234,
|
|
"num_input_tokens_seen": 144077152,
|
|
"step": 1830,
|
|
"train_runtime": 24227.8337,
|
|
"train_tokens_per_second": 5946.762
|
|
},
|
|
{
|
|
"epoch": 0.734,
|
|
"grad_norm": 0.7067376629815052,
|
|
"learning_rate": 7.031769711887999e-06,
|
|
"loss": 0.2143,
|
|
"num_input_tokens_seen": 144484576,
|
|
"step": 1835,
|
|
"train_runtime": 24292.9239,
|
|
"train_tokens_per_second": 5947.599
|
|
},
|
|
{
|
|
"epoch": 0.736,
|
|
"grad_norm": 0.7142769637706615,
|
|
"learning_rate": 7.017407095670594e-06,
|
|
"loss": 0.2273,
|
|
"num_input_tokens_seen": 144852640,
|
|
"step": 1840,
|
|
"train_runtime": 24349.9516,
|
|
"train_tokens_per_second": 5948.786
|
|
},
|
|
{
|
|
"epoch": 0.738,
|
|
"grad_norm": 0.7450024424388124,
|
|
"learning_rate": 7.003024568459614e-06,
|
|
"loss": 0.2441,
|
|
"num_input_tokens_seen": 145182656,
|
|
"step": 1845,
|
|
"train_runtime": 24400.0657,
|
|
"train_tokens_per_second": 5950.093
|
|
},
|
|
{
|
|
"epoch": 0.74,
|
|
"grad_norm": 0.583393807541574,
|
|
"learning_rate": 6.988622272204799e-06,
|
|
"loss": 0.2422,
|
|
"num_input_tokens_seen": 145621648,
|
|
"step": 1850,
|
|
"train_runtime": 24475.6918,
|
|
"train_tokens_per_second": 5949.644
|
|
},
|
|
{
|
|
"epoch": 0.742,
|
|
"grad_norm": 0.6180993512501228,
|
|
"learning_rate": 6.974200349050996e-06,
|
|
"loss": 0.235,
|
|
"num_input_tokens_seen": 146013264,
|
|
"step": 1855,
|
|
"train_runtime": 24541.8438,
|
|
"train_tokens_per_second": 5949.564
|
|
},
|
|
{
|
|
"epoch": 0.744,
|
|
"grad_norm": 0.7147341091774608,
|
|
"learning_rate": 6.959758941336762e-06,
|
|
"loss": 0.2716,
|
|
"num_input_tokens_seen": 146365616,
|
|
"step": 1860,
|
|
"train_runtime": 24601.9867,
|
|
"train_tokens_per_second": 5949.341
|
|
},
|
|
{
|
|
"epoch": 0.746,
|
|
"grad_norm": 0.86917031416008,
|
|
"learning_rate": 6.945298191592967e-06,
|
|
"loss": 0.2341,
|
|
"num_input_tokens_seen": 146754320,
|
|
"step": 1865,
|
|
"train_runtime": 24667.9934,
|
|
"train_tokens_per_second": 5949.179
|
|
},
|
|
{
|
|
"epoch": 0.748,
|
|
"grad_norm": 0.7262798973273732,
|
|
"learning_rate": 6.930818242541368e-06,
|
|
"loss": 0.2514,
|
|
"num_input_tokens_seen": 147171456,
|
|
"step": 1870,
|
|
"train_runtime": 24727.888,
|
|
"train_tokens_per_second": 5951.639
|
|
},
|
|
{
|
|
"epoch": 0.75,
|
|
"grad_norm": 0.6370198483444947,
|
|
"learning_rate": 6.916319237093219e-06,
|
|
"loss": 0.2189,
|
|
"num_input_tokens_seen": 147646320,
|
|
"step": 1875,
|
|
"train_runtime": 24806.7081,
|
|
"train_tokens_per_second": 5951.871
|
|
},
|
|
{
|
|
"epoch": 0.752,
|
|
"grad_norm": 0.8726760293713298,
|
|
"learning_rate": 6.901801318347848e-06,
|
|
"loss": 0.2585,
|
|
"num_input_tokens_seen": 147975568,
|
|
"step": 1880,
|
|
"train_runtime": 24864.9692,
|
|
"train_tokens_per_second": 5951.166
|
|
},
|
|
{
|
|
"epoch": 0.754,
|
|
"grad_norm": 0.7702378297000733,
|
|
"learning_rate": 6.887264629591254e-06,
|
|
"loss": 0.2672,
|
|
"num_input_tokens_seen": 148400576,
|
|
"step": 1885,
|
|
"train_runtime": 24934.885,
|
|
"train_tokens_per_second": 5951.524
|
|
},
|
|
{
|
|
"epoch": 0.756,
|
|
"grad_norm": 0.8206586292419491,
|
|
"learning_rate": 6.872709314294685e-06,
|
|
"loss": 0.2799,
|
|
"num_input_tokens_seen": 148783072,
|
|
"step": 1890,
|
|
"train_runtime": 25003.0005,
|
|
"train_tokens_per_second": 5950.609
|
|
},
|
|
{
|
|
"epoch": 0.758,
|
|
"grad_norm": 0.6874374001615647,
|
|
"learning_rate": 6.858135516113226e-06,
|
|
"loss": 0.2466,
|
|
"num_input_tokens_seen": 149130848,
|
|
"step": 1895,
|
|
"train_runtime": 25065.5397,
|
|
"train_tokens_per_second": 5949.636
|
|
},
|
|
{
|
|
"epoch": 0.76,
|
|
"grad_norm": 0.8392979612325142,
|
|
"learning_rate": 6.8435433788843865e-06,
|
|
"loss": 0.2659,
|
|
"num_input_tokens_seen": 149563296,
|
|
"step": 1900,
|
|
"train_runtime": 25136.1861,
|
|
"train_tokens_per_second": 5950.119
|
|
},
|
|
{
|
|
"epoch": 0.762,
|
|
"grad_norm": 0.8786055292411358,
|
|
"learning_rate": 6.8289330466266635e-06,
|
|
"loss": 0.2309,
|
|
"num_input_tokens_seen": 149916624,
|
|
"step": 1905,
|
|
"train_runtime": 25194.5613,
|
|
"train_tokens_per_second": 5950.357
|
|
},
|
|
{
|
|
"epoch": 0.764,
|
|
"grad_norm": 0.8701214273853315,
|
|
"learning_rate": 6.814304663538142e-06,
|
|
"loss": 0.2335,
|
|
"num_input_tokens_seen": 150286112,
|
|
"step": 1910,
|
|
"train_runtime": 25261.7882,
|
|
"train_tokens_per_second": 5949.148
|
|
},
|
|
{
|
|
"epoch": 0.766,
|
|
"grad_norm": 0.7772777271877992,
|
|
"learning_rate": 6.799658373995054e-06,
|
|
"loss": 0.2577,
|
|
"num_input_tokens_seen": 150645008,
|
|
"step": 1915,
|
|
"train_runtime": 25327.1219,
|
|
"train_tokens_per_second": 5947.972
|
|
},
|
|
{
|
|
"epoch": 0.768,
|
|
"grad_norm": 0.6789678615174672,
|
|
"learning_rate": 6.784994322550367e-06,
|
|
"loss": 0.2399,
|
|
"num_input_tokens_seen": 151060512,
|
|
"step": 1920,
|
|
"train_runtime": 25397.5162,
|
|
"train_tokens_per_second": 5947.846
|
|
},
|
|
{
|
|
"epoch": 0.77,
|
|
"grad_norm": 0.8342583329233456,
|
|
"learning_rate": 6.770312653932346e-06,
|
|
"loss": 0.2615,
|
|
"num_input_tokens_seen": 151368336,
|
|
"step": 1925,
|
|
"train_runtime": 25449.7373,
|
|
"train_tokens_per_second": 5947.737
|
|
},
|
|
{
|
|
"epoch": 0.772,
|
|
"grad_norm": 0.7715569011388002,
|
|
"learning_rate": 6.755613513043136e-06,
|
|
"loss": 0.2686,
|
|
"num_input_tokens_seen": 151745056,
|
|
"step": 1930,
|
|
"train_runtime": 25520.8898,
|
|
"train_tokens_per_second": 5945.916
|
|
},
|
|
{
|
|
"epoch": 0.774,
|
|
"grad_norm": 0.5625454378176744,
|
|
"learning_rate": 6.740897044957322e-06,
|
|
"loss": 0.2523,
|
|
"num_input_tokens_seen": 152255616,
|
|
"step": 1935,
|
|
"train_runtime": 25590.1646,
|
|
"train_tokens_per_second": 5949.771
|
|
},
|
|
{
|
|
"epoch": 0.776,
|
|
"grad_norm": 0.6661207653183532,
|
|
"learning_rate": 6.726163394920503e-06,
|
|
"loss": 0.2364,
|
|
"num_input_tokens_seen": 152666400,
|
|
"step": 1940,
|
|
"train_runtime": 25660.9655,
|
|
"train_tokens_per_second": 5949.363
|
|
},
|
|
{
|
|
"epoch": 0.778,
|
|
"grad_norm": 0.6388285351639795,
|
|
"learning_rate": 6.711412708347857e-06,
|
|
"loss": 0.2455,
|
|
"num_input_tokens_seen": 153036000,
|
|
"step": 1945,
|
|
"train_runtime": 25720.8358,
|
|
"train_tokens_per_second": 5949.884
|
|
},
|
|
{
|
|
"epoch": 0.78,
|
|
"grad_norm": 0.8766843893276587,
|
|
"learning_rate": 6.696645130822704e-06,
|
|
"loss": 0.2646,
|
|
"num_input_tokens_seen": 153381872,
|
|
"step": 1950,
|
|
"train_runtime": 25775.8047,
|
|
"train_tokens_per_second": 5950.614
|
|
},
|
|
{
|
|
"epoch": 0.782,
|
|
"grad_norm": 0.7564699089666967,
|
|
"learning_rate": 6.681860808095074e-06,
|
|
"loss": 0.2373,
|
|
"num_input_tokens_seen": 153796576,
|
|
"step": 1955,
|
|
"train_runtime": 25843.2925,
|
|
"train_tokens_per_second": 5951.122
|
|
},
|
|
{
|
|
"epoch": 0.784,
|
|
"grad_norm": 0.6125793792916168,
|
|
"learning_rate": 6.667059886080263e-06,
|
|
"loss": 0.2367,
|
|
"num_input_tokens_seen": 154185392,
|
|
"step": 1960,
|
|
"train_runtime": 25902.8859,
|
|
"train_tokens_per_second": 5952.441
|
|
},
|
|
{
|
|
"epoch": 0.786,
|
|
"grad_norm": 0.7264229713494964,
|
|
"learning_rate": 6.652242510857395e-06,
|
|
"loss": 0.2566,
|
|
"num_input_tokens_seen": 154549680,
|
|
"step": 1965,
|
|
"train_runtime": 25956.6843,
|
|
"train_tokens_per_second": 5954.138
|
|
},
|
|
{
|
|
"epoch": 0.788,
|
|
"grad_norm": 0.6457872880391132,
|
|
"learning_rate": 6.637408828667982e-06,
|
|
"loss": 0.2559,
|
|
"num_input_tokens_seen": 154973808,
|
|
"step": 1970,
|
|
"train_runtime": 26025.2685,
|
|
"train_tokens_per_second": 5954.744
|
|
},
|
|
{
|
|
"epoch": 0.79,
|
|
"grad_norm": 0.7336303068433705,
|
|
"learning_rate": 6.622558985914478e-06,
|
|
"loss": 0.2273,
|
|
"num_input_tokens_seen": 155365328,
|
|
"step": 1975,
|
|
"train_runtime": 26095.6873,
|
|
"train_tokens_per_second": 5953.678
|
|
},
|
|
{
|
|
"epoch": 0.792,
|
|
"grad_norm": 0.7703023606949606,
|
|
"learning_rate": 6.6076931291588375e-06,
|
|
"loss": 0.2382,
|
|
"num_input_tokens_seen": 155713088,
|
|
"step": 1980,
|
|
"train_runtime": 26156.9246,
|
|
"train_tokens_per_second": 5953.035
|
|
},
|
|
{
|
|
"epoch": 0.794,
|
|
"grad_norm": 0.6634539968504769,
|
|
"learning_rate": 6.592811405121064e-06,
|
|
"loss": 0.2294,
|
|
"num_input_tokens_seen": 156104880,
|
|
"step": 1985,
|
|
"train_runtime": 26224.5285,
|
|
"train_tokens_per_second": 5952.629
|
|
},
|
|
{
|
|
"epoch": 0.796,
|
|
"grad_norm": 0.7228410141497181,
|
|
"learning_rate": 6.577913960677766e-06,
|
|
"loss": 0.2317,
|
|
"num_input_tokens_seen": 156474112,
|
|
"step": 1990,
|
|
"train_runtime": 26280.5612,
|
|
"train_tokens_per_second": 5953.987
|
|
},
|
|
{
|
|
"epoch": 0.798,
|
|
"grad_norm": 0.7453160213506707,
|
|
"learning_rate": 6.5630009428607065e-06,
|
|
"loss": 0.2452,
|
|
"num_input_tokens_seen": 156803472,
|
|
"step": 1995,
|
|
"train_runtime": 26338.1332,
|
|
"train_tokens_per_second": 5953.477
|
|
},
|
|
{
|
|
"epoch": 0.8,
|
|
"grad_norm": 0.7218884021194475,
|
|
"learning_rate": 6.54807249885535e-06,
|
|
"loss": 0.2334,
|
|
"num_input_tokens_seen": 157110992,
|
|
"step": 2000,
|
|
"train_runtime": 26383.3178,
|
|
"train_tokens_per_second": 5954.937
|
|
},
|
|
{
|
|
"epoch": 0.802,
|
|
"grad_norm": 0.5333416528634705,
|
|
"learning_rate": 6.533128775999411e-06,
|
|
"loss": 0.2265,
|
|
"num_input_tokens_seen": 157500272,
|
|
"step": 2005,
|
|
"train_runtime": 26454.7029,
|
|
"train_tokens_per_second": 5953.583
|
|
},
|
|
{
|
|
"epoch": 0.804,
|
|
"grad_norm": 0.6743123682865275,
|
|
"learning_rate": 6.5181699217814025e-06,
|
|
"loss": 0.2163,
|
|
"num_input_tokens_seen": 157834992,
|
|
"step": 2010,
|
|
"train_runtime": 26522.5739,
|
|
"train_tokens_per_second": 5950.968
|
|
},
|
|
{
|
|
"epoch": 0.806,
|
|
"grad_norm": 0.6875769892486772,
|
|
"learning_rate": 6.503196083839175e-06,
|
|
"loss": 0.2625,
|
|
"num_input_tokens_seen": 158224720,
|
|
"step": 2015,
|
|
"train_runtime": 26587.824,
|
|
"train_tokens_per_second": 5951.022
|
|
},
|
|
{
|
|
"epoch": 0.808,
|
|
"grad_norm": 0.6570377982154686,
|
|
"learning_rate": 6.488207409958466e-06,
|
|
"loss": 0.2608,
|
|
"num_input_tokens_seen": 158592160,
|
|
"step": 2020,
|
|
"train_runtime": 26642.0577,
|
|
"train_tokens_per_second": 5952.699
|
|
},
|
|
{
|
|
"epoch": 0.81,
|
|
"grad_norm": 0.7948682216403246,
|
|
"learning_rate": 6.473204048071433e-06,
|
|
"loss": 0.253,
|
|
"num_input_tokens_seen": 158955232,
|
|
"step": 2025,
|
|
"train_runtime": 26698.2361,
|
|
"train_tokens_per_second": 5953.773
|
|
},
|
|
{
|
|
"epoch": 0.812,
|
|
"grad_norm": 0.5825323695015356,
|
|
"learning_rate": 6.458186146255203e-06,
|
|
"loss": 0.2568,
|
|
"num_input_tokens_seen": 159277888,
|
|
"step": 2030,
|
|
"train_runtime": 26754.9701,
|
|
"train_tokens_per_second": 5953.207
|
|
},
|
|
{
|
|
"epoch": 0.814,
|
|
"grad_norm": 0.7005050901769546,
|
|
"learning_rate": 6.443153852730404e-06,
|
|
"loss": 0.229,
|
|
"num_input_tokens_seen": 159700576,
|
|
"step": 2035,
|
|
"train_runtime": 26818.2772,
|
|
"train_tokens_per_second": 5954.916
|
|
},
|
|
{
|
|
"epoch": 0.816,
|
|
"grad_norm": 0.8854758398921162,
|
|
"learning_rate": 6.428107315859702e-06,
|
|
"loss": 0.2511,
|
|
"num_input_tokens_seen": 160017808,
|
|
"step": 2040,
|
|
"train_runtime": 26880.0385,
|
|
"train_tokens_per_second": 5953.035
|
|
},
|
|
{
|
|
"epoch": 0.818,
|
|
"grad_norm": 0.685561132332679,
|
|
"learning_rate": 6.413046684146343e-06,
|
|
"loss": 0.2343,
|
|
"num_input_tokens_seen": 160373024,
|
|
"step": 2045,
|
|
"train_runtime": 26950.2096,
|
|
"train_tokens_per_second": 5950.715
|
|
},
|
|
{
|
|
"epoch": 0.82,
|
|
"grad_norm": 0.7082441136939686,
|
|
"learning_rate": 6.3979721062326815e-06,
|
|
"loss": 0.2231,
|
|
"num_input_tokens_seen": 160775872,
|
|
"step": 2050,
|
|
"train_runtime": 27019.1206,
|
|
"train_tokens_per_second": 5950.448
|
|
},
|
|
{
|
|
"epoch": 0.822,
|
|
"grad_norm": 0.5096417611075408,
|
|
"learning_rate": 6.382883730898717e-06,
|
|
"loss": 0.2134,
|
|
"num_input_tokens_seen": 161209616,
|
|
"step": 2055,
|
|
"train_runtime": 27091.3587,
|
|
"train_tokens_per_second": 5950.592
|
|
},
|
|
{
|
|
"epoch": 0.824,
|
|
"grad_norm": 0.8009013794002183,
|
|
"learning_rate": 6.36778170706062e-06,
|
|
"loss": 0.2574,
|
|
"num_input_tokens_seen": 161526656,
|
|
"step": 2060,
|
|
"train_runtime": 27139.6623,
|
|
"train_tokens_per_second": 5951.683
|
|
},
|
|
{
|
|
"epoch": 0.826,
|
|
"grad_norm": 0.6785197101100082,
|
|
"learning_rate": 6.352666183769269e-06,
|
|
"loss": 0.2264,
|
|
"num_input_tokens_seen": 162002192,
|
|
"step": 2065,
|
|
"train_runtime": 27214.9638,
|
|
"train_tokens_per_second": 5952.688
|
|
},
|
|
{
|
|
"epoch": 0.828,
|
|
"grad_norm": 0.7744495254464379,
|
|
"learning_rate": 6.337537310208779e-06,
|
|
"loss": 0.2579,
|
|
"num_input_tokens_seen": 162370528,
|
|
"step": 2070,
|
|
"train_runtime": 27284.1663,
|
|
"train_tokens_per_second": 5951.09
|
|
},
|
|
{
|
|
"epoch": 0.83,
|
|
"grad_norm": 0.7760494440011119,
|
|
"learning_rate": 6.322395235695022e-06,
|
|
"loss": 0.2442,
|
|
"num_input_tokens_seen": 162742848,
|
|
"step": 2075,
|
|
"train_runtime": 27350.3482,
|
|
"train_tokens_per_second": 5950.303
|
|
},
|
|
{
|
|
"epoch": 0.832,
|
|
"grad_norm": 1.0101069822281035,
|
|
"learning_rate": 6.307240109674162e-06,
|
|
"loss": 0.2468,
|
|
"num_input_tokens_seen": 163114144,
|
|
"step": 2080,
|
|
"train_runtime": 27402.3481,
|
|
"train_tokens_per_second": 5952.561
|
|
},
|
|
{
|
|
"epoch": 0.834,
|
|
"grad_norm": 0.6818940132851085,
|
|
"learning_rate": 6.292072081721173e-06,
|
|
"loss": 0.2531,
|
|
"num_input_tokens_seen": 163504080,
|
|
"step": 2085,
|
|
"train_runtime": 27466.6183,
|
|
"train_tokens_per_second": 5952.829
|
|
},
|
|
{
|
|
"epoch": 0.836,
|
|
"grad_norm": 0.6574555343522533,
|
|
"learning_rate": 6.2768913015383696e-06,
|
|
"loss": 0.2476,
|
|
"num_input_tokens_seen": 163972864,
|
|
"step": 2090,
|
|
"train_runtime": 27543.1965,
|
|
"train_tokens_per_second": 5953.298
|
|
},
|
|
{
|
|
"epoch": 0.838,
|
|
"grad_norm": 0.878884816070722,
|
|
"learning_rate": 6.261697918953922e-06,
|
|
"loss": 0.2503,
|
|
"num_input_tokens_seen": 164394080,
|
|
"step": 2095,
|
|
"train_runtime": 27608.9053,
|
|
"train_tokens_per_second": 5954.386
|
|
},
|
|
{
|
|
"epoch": 0.84,
|
|
"grad_norm": 0.708190951091209,
|
|
"learning_rate": 6.2464920839203805e-06,
|
|
"loss": 0.2337,
|
|
"num_input_tokens_seen": 164803104,
|
|
"step": 2100,
|
|
"train_runtime": 27675.9486,
|
|
"train_tokens_per_second": 5954.741
|
|
},
|
|
{
|
|
"epoch": 0.842,
|
|
"grad_norm": 0.6729880610621995,
|
|
"learning_rate": 6.231273946513201e-06,
|
|
"loss": 0.2475,
|
|
"num_input_tokens_seen": 165165728,
|
|
"step": 2105,
|
|
"train_runtime": 27742.8541,
|
|
"train_tokens_per_second": 5953.451
|
|
},
|
|
{
|
|
"epoch": 0.844,
|
|
"grad_norm": 1.0390349425994523,
|
|
"learning_rate": 6.216043656929254e-06,
|
|
"loss": 0.226,
|
|
"num_input_tokens_seen": 165552752,
|
|
"step": 2110,
|
|
"train_runtime": 27816.0039,
|
|
"train_tokens_per_second": 5951.709
|
|
},
|
|
{
|
|
"epoch": 0.846,
|
|
"grad_norm": 0.6678856927176096,
|
|
"learning_rate": 6.2008013654853505e-06,
|
|
"loss": 0.239,
|
|
"num_input_tokens_seen": 165952016,
|
|
"step": 2115,
|
|
"train_runtime": 27876.694,
|
|
"train_tokens_per_second": 5953.074
|
|
},
|
|
{
|
|
"epoch": 0.848,
|
|
"grad_norm": 0.6209290845661071,
|
|
"learning_rate": 6.1855472226167525e-06,
|
|
"loss": 0.2259,
|
|
"num_input_tokens_seen": 166406208,
|
|
"step": 2120,
|
|
"train_runtime": 27952.9765,
|
|
"train_tokens_per_second": 5953.077
|
|
},
|
|
{
|
|
"epoch": 0.85,
|
|
"grad_norm": 0.9264111697053214,
|
|
"learning_rate": 6.170281378875692e-06,
|
|
"loss": 0.2217,
|
|
"num_input_tokens_seen": 166793568,
|
|
"step": 2125,
|
|
"train_runtime": 28026.8287,
|
|
"train_tokens_per_second": 5951.211
|
|
},
|
|
{
|
|
"epoch": 0.852,
|
|
"grad_norm": 0.8117944248091487,
|
|
"learning_rate": 6.155003984929883e-06,
|
|
"loss": 0.2205,
|
|
"num_input_tokens_seen": 167110880,
|
|
"step": 2130,
|
|
"train_runtime": 28083.294,
|
|
"train_tokens_per_second": 5950.544
|
|
},
|
|
{
|
|
"epoch": 0.854,
|
|
"grad_norm": 0.7750515953804475,
|
|
"learning_rate": 6.139715191561038e-06,
|
|
"loss": 0.2505,
|
|
"num_input_tokens_seen": 167529632,
|
|
"step": 2135,
|
|
"train_runtime": 28151.1623,
|
|
"train_tokens_per_second": 5951.073
|
|
},
|
|
{
|
|
"epoch": 0.856,
|
|
"grad_norm": 0.9646210816534532,
|
|
"learning_rate": 6.124415149663374e-06,
|
|
"loss": 0.2498,
|
|
"num_input_tokens_seen": 167902176,
|
|
"step": 2140,
|
|
"train_runtime": 28212.803,
|
|
"train_tokens_per_second": 5951.276
|
|
},
|
|
{
|
|
"epoch": 0.858,
|
|
"grad_norm": 0.637371204897658,
|
|
"learning_rate": 6.109104010242127e-06,
|
|
"loss": 0.2226,
|
|
"num_input_tokens_seen": 168281184,
|
|
"step": 2145,
|
|
"train_runtime": 28272.597,
|
|
"train_tokens_per_second": 5952.095
|
|
},
|
|
{
|
|
"epoch": 0.86,
|
|
"grad_norm": 0.7820949153505182,
|
|
"learning_rate": 6.093781924412063e-06,
|
|
"loss": 0.223,
|
|
"num_input_tokens_seen": 168648480,
|
|
"step": 2150,
|
|
"train_runtime": 28336.1128,
|
|
"train_tokens_per_second": 5951.715
|
|
},
|
|
{
|
|
"epoch": 0.862,
|
|
"grad_norm": 0.7820636325924925,
|
|
"learning_rate": 6.078449043395982e-06,
|
|
"loss": 0.2435,
|
|
"num_input_tokens_seen": 169014928,
|
|
"step": 2155,
|
|
"train_runtime": 28402.0916,
|
|
"train_tokens_per_second": 5950.792
|
|
},
|
|
{
|
|
"epoch": 0.864,
|
|
"grad_norm": 0.658338208972596,
|
|
"learning_rate": 6.06310551852323e-06,
|
|
"loss": 0.2333,
|
|
"num_input_tokens_seen": 169395632,
|
|
"step": 2160,
|
|
"train_runtime": 28465.5346,
|
|
"train_tokens_per_second": 5950.903
|
|
},
|
|
{
|
|
"epoch": 0.866,
|
|
"grad_norm": 0.7066861787934736,
|
|
"learning_rate": 6.047751501228203e-06,
|
|
"loss": 0.2464,
|
|
"num_input_tokens_seen": 169811824,
|
|
"step": 2165,
|
|
"train_runtime": 28543.6007,
|
|
"train_tokens_per_second": 5949.208
|
|
},
|
|
{
|
|
"epoch": 0.868,
|
|
"grad_norm": 0.781375321039837,
|
|
"learning_rate": 6.032387143048853e-06,
|
|
"loss": 0.231,
|
|
"num_input_tokens_seen": 170151744,
|
|
"step": 2170,
|
|
"train_runtime": 28602.3354,
|
|
"train_tokens_per_second": 5948.876
|
|
},
|
|
{
|
|
"epoch": 0.87,
|
|
"grad_norm": 0.93859473763133,
|
|
"learning_rate": 6.0170125956251935e-06,
|
|
"loss": 0.2206,
|
|
"num_input_tokens_seen": 170534368,
|
|
"step": 2175,
|
|
"train_runtime": 28668.7905,
|
|
"train_tokens_per_second": 5948.433
|
|
},
|
|
{
|
|
"epoch": 0.872,
|
|
"grad_norm": 0.7865219290835191,
|
|
"learning_rate": 6.0016280106978e-06,
|
|
"loss": 0.2541,
|
|
"num_input_tokens_seen": 170939264,
|
|
"step": 2180,
|
|
"train_runtime": 28739.4293,
|
|
"train_tokens_per_second": 5947.9
|
|
},
|
|
{
|
|
"epoch": 0.874,
|
|
"grad_norm": 1.0981142367719585,
|
|
"learning_rate": 5.986233540106315e-06,
|
|
"loss": 0.2198,
|
|
"num_input_tokens_seen": 171327728,
|
|
"step": 2185,
|
|
"train_runtime": 28810.52,
|
|
"train_tokens_per_second": 5946.707
|
|
},
|
|
{
|
|
"epoch": 0.876,
|
|
"grad_norm": 0.6189848711597874,
|
|
"learning_rate": 5.970829335787946e-06,
|
|
"loss": 0.2446,
|
|
"num_input_tokens_seen": 171683792,
|
|
"step": 2190,
|
|
"train_runtime": 28867.3719,
|
|
"train_tokens_per_second": 5947.33
|
|
},
|
|
{
|
|
"epoch": 0.878,
|
|
"grad_norm": 0.8024094051926371,
|
|
"learning_rate": 5.955415549775975e-06,
|
|
"loss": 0.2166,
|
|
"num_input_tokens_seen": 171980720,
|
|
"step": 2195,
|
|
"train_runtime": 28917.9366,
|
|
"train_tokens_per_second": 5947.199
|
|
},
|
|
{
|
|
"epoch": 0.88,
|
|
"grad_norm": 0.700283931520735,
|
|
"learning_rate": 5.939992334198242e-06,
|
|
"loss": 0.2486,
|
|
"num_input_tokens_seen": 172406304,
|
|
"step": 2200,
|
|
"train_runtime": 28995.7249,
|
|
"train_tokens_per_second": 5945.922
|
|
},
|
|
{
|
|
"epoch": 0.882,
|
|
"grad_norm": 0.6156776119471373,
|
|
"learning_rate": 5.924559841275661e-06,
|
|
"loss": 0.2502,
|
|
"num_input_tokens_seen": 172786272,
|
|
"step": 2205,
|
|
"train_runtime": 29058.6595,
|
|
"train_tokens_per_second": 5946.12
|
|
},
|
|
{
|
|
"epoch": 0.884,
|
|
"grad_norm": 0.7100376433954627,
|
|
"learning_rate": 5.9091182233207075e-06,
|
|
"loss": 0.2422,
|
|
"num_input_tokens_seen": 173227264,
|
|
"step": 2210,
|
|
"train_runtime": 29131.5652,
|
|
"train_tokens_per_second": 5946.377
|
|
},
|
|
{
|
|
"epoch": 0.886,
|
|
"grad_norm": 0.8147996007145993,
|
|
"learning_rate": 5.893667632735915e-06,
|
|
"loss": 0.2352,
|
|
"num_input_tokens_seen": 173598624,
|
|
"step": 2215,
|
|
"train_runtime": 29202.1961,
|
|
"train_tokens_per_second": 5944.711
|
|
},
|
|
{
|
|
"epoch": 0.888,
|
|
"grad_norm": 0.5311637083968614,
|
|
"learning_rate": 5.878208222012377e-06,
|
|
"loss": 0.2289,
|
|
"num_input_tokens_seen": 173997648,
|
|
"step": 2220,
|
|
"train_runtime": 29260.9457,
|
|
"train_tokens_per_second": 5946.412
|
|
},
|
|
{
|
|
"epoch": 0.89,
|
|
"grad_norm": 0.6006361048911637,
|
|
"learning_rate": 5.8627401437282334e-06,
|
|
"loss": 0.2277,
|
|
"num_input_tokens_seen": 174440288,
|
|
"step": 2225,
|
|
"train_runtime": 29338.854,
|
|
"train_tokens_per_second": 5945.709
|
|
},
|
|
{
|
|
"epoch": 0.892,
|
|
"grad_norm": 0.5915073750833558,
|
|
"learning_rate": 5.847263550547174e-06,
|
|
"loss": 0.2295,
|
|
"num_input_tokens_seen": 174846016,
|
|
"step": 2230,
|
|
"train_runtime": 29404.7298,
|
|
"train_tokens_per_second": 5946.187
|
|
},
|
|
{
|
|
"epoch": 0.894,
|
|
"grad_norm": 0.8132516342886842,
|
|
"learning_rate": 5.8317785952169245e-06,
|
|
"loss": 0.2405,
|
|
"num_input_tokens_seen": 175197376,
|
|
"step": 2235,
|
|
"train_runtime": 29465.5737,
|
|
"train_tokens_per_second": 5945.833
|
|
},
|
|
{
|
|
"epoch": 0.896,
|
|
"grad_norm": 0.9838730375194601,
|
|
"learning_rate": 5.816285430567743e-06,
|
|
"loss": 0.2464,
|
|
"num_input_tokens_seen": 175543776,
|
|
"step": 2240,
|
|
"train_runtime": 29512.3984,
|
|
"train_tokens_per_second": 5948.137
|
|
},
|
|
{
|
|
"epoch": 0.898,
|
|
"grad_norm": 0.5852209016193204,
|
|
"learning_rate": 5.80078420951091e-06,
|
|
"loss": 0.2315,
|
|
"num_input_tokens_seen": 175959728,
|
|
"step": 2245,
|
|
"train_runtime": 29585.2542,
|
|
"train_tokens_per_second": 5947.548
|
|
},
|
|
{
|
|
"epoch": 0.9,
|
|
"grad_norm": 0.8236650897027592,
|
|
"learning_rate": 5.785275085037218e-06,
|
|
"loss": 0.2683,
|
|
"num_input_tokens_seen": 176298768,
|
|
"step": 2250,
|
|
"train_runtime": 29641.8108,
|
|
"train_tokens_per_second": 5947.638
|
|
},
|
|
{
|
|
"epoch": 0.902,
|
|
"grad_norm": 0.5611644053571633,
|
|
"learning_rate": 5.769758210215466e-06,
|
|
"loss": 0.2277,
|
|
"num_input_tokens_seen": 176757936,
|
|
"step": 2255,
|
|
"train_runtime": 29716.4289,
|
|
"train_tokens_per_second": 5948.155
|
|
},
|
|
{
|
|
"epoch": 0.904,
|
|
"grad_norm": 0.6457725745525457,
|
|
"learning_rate": 5.754233738190942e-06,
|
|
"loss": 0.2306,
|
|
"num_input_tokens_seen": 177153168,
|
|
"step": 2260,
|
|
"train_runtime": 29779.1106,
|
|
"train_tokens_per_second": 5948.907
|
|
},
|
|
{
|
|
"epoch": 0.906,
|
|
"grad_norm": 0.7742797303479264,
|
|
"learning_rate": 5.7387018221839195e-06,
|
|
"loss": 0.2447,
|
|
"num_input_tokens_seen": 177558336,
|
|
"step": 2265,
|
|
"train_runtime": 29847.2103,
|
|
"train_tokens_per_second": 5948.909
|
|
},
|
|
{
|
|
"epoch": 0.908,
|
|
"grad_norm": 0.6731925005917008,
|
|
"learning_rate": 5.723162615488137e-06,
|
|
"loss": 0.2224,
|
|
"num_input_tokens_seen": 177970112,
|
|
"step": 2270,
|
|
"train_runtime": 29915.2381,
|
|
"train_tokens_per_second": 5949.146
|
|
},
|
|
{
|
|
"epoch": 0.91,
|
|
"grad_norm": 0.600224184362238,
|
|
"learning_rate": 5.707616271469293e-06,
|
|
"loss": 0.2213,
|
|
"num_input_tokens_seen": 178365456,
|
|
"step": 2275,
|
|
"train_runtime": 29987.3778,
|
|
"train_tokens_per_second": 5948.018
|
|
},
|
|
{
|
|
"epoch": 0.912,
|
|
"grad_norm": 0.6578513225026819,
|
|
"learning_rate": 5.692062943563525e-06,
|
|
"loss": 0.2283,
|
|
"num_input_tokens_seen": 178744496,
|
|
"step": 2280,
|
|
"train_runtime": 30060.8882,
|
|
"train_tokens_per_second": 5946.082
|
|
},
|
|
{
|
|
"epoch": 0.914,
|
|
"grad_norm": 0.6546013647844027,
|
|
"learning_rate": 5.6765027852759015e-06,
|
|
"loss": 0.2273,
|
|
"num_input_tokens_seen": 179089216,
|
|
"step": 2285,
|
|
"train_runtime": 30116.3719,
|
|
"train_tokens_per_second": 5946.573
|
|
},
|
|
{
|
|
"epoch": 0.916,
|
|
"grad_norm": 0.6436125861923324,
|
|
"learning_rate": 5.660935950178904e-06,
|
|
"loss": 0.2114,
|
|
"num_input_tokens_seen": 179463584,
|
|
"step": 2290,
|
|
"train_runtime": 30185.9557,
|
|
"train_tokens_per_second": 5945.268
|
|
},
|
|
{
|
|
"epoch": 0.918,
|
|
"grad_norm": 1.1106079072044501,
|
|
"learning_rate": 5.645362591910908e-06,
|
|
"loss": 0.2317,
|
|
"num_input_tokens_seen": 179834016,
|
|
"step": 2295,
|
|
"train_runtime": 30244.7067,
|
|
"train_tokens_per_second": 5945.967
|
|
},
|
|
{
|
|
"epoch": 0.92,
|
|
"grad_norm": 0.7625223505139128,
|
|
"learning_rate": 5.629782864174672e-06,
|
|
"loss": 0.2542,
|
|
"num_input_tokens_seen": 180259712,
|
|
"step": 2300,
|
|
"train_runtime": 30314.1024,
|
|
"train_tokens_per_second": 5946.398
|
|
},
|
|
{
|
|
"epoch": 0.922,
|
|
"grad_norm": 0.8050923063608859,
|
|
"learning_rate": 5.614196920735822e-06,
|
|
"loss": 0.253,
|
|
"num_input_tokens_seen": 180769440,
|
|
"step": 2305,
|
|
"train_runtime": 30390.5223,
|
|
"train_tokens_per_second": 5948.218
|
|
},
|
|
{
|
|
"epoch": 0.924,
|
|
"grad_norm": 0.838730652939852,
|
|
"learning_rate": 5.598604915421324e-06,
|
|
"loss": 0.2404,
|
|
"num_input_tokens_seen": 181141040,
|
|
"step": 2310,
|
|
"train_runtime": 30446.9371,
|
|
"train_tokens_per_second": 5949.401
|
|
},
|
|
{
|
|
"epoch": 0.926,
|
|
"grad_norm": 0.7311635967485809,
|
|
"learning_rate": 5.5830070021179785e-06,
|
|
"loss": 0.2475,
|
|
"num_input_tokens_seen": 181512128,
|
|
"step": 2315,
|
|
"train_runtime": 30511.8838,
|
|
"train_tokens_per_second": 5948.899
|
|
},
|
|
{
|
|
"epoch": 0.928,
|
|
"grad_norm": 0.8333701668205385,
|
|
"learning_rate": 5.567403334770891e-06,
|
|
"loss": 0.241,
|
|
"num_input_tokens_seen": 181898720,
|
|
"step": 2320,
|
|
"train_runtime": 30575.5824,
|
|
"train_tokens_per_second": 5949.15
|
|
},
|
|
{
|
|
"epoch": 0.93,
|
|
"grad_norm": 1.4982827092355415,
|
|
"learning_rate": 5.551794067381959e-06,
|
|
"loss": 0.2296,
|
|
"num_input_tokens_seen": 182339792,
|
|
"step": 2325,
|
|
"train_runtime": 30653.1374,
|
|
"train_tokens_per_second": 5948.487
|
|
},
|
|
{
|
|
"epoch": 0.932,
|
|
"grad_norm": 0.8970555784936441,
|
|
"learning_rate": 5.536179354008351e-06,
|
|
"loss": 0.2179,
|
|
"num_input_tokens_seen": 182758928,
|
|
"step": 2330,
|
|
"train_runtime": 30726.7154,
|
|
"train_tokens_per_second": 5947.884
|
|
},
|
|
{
|
|
"epoch": 0.934,
|
|
"grad_norm": 0.7859900791455534,
|
|
"learning_rate": 5.520559348760984e-06,
|
|
"loss": 0.2383,
|
|
"num_input_tokens_seen": 183131360,
|
|
"step": 2335,
|
|
"train_runtime": 30796.714,
|
|
"train_tokens_per_second": 5946.458
|
|
},
|
|
{
|
|
"epoch": 0.936,
|
|
"grad_norm": 0.9506801273249746,
|
|
"learning_rate": 5.504934205803002e-06,
|
|
"loss": 0.2529,
|
|
"num_input_tokens_seen": 183537936,
|
|
"step": 2340,
|
|
"train_runtime": 30870.769,
|
|
"train_tokens_per_second": 5945.363
|
|
},
|
|
{
|
|
"epoch": 0.938,
|
|
"grad_norm": 0.7170187918020063,
|
|
"learning_rate": 5.489304079348259e-06,
|
|
"loss": 0.2478,
|
|
"num_input_tokens_seen": 183862896,
|
|
"step": 2345,
|
|
"train_runtime": 30933.3538,
|
|
"train_tokens_per_second": 5943.84
|
|
},
|
|
{
|
|
"epoch": 0.94,
|
|
"grad_norm": 0.6021121497604376,
|
|
"learning_rate": 5.473669123659793e-06,
|
|
"loss": 0.2532,
|
|
"num_input_tokens_seen": 184259888,
|
|
"step": 2350,
|
|
"train_runtime": 30996.337,
|
|
"train_tokens_per_second": 5944.57
|
|
},
|
|
{
|
|
"epoch": 0.942,
|
|
"grad_norm": 0.7051727487587609,
|
|
"learning_rate": 5.458029493048303e-06,
|
|
"loss": 0.2123,
|
|
"num_input_tokens_seen": 184656352,
|
|
"step": 2355,
|
|
"train_runtime": 31067.0032,
|
|
"train_tokens_per_second": 5943.81
|
|
},
|
|
{
|
|
"epoch": 0.944,
|
|
"grad_norm": 0.6635146242890422,
|
|
"learning_rate": 5.442385341870633e-06,
|
|
"loss": 0.2118,
|
|
"num_input_tokens_seen": 185019024,
|
|
"step": 2360,
|
|
"train_runtime": 31131.4898,
|
|
"train_tokens_per_second": 5943.147
|
|
},
|
|
{
|
|
"epoch": 0.946,
|
|
"grad_norm": 0.6724672853288053,
|
|
"learning_rate": 5.426736824528236e-06,
|
|
"loss": 0.2506,
|
|
"num_input_tokens_seen": 185474944,
|
|
"step": 2365,
|
|
"train_runtime": 31205.1483,
|
|
"train_tokens_per_second": 5943.729
|
|
},
|
|
{
|
|
"epoch": 0.948,
|
|
"grad_norm": 0.7639385973705092,
|
|
"learning_rate": 5.411084095465661e-06,
|
|
"loss": 0.253,
|
|
"num_input_tokens_seen": 185960416,
|
|
"step": 2370,
|
|
"train_runtime": 31275.112,
|
|
"train_tokens_per_second": 5945.955
|
|
},
|
|
{
|
|
"epoch": 0.95,
|
|
"grad_norm": 0.6731404031064729,
|
|
"learning_rate": 5.3954273091690245e-06,
|
|
"loss": 0.2305,
|
|
"num_input_tokens_seen": 186388384,
|
|
"step": 2375,
|
|
"train_runtime": 31345.6404,
|
|
"train_tokens_per_second": 5946.23
|
|
},
|
|
{
|
|
"epoch": 0.952,
|
|
"grad_norm": 0.7944137119655447,
|
|
"learning_rate": 5.379766620164488e-06,
|
|
"loss": 0.242,
|
|
"num_input_tokens_seen": 186822368,
|
|
"step": 2380,
|
|
"train_runtime": 31414.4063,
|
|
"train_tokens_per_second": 5947.028
|
|
},
|
|
{
|
|
"epoch": 0.954,
|
|
"grad_norm": 0.7009221618788651,
|
|
"learning_rate": 5.36410218301673e-06,
|
|
"loss": 0.231,
|
|
"num_input_tokens_seen": 187241824,
|
|
"step": 2385,
|
|
"train_runtime": 31487.9223,
|
|
"train_tokens_per_second": 5946.465
|
|
},
|
|
{
|
|
"epoch": 0.956,
|
|
"grad_norm": 0.7826192747499381,
|
|
"learning_rate": 5.348434152327418e-06,
|
|
"loss": 0.2367,
|
|
"num_input_tokens_seen": 187634528,
|
|
"step": 2390,
|
|
"train_runtime": 31557.8152,
|
|
"train_tokens_per_second": 5945.739
|
|
},
|
|
{
|
|
"epoch": 0.958,
|
|
"grad_norm": 0.8568472463615774,
|
|
"learning_rate": 5.3327626827336906e-06,
|
|
"loss": 0.23,
|
|
"num_input_tokens_seen": 188055872,
|
|
"step": 2395,
|
|
"train_runtime": 31621.8896,
|
|
"train_tokens_per_second": 5947.016
|
|
},
|
|
{
|
|
"epoch": 0.96,
|
|
"grad_norm": 0.9212451337260199,
|
|
"learning_rate": 5.3170879289066265e-06,
|
|
"loss": 0.2423,
|
|
"num_input_tokens_seen": 188417040,
|
|
"step": 2400,
|
|
"train_runtime": 31681.7657,
|
|
"train_tokens_per_second": 5947.176
|
|
},
|
|
{
|
|
"epoch": 0.962,
|
|
"grad_norm": 0.6202368278565747,
|
|
"learning_rate": 5.301410045549719e-06,
|
|
"loss": 0.2283,
|
|
"num_input_tokens_seen": 188757392,
|
|
"step": 2405,
|
|
"train_runtime": 31735.9795,
|
|
"train_tokens_per_second": 5947.741
|
|
},
|
|
{
|
|
"epoch": 0.964,
|
|
"grad_norm": 0.8197217478906974,
|
|
"learning_rate": 5.285729187397344e-06,
|
|
"loss": 0.2321,
|
|
"num_input_tokens_seen": 189109872,
|
|
"step": 2410,
|
|
"train_runtime": 31803.2473,
|
|
"train_tokens_per_second": 5946.244
|
|
},
|
|
{
|
|
"epoch": 0.966,
|
|
"grad_norm": 0.8149889759430892,
|
|
"learning_rate": 5.270045509213244e-06,
|
|
"loss": 0.2244,
|
|
"num_input_tokens_seen": 189461472,
|
|
"step": 2415,
|
|
"train_runtime": 31871.1936,
|
|
"train_tokens_per_second": 5944.599
|
|
},
|
|
{
|
|
"epoch": 0.968,
|
|
"grad_norm": 0.6823638505459694,
|
|
"learning_rate": 5.25435916578899e-06,
|
|
"loss": 0.2451,
|
|
"num_input_tokens_seen": 189885568,
|
|
"step": 2420,
|
|
"train_runtime": 31945.3988,
|
|
"train_tokens_per_second": 5944.066
|
|
},
|
|
{
|
|
"epoch": 0.97,
|
|
"grad_norm": 0.6838081564497045,
|
|
"learning_rate": 5.238670311942459e-06,
|
|
"loss": 0.2443,
|
|
"num_input_tokens_seen": 190242304,
|
|
"step": 2425,
|
|
"train_runtime": 31993.066,
|
|
"train_tokens_per_second": 5946.361
|
|
},
|
|
{
|
|
"epoch": 0.972,
|
|
"grad_norm": 0.6769627193812837,
|
|
"learning_rate": 5.222979102516304e-06,
|
|
"loss": 0.2422,
|
|
"num_input_tokens_seen": 190598224,
|
|
"step": 2430,
|
|
"train_runtime": 32054.5311,
|
|
"train_tokens_per_second": 5946.062
|
|
},
|
|
{
|
|
"epoch": 0.974,
|
|
"grad_norm": 0.8137418632037458,
|
|
"learning_rate": 5.207285692376427e-06,
|
|
"loss": 0.2372,
|
|
"num_input_tokens_seen": 190981888,
|
|
"step": 2435,
|
|
"train_runtime": 32120.4466,
|
|
"train_tokens_per_second": 5945.804
|
|
},
|
|
{
|
|
"epoch": 0.976,
|
|
"grad_norm": 0.8709294531660275,
|
|
"learning_rate": 5.191590236410451e-06,
|
|
"loss": 0.2312,
|
|
"num_input_tokens_seen": 191325504,
|
|
"step": 2440,
|
|
"train_runtime": 32190.2973,
|
|
"train_tokens_per_second": 5943.577
|
|
},
|
|
{
|
|
"epoch": 0.978,
|
|
"grad_norm": 0.8141333292380133,
|
|
"learning_rate": 5.175892889526189e-06,
|
|
"loss": 0.2086,
|
|
"num_input_tokens_seen": 191691824,
|
|
"step": 2445,
|
|
"train_runtime": 32250.6545,
|
|
"train_tokens_per_second": 5943.812
|
|
},
|
|
{
|
|
"epoch": 0.98,
|
|
"grad_norm": 0.6568883957821576,
|
|
"learning_rate": 5.16019380665012e-06,
|
|
"loss": 0.2279,
|
|
"num_input_tokens_seen": 192164848,
|
|
"step": 2450,
|
|
"train_runtime": 32329.2932,
|
|
"train_tokens_per_second": 5943.985
|
|
},
|
|
{
|
|
"epoch": 0.982,
|
|
"grad_norm": 0.8113314122650447,
|
|
"learning_rate": 5.144493142725851e-06,
|
|
"loss": 0.2391,
|
|
"num_input_tokens_seen": 192517376,
|
|
"step": 2455,
|
|
"train_runtime": 32392.0021,
|
|
"train_tokens_per_second": 5943.361
|
|
},
|
|
{
|
|
"epoch": 0.984,
|
|
"grad_norm": 0.8866398589116381,
|
|
"learning_rate": 5.128791052712597e-06,
|
|
"loss": 0.236,
|
|
"num_input_tokens_seen": 192975344,
|
|
"step": 2460,
|
|
"train_runtime": 32467.0335,
|
|
"train_tokens_per_second": 5943.732
|
|
},
|
|
{
|
|
"epoch": 0.986,
|
|
"grad_norm": 0.6305031077039938,
|
|
"learning_rate": 5.1130876915836495e-06,
|
|
"loss": 0.2355,
|
|
"num_input_tokens_seen": 193448704,
|
|
"step": 2465,
|
|
"train_runtime": 32543.6576,
|
|
"train_tokens_per_second": 5944.283
|
|
},
|
|
{
|
|
"epoch": 0.988,
|
|
"grad_norm": 0.7628934806649452,
|
|
"learning_rate": 5.0973832143248405e-06,
|
|
"loss": 0.2254,
|
|
"num_input_tokens_seen": 193822592,
|
|
"step": 2470,
|
|
"train_runtime": 32598.0646,
|
|
"train_tokens_per_second": 5945.831
|
|
},
|
|
{
|
|
"epoch": 0.99,
|
|
"grad_norm": 0.70672706494417,
|
|
"learning_rate": 5.0816777759330215e-06,
|
|
"loss": 0.2537,
|
|
"num_input_tokens_seen": 194232336,
|
|
"step": 2475,
|
|
"train_runtime": 32670.2703,
|
|
"train_tokens_per_second": 5945.232
|
|
},
|
|
{
|
|
"epoch": 0.992,
|
|
"grad_norm": 0.7385436359837361,
|
|
"learning_rate": 5.065971531414528e-06,
|
|
"loss": 0.2267,
|
|
"num_input_tokens_seen": 194573072,
|
|
"step": 2480,
|
|
"train_runtime": 32732.6925,
|
|
"train_tokens_per_second": 5944.304
|
|
},
|
|
{
|
|
"epoch": 0.994,
|
|
"grad_norm": 0.8708620218303826,
|
|
"learning_rate": 5.050264635783654e-06,
|
|
"loss": 0.2445,
|
|
"num_input_tokens_seen": 194995520,
|
|
"step": 2485,
|
|
"train_runtime": 32808.6939,
|
|
"train_tokens_per_second": 5943.41
|
|
},
|
|
{
|
|
"epoch": 0.996,
|
|
"grad_norm": 0.8837777853923816,
|
|
"learning_rate": 5.034557244061117e-06,
|
|
"loss": 0.2221,
|
|
"num_input_tokens_seen": 195391968,
|
|
"step": 2490,
|
|
"train_runtime": 32866.1399,
|
|
"train_tokens_per_second": 5945.084
|
|
},
|
|
{
|
|
"epoch": 0.998,
|
|
"grad_norm": 2.625974706230731,
|
|
"learning_rate": 5.018849511272532e-06,
|
|
"loss": 0.2541,
|
|
"num_input_tokens_seen": 195720288,
|
|
"step": 2495,
|
|
"train_runtime": 32917.1453,
|
|
"train_tokens_per_second": 5945.846
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"grad_norm": 0.7009528907653958,
|
|
"learning_rate": 5.0031415924468816e-06,
|
|
"loss": 0.2342,
|
|
"num_input_tokens_seen": 196169248,
|
|
"step": 2500,
|
|
"train_runtime": 32991.3291,
|
|
"train_tokens_per_second": 5946.085
|
|
},
|
|
{
|
|
"epoch": 1.002,
|
|
"grad_norm": 0.8206884102659574,
|
|
"learning_rate": 4.987433642614981e-06,
|
|
"loss": 0.179,
|
|
"num_input_tokens_seen": 196494000,
|
|
"step": 2505,
|
|
"train_runtime": 33166.3135,
|
|
"train_tokens_per_second": 5924.505
|
|
},
|
|
{
|
|
"epoch": 1.004,
|
|
"grad_norm": 0.6627396630282877,
|
|
"learning_rate": 4.971725816807956e-06,
|
|
"loss": 0.1623,
|
|
"num_input_tokens_seen": 196910592,
|
|
"step": 2510,
|
|
"train_runtime": 33244.1967,
|
|
"train_tokens_per_second": 5923.157
|
|
},
|
|
{
|
|
"epoch": 1.006,
|
|
"grad_norm": 1.017086618512458,
|
|
"learning_rate": 4.956018270055703e-06,
|
|
"loss": 0.1427,
|
|
"num_input_tokens_seen": 197247360,
|
|
"step": 2515,
|
|
"train_runtime": 33293.3805,
|
|
"train_tokens_per_second": 5924.522
|
|
},
|
|
{
|
|
"epoch": 1.008,
|
|
"grad_norm": 0.6707668012862857,
|
|
"learning_rate": 4.940311157385369e-06,
|
|
"loss": 0.1741,
|
|
"num_input_tokens_seen": 197613104,
|
|
"step": 2520,
|
|
"train_runtime": 33348.8345,
|
|
"train_tokens_per_second": 5925.637
|
|
},
|
|
{
|
|
"epoch": 1.01,
|
|
"grad_norm": 0.699807623790579,
|
|
"learning_rate": 4.924604633819815e-06,
|
|
"loss": 0.1804,
|
|
"num_input_tokens_seen": 197948240,
|
|
"step": 2525,
|
|
"train_runtime": 33410.5691,
|
|
"train_tokens_per_second": 5924.719
|
|
},
|
|
{
|
|
"epoch": 1.012,
|
|
"grad_norm": 0.7643010061340277,
|
|
"learning_rate": 4.908898854376086e-06,
|
|
"loss": 0.1432,
|
|
"num_input_tokens_seen": 198299104,
|
|
"step": 2530,
|
|
"train_runtime": 33475.714,
|
|
"train_tokens_per_second": 5923.671
|
|
},
|
|
{
|
|
"epoch": 1.014,
|
|
"grad_norm": 0.7948822156091124,
|
|
"learning_rate": 4.893193974063885e-06,
|
|
"loss": 0.1555,
|
|
"num_input_tokens_seen": 198690672,
|
|
"step": 2535,
|
|
"train_runtime": 33536.2509,
|
|
"train_tokens_per_second": 5924.654
|
|
},
|
|
{
|
|
"epoch": 1.016,
|
|
"grad_norm": 0.6735741844731251,
|
|
"learning_rate": 4.877490147884042e-06,
|
|
"loss": 0.1601,
|
|
"num_input_tokens_seen": 199144304,
|
|
"step": 2540,
|
|
"train_runtime": 33606.4469,
|
|
"train_tokens_per_second": 5925.777
|
|
},
|
|
{
|
|
"epoch": 1.018,
|
|
"grad_norm": 0.7137817654846128,
|
|
"learning_rate": 4.861787530826979e-06,
|
|
"loss": 0.1782,
|
|
"num_input_tokens_seen": 199492576,
|
|
"step": 2545,
|
|
"train_runtime": 33667.8705,
|
|
"train_tokens_per_second": 5925.31
|
|
},
|
|
{
|
|
"epoch": 1.02,
|
|
"grad_norm": 0.6031853805879228,
|
|
"learning_rate": 4.846086277871188e-06,
|
|
"loss": 0.1579,
|
|
"num_input_tokens_seen": 199922256,
|
|
"step": 2550,
|
|
"train_runtime": 33732.8492,
|
|
"train_tokens_per_second": 5926.634
|
|
},
|
|
{
|
|
"epoch": 1.022,
|
|
"grad_norm": 0.8180055304728591,
|
|
"learning_rate": 4.830386543981696e-06,
|
|
"loss": 0.1415,
|
|
"num_input_tokens_seen": 200273824,
|
|
"step": 2555,
|
|
"train_runtime": 33792.1805,
|
|
"train_tokens_per_second": 5926.632
|
|
},
|
|
{
|
|
"epoch": 1.024,
|
|
"grad_norm": 0.7237157323683006,
|
|
"learning_rate": 4.8146884841085405e-06,
|
|
"loss": 0.1778,
|
|
"num_input_tokens_seen": 200711360,
|
|
"step": 2560,
|
|
"train_runtime": 33868.9714,
|
|
"train_tokens_per_second": 5926.113
|
|
},
|
|
{
|
|
"epoch": 1.026,
|
|
"grad_norm": 0.655625185455015,
|
|
"learning_rate": 4.798992253185233e-06,
|
|
"loss": 0.1405,
|
|
"num_input_tokens_seen": 201079552,
|
|
"step": 2565,
|
|
"train_runtime": 33936.5377,
|
|
"train_tokens_per_second": 5925.164
|
|
},
|
|
{
|
|
"epoch": 1.028,
|
|
"grad_norm": 0.7247112294905705,
|
|
"learning_rate": 4.783298006127238e-06,
|
|
"loss": 0.1822,
|
|
"num_input_tokens_seen": 201507760,
|
|
"step": 2570,
|
|
"train_runtime": 34001.4926,
|
|
"train_tokens_per_second": 5926.439
|
|
},
|
|
{
|
|
"epoch": 1.03,
|
|
"grad_norm": 0.8262626624707906,
|
|
"learning_rate": 4.767605897830436e-06,
|
|
"loss": 0.1772,
|
|
"num_input_tokens_seen": 202004576,
|
|
"step": 2575,
|
|
"train_runtime": 34072.6966,
|
|
"train_tokens_per_second": 5928.635
|
|
},
|
|
{
|
|
"epoch": 1.032,
|
|
"grad_norm": 0.7100267318929274,
|
|
"learning_rate": 4.7519160831696e-06,
|
|
"loss": 0.1745,
|
|
"num_input_tokens_seen": 202427216,
|
|
"step": 2580,
|
|
"train_runtime": 34141.9126,
|
|
"train_tokens_per_second": 5928.995
|
|
},
|
|
{
|
|
"epoch": 1.034,
|
|
"grad_norm": 0.7319887001493858,
|
|
"learning_rate": 4.736228716996868e-06,
|
|
"loss": 0.1639,
|
|
"num_input_tokens_seen": 202837472,
|
|
"step": 2585,
|
|
"train_runtime": 34210.2173,
|
|
"train_tokens_per_second": 5929.149
|
|
},
|
|
{
|
|
"epoch": 1.036,
|
|
"grad_norm": 0.6357869825753699,
|
|
"learning_rate": 4.72054395414021e-06,
|
|
"loss": 0.1646,
|
|
"num_input_tokens_seen": 203262240,
|
|
"step": 2590,
|
|
"train_runtime": 34275.1632,
|
|
"train_tokens_per_second": 5930.307
|
|
},
|
|
{
|
|
"epoch": 1.038,
|
|
"grad_norm": 1.1476911091838051,
|
|
"learning_rate": 4.704861949401904e-06,
|
|
"loss": 0.1651,
|
|
"num_input_tokens_seen": 203665168,
|
|
"step": 2595,
|
|
"train_runtime": 34341.1889,
|
|
"train_tokens_per_second": 5930.638
|
|
},
|
|
{
|
|
"epoch": 1.04,
|
|
"grad_norm": 0.7461006353904251,
|
|
"learning_rate": 4.689182857557006e-06,
|
|
"loss": 0.1572,
|
|
"num_input_tokens_seen": 204024048,
|
|
"step": 2600,
|
|
"train_runtime": 34386.7846,
|
|
"train_tokens_per_second": 5933.211
|
|
},
|
|
{
|
|
"epoch": 1.042,
|
|
"grad_norm": 0.9203596903922054,
|
|
"learning_rate": 4.673506833351821e-06,
|
|
"loss": 0.1605,
|
|
"num_input_tokens_seen": 204431792,
|
|
"step": 2605,
|
|
"train_runtime": 34460.4668,
|
|
"train_tokens_per_second": 5932.357
|
|
},
|
|
{
|
|
"epoch": 1.044,
|
|
"grad_norm": 0.7166018914600659,
|
|
"learning_rate": 4.65783403150238e-06,
|
|
"loss": 0.1616,
|
|
"num_input_tokens_seen": 204799008,
|
|
"step": 2610,
|
|
"train_runtime": 34527.0501,
|
|
"train_tokens_per_second": 5931.552
|
|
},
|
|
{
|
|
"epoch": 1.046,
|
|
"grad_norm": 0.5855573422787974,
|
|
"learning_rate": 4.642164606692912e-06,
|
|
"loss": 0.1549,
|
|
"num_input_tokens_seen": 205228960,
|
|
"step": 2615,
|
|
"train_runtime": 34598.5642,
|
|
"train_tokens_per_second": 5931.719
|
|
},
|
|
{
|
|
"epoch": 1.048,
|
|
"grad_norm": 0.7585683528427378,
|
|
"learning_rate": 4.626498713574311e-06,
|
|
"loss": 0.168,
|
|
"num_input_tokens_seen": 205586784,
|
|
"step": 2620,
|
|
"train_runtime": 34669.4772,
|
|
"train_tokens_per_second": 5929.907
|
|
},
|
|
{
|
|
"epoch": 1.05,
|
|
"grad_norm": 0.6937008355050617,
|
|
"learning_rate": 4.610836506762618e-06,
|
|
"loss": 0.1796,
|
|
"num_input_tokens_seen": 206006096,
|
|
"step": 2625,
|
|
"train_runtime": 34747.5316,
|
|
"train_tokens_per_second": 5928.654
|
|
},
|
|
{
|
|
"epoch": 1.052,
|
|
"grad_norm": 0.778797817568551,
|
|
"learning_rate": 4.5951781408374915e-06,
|
|
"loss": 0.1714,
|
|
"num_input_tokens_seen": 206348848,
|
|
"step": 2630,
|
|
"train_runtime": 34805.4063,
|
|
"train_tokens_per_second": 5928.644
|
|
},
|
|
{
|
|
"epoch": 1.054,
|
|
"grad_norm": 0.6764175399102008,
|
|
"learning_rate": 4.579523770340681e-06,
|
|
"loss": 0.1777,
|
|
"num_input_tokens_seen": 206713632,
|
|
"step": 2635,
|
|
"train_runtime": 34867.1709,
|
|
"train_tokens_per_second": 5928.604
|
|
},
|
|
{
|
|
"epoch": 1.056,
|
|
"grad_norm": 0.7248451754762781,
|
|
"learning_rate": 4.563873549774506e-06,
|
|
"loss": 0.1582,
|
|
"num_input_tokens_seen": 207167536,
|
|
"step": 2640,
|
|
"train_runtime": 34932.6035,
|
|
"train_tokens_per_second": 5930.492
|
|
},
|
|
{
|
|
"epoch": 1.058,
|
|
"grad_norm": 0.6261065215919333,
|
|
"learning_rate": 4.548227633600322e-06,
|
|
"loss": 0.1607,
|
|
"num_input_tokens_seen": 207670624,
|
|
"step": 2645,
|
|
"train_runtime": 35011.047,
|
|
"train_tokens_per_second": 5931.574
|
|
},
|
|
{
|
|
"epoch": 1.06,
|
|
"grad_norm": 0.7527498017528644,
|
|
"learning_rate": 4.532586176237007e-06,
|
|
"loss": 0.1679,
|
|
"num_input_tokens_seen": 207981200,
|
|
"step": 2650,
|
|
"train_runtime": 35065.6722,
|
|
"train_tokens_per_second": 5931.191
|
|
},
|
|
{
|
|
"epoch": 1.062,
|
|
"grad_norm": 0.6921855522751097,
|
|
"learning_rate": 4.516949332059429e-06,
|
|
"loss": 0.1718,
|
|
"num_input_tokens_seen": 208370544,
|
|
"step": 2655,
|
|
"train_runtime": 35128.709,
|
|
"train_tokens_per_second": 5931.631
|
|
},
|
|
{
|
|
"epoch": 1.064,
|
|
"grad_norm": 0.701705665527989,
|
|
"learning_rate": 4.501317255396931e-06,
|
|
"loss": 0.1636,
|
|
"num_input_tokens_seen": 208748112,
|
|
"step": 2660,
|
|
"train_runtime": 35191.7728,
|
|
"train_tokens_per_second": 5931.731
|
|
},
|
|
{
|
|
"epoch": 1.066,
|
|
"grad_norm": 0.7946157283324536,
|
|
"learning_rate": 4.485690100531793e-06,
|
|
"loss": 0.157,
|
|
"num_input_tokens_seen": 209150032,
|
|
"step": 2665,
|
|
"train_runtime": 35259.9097,
|
|
"train_tokens_per_second": 5931.667
|
|
},
|
|
{
|
|
"epoch": 1.068,
|
|
"grad_norm": 0.7809017513044929,
|
|
"learning_rate": 4.470068021697728e-06,
|
|
"loss": 0.1565,
|
|
"num_input_tokens_seen": 209517296,
|
|
"step": 2670,
|
|
"train_runtime": 35321.313,
|
|
"train_tokens_per_second": 5931.753
|
|
},
|
|
{
|
|
"epoch": 1.07,
|
|
"grad_norm": 0.7386831918244939,
|
|
"learning_rate": 4.454451173078347e-06,
|
|
"loss": 0.173,
|
|
"num_input_tokens_seen": 209952960,
|
|
"step": 2675,
|
|
"train_runtime": 35399.5504,
|
|
"train_tokens_per_second": 5930.95
|
|
},
|
|
{
|
|
"epoch": 1.072,
|
|
"grad_norm": 0.8434935251816089,
|
|
"learning_rate": 4.43883970880564e-06,
|
|
"loss": 0.1545,
|
|
"num_input_tokens_seen": 210308672,
|
|
"step": 2680,
|
|
"train_runtime": 35461.7688,
|
|
"train_tokens_per_second": 5930.575
|
|
},
|
|
{
|
|
"epoch": 1.074,
|
|
"grad_norm": 0.6266715079657134,
|
|
"learning_rate": 4.423233782958459e-06,
|
|
"loss": 0.1552,
|
|
"num_input_tokens_seen": 210626720,
|
|
"step": 2685,
|
|
"train_runtime": 35511.6008,
|
|
"train_tokens_per_second": 5931.209
|
|
},
|
|
{
|
|
"epoch": 1.076,
|
|
"grad_norm": 0.8498062792861351,
|
|
"learning_rate": 4.407633549560991e-06,
|
|
"loss": 0.1752,
|
|
"num_input_tokens_seen": 211055456,
|
|
"step": 2690,
|
|
"train_runtime": 35584.5256,
|
|
"train_tokens_per_second": 5931.102
|
|
},
|
|
{
|
|
"epoch": 1.078,
|
|
"grad_norm": 0.7743065335398452,
|
|
"learning_rate": 4.392039162581239e-06,
|
|
"loss": 0.1608,
|
|
"num_input_tokens_seen": 211475760,
|
|
"step": 2695,
|
|
"train_runtime": 35655.8368,
|
|
"train_tokens_per_second": 5931.028
|
|
},
|
|
{
|
|
"epoch": 1.08,
|
|
"grad_norm": 0.6711963227719795,
|
|
"learning_rate": 4.37645077592951e-06,
|
|
"loss": 0.1658,
|
|
"num_input_tokens_seen": 211864080,
|
|
"step": 2700,
|
|
"train_runtime": 35717.1089,
|
|
"train_tokens_per_second": 5931.725
|
|
},
|
|
{
|
|
"epoch": 1.082,
|
|
"grad_norm": 0.8872325740198352,
|
|
"learning_rate": 4.360868543456883e-06,
|
|
"loss": 0.1707,
|
|
"num_input_tokens_seen": 212299776,
|
|
"step": 2705,
|
|
"train_runtime": 35787.4154,
|
|
"train_tokens_per_second": 5932.247
|
|
},
|
|
{
|
|
"epoch": 1.084,
|
|
"grad_norm": 0.8448321328516085,
|
|
"learning_rate": 4.3452926189537056e-06,
|
|
"loss": 0.1534,
|
|
"num_input_tokens_seen": 212762192,
|
|
"step": 2710,
|
|
"train_runtime": 35865.8141,
|
|
"train_tokens_per_second": 5932.172
|
|
},
|
|
{
|
|
"epoch": 1.086,
|
|
"grad_norm": 0.8812169080445897,
|
|
"learning_rate": 4.329723156148064e-06,
|
|
"loss": 0.1615,
|
|
"num_input_tokens_seen": 213195072,
|
|
"step": 2715,
|
|
"train_runtime": 35933.0687,
|
|
"train_tokens_per_second": 5933.116
|
|
},
|
|
{
|
|
"epoch": 1.088,
|
|
"grad_norm": 0.6244313575485646,
|
|
"learning_rate": 4.314160308704269e-06,
|
|
"loss": 0.1604,
|
|
"num_input_tokens_seen": 213630928,
|
|
"step": 2720,
|
|
"train_runtime": 36003.4332,
|
|
"train_tokens_per_second": 5933.627
|
|
},
|
|
{
|
|
"epoch": 1.09,
|
|
"grad_norm": 0.7601192659202312,
|
|
"learning_rate": 4.298604230221341e-06,
|
|
"loss": 0.1665,
|
|
"num_input_tokens_seen": 214053840,
|
|
"step": 2725,
|
|
"train_runtime": 36075.8243,
|
|
"train_tokens_per_second": 5933.443
|
|
},
|
|
{
|
|
"epoch": 1.092,
|
|
"grad_norm": 0.7403060689389939,
|
|
"learning_rate": 4.283055074231498e-06,
|
|
"loss": 0.1638,
|
|
"num_input_tokens_seen": 214438800,
|
|
"step": 2730,
|
|
"train_runtime": 36128.8149,
|
|
"train_tokens_per_second": 5935.395
|
|
},
|
|
{
|
|
"epoch": 1.094,
|
|
"grad_norm": 0.854157761603958,
|
|
"learning_rate": 4.267512994198629e-06,
|
|
"loss": 0.1783,
|
|
"num_input_tokens_seen": 214859088,
|
|
"step": 2735,
|
|
"train_runtime": 36200.1342,
|
|
"train_tokens_per_second": 5935.312
|
|
},
|
|
{
|
|
"epoch": 1.096,
|
|
"grad_norm": 0.5299682207565466,
|
|
"learning_rate": 4.251978143516789e-06,
|
|
"loss": 0.1546,
|
|
"num_input_tokens_seen": 215328352,
|
|
"step": 2740,
|
|
"train_runtime": 36275.6001,
|
|
"train_tokens_per_second": 5935.9
|
|
},
|
|
{
|
|
"epoch": 1.098,
|
|
"grad_norm": 1.1011844677630107,
|
|
"learning_rate": 4.2364506755086856e-06,
|
|
"loss": 0.1638,
|
|
"num_input_tokens_seen": 215694144,
|
|
"step": 2745,
|
|
"train_runtime": 36344.6796,
|
|
"train_tokens_per_second": 5934.683
|
|
},
|
|
{
|
|
"epoch": 1.1,
|
|
"grad_norm": 0.7378238590611744,
|
|
"learning_rate": 4.220930743424157e-06,
|
|
"loss": 0.1749,
|
|
"num_input_tokens_seen": 216036784,
|
|
"step": 2750,
|
|
"train_runtime": 36405.0498,
|
|
"train_tokens_per_second": 5934.253
|
|
},
|
|
{
|
|
"epoch": 1.102,
|
|
"grad_norm": 0.7620842922462738,
|
|
"learning_rate": 4.2054185004386675e-06,
|
|
"loss": 0.1536,
|
|
"num_input_tokens_seen": 216440592,
|
|
"step": 2755,
|
|
"train_runtime": 36477.6764,
|
|
"train_tokens_per_second": 5933.508
|
|
},
|
|
{
|
|
"epoch": 1.104,
|
|
"grad_norm": 0.672929982728578,
|
|
"learning_rate": 4.1899140996517934e-06,
|
|
"loss": 0.176,
|
|
"num_input_tokens_seen": 216818816,
|
|
"step": 2760,
|
|
"train_runtime": 36542.2699,
|
|
"train_tokens_per_second": 5933.37
|
|
},
|
|
{
|
|
"epoch": 1.106,
|
|
"grad_norm": 0.937019791287993,
|
|
"learning_rate": 4.174417694085711e-06,
|
|
"loss": 0.17,
|
|
"num_input_tokens_seen": 217166288,
|
|
"step": 2765,
|
|
"train_runtime": 36591.6042,
|
|
"train_tokens_per_second": 5934.867
|
|
},
|
|
{
|
|
"epoch": 1.108,
|
|
"grad_norm": 0.7228527351831493,
|
|
"learning_rate": 4.158929436683687e-06,
|
|
"loss": 0.1498,
|
|
"num_input_tokens_seen": 217524848,
|
|
"step": 2770,
|
|
"train_runtime": 36642.6781,
|
|
"train_tokens_per_second": 5936.38
|
|
},
|
|
{
|
|
"epoch": 1.11,
|
|
"grad_norm": 0.8883666084073585,
|
|
"learning_rate": 4.143449480308569e-06,
|
|
"loss": 0.1686,
|
|
"num_input_tokens_seen": 217843776,
|
|
"step": 2775,
|
|
"train_runtime": 36700.2148,
|
|
"train_tokens_per_second": 5935.763
|
|
},
|
|
{
|
|
"epoch": 1.112,
|
|
"grad_norm": 0.8638088967792964,
|
|
"learning_rate": 4.127977977741277e-06,
|
|
"loss": 0.1593,
|
|
"num_input_tokens_seen": 218174688,
|
|
"step": 2780,
|
|
"train_runtime": 36755.6126,
|
|
"train_tokens_per_second": 5935.82
|
|
},
|
|
{
|
|
"epoch": 1.114,
|
|
"grad_norm": 0.7707505837930239,
|
|
"learning_rate": 4.112515081679295e-06,
|
|
"loss": 0.1739,
|
|
"num_input_tokens_seen": 218560048,
|
|
"step": 2785,
|
|
"train_runtime": 36820.8427,
|
|
"train_tokens_per_second": 5935.77
|
|
},
|
|
{
|
|
"epoch": 1.116,
|
|
"grad_norm": 0.7373894872140202,
|
|
"learning_rate": 4.0970609447351635e-06,
|
|
"loss": 0.1641,
|
|
"num_input_tokens_seen": 218888000,
|
|
"step": 2790,
|
|
"train_runtime": 36866.5779,
|
|
"train_tokens_per_second": 5937.302
|
|
},
|
|
{
|
|
"epoch": 1.1179999999999999,
|
|
"grad_norm": 0.7384139140945083,
|
|
"learning_rate": 4.081615719434978e-06,
|
|
"loss": 0.1496,
|
|
"num_input_tokens_seen": 219226272,
|
|
"step": 2795,
|
|
"train_runtime": 36928.1512,
|
|
"train_tokens_per_second": 5936.562
|
|
},
|
|
{
|
|
"epoch": 1.12,
|
|
"grad_norm": 0.7912554551323161,
|
|
"learning_rate": 4.066179558216874e-06,
|
|
"loss": 0.1596,
|
|
"num_input_tokens_seen": 219614112,
|
|
"step": 2800,
|
|
"train_runtime": 36998.2761,
|
|
"train_tokens_per_second": 5935.793
|
|
},
|
|
{
|
|
"epoch": 1.1219999999999999,
|
|
"grad_norm": 0.7325341959934607,
|
|
"learning_rate": 4.0507526134295314e-06,
|
|
"loss": 0.1649,
|
|
"num_input_tokens_seen": 220054416,
|
|
"step": 2805,
|
|
"train_runtime": 37072.1048,
|
|
"train_tokens_per_second": 5935.849
|
|
},
|
|
{
|
|
"epoch": 1.124,
|
|
"grad_norm": 0.78218800500567,
|
|
"learning_rate": 4.035335037330668e-06,
|
|
"loss": 0.1585,
|
|
"num_input_tokens_seen": 220482096,
|
|
"step": 2810,
|
|
"train_runtime": 37132.8991,
|
|
"train_tokens_per_second": 5937.648
|
|
},
|
|
{
|
|
"epoch": 1.126,
|
|
"grad_norm": 0.83787727815612,
|
|
"learning_rate": 4.019926982085536e-06,
|
|
"loss": 0.1638,
|
|
"num_input_tokens_seen": 220802496,
|
|
"step": 2815,
|
|
"train_runtime": 37185.5697,
|
|
"train_tokens_per_second": 5937.854
|
|
},
|
|
{
|
|
"epoch": 1.1280000000000001,
|
|
"grad_norm": 0.8555273246252996,
|
|
"learning_rate": 4.004528599765419e-06,
|
|
"loss": 0.1583,
|
|
"num_input_tokens_seen": 221218208,
|
|
"step": 2820,
|
|
"train_runtime": 37257.4076,
|
|
"train_tokens_per_second": 5937.563
|
|
},
|
|
{
|
|
"epoch": 1.13,
|
|
"grad_norm": 0.7346374432697927,
|
|
"learning_rate": 3.989140042346134e-06,
|
|
"loss": 0.1714,
|
|
"num_input_tokens_seen": 221641024,
|
|
"step": 2825,
|
|
"train_runtime": 37325.4615,
|
|
"train_tokens_per_second": 5938.065
|
|
},
|
|
{
|
|
"epoch": 1.1320000000000001,
|
|
"grad_norm": 0.7067972160709773,
|
|
"learning_rate": 3.97376146170653e-06,
|
|
"loss": 0.1524,
|
|
"num_input_tokens_seen": 222048304,
|
|
"step": 2830,
|
|
"train_runtime": 37403.4806,
|
|
"train_tokens_per_second": 5936.568
|
|
},
|
|
{
|
|
"epoch": 1.134,
|
|
"grad_norm": 0.6181439723978389,
|
|
"learning_rate": 3.95839300962699e-06,
|
|
"loss": 0.1606,
|
|
"num_input_tokens_seen": 222383824,
|
|
"step": 2835,
|
|
"train_runtime": 37464.6763,
|
|
"train_tokens_per_second": 5935.827
|
|
},
|
|
{
|
|
"epoch": 1.1360000000000001,
|
|
"grad_norm": 0.7810560372233574,
|
|
"learning_rate": 3.9430348377879315e-06,
|
|
"loss": 0.1703,
|
|
"num_input_tokens_seen": 222702688,
|
|
"step": 2840,
|
|
"train_runtime": 37516.4758,
|
|
"train_tokens_per_second": 5936.13
|
|
},
|
|
{
|
|
"epoch": 1.138,
|
|
"grad_norm": 0.7487288889954055,
|
|
"learning_rate": 3.927687097768309e-06,
|
|
"loss": 0.1612,
|
|
"num_input_tokens_seen": 223138048,
|
|
"step": 2845,
|
|
"train_runtime": 37581.7764,
|
|
"train_tokens_per_second": 5937.4
|
|
},
|
|
{
|
|
"epoch": 1.1400000000000001,
|
|
"grad_norm": 0.6635798790456804,
|
|
"learning_rate": 3.912349941044122e-06,
|
|
"loss": 0.1756,
|
|
"num_input_tokens_seen": 223556928,
|
|
"step": 2850,
|
|
"train_runtime": 37647.8087,
|
|
"train_tokens_per_second": 5938.113
|
|
},
|
|
{
|
|
"epoch": 1.142,
|
|
"grad_norm": 0.9217117016523089,
|
|
"learning_rate": 3.897023518986915e-06,
|
|
"loss": 0.1546,
|
|
"num_input_tokens_seen": 223918384,
|
|
"step": 2855,
|
|
"train_runtime": 37716.3749,
|
|
"train_tokens_per_second": 5936.901
|
|
},
|
|
{
|
|
"epoch": 1.144,
|
|
"grad_norm": 0.8541649505876854,
|
|
"learning_rate": 3.8817079828622855e-06,
|
|
"loss": 0.1618,
|
|
"num_input_tokens_seen": 224316224,
|
|
"step": 2860,
|
|
"train_runtime": 37789.3908,
|
|
"train_tokens_per_second": 5935.958
|
|
},
|
|
{
|
|
"epoch": 1.146,
|
|
"grad_norm": 0.6591325927248158,
|
|
"learning_rate": 3.866403483828392e-06,
|
|
"loss": 0.1891,
|
|
"num_input_tokens_seen": 224745296,
|
|
"step": 2865,
|
|
"train_runtime": 37862.4086,
|
|
"train_tokens_per_second": 5935.843
|
|
},
|
|
{
|
|
"epoch": 1.148,
|
|
"grad_norm": 0.7577605411866083,
|
|
"learning_rate": 3.851110172934463e-06,
|
|
"loss": 0.166,
|
|
"num_input_tokens_seen": 225073936,
|
|
"step": 2870,
|
|
"train_runtime": 37920.3318,
|
|
"train_tokens_per_second": 5935.442
|
|
},
|
|
{
|
|
"epoch": 1.15,
|
|
"grad_norm": 0.9012162426473633,
|
|
"learning_rate": 3.835828201119302e-06,
|
|
"loss": 0.1702,
|
|
"num_input_tokens_seen": 225454176,
|
|
"step": 2875,
|
|
"train_runtime": 37997.6922,
|
|
"train_tokens_per_second": 5933.365
|
|
},
|
|
{
|
|
"epoch": 1.152,
|
|
"grad_norm": 0.5988054918135639,
|
|
"learning_rate": 3.820557719209799e-06,
|
|
"loss": 0.1539,
|
|
"num_input_tokens_seen": 225879344,
|
|
"step": 2880,
|
|
"train_runtime": 38066.6304,
|
|
"train_tokens_per_second": 5933.789
|
|
},
|
|
{
|
|
"epoch": 1.154,
|
|
"grad_norm": 0.902317690732245,
|
|
"learning_rate": 3.8052988779194478e-06,
|
|
"loss": 0.1578,
|
|
"num_input_tokens_seen": 226262112,
|
|
"step": 2885,
|
|
"train_runtime": 38124.5945,
|
|
"train_tokens_per_second": 5934.807
|
|
},
|
|
{
|
|
"epoch": 1.156,
|
|
"grad_norm": 0.9044557837257774,
|
|
"learning_rate": 3.790051827846851e-06,
|
|
"loss": 0.1625,
|
|
"num_input_tokens_seen": 226648544,
|
|
"step": 2890,
|
|
"train_runtime": 38198.3737,
|
|
"train_tokens_per_second": 5933.461
|
|
},
|
|
{
|
|
"epoch": 1.158,
|
|
"grad_norm": 0.6818182606382266,
|
|
"learning_rate": 3.774816719474238e-06,
|
|
"loss": 0.1799,
|
|
"num_input_tokens_seen": 227010720,
|
|
"step": 2895,
|
|
"train_runtime": 38255.6362,
|
|
"train_tokens_per_second": 5934.046
|
|
},
|
|
{
|
|
"epoch": 1.16,
|
|
"grad_norm": 0.6800066890944376,
|
|
"learning_rate": 3.7595937031659775e-06,
|
|
"loss": 0.1679,
|
|
"num_input_tokens_seen": 227427232,
|
|
"step": 2900,
|
|
"train_runtime": 38328.8405,
|
|
"train_tokens_per_second": 5933.58
|
|
},
|
|
{
|
|
"epoch": 1.162,
|
|
"grad_norm": 0.6932417405012483,
|
|
"learning_rate": 3.744382929167094e-06,
|
|
"loss": 0.1538,
|
|
"num_input_tokens_seen": 227847312,
|
|
"step": 2905,
|
|
"train_runtime": 38401.2884,
|
|
"train_tokens_per_second": 5933.325
|
|
},
|
|
{
|
|
"epoch": 1.164,
|
|
"grad_norm": 0.9155937150504987,
|
|
"learning_rate": 3.729184547601786e-06,
|
|
"loss": 0.178,
|
|
"num_input_tokens_seen": 228165488,
|
|
"step": 2910,
|
|
"train_runtime": 38456.5846,
|
|
"train_tokens_per_second": 5933.067
|
|
},
|
|
{
|
|
"epoch": 1.166,
|
|
"grad_norm": 0.6528134649077573,
|
|
"learning_rate": 3.7139987084719463e-06,
|
|
"loss": 0.1525,
|
|
"num_input_tokens_seen": 228555376,
|
|
"step": 2915,
|
|
"train_runtime": 38516.838,
|
|
"train_tokens_per_second": 5933.908
|
|
},
|
|
{
|
|
"epoch": 1.168,
|
|
"grad_norm": 0.6859812209491093,
|
|
"learning_rate": 3.6988255616556725e-06,
|
|
"loss": 0.1753,
|
|
"num_input_tokens_seen": 228986000,
|
|
"step": 2920,
|
|
"train_runtime": 38587.1766,
|
|
"train_tokens_per_second": 5934.251
|
|
},
|
|
{
|
|
"epoch": 1.17,
|
|
"grad_norm": 0.8080941871588403,
|
|
"learning_rate": 3.6836652569057994e-06,
|
|
"loss": 0.1329,
|
|
"num_input_tokens_seen": 229411824,
|
|
"step": 2925,
|
|
"train_runtime": 38654.0215,
|
|
"train_tokens_per_second": 5935.005
|
|
},
|
|
{
|
|
"epoch": 1.172,
|
|
"grad_norm": 0.7493107552736412,
|
|
"learning_rate": 3.668517943848416e-06,
|
|
"loss": 0.1795,
|
|
"num_input_tokens_seen": 229778192,
|
|
"step": 2930,
|
|
"train_runtime": 38722.2631,
|
|
"train_tokens_per_second": 5934.007
|
|
},
|
|
{
|
|
"epoch": 1.174,
|
|
"grad_norm": 0.8202733220112606,
|
|
"learning_rate": 3.653383771981385e-06,
|
|
"loss": 0.1649,
|
|
"num_input_tokens_seen": 230140048,
|
|
"step": 2935,
|
|
"train_runtime": 38784.5829,
|
|
"train_tokens_per_second": 5933.802
|
|
},
|
|
{
|
|
"epoch": 1.176,
|
|
"grad_norm": 0.6750929884539376,
|
|
"learning_rate": 3.6382628906728735e-06,
|
|
"loss": 0.1572,
|
|
"num_input_tokens_seen": 230533984,
|
|
"step": 2940,
|
|
"train_runtime": 38854.0671,
|
|
"train_tokens_per_second": 5933.33
|
|
},
|
|
{
|
|
"epoch": 1.178,
|
|
"grad_norm": 0.9540995787604724,
|
|
"learning_rate": 3.6231554491598766e-06,
|
|
"loss": 0.1687,
|
|
"num_input_tokens_seen": 230871408,
|
|
"step": 2945,
|
|
"train_runtime": 38918.067,
|
|
"train_tokens_per_second": 5932.242
|
|
},
|
|
{
|
|
"epoch": 1.18,
|
|
"grad_norm": 0.7113190105023284,
|
|
"learning_rate": 3.60806159654674e-06,
|
|
"loss": 0.1841,
|
|
"num_input_tokens_seen": 231276048,
|
|
"step": 2950,
|
|
"train_runtime": 38980.7436,
|
|
"train_tokens_per_second": 5933.085
|
|
},
|
|
{
|
|
"epoch": 1.182,
|
|
"grad_norm": 0.5694070437259657,
|
|
"learning_rate": 3.592981481803699e-06,
|
|
"loss": 0.1734,
|
|
"num_input_tokens_seen": 231750416,
|
|
"step": 2955,
|
|
"train_runtime": 39051.2876,
|
|
"train_tokens_per_second": 5934.514
|
|
},
|
|
{
|
|
"epoch": 1.184,
|
|
"grad_norm": 0.7696320118443719,
|
|
"learning_rate": 3.577915253765396e-06,
|
|
"loss": 0.1746,
|
|
"num_input_tokens_seen": 232149872,
|
|
"step": 2960,
|
|
"train_runtime": 39121.9129,
|
|
"train_tokens_per_second": 5934.011
|
|
},
|
|
{
|
|
"epoch": 1.186,
|
|
"grad_norm": 0.6702860003504424,
|
|
"learning_rate": 3.562863061129419e-06,
|
|
"loss": 0.1536,
|
|
"num_input_tokens_seen": 232498144,
|
|
"step": 2965,
|
|
"train_runtime": 39189.0099,
|
|
"train_tokens_per_second": 5932.738
|
|
},
|
|
{
|
|
"epoch": 1.188,
|
|
"grad_norm": 1.1669807865715685,
|
|
"learning_rate": 3.547825052454833e-06,
|
|
"loss": 0.1697,
|
|
"num_input_tokens_seen": 232837008,
|
|
"step": 2970,
|
|
"train_runtime": 39257.4801,
|
|
"train_tokens_per_second": 5931.023
|
|
},
|
|
{
|
|
"epoch": 1.19,
|
|
"grad_norm": 0.6314310157948689,
|
|
"learning_rate": 3.532801376160713e-06,
|
|
"loss": 0.1655,
|
|
"num_input_tokens_seen": 233268432,
|
|
"step": 2975,
|
|
"train_runtime": 39329.48,
|
|
"train_tokens_per_second": 5931.134
|
|
},
|
|
{
|
|
"epoch": 1.192,
|
|
"grad_norm": 0.7747680172121664,
|
|
"learning_rate": 3.5177921805246772e-06,
|
|
"loss": 0.1545,
|
|
"num_input_tokens_seen": 233693104,
|
|
"step": 2980,
|
|
"train_runtime": 39406.2422,
|
|
"train_tokens_per_second": 5930.358
|
|
},
|
|
{
|
|
"epoch": 1.194,
|
|
"grad_norm": 0.7496226066719307,
|
|
"learning_rate": 3.502797613681429e-06,
|
|
"loss": 0.1584,
|
|
"num_input_tokens_seen": 234108256,
|
|
"step": 2985,
|
|
"train_runtime": 39478.8245,
|
|
"train_tokens_per_second": 5929.97
|
|
},
|
|
{
|
|
"epoch": 1.196,
|
|
"grad_norm": 0.8103593506278386,
|
|
"learning_rate": 3.4878178236212883e-06,
|
|
"loss": 0.1716,
|
|
"num_input_tokens_seen": 234497200,
|
|
"step": 2990,
|
|
"train_runtime": 39548.5055,
|
|
"train_tokens_per_second": 5929.357
|
|
},
|
|
{
|
|
"epoch": 1.198,
|
|
"grad_norm": 0.7510912961931008,
|
|
"learning_rate": 3.472852958188736e-06,
|
|
"loss": 0.156,
|
|
"num_input_tokens_seen": 234829648,
|
|
"step": 2995,
|
|
"train_runtime": 39600.9243,
|
|
"train_tokens_per_second": 5929.903
|
|
},
|
|
{
|
|
"epoch": 1.2,
|
|
"grad_norm": 0.6180898945651564,
|
|
"learning_rate": 3.457903165080952e-06,
|
|
"loss": 0.1658,
|
|
"num_input_tokens_seen": 235222976,
|
|
"step": 3000,
|
|
"train_runtime": 39670.9266,
|
|
"train_tokens_per_second": 5929.354
|
|
},
|
|
{
|
|
"epoch": 1.202,
|
|
"grad_norm": 0.7343635784563662,
|
|
"learning_rate": 3.442968591846359e-06,
|
|
"loss": 0.1759,
|
|
"num_input_tokens_seen": 235677408,
|
|
"step": 3005,
|
|
"train_runtime": 39742.8791,
|
|
"train_tokens_per_second": 5930.054
|
|
},
|
|
{
|
|
"epoch": 1.204,
|
|
"grad_norm": 0.7483883731480301,
|
|
"learning_rate": 3.4280493858831665e-06,
|
|
"loss": 0.1662,
|
|
"num_input_tokens_seen": 236101648,
|
|
"step": 3010,
|
|
"train_runtime": 39815.8004,
|
|
"train_tokens_per_second": 5929.848
|
|
},
|
|
{
|
|
"epoch": 1.206,
|
|
"grad_norm": 0.7546691801100126,
|
|
"learning_rate": 3.4131456944379126e-06,
|
|
"loss": 0.1649,
|
|
"num_input_tokens_seen": 236482832,
|
|
"step": 3015,
|
|
"train_runtime": 39880.4542,
|
|
"train_tokens_per_second": 5929.793
|
|
},
|
|
{
|
|
"epoch": 1.208,
|
|
"grad_norm": 0.8021162674310758,
|
|
"learning_rate": 3.398257664604015e-06,
|
|
"loss": 0.1506,
|
|
"num_input_tokens_seen": 236848400,
|
|
"step": 3020,
|
|
"train_runtime": 39939.203,
|
|
"train_tokens_per_second": 5930.223
|
|
},
|
|
{
|
|
"epoch": 1.21,
|
|
"grad_norm": 0.7324604704039218,
|
|
"learning_rate": 3.3833854433203185e-06,
|
|
"loss": 0.1814,
|
|
"num_input_tokens_seen": 237235776,
|
|
"step": 3025,
|
|
"train_runtime": 40008.8226,
|
|
"train_tokens_per_second": 5929.587
|
|
},
|
|
{
|
|
"epoch": 1.212,
|
|
"grad_norm": 0.7276644088071897,
|
|
"learning_rate": 3.3685291773696425e-06,
|
|
"loss": 0.165,
|
|
"num_input_tokens_seen": 237587584,
|
|
"step": 3030,
|
|
"train_runtime": 40061.4369,
|
|
"train_tokens_per_second": 5930.581
|
|
},
|
|
{
|
|
"epoch": 1.214,
|
|
"grad_norm": 0.6701812890457569,
|
|
"learning_rate": 3.3536890133773346e-06,
|
|
"loss": 0.158,
|
|
"num_input_tokens_seen": 237916544,
|
|
"step": 3035,
|
|
"train_runtime": 40116.8793,
|
|
"train_tokens_per_second": 5930.585
|
|
},
|
|
{
|
|
"epoch": 1.216,
|
|
"grad_norm": 0.719384224007256,
|
|
"learning_rate": 3.3388650978098218e-06,
|
|
"loss": 0.1717,
|
|
"num_input_tokens_seen": 238282032,
|
|
"step": 3040,
|
|
"train_runtime": 40183.6956,
|
|
"train_tokens_per_second": 5929.819
|
|
},
|
|
{
|
|
"epoch": 1.218,
|
|
"grad_norm": 0.699506572979744,
|
|
"learning_rate": 3.3240575769731662e-06,
|
|
"loss": 0.1584,
|
|
"num_input_tokens_seen": 238693680,
|
|
"step": 3045,
|
|
"train_runtime": 40255.7335,
|
|
"train_tokens_per_second": 5929.433
|
|
},
|
|
{
|
|
"epoch": 1.22,
|
|
"grad_norm": 0.8411131577131142,
|
|
"learning_rate": 3.309266597011621e-06,
|
|
"loss": 0.1559,
|
|
"num_input_tokens_seen": 239034096,
|
|
"step": 3050,
|
|
"train_runtime": 40318.7636,
|
|
"train_tokens_per_second": 5928.607
|
|
},
|
|
{
|
|
"epoch": 1.222,
|
|
"grad_norm": 0.6240009437213169,
|
|
"learning_rate": 3.294492303906188e-06,
|
|
"loss": 0.1681,
|
|
"num_input_tokens_seen": 239441184,
|
|
"step": 3055,
|
|
"train_runtime": 40391.8486,
|
|
"train_tokens_per_second": 5927.958
|
|
},
|
|
{
|
|
"epoch": 1.224,
|
|
"grad_norm": 0.8688895499518909,
|
|
"learning_rate": 3.2797348434731725e-06,
|
|
"loss": 0.1596,
|
|
"num_input_tokens_seen": 239805952,
|
|
"step": 3060,
|
|
"train_runtime": 40459.5599,
|
|
"train_tokens_per_second": 5927.053
|
|
},
|
|
{
|
|
"epoch": 1.226,
|
|
"grad_norm": 0.7779088672450006,
|
|
"learning_rate": 3.264994361362753e-06,
|
|
"loss": 0.1764,
|
|
"num_input_tokens_seen": 240245696,
|
|
"step": 3065,
|
|
"train_runtime": 40532.7493,
|
|
"train_tokens_per_second": 5927.2
|
|
},
|
|
{
|
|
"epoch": 1.228,
|
|
"grad_norm": 0.8142718165293787,
|
|
"learning_rate": 3.250271003057537e-06,
|
|
"loss": 0.1557,
|
|
"num_input_tokens_seen": 240583344,
|
|
"step": 3070,
|
|
"train_runtime": 40592.0249,
|
|
"train_tokens_per_second": 5926.862
|
|
},
|
|
{
|
|
"epoch": 1.23,
|
|
"grad_norm": 1.0827248398644935,
|
|
"learning_rate": 3.235564913871126e-06,
|
|
"loss": 0.1648,
|
|
"num_input_tokens_seen": 240959856,
|
|
"step": 3075,
|
|
"train_runtime": 40652.1617,
|
|
"train_tokens_per_second": 5927.357
|
|
},
|
|
{
|
|
"epoch": 1.232,
|
|
"grad_norm": 0.6668211984558198,
|
|
"learning_rate": 3.220876238946684e-06,
|
|
"loss": 0.1688,
|
|
"num_input_tokens_seen": 241359872,
|
|
"step": 3080,
|
|
"train_runtime": 40726.1793,
|
|
"train_tokens_per_second": 5926.406
|
|
},
|
|
{
|
|
"epoch": 1.234,
|
|
"grad_norm": 0.7230319930253292,
|
|
"learning_rate": 3.2062051232555024e-06,
|
|
"loss": 0.1615,
|
|
"num_input_tokens_seen": 241787296,
|
|
"step": 3085,
|
|
"train_runtime": 40794.7312,
|
|
"train_tokens_per_second": 5926.925
|
|
},
|
|
{
|
|
"epoch": 1.236,
|
|
"grad_norm": 0.5573622635818417,
|
|
"learning_rate": 3.1915517115955704e-06,
|
|
"loss": 0.1539,
|
|
"num_input_tokens_seen": 242103696,
|
|
"step": 3090,
|
|
"train_runtime": 40857.2345,
|
|
"train_tokens_per_second": 5925.602
|
|
},
|
|
{
|
|
"epoch": 1.238,
|
|
"grad_norm": 0.9075670158763212,
|
|
"learning_rate": 3.1769161485901445e-06,
|
|
"loss": 0.1544,
|
|
"num_input_tokens_seen": 242530544,
|
|
"step": 3095,
|
|
"train_runtime": 40923.0706,
|
|
"train_tokens_per_second": 5926.499
|
|
},
|
|
{
|
|
"epoch": 1.24,
|
|
"grad_norm": 0.7869485271603684,
|
|
"learning_rate": 3.1622985786863236e-06,
|
|
"loss": 0.158,
|
|
"num_input_tokens_seen": 242906448,
|
|
"step": 3100,
|
|
"train_runtime": 40984.6933,
|
|
"train_tokens_per_second": 5926.76
|
|
},
|
|
{
|
|
"epoch": 1.242,
|
|
"grad_norm": 0.7086002152075986,
|
|
"learning_rate": 3.147699146153621e-06,
|
|
"loss": 0.1563,
|
|
"num_input_tokens_seen": 243322160,
|
|
"step": 3105,
|
|
"train_runtime": 41060.1102,
|
|
"train_tokens_per_second": 5925.999
|
|
},
|
|
{
|
|
"epoch": 1.244,
|
|
"grad_norm": 0.9310354598106708,
|
|
"learning_rate": 3.1331179950825415e-06,
|
|
"loss": 0.1557,
|
|
"num_input_tokens_seen": 243624320,
|
|
"step": 3110,
|
|
"train_runtime": 41118.8384,
|
|
"train_tokens_per_second": 5924.883
|
|
},
|
|
{
|
|
"epoch": 1.246,
|
|
"grad_norm": 0.550828167386558,
|
|
"learning_rate": 3.1185552693831595e-06,
|
|
"loss": 0.1482,
|
|
"num_input_tokens_seen": 244055008,
|
|
"step": 3115,
|
|
"train_runtime": 41197.374,
|
|
"train_tokens_per_second": 5924.043
|
|
},
|
|
{
|
|
"epoch": 1.248,
|
|
"grad_norm": 0.6775912628994292,
|
|
"learning_rate": 3.1040111127836994e-06,
|
|
"loss": 0.1644,
|
|
"num_input_tokens_seen": 244411056,
|
|
"step": 3120,
|
|
"train_runtime": 41254.3234,
|
|
"train_tokens_per_second": 5924.496
|
|
},
|
|
{
|
|
"epoch": 1.25,
|
|
"grad_norm": 0.7087611032845899,
|
|
"learning_rate": 3.089485668829113e-06,
|
|
"loss": 0.1562,
|
|
"num_input_tokens_seen": 244801856,
|
|
"step": 3125,
|
|
"train_runtime": 41317.0315,
|
|
"train_tokens_per_second": 5924.962
|
|
},
|
|
{
|
|
"epoch": 1.252,
|
|
"grad_norm": 0.671755840044814,
|
|
"learning_rate": 3.074979080879671e-06,
|
|
"loss": 0.1669,
|
|
"num_input_tokens_seen": 245303888,
|
|
"step": 3130,
|
|
"train_runtime": 41393.7568,
|
|
"train_tokens_per_second": 5926.108
|
|
},
|
|
{
|
|
"epoch": 1.254,
|
|
"grad_norm": 0.8854341953884204,
|
|
"learning_rate": 3.0604914921095373e-06,
|
|
"loss": 0.1616,
|
|
"num_input_tokens_seen": 245696576,
|
|
"step": 3135,
|
|
"train_runtime": 41471.6223,
|
|
"train_tokens_per_second": 5924.451
|
|
},
|
|
{
|
|
"epoch": 1.256,
|
|
"grad_norm": 0.9344280187391603,
|
|
"learning_rate": 3.046023045505366e-06,
|
|
"loss": 0.1582,
|
|
"num_input_tokens_seen": 246072144,
|
|
"step": 3140,
|
|
"train_runtime": 41539.1221,
|
|
"train_tokens_per_second": 5923.865
|
|
},
|
|
{
|
|
"epoch": 1.258,
|
|
"grad_norm": 0.7130633350935699,
|
|
"learning_rate": 3.031573883864882e-06,
|
|
"loss": 0.1639,
|
|
"num_input_tokens_seen": 246507184,
|
|
"step": 3145,
|
|
"train_runtime": 41617.5598,
|
|
"train_tokens_per_second": 5923.153
|
|
},
|
|
{
|
|
"epoch": 1.26,
|
|
"grad_norm": 0.8510568678796733,
|
|
"learning_rate": 3.0171441497954807e-06,
|
|
"loss": 0.1395,
|
|
"num_input_tokens_seen": 246873408,
|
|
"step": 3150,
|
|
"train_runtime": 41681.8426,
|
|
"train_tokens_per_second": 5922.805
|
|
},
|
|
{
|
|
"epoch": 1.262,
|
|
"grad_norm": 0.7775351635430708,
|
|
"learning_rate": 3.002733985712808e-06,
|
|
"loss": 0.1715,
|
|
"num_input_tokens_seen": 247320912,
|
|
"step": 3155,
|
|
"train_runtime": 41745.1701,
|
|
"train_tokens_per_second": 5924.54
|
|
},
|
|
{
|
|
"epoch": 1.264,
|
|
"grad_norm": 0.9645462964971862,
|
|
"learning_rate": 2.9883435338393674e-06,
|
|
"loss": 0.1814,
|
|
"num_input_tokens_seen": 247653568,
|
|
"step": 3160,
|
|
"train_runtime": 41810.0185,
|
|
"train_tokens_per_second": 5923.307
|
|
},
|
|
{
|
|
"epoch": 1.266,
|
|
"grad_norm": 0.9066188936891787,
|
|
"learning_rate": 2.97397293620311e-06,
|
|
"loss": 0.1655,
|
|
"num_input_tokens_seen": 248031600,
|
|
"step": 3165,
|
|
"train_runtime": 41883.9078,
|
|
"train_tokens_per_second": 5921.883
|
|
},
|
|
{
|
|
"epoch": 1.268,
|
|
"grad_norm": 0.6535637643312067,
|
|
"learning_rate": 2.959622334636031e-06,
|
|
"loss": 0.1643,
|
|
"num_input_tokens_seen": 248424528,
|
|
"step": 3170,
|
|
"train_runtime": 41955.6238,
|
|
"train_tokens_per_second": 5921.126
|
|
},
|
|
{
|
|
"epoch": 1.27,
|
|
"grad_norm": 0.776964268072871,
|
|
"learning_rate": 2.945291870772776e-06,
|
|
"loss": 0.1791,
|
|
"num_input_tokens_seen": 248832000,
|
|
"step": 3175,
|
|
"train_runtime": 42025.4971,
|
|
"train_tokens_per_second": 5920.977
|
|
},
|
|
{
|
|
"epoch": 1.272,
|
|
"grad_norm": 0.7762244233066542,
|
|
"learning_rate": 2.930981686049237e-06,
|
|
"loss": 0.1572,
|
|
"num_input_tokens_seen": 249175552,
|
|
"step": 3180,
|
|
"train_runtime": 42086.5097,
|
|
"train_tokens_per_second": 5920.556
|
|
},
|
|
{
|
|
"epoch": 1.274,
|
|
"grad_norm": 0.7373577512254087,
|
|
"learning_rate": 2.91669192170116e-06,
|
|
"loss": 0.1537,
|
|
"num_input_tokens_seen": 249553200,
|
|
"step": 3185,
|
|
"train_runtime": 42153.488,
|
|
"train_tokens_per_second": 5920.108
|
|
},
|
|
{
|
|
"epoch": 1.276,
|
|
"grad_norm": 0.8257165963992682,
|
|
"learning_rate": 2.902422718762752e-06,
|
|
"loss": 0.1632,
|
|
"num_input_tokens_seen": 249943936,
|
|
"step": 3190,
|
|
"train_runtime": 42216.3349,
|
|
"train_tokens_per_second": 5920.55
|
|
},
|
|
{
|
|
"epoch": 1.278,
|
|
"grad_norm": 0.8128476390270747,
|
|
"learning_rate": 2.8881742180652813e-06,
|
|
"loss": 0.1657,
|
|
"num_input_tokens_seen": 250358672,
|
|
"step": 3195,
|
|
"train_runtime": 42287.7269,
|
|
"train_tokens_per_second": 5920.362
|
|
},
|
|
{
|
|
"epoch": 1.28,
|
|
"grad_norm": 0.7646471737046436,
|
|
"learning_rate": 2.8739465602357014e-06,
|
|
"loss": 0.1622,
|
|
"num_input_tokens_seen": 250754560,
|
|
"step": 3200,
|
|
"train_runtime": 42363.4427,
|
|
"train_tokens_per_second": 5919.126
|
|
},
|
|
{
|
|
"epoch": 1.282,
|
|
"grad_norm": 0.8530492677177867,
|
|
"learning_rate": 2.8597398856952473e-06,
|
|
"loss": 0.166,
|
|
"num_input_tokens_seen": 251117984,
|
|
"step": 3205,
|
|
"train_runtime": 42429.7577,
|
|
"train_tokens_per_second": 5918.44
|
|
},
|
|
{
|
|
"epoch": 1.284,
|
|
"grad_norm": 0.6891207555109584,
|
|
"learning_rate": 2.845554334658066e-06,
|
|
"loss": 0.1619,
|
|
"num_input_tokens_seen": 251519024,
|
|
"step": 3210,
|
|
"train_runtime": 42500.5549,
|
|
"train_tokens_per_second": 5918.017
|
|
},
|
|
{
|
|
"epoch": 1.286,
|
|
"grad_norm": 0.6286038787283127,
|
|
"learning_rate": 2.831390047129815e-06,
|
|
"loss": 0.1561,
|
|
"num_input_tokens_seen": 251863440,
|
|
"step": 3215,
|
|
"train_runtime": 42557.732,
|
|
"train_tokens_per_second": 5918.159
|
|
},
|
|
{
|
|
"epoch": 1.288,
|
|
"grad_norm": 0.6954233683193354,
|
|
"learning_rate": 2.817247162906297e-06,
|
|
"loss": 0.1666,
|
|
"num_input_tokens_seen": 252342144,
|
|
"step": 3220,
|
|
"train_runtime": 42635.7387,
|
|
"train_tokens_per_second": 5918.559
|
|
},
|
|
{
|
|
"epoch": 1.29,
|
|
"grad_norm": 1.2912645764370834,
|
|
"learning_rate": 2.803125821572068e-06,
|
|
"loss": 0.1488,
|
|
"num_input_tokens_seen": 252714960,
|
|
"step": 3225,
|
|
"train_runtime": 42710.0498,
|
|
"train_tokens_per_second": 5916.991
|
|
},
|
|
{
|
|
"epoch": 1.292,
|
|
"grad_norm": 0.7779010609742523,
|
|
"learning_rate": 2.7890261624990643e-06,
|
|
"loss": 0.1654,
|
|
"num_input_tokens_seen": 253093040,
|
|
"step": 3230,
|
|
"train_runtime": 42773.4184,
|
|
"train_tokens_per_second": 5917.064
|
|
},
|
|
{
|
|
"epoch": 1.294,
|
|
"grad_norm": 0.8348611236125332,
|
|
"learning_rate": 2.7749483248452324e-06,
|
|
"loss": 0.1564,
|
|
"num_input_tokens_seen": 253534096,
|
|
"step": 3235,
|
|
"train_runtime": 42852.1371,
|
|
"train_tokens_per_second": 5916.487
|
|
},
|
|
{
|
|
"epoch": 1.296,
|
|
"grad_norm": 0.7339152402479057,
|
|
"learning_rate": 2.760892447553143e-06,
|
|
"loss": 0.1615,
|
|
"num_input_tokens_seen": 253877168,
|
|
"step": 3240,
|
|
"train_runtime": 42909.3874,
|
|
"train_tokens_per_second": 5916.588
|
|
},
|
|
{
|
|
"epoch": 1.298,
|
|
"grad_norm": 0.7276311865781885,
|
|
"learning_rate": 2.746858669348634e-06,
|
|
"loss": 0.1518,
|
|
"num_input_tokens_seen": 254340192,
|
|
"step": 3245,
|
|
"train_runtime": 42983.7231,
|
|
"train_tokens_per_second": 5917.128
|
|
},
|
|
{
|
|
"epoch": 1.3,
|
|
"grad_norm": 0.7564142166342812,
|
|
"learning_rate": 2.7328471287394265e-06,
|
|
"loss": 0.173,
|
|
"num_input_tokens_seen": 254712384,
|
|
"step": 3250,
|
|
"train_runtime": 43055.0532,
|
|
"train_tokens_per_second": 5915.97
|
|
},
|
|
{
|
|
"epoch": 1.302,
|
|
"grad_norm": 0.8935746595628307,
|
|
"learning_rate": 2.718857964013773e-06,
|
|
"loss": 0.1619,
|
|
"num_input_tokens_seen": 255079824,
|
|
"step": 3255,
|
|
"train_runtime": 43116.5739,
|
|
"train_tokens_per_second": 5916.05
|
|
},
|
|
{
|
|
"epoch": 1.304,
|
|
"grad_norm": 0.6831223745333709,
|
|
"learning_rate": 2.7048913132390787e-06,
|
|
"loss": 0.1559,
|
|
"num_input_tokens_seen": 255544896,
|
|
"step": 3260,
|
|
"train_runtime": 43187.2601,
|
|
"train_tokens_per_second": 5917.136
|
|
},
|
|
{
|
|
"epoch": 1.306,
|
|
"grad_norm": 0.9387199489260992,
|
|
"learning_rate": 2.6909473142605522e-06,
|
|
"loss": 0.1604,
|
|
"num_input_tokens_seen": 255937552,
|
|
"step": 3265,
|
|
"train_runtime": 43249.3196,
|
|
"train_tokens_per_second": 5917.724
|
|
},
|
|
{
|
|
"epoch": 1.308,
|
|
"grad_norm": 0.6805034841314415,
|
|
"learning_rate": 2.6770261046998315e-06,
|
|
"loss": 0.1509,
|
|
"num_input_tokens_seen": 256399136,
|
|
"step": 3270,
|
|
"train_runtime": 43324.4225,
|
|
"train_tokens_per_second": 5918.12
|
|
},
|
|
{
|
|
"epoch": 1.31,
|
|
"grad_norm": 1.0364186827205375,
|
|
"learning_rate": 2.663127821953633e-06,
|
|
"loss": 0.1676,
|
|
"num_input_tokens_seen": 256726480,
|
|
"step": 3275,
|
|
"train_runtime": 43388.856,
|
|
"train_tokens_per_second": 5916.876
|
|
},
|
|
{
|
|
"epoch": 1.312,
|
|
"grad_norm": 0.7558495047876609,
|
|
"learning_rate": 2.6492526031924005e-06,
|
|
"loss": 0.1677,
|
|
"num_input_tokens_seen": 257112800,
|
|
"step": 3280,
|
|
"train_runtime": 43455.7903,
|
|
"train_tokens_per_second": 5916.652
|
|
},
|
|
{
|
|
"epoch": 1.314,
|
|
"grad_norm": 0.5980806083914143,
|
|
"learning_rate": 2.635400585358937e-06,
|
|
"loss": 0.1699,
|
|
"num_input_tokens_seen": 257521472,
|
|
"step": 3285,
|
|
"train_runtime": 43513.7104,
|
|
"train_tokens_per_second": 5918.169
|
|
},
|
|
{
|
|
"epoch": 1.316,
|
|
"grad_norm": 0.8992052140691096,
|
|
"learning_rate": 2.6215719051670705e-06,
|
|
"loss": 0.164,
|
|
"num_input_tokens_seen": 257892352,
|
|
"step": 3290,
|
|
"train_runtime": 43582.7229,
|
|
"train_tokens_per_second": 5917.307
|
|
},
|
|
{
|
|
"epoch": 1.318,
|
|
"grad_norm": 0.813940297189925,
|
|
"learning_rate": 2.607766699100288e-06,
|
|
"loss": 0.1548,
|
|
"num_input_tokens_seen": 258258560,
|
|
"step": 3295,
|
|
"train_runtime": 43644.9456,
|
|
"train_tokens_per_second": 5917.262
|
|
},
|
|
{
|
|
"epoch": 1.32,
|
|
"grad_norm": 0.6532369480179456,
|
|
"learning_rate": 2.5939851034104035e-06,
|
|
"loss": 0.1614,
|
|
"num_input_tokens_seen": 258634672,
|
|
"step": 3300,
|
|
"train_runtime": 43713.1256,
|
|
"train_tokens_per_second": 5916.636
|
|
},
|
|
{
|
|
"epoch": 1.322,
|
|
"grad_norm": 0.6428583381101993,
|
|
"learning_rate": 2.580227254116199e-06,
|
|
"loss": 0.1577,
|
|
"num_input_tokens_seen": 259033664,
|
|
"step": 3305,
|
|
"train_runtime": 43778.0144,
|
|
"train_tokens_per_second": 5916.981
|
|
},
|
|
{
|
|
"epoch": 1.324,
|
|
"grad_norm": 0.6657006866349452,
|
|
"learning_rate": 2.5664932870020966e-06,
|
|
"loss": 0.1719,
|
|
"num_input_tokens_seen": 259396128,
|
|
"step": 3310,
|
|
"train_runtime": 43844.1232,
|
|
"train_tokens_per_second": 5916.326
|
|
},
|
|
{
|
|
"epoch": 1.326,
|
|
"grad_norm": 0.8000719535948124,
|
|
"learning_rate": 2.5527833376168055e-06,
|
|
"loss": 0.1672,
|
|
"num_input_tokens_seen": 259854000,
|
|
"step": 3315,
|
|
"train_runtime": 43911.7043,
|
|
"train_tokens_per_second": 5917.648
|
|
},
|
|
{
|
|
"epoch": 1.328,
|
|
"grad_norm": 0.822202135733305,
|
|
"learning_rate": 2.5390975412719897e-06,
|
|
"loss": 0.157,
|
|
"num_input_tokens_seen": 260216000,
|
|
"step": 3320,
|
|
"train_runtime": 43969.6142,
|
|
"train_tokens_per_second": 5918.087
|
|
},
|
|
{
|
|
"epoch": 1.33,
|
|
"grad_norm": 0.7161314906432911,
|
|
"learning_rate": 2.5254360330409343e-06,
|
|
"loss": 0.1788,
|
|
"num_input_tokens_seen": 260648016,
|
|
"step": 3325,
|
|
"train_runtime": 44042.8511,
|
|
"train_tokens_per_second": 5918.055
|
|
},
|
|
{
|
|
"epoch": 1.332,
|
|
"grad_norm": 0.6228455429058426,
|
|
"learning_rate": 2.5117989477572126e-06,
|
|
"loss": 0.1476,
|
|
"num_input_tokens_seen": 261051520,
|
|
"step": 3330,
|
|
"train_runtime": 44115.0395,
|
|
"train_tokens_per_second": 5917.518
|
|
},
|
|
{
|
|
"epoch": 1.334,
|
|
"grad_norm": 0.7916484998008849,
|
|
"learning_rate": 2.4981864200133483e-06,
|
|
"loss": 0.1646,
|
|
"num_input_tokens_seen": 261412496,
|
|
"step": 3335,
|
|
"train_runtime": 44182.5012,
|
|
"train_tokens_per_second": 5916.652
|
|
},
|
|
{
|
|
"epoch": 1.336,
|
|
"grad_norm": 0.6651031840130643,
|
|
"learning_rate": 2.484598584159494e-06,
|
|
"loss": 0.1568,
|
|
"num_input_tokens_seen": 261753792,
|
|
"step": 3340,
|
|
"train_runtime": 44243.6228,
|
|
"train_tokens_per_second": 5916.193
|
|
},
|
|
{
|
|
"epoch": 1.338,
|
|
"grad_norm": 0.9722609304905037,
|
|
"learning_rate": 2.4710355743021077e-06,
|
|
"loss": 0.1666,
|
|
"num_input_tokens_seen": 262177136,
|
|
"step": 3345,
|
|
"train_runtime": 44311.5134,
|
|
"train_tokens_per_second": 5916.682
|
|
},
|
|
{
|
|
"epoch": 1.34,
|
|
"grad_norm": 0.984542406464338,
|
|
"learning_rate": 2.457497524302616e-06,
|
|
"loss": 0.1648,
|
|
"num_input_tokens_seen": 262546256,
|
|
"step": 3350,
|
|
"train_runtime": 44370.6059,
|
|
"train_tokens_per_second": 5917.121
|
|
},
|
|
{
|
|
"epoch": 1.342,
|
|
"grad_norm": 0.7695626696226255,
|
|
"learning_rate": 2.4439845677761124e-06,
|
|
"loss": 0.1685,
|
|
"num_input_tokens_seen": 262941872,
|
|
"step": 3355,
|
|
"train_runtime": 44436.3901,
|
|
"train_tokens_per_second": 5917.264
|
|
},
|
|
{
|
|
"epoch": 1.3439999999999999,
|
|
"grad_norm": 0.7079714815933946,
|
|
"learning_rate": 2.430496838090017e-06,
|
|
"loss": 0.1571,
|
|
"num_input_tokens_seen": 263313296,
|
|
"step": 3360,
|
|
"train_runtime": 44500.6796,
|
|
"train_tokens_per_second": 5917.062
|
|
},
|
|
{
|
|
"epoch": 1.346,
|
|
"grad_norm": 0.6442945680488377,
|
|
"learning_rate": 2.417034468362782e-06,
|
|
"loss": 0.157,
|
|
"num_input_tokens_seen": 263787248,
|
|
"step": 3365,
|
|
"train_runtime": 44578.6134,
|
|
"train_tokens_per_second": 5917.35
|
|
},
|
|
{
|
|
"epoch": 1.3479999999999999,
|
|
"grad_norm": 0.7805989978825958,
|
|
"learning_rate": 2.403597591462557e-06,
|
|
"loss": 0.1776,
|
|
"num_input_tokens_seen": 264157904,
|
|
"step": 3370,
|
|
"train_runtime": 44642.2937,
|
|
"train_tokens_per_second": 5917.212
|
|
},
|
|
{
|
|
"epoch": 1.35,
|
|
"grad_norm": 0.9329090164798857,
|
|
"learning_rate": 2.3901863400058954e-06,
|
|
"loss": 0.1713,
|
|
"num_input_tokens_seen": 264551248,
|
|
"step": 3375,
|
|
"train_runtime": 44701.3264,
|
|
"train_tokens_per_second": 5918.197
|
|
},
|
|
{
|
|
"epoch": 1.3519999999999999,
|
|
"grad_norm": 0.8147375095413973,
|
|
"learning_rate": 2.376800846356434e-06,
|
|
"loss": 0.1594,
|
|
"num_input_tokens_seen": 264916240,
|
|
"step": 3380,
|
|
"train_runtime": 44756.8792,
|
|
"train_tokens_per_second": 5919.006
|
|
},
|
|
{
|
|
"epoch": 1.354,
|
|
"grad_norm": 0.7856198693751099,
|
|
"learning_rate": 2.3634412426235886e-06,
|
|
"loss": 0.154,
|
|
"num_input_tokens_seen": 265281024,
|
|
"step": 3385,
|
|
"train_runtime": 44814.9565,
|
|
"train_tokens_per_second": 5919.475
|
|
},
|
|
{
|
|
"epoch": 1.3559999999999999,
|
|
"grad_norm": 0.8670101446125132,
|
|
"learning_rate": 2.3501076606612587e-06,
|
|
"loss": 0.1657,
|
|
"num_input_tokens_seen": 265682112,
|
|
"step": 3390,
|
|
"train_runtime": 44881.1591,
|
|
"train_tokens_per_second": 5919.68
|
|
},
|
|
{
|
|
"epoch": 1.358,
|
|
"grad_norm": 0.6876212628735606,
|
|
"learning_rate": 2.3368002320665118e-06,
|
|
"loss": 0.1581,
|
|
"num_input_tokens_seen": 266105504,
|
|
"step": 3395,
|
|
"train_runtime": 44954.5086,
|
|
"train_tokens_per_second": 5919.44
|
|
},
|
|
{
|
|
"epoch": 1.3599999999999999,
|
|
"grad_norm": 0.9143282304439698,
|
|
"learning_rate": 2.323519088178299e-06,
|
|
"loss": 0.1688,
|
|
"num_input_tokens_seen": 266487728,
|
|
"step": 3400,
|
|
"train_runtime": 45022.0586,
|
|
"train_tokens_per_second": 5919.048
|
|
},
|
|
{
|
|
"epoch": 1.362,
|
|
"grad_norm": 0.8422086024571543,
|
|
"learning_rate": 2.3102643600761445e-06,
|
|
"loss": 0.1658,
|
|
"num_input_tokens_seen": 266804880,
|
|
"step": 3405,
|
|
"train_runtime": 45070.8272,
|
|
"train_tokens_per_second": 5919.68
|
|
},
|
|
{
|
|
"epoch": 1.3639999999999999,
|
|
"grad_norm": 0.9413574952585082,
|
|
"learning_rate": 2.2970361785788673e-06,
|
|
"loss": 0.1712,
|
|
"num_input_tokens_seen": 267089664,
|
|
"step": 3410,
|
|
"train_runtime": 45107.2251,
|
|
"train_tokens_per_second": 5921.217
|
|
},
|
|
{
|
|
"epoch": 1.366,
|
|
"grad_norm": 0.8801247630953964,
|
|
"learning_rate": 2.2838346742432753e-06,
|
|
"loss": 0.1602,
|
|
"num_input_tokens_seen": 267493472,
|
|
"step": 3415,
|
|
"train_runtime": 45174.2728,
|
|
"train_tokens_per_second": 5921.368
|
|
},
|
|
{
|
|
"epoch": 1.3679999999999999,
|
|
"grad_norm": 0.7240749138563003,
|
|
"learning_rate": 2.2706599773628906e-06,
|
|
"loss": 0.1424,
|
|
"num_input_tokens_seen": 267800368,
|
|
"step": 3420,
|
|
"train_runtime": 45229.5918,
|
|
"train_tokens_per_second": 5920.911
|
|
},
|
|
{
|
|
"epoch": 1.37,
|
|
"grad_norm": 1.0053581927960462,
|
|
"learning_rate": 2.25751221796665e-06,
|
|
"loss": 0.1604,
|
|
"num_input_tokens_seen": 268160336,
|
|
"step": 3425,
|
|
"train_runtime": 45286.4151,
|
|
"train_tokens_per_second": 5921.43
|
|
},
|
|
{
|
|
"epoch": 1.3719999999999999,
|
|
"grad_norm": 0.7139195236329295,
|
|
"learning_rate": 2.2443915258176283e-06,
|
|
"loss": 0.1704,
|
|
"num_input_tokens_seen": 268535248,
|
|
"step": 3430,
|
|
"train_runtime": 45349.9427,
|
|
"train_tokens_per_second": 5921.402
|
|
},
|
|
{
|
|
"epoch": 1.374,
|
|
"grad_norm": 0.78422140489144,
|
|
"learning_rate": 2.2312980304117656e-06,
|
|
"loss": 0.1633,
|
|
"num_input_tokens_seen": 268962320,
|
|
"step": 3435,
|
|
"train_runtime": 45422.8264,
|
|
"train_tokens_per_second": 5921.303
|
|
},
|
|
{
|
|
"epoch": 1.376,
|
|
"grad_norm": 1.0813375023090641,
|
|
"learning_rate": 2.2182318609765703e-06,
|
|
"loss": 0.1599,
|
|
"num_input_tokens_seen": 269273584,
|
|
"step": 3440,
|
|
"train_runtime": 45470.068,
|
|
"train_tokens_per_second": 5921.997
|
|
},
|
|
{
|
|
"epoch": 1.3780000000000001,
|
|
"grad_norm": 1.039109997760742,
|
|
"learning_rate": 2.2051931464698636e-06,
|
|
"loss": 0.1588,
|
|
"num_input_tokens_seen": 269618864,
|
|
"step": 3445,
|
|
"train_runtime": 45528.1781,
|
|
"train_tokens_per_second": 5922.022
|
|
},
|
|
{
|
|
"epoch": 1.38,
|
|
"grad_norm": 0.7492310498974429,
|
|
"learning_rate": 2.19218201557849e-06,
|
|
"loss": 0.1642,
|
|
"num_input_tokens_seen": 270000000,
|
|
"step": 3450,
|
|
"train_runtime": 45587.9089,
|
|
"train_tokens_per_second": 5922.623
|
|
},
|
|
{
|
|
"epoch": 1.3820000000000001,
|
|
"grad_norm": 0.9152884810547635,
|
|
"learning_rate": 2.179198596717063e-06,
|
|
"loss": 0.1585,
|
|
"num_input_tokens_seen": 270358256,
|
|
"step": 3455,
|
|
"train_runtime": 45631.5112,
|
|
"train_tokens_per_second": 5924.815
|
|
},
|
|
{
|
|
"epoch": 1.384,
|
|
"grad_norm": 0.7724536269842872,
|
|
"learning_rate": 2.1662430180266808e-06,
|
|
"loss": 0.1493,
|
|
"num_input_tokens_seen": 270752928,
|
|
"step": 3460,
|
|
"train_runtime": 45692.8325,
|
|
"train_tokens_per_second": 5925.501
|
|
},
|
|
{
|
|
"epoch": 1.3860000000000001,
|
|
"grad_norm": 0.8628553249819737,
|
|
"learning_rate": 2.153315407373679e-06,
|
|
"loss": 0.1592,
|
|
"num_input_tokens_seen": 271107200,
|
|
"step": 3465,
|
|
"train_runtime": 45748.4706,
|
|
"train_tokens_per_second": 5926.039
|
|
},
|
|
{
|
|
"epoch": 1.388,
|
|
"grad_norm": 0.8893492591724887,
|
|
"learning_rate": 2.1404158923483524e-06,
|
|
"loss": 0.1634,
|
|
"num_input_tokens_seen": 271433216,
|
|
"step": 3470,
|
|
"train_runtime": 45809.4912,
|
|
"train_tokens_per_second": 5925.262
|
|
},
|
|
{
|
|
"epoch": 1.3900000000000001,
|
|
"grad_norm": 0.6668075154572731,
|
|
"learning_rate": 2.1275446002637063e-06,
|
|
"loss": 0.1663,
|
|
"num_input_tokens_seen": 271802272,
|
|
"step": 3475,
|
|
"train_runtime": 45865.6472,
|
|
"train_tokens_per_second": 5926.053
|
|
},
|
|
{
|
|
"epoch": 1.392,
|
|
"grad_norm": 0.6380682100859386,
|
|
"learning_rate": 2.1147016581542e-06,
|
|
"loss": 0.1663,
|
|
"num_input_tokens_seen": 272124656,
|
|
"step": 3480,
|
|
"train_runtime": 45909.1459,
|
|
"train_tokens_per_second": 5927.461
|
|
},
|
|
{
|
|
"epoch": 1.3940000000000001,
|
|
"grad_norm": 0.8327094191494121,
|
|
"learning_rate": 2.1018871927744844e-06,
|
|
"loss": 0.1606,
|
|
"num_input_tokens_seen": 272526576,
|
|
"step": 3485,
|
|
"train_runtime": 45964.9817,
|
|
"train_tokens_per_second": 5929.004
|
|
},
|
|
{
|
|
"epoch": 1.396,
|
|
"grad_norm": 0.6626172180102655,
|
|
"learning_rate": 2.0891013305981615e-06,
|
|
"loss": 0.1777,
|
|
"num_input_tokens_seen": 272960928,
|
|
"step": 3490,
|
|
"train_runtime": 46038.941,
|
|
"train_tokens_per_second": 5928.914
|
|
},
|
|
{
|
|
"epoch": 1.3980000000000001,
|
|
"grad_norm": 0.8864352806591932,
|
|
"learning_rate": 2.076344197816527e-06,
|
|
"loss": 0.159,
|
|
"num_input_tokens_seen": 273359360,
|
|
"step": 3495,
|
|
"train_runtime": 46106.2762,
|
|
"train_tokens_per_second": 5928.897
|
|
},
|
|
{
|
|
"epoch": 1.4,
|
|
"grad_norm": 1.0689235023691157,
|
|
"learning_rate": 2.0636159203373344e-06,
|
|
"loss": 0.1688,
|
|
"num_input_tokens_seen": 273776336,
|
|
"step": 3500,
|
|
"train_runtime": 46176.8915,
|
|
"train_tokens_per_second": 5928.86
|
|
},
|
|
{
|
|
"epoch": 1.4020000000000001,
|
|
"grad_norm": 0.6950832286250193,
|
|
"learning_rate": 2.0509166237835398e-06,
|
|
"loss": 0.1531,
|
|
"num_input_tokens_seen": 274174848,
|
|
"step": 3505,
|
|
"train_runtime": 46240.328,
|
|
"train_tokens_per_second": 5929.345
|
|
},
|
|
{
|
|
"epoch": 1.404,
|
|
"grad_norm": 0.6214713725746865,
|
|
"learning_rate": 2.0382464334920774e-06,
|
|
"loss": 0.1608,
|
|
"num_input_tokens_seen": 274657952,
|
|
"step": 3510,
|
|
"train_runtime": 46312.2065,
|
|
"train_tokens_per_second": 5930.574
|
|
},
|
|
{
|
|
"epoch": 1.4060000000000001,
|
|
"grad_norm": 0.6835174204746227,
|
|
"learning_rate": 2.025605474512608e-06,
|
|
"loss": 0.15,
|
|
"num_input_tokens_seen": 275033072,
|
|
"step": 3515,
|
|
"train_runtime": 46373.5523,
|
|
"train_tokens_per_second": 5930.817
|
|
},
|
|
{
|
|
"epoch": 1.408,
|
|
"grad_norm": 0.7799020382770737,
|
|
"learning_rate": 2.0129938716062917e-06,
|
|
"loss": 0.1671,
|
|
"num_input_tokens_seen": 275362944,
|
|
"step": 3520,
|
|
"train_runtime": 46433.6607,
|
|
"train_tokens_per_second": 5930.244
|
|
},
|
|
{
|
|
"epoch": 1.41,
|
|
"grad_norm": 0.6362165159024328,
|
|
"learning_rate": 2.0004117492445614e-06,
|
|
"loss": 0.1481,
|
|
"num_input_tokens_seen": 275762640,
|
|
"step": 3525,
|
|
"train_runtime": 46510.5851,
|
|
"train_tokens_per_second": 5929.03
|
|
},
|
|
{
|
|
"epoch": 1.412,
|
|
"grad_norm": 0.6774039235399333,
|
|
"learning_rate": 1.9878592316078813e-06,
|
|
"loss": 0.1511,
|
|
"num_input_tokens_seen": 276174128,
|
|
"step": 3530,
|
|
"train_runtime": 46576.4046,
|
|
"train_tokens_per_second": 5929.486
|
|
},
|
|
{
|
|
"epoch": 1.414,
|
|
"grad_norm": 0.8041300374257803,
|
|
"learning_rate": 1.975336442584537e-06,
|
|
"loss": 0.1509,
|
|
"num_input_tokens_seen": 276565680,
|
|
"step": 3535,
|
|
"train_runtime": 46644.2245,
|
|
"train_tokens_per_second": 5929.259
|
|
},
|
|
{
|
|
"epoch": 1.416,
|
|
"grad_norm": 0.6161702240382638,
|
|
"learning_rate": 1.9628435057693963e-06,
|
|
"loss": 0.1595,
|
|
"num_input_tokens_seen": 276941040,
|
|
"step": 3540,
|
|
"train_runtime": 46714.76,
|
|
"train_tokens_per_second": 5928.341
|
|
},
|
|
{
|
|
"epoch": 1.418,
|
|
"grad_norm": 0.7110979323675918,
|
|
"learning_rate": 1.9503805444627054e-06,
|
|
"loss": 0.1604,
|
|
"num_input_tokens_seen": 277400160,
|
|
"step": 3545,
|
|
"train_runtime": 46787.685,
|
|
"train_tokens_per_second": 5928.914
|
|
},
|
|
{
|
|
"epoch": 1.42,
|
|
"grad_norm": 0.7274432684526562,
|
|
"learning_rate": 1.937947681668858e-06,
|
|
"loss": 0.1483,
|
|
"num_input_tokens_seen": 277738800,
|
|
"step": 3550,
|
|
"train_runtime": 46840.7859,
|
|
"train_tokens_per_second": 5929.422
|
|
},
|
|
{
|
|
"epoch": 1.422,
|
|
"grad_norm": 0.7150895551437593,
|
|
"learning_rate": 1.9255450400951937e-06,
|
|
"loss": 0.1545,
|
|
"num_input_tokens_seen": 278133904,
|
|
"step": 3555,
|
|
"train_runtime": 46897.7755,
|
|
"train_tokens_per_second": 5930.642
|
|
},
|
|
{
|
|
"epoch": 1.424,
|
|
"grad_norm": 0.7276963772399333,
|
|
"learning_rate": 1.913172742150774e-06,
|
|
"loss": 0.1719,
|
|
"num_input_tokens_seen": 278502048,
|
|
"step": 3560,
|
|
"train_runtime": 46969.1653,
|
|
"train_tokens_per_second": 5929.466
|
|
},
|
|
{
|
|
"epoch": 1.426,
|
|
"grad_norm": 0.6348868767790892,
|
|
"learning_rate": 1.900830909945189e-06,
|
|
"loss": 0.1564,
|
|
"num_input_tokens_seen": 278939024,
|
|
"step": 3565,
|
|
"train_runtime": 47046.1776,
|
|
"train_tokens_per_second": 5929.048
|
|
},
|
|
{
|
|
"epoch": 1.428,
|
|
"grad_norm": 0.671235167124699,
|
|
"learning_rate": 1.8885196652873372e-06,
|
|
"loss": 0.1466,
|
|
"num_input_tokens_seen": 279267216,
|
|
"step": 3570,
|
|
"train_runtime": 47111.668,
|
|
"train_tokens_per_second": 5927.772
|
|
},
|
|
{
|
|
"epoch": 1.43,
|
|
"grad_norm": 1.898051394985332,
|
|
"learning_rate": 1.876239129684232e-06,
|
|
"loss": 0.1859,
|
|
"num_input_tokens_seen": 279700784,
|
|
"step": 3575,
|
|
"train_runtime": 47180.459,
|
|
"train_tokens_per_second": 5928.318
|
|
},
|
|
{
|
|
"epoch": 1.432,
|
|
"grad_norm": 0.7842508078959054,
|
|
"learning_rate": 1.8639894243398055e-06,
|
|
"loss": 0.1595,
|
|
"num_input_tokens_seen": 280056448,
|
|
"step": 3580,
|
|
"train_runtime": 47244.8125,
|
|
"train_tokens_per_second": 5927.771
|
|
},
|
|
{
|
|
"epoch": 1.434,
|
|
"grad_norm": 0.7410998818580086,
|
|
"learning_rate": 1.8517706701536998e-06,
|
|
"loss": 0.1596,
|
|
"num_input_tokens_seen": 280414336,
|
|
"step": 3585,
|
|
"train_runtime": 47305.37,
|
|
"train_tokens_per_second": 5927.749
|
|
},
|
|
{
|
|
"epoch": 1.436,
|
|
"grad_norm": 0.8700763169768161,
|
|
"learning_rate": 1.8395829877200904e-06,
|
|
"loss": 0.1472,
|
|
"num_input_tokens_seen": 280832880,
|
|
"step": 3590,
|
|
"train_runtime": 47370.204,
|
|
"train_tokens_per_second": 5928.471
|
|
},
|
|
{
|
|
"epoch": 1.438,
|
|
"grad_norm": 0.7509665576666095,
|
|
"learning_rate": 1.8274264973264782e-06,
|
|
"loss": 0.1507,
|
|
"num_input_tokens_seen": 281229968,
|
|
"step": 3595,
|
|
"train_runtime": 47443.3851,
|
|
"train_tokens_per_second": 5927.696
|
|
},
|
|
{
|
|
"epoch": 1.44,
|
|
"grad_norm": 0.8113536511822692,
|
|
"learning_rate": 1.8153013189525192e-06,
|
|
"loss": 0.163,
|
|
"num_input_tokens_seen": 281613376,
|
|
"step": 3600,
|
|
"train_runtime": 47506.0482,
|
|
"train_tokens_per_second": 5927.948
|
|
},
|
|
{
|
|
"epoch": 1.442,
|
|
"grad_norm": 0.6115394498148928,
|
|
"learning_rate": 1.803207572268826e-06,
|
|
"loss": 0.1731,
|
|
"num_input_tokens_seen": 282032944,
|
|
"step": 3605,
|
|
"train_runtime": 47563.5879,
|
|
"train_tokens_per_second": 5929.598
|
|
},
|
|
{
|
|
"epoch": 1.444,
|
|
"grad_norm": 0.6405955225670742,
|
|
"learning_rate": 1.7911453766357983e-06,
|
|
"loss": 0.1618,
|
|
"num_input_tokens_seen": 282389792,
|
|
"step": 3610,
|
|
"train_runtime": 47626.033,
|
|
"train_tokens_per_second": 5929.316
|
|
},
|
|
{
|
|
"epoch": 1.446,
|
|
"grad_norm": 0.6130313201579569,
|
|
"learning_rate": 1.779114851102437e-06,
|
|
"loss": 0.1633,
|
|
"num_input_tokens_seen": 282890112,
|
|
"step": 3615,
|
|
"train_runtime": 47695.0374,
|
|
"train_tokens_per_second": 5931.227
|
|
},
|
|
{
|
|
"epoch": 1.448,
|
|
"grad_norm": 0.6302668789165032,
|
|
"learning_rate": 1.767116114405169e-06,
|
|
"loss": 0.1526,
|
|
"num_input_tokens_seen": 283283696,
|
|
"step": 3620,
|
|
"train_runtime": 47762.1972,
|
|
"train_tokens_per_second": 5931.128
|
|
},
|
|
{
|
|
"epoch": 1.45,
|
|
"grad_norm": 0.7741954401409908,
|
|
"learning_rate": 1.7551492849666857e-06,
|
|
"loss": 0.1725,
|
|
"num_input_tokens_seen": 283685808,
|
|
"step": 3625,
|
|
"train_runtime": 47824.1282,
|
|
"train_tokens_per_second": 5931.855
|
|
},
|
|
{
|
|
"epoch": 1.452,
|
|
"grad_norm": 1.3817026636466954,
|
|
"learning_rate": 1.7432144808947587e-06,
|
|
"loss": 0.1691,
|
|
"num_input_tokens_seen": 284112096,
|
|
"step": 3630,
|
|
"train_runtime": 47902.1143,
|
|
"train_tokens_per_second": 5931.097
|
|
},
|
|
{
|
|
"epoch": 1.454,
|
|
"grad_norm": 0.7099453612067773,
|
|
"learning_rate": 1.7313118199810897e-06,
|
|
"loss": 0.1858,
|
|
"num_input_tokens_seen": 284461312,
|
|
"step": 3635,
|
|
"train_runtime": 47957.2926,
|
|
"train_tokens_per_second": 5931.555
|
|
},
|
|
{
|
|
"epoch": 1.456,
|
|
"grad_norm": 0.8122207590733628,
|
|
"learning_rate": 1.719441419700133e-06,
|
|
"loss": 0.164,
|
|
"num_input_tokens_seen": 284868512,
|
|
"step": 3640,
|
|
"train_runtime": 48029.1655,
|
|
"train_tokens_per_second": 5931.157
|
|
},
|
|
{
|
|
"epoch": 1.458,
|
|
"grad_norm": 0.8572956528482197,
|
|
"learning_rate": 1.7076033972079503e-06,
|
|
"loss": 0.1564,
|
|
"num_input_tokens_seen": 285185056,
|
|
"step": 3645,
|
|
"train_runtime": 48091.5097,
|
|
"train_tokens_per_second": 5930.05
|
|
},
|
|
{
|
|
"epoch": 1.46,
|
|
"grad_norm": 0.873938357262156,
|
|
"learning_rate": 1.6957978693410414e-06,
|
|
"loss": 0.1632,
|
|
"num_input_tokens_seen": 285571648,
|
|
"step": 3650,
|
|
"train_runtime": 48149.9078,
|
|
"train_tokens_per_second": 5930.887
|
|
},
|
|
{
|
|
"epoch": 1.462,
|
|
"grad_norm": 0.7103177752858402,
|
|
"learning_rate": 1.6840249526152036e-06,
|
|
"loss": 0.1668,
|
|
"num_input_tokens_seen": 285983264,
|
|
"step": 3655,
|
|
"train_runtime": 48211.3382,
|
|
"train_tokens_per_second": 5931.867
|
|
},
|
|
{
|
|
"epoch": 1.464,
|
|
"grad_norm": 0.8369786068973288,
|
|
"learning_rate": 1.6722847632243699e-06,
|
|
"loss": 0.1591,
|
|
"num_input_tokens_seen": 286456640,
|
|
"step": 3660,
|
|
"train_runtime": 48288.4145,
|
|
"train_tokens_per_second": 5932.202
|
|
},
|
|
{
|
|
"epoch": 1.466,
|
|
"grad_norm": 0.7265571979210181,
|
|
"learning_rate": 1.6605774170394683e-06,
|
|
"loss": 0.1556,
|
|
"num_input_tokens_seen": 286908176,
|
|
"step": 3665,
|
|
"train_runtime": 48361.8519,
|
|
"train_tokens_per_second": 5932.531
|
|
},
|
|
{
|
|
"epoch": 1.468,
|
|
"grad_norm": 0.6864011131778082,
|
|
"learning_rate": 1.6489030296072833e-06,
|
|
"loss": 0.151,
|
|
"num_input_tokens_seen": 287294160,
|
|
"step": 3670,
|
|
"train_runtime": 48418.8864,
|
|
"train_tokens_per_second": 5933.514
|
|
},
|
|
{
|
|
"epoch": 1.47,
|
|
"grad_norm": 0.7996330627370122,
|
|
"learning_rate": 1.6372617161493014e-06,
|
|
"loss": 0.1758,
|
|
"num_input_tokens_seen": 287716720,
|
|
"step": 3675,
|
|
"train_runtime": 48494.7014,
|
|
"train_tokens_per_second": 5932.952
|
|
},
|
|
{
|
|
"epoch": 1.472,
|
|
"grad_norm": 0.6872602791154082,
|
|
"learning_rate": 1.6256535915605904e-06,
|
|
"loss": 0.1624,
|
|
"num_input_tokens_seen": 288152368,
|
|
"step": 3680,
|
|
"train_runtime": 48563.8173,
|
|
"train_tokens_per_second": 5933.479
|
|
},
|
|
{
|
|
"epoch": 1.474,
|
|
"grad_norm": 0.8039815691495285,
|
|
"learning_rate": 1.6140787704086502e-06,
|
|
"loss": 0.157,
|
|
"num_input_tokens_seen": 288577920,
|
|
"step": 3685,
|
|
"train_runtime": 48630.6755,
|
|
"train_tokens_per_second": 5934.072
|
|
},
|
|
{
|
|
"epoch": 1.476,
|
|
"grad_norm": 0.7751500817420555,
|
|
"learning_rate": 1.6025373669322963e-06,
|
|
"loss": 0.1628,
|
|
"num_input_tokens_seen": 288934560,
|
|
"step": 3690,
|
|
"train_runtime": 48676.9536,
|
|
"train_tokens_per_second": 5935.757
|
|
},
|
|
{
|
|
"epoch": 1.478,
|
|
"grad_norm": 0.7540438680547615,
|
|
"learning_rate": 1.591029495040518e-06,
|
|
"loss": 0.1564,
|
|
"num_input_tokens_seen": 289320864,
|
|
"step": 3695,
|
|
"train_runtime": 48745.6477,
|
|
"train_tokens_per_second": 5935.317
|
|
},
|
|
{
|
|
"epoch": 1.48,
|
|
"grad_norm": 0.7341652825778272,
|
|
"learning_rate": 1.5795552683113679e-06,
|
|
"loss": 0.1628,
|
|
"num_input_tokens_seen": 289703696,
|
|
"step": 3700,
|
|
"train_runtime": 48807.1603,
|
|
"train_tokens_per_second": 5935.68
|
|
},
|
|
{
|
|
"epoch": 1.482,
|
|
"grad_norm": 0.6671644486635318,
|
|
"learning_rate": 1.5681147999908308e-06,
|
|
"loss": 0.159,
|
|
"num_input_tokens_seen": 290105360,
|
|
"step": 3705,
|
|
"train_runtime": 48868.9711,
|
|
"train_tokens_per_second": 5936.392
|
|
},
|
|
{
|
|
"epoch": 1.484,
|
|
"grad_norm": 0.9144494381127112,
|
|
"learning_rate": 1.5567082029917074e-06,
|
|
"loss": 0.1742,
|
|
"num_input_tokens_seen": 290475616,
|
|
"step": 3710,
|
|
"train_runtime": 48938.6567,
|
|
"train_tokens_per_second": 5935.504
|
|
},
|
|
{
|
|
"epoch": 1.486,
|
|
"grad_norm": 0.7018359725373299,
|
|
"learning_rate": 1.5453355898925094e-06,
|
|
"loss": 0.1537,
|
|
"num_input_tokens_seen": 290900160,
|
|
"step": 3715,
|
|
"train_runtime": 49007.408,
|
|
"train_tokens_per_second": 5935.841
|
|
},
|
|
{
|
|
"epoch": 1.488,
|
|
"grad_norm": 0.7092657337896592,
|
|
"learning_rate": 1.533997072936333e-06,
|
|
"loss": 0.1732,
|
|
"num_input_tokens_seen": 291311376,
|
|
"step": 3720,
|
|
"train_runtime": 49074.0302,
|
|
"train_tokens_per_second": 5936.162
|
|
},
|
|
{
|
|
"epoch": 1.49,
|
|
"grad_norm": 0.6739752826788876,
|
|
"learning_rate": 1.5226927640297663e-06,
|
|
"loss": 0.1657,
|
|
"num_input_tokens_seen": 291717008,
|
|
"step": 3725,
|
|
"train_runtime": 49143.9674,
|
|
"train_tokens_per_second": 5935.968
|
|
},
|
|
{
|
|
"epoch": 1.492,
|
|
"grad_norm": 0.6883913285947694,
|
|
"learning_rate": 1.511422774741771e-06,
|
|
"loss": 0.1593,
|
|
"num_input_tokens_seen": 292120192,
|
|
"step": 3730,
|
|
"train_runtime": 49213.2445,
|
|
"train_tokens_per_second": 5935.804
|
|
},
|
|
{
|
|
"epoch": 1.494,
|
|
"grad_norm": 0.617957901711163,
|
|
"learning_rate": 1.5001872163025954e-06,
|
|
"loss": 0.149,
|
|
"num_input_tokens_seen": 292536320,
|
|
"step": 3735,
|
|
"train_runtime": 49286.3515,
|
|
"train_tokens_per_second": 5935.443
|
|
},
|
|
{
|
|
"epoch": 1.496,
|
|
"grad_norm": 0.6696532687085773,
|
|
"learning_rate": 1.4889861996026617e-06,
|
|
"loss": 0.1528,
|
|
"num_input_tokens_seen": 292950032,
|
|
"step": 3740,
|
|
"train_runtime": 49350.7769,
|
|
"train_tokens_per_second": 5936.077
|
|
},
|
|
{
|
|
"epoch": 1.498,
|
|
"grad_norm": 0.8585993308197738,
|
|
"learning_rate": 1.4778198351914853e-06,
|
|
"loss": 0.1563,
|
|
"num_input_tokens_seen": 293339328,
|
|
"step": 3745,
|
|
"train_runtime": 49414.2463,
|
|
"train_tokens_per_second": 5936.331
|
|
},
|
|
{
|
|
"epoch": 1.5,
|
|
"grad_norm": 0.6883622617430676,
|
|
"learning_rate": 1.4666882332765747e-06,
|
|
"loss": 0.1423,
|
|
"num_input_tokens_seen": 293683568,
|
|
"step": 3750,
|
|
"train_runtime": 49478.6753,
|
|
"train_tokens_per_second": 5935.558
|
|
},
|
|
{
|
|
"epoch": 1.502,
|
|
"grad_norm": 0.6282398714387517,
|
|
"learning_rate": 1.4555915037223438e-06,
|
|
"loss": 0.1538,
|
|
"num_input_tokens_seen": 294050448,
|
|
"step": 3755,
|
|
"train_runtime": 49536.3353,
|
|
"train_tokens_per_second": 5936.056
|
|
},
|
|
{
|
|
"epoch": 1.504,
|
|
"grad_norm": 0.7830547601957741,
|
|
"learning_rate": 1.4445297560490373e-06,
|
|
"loss": 0.1608,
|
|
"num_input_tokens_seen": 294429296,
|
|
"step": 3760,
|
|
"train_runtime": 49593.9525,
|
|
"train_tokens_per_second": 5936.798
|
|
},
|
|
{
|
|
"epoch": 1.506,
|
|
"grad_norm": 0.6503071391641585,
|
|
"learning_rate": 1.4335030994316357e-06,
|
|
"loss": 0.1671,
|
|
"num_input_tokens_seen": 294819536,
|
|
"step": 3765,
|
|
"train_runtime": 49663.9102,
|
|
"train_tokens_per_second": 5936.293
|
|
},
|
|
{
|
|
"epoch": 1.508,
|
|
"grad_norm": 0.8378464313609364,
|
|
"learning_rate": 1.4225116426987916e-06,
|
|
"loss": 0.1636,
|
|
"num_input_tokens_seen": 295168448,
|
|
"step": 3770,
|
|
"train_runtime": 49723.3275,
|
|
"train_tokens_per_second": 5936.217
|
|
},
|
|
{
|
|
"epoch": 1.51,
|
|
"grad_norm": 0.8093368701191689,
|
|
"learning_rate": 1.4115554943317416e-06,
|
|
"loss": 0.1775,
|
|
"num_input_tokens_seen": 295616576,
|
|
"step": 3775,
|
|
"train_runtime": 49789.5792,
|
|
"train_tokens_per_second": 5937.318
|
|
},
|
|
{
|
|
"epoch": 1.512,
|
|
"grad_norm": 0.6354092381471135,
|
|
"learning_rate": 1.4006347624632505e-06,
|
|
"loss": 0.1524,
|
|
"num_input_tokens_seen": 296032560,
|
|
"step": 3780,
|
|
"train_runtime": 49859.4468,
|
|
"train_tokens_per_second": 5937.341
|
|
},
|
|
{
|
|
"epoch": 1.514,
|
|
"grad_norm": 0.693475579643076,
|
|
"learning_rate": 1.38974955487653e-06,
|
|
"loss": 0.1603,
|
|
"num_input_tokens_seen": 296454512,
|
|
"step": 3785,
|
|
"train_runtime": 49928.7364,
|
|
"train_tokens_per_second": 5937.553
|
|
},
|
|
{
|
|
"epoch": 1.516,
|
|
"grad_norm": 0.724195508398729,
|
|
"learning_rate": 1.3788999790041867e-06,
|
|
"loss": 0.1649,
|
|
"num_input_tokens_seen": 296844976,
|
|
"step": 3790,
|
|
"train_runtime": 49991.3408,
|
|
"train_tokens_per_second": 5937.928
|
|
},
|
|
{
|
|
"epoch": 1.518,
|
|
"grad_norm": 0.8428373420382386,
|
|
"learning_rate": 1.368086141927154e-06,
|
|
"loss": 0.1556,
|
|
"num_input_tokens_seen": 297262656,
|
|
"step": 3795,
|
|
"train_runtime": 50052.7204,
|
|
"train_tokens_per_second": 5938.991
|
|
},
|
|
{
|
|
"epoch": 1.52,
|
|
"grad_norm": 0.87398573790114,
|
|
"learning_rate": 1.3573081503736362e-06,
|
|
"loss": 0.1623,
|
|
"num_input_tokens_seen": 297664192,
|
|
"step": 3800,
|
|
"train_runtime": 50124.0715,
|
|
"train_tokens_per_second": 5938.548
|
|
},
|
|
{
|
|
"epoch": 1.522,
|
|
"grad_norm": 0.9011870596099121,
|
|
"learning_rate": 1.346566110718061e-06,
|
|
"loss": 0.1721,
|
|
"num_input_tokens_seen": 298044432,
|
|
"step": 3805,
|
|
"train_runtime": 50190.8923,
|
|
"train_tokens_per_second": 5938.217
|
|
},
|
|
{
|
|
"epoch": 1.524,
|
|
"grad_norm": 0.8611308450361769,
|
|
"learning_rate": 1.3358601289800211e-06,
|
|
"loss": 0.1573,
|
|
"num_input_tokens_seen": 298445792,
|
|
"step": 3810,
|
|
"train_runtime": 50254.921,
|
|
"train_tokens_per_second": 5938.638
|
|
},
|
|
{
|
|
"epoch": 1.526,
|
|
"grad_norm": 1.1145695760053962,
|
|
"learning_rate": 1.3251903108232362e-06,
|
|
"loss": 0.1726,
|
|
"num_input_tokens_seen": 298799232,
|
|
"step": 3815,
|
|
"train_runtime": 50314.8047,
|
|
"train_tokens_per_second": 5938.595
|
|
},
|
|
{
|
|
"epoch": 1.528,
|
|
"grad_norm": 0.8435186759355315,
|
|
"learning_rate": 1.3145567615545013e-06,
|
|
"loss": 0.1556,
|
|
"num_input_tokens_seen": 299246880,
|
|
"step": 3820,
|
|
"train_runtime": 50390.9674,
|
|
"train_tokens_per_second": 5938.502
|
|
},
|
|
{
|
|
"epoch": 1.53,
|
|
"grad_norm": 0.8236054296751814,
|
|
"learning_rate": 1.3039595861226579e-06,
|
|
"loss": 0.1562,
|
|
"num_input_tokens_seen": 299644480,
|
|
"step": 3825,
|
|
"train_runtime": 50459.1553,
|
|
"train_tokens_per_second": 5938.357
|
|
},
|
|
{
|
|
"epoch": 1.532,
|
|
"grad_norm": 0.7531047196182729,
|
|
"learning_rate": 1.2933988891175458e-06,
|
|
"loss": 0.1392,
|
|
"num_input_tokens_seen": 299946608,
|
|
"step": 3830,
|
|
"train_runtime": 50506.1397,
|
|
"train_tokens_per_second": 5938.815
|
|
},
|
|
{
|
|
"epoch": 1.534,
|
|
"grad_norm": 0.7439741360639419,
|
|
"learning_rate": 1.2828747747689846e-06,
|
|
"loss": 0.1676,
|
|
"num_input_tokens_seen": 300291984,
|
|
"step": 3835,
|
|
"train_runtime": 50564.1658,
|
|
"train_tokens_per_second": 5938.83
|
|
},
|
|
{
|
|
"epoch": 1.536,
|
|
"grad_norm": 0.7324767451032246,
|
|
"learning_rate": 1.2723873469457304e-06,
|
|
"loss": 0.1464,
|
|
"num_input_tokens_seen": 300690848,
|
|
"step": 3840,
|
|
"train_runtime": 50623.2921,
|
|
"train_tokens_per_second": 5939.773
|
|
},
|
|
{
|
|
"epoch": 1.538,
|
|
"grad_norm": 0.8166097109061963,
|
|
"learning_rate": 1.2619367091544654e-06,
|
|
"loss": 0.1485,
|
|
"num_input_tokens_seen": 300993296,
|
|
"step": 3845,
|
|
"train_runtime": 50675.2042,
|
|
"train_tokens_per_second": 5939.656
|
|
},
|
|
{
|
|
"epoch": 1.54,
|
|
"grad_norm": 0.8516924618819338,
|
|
"learning_rate": 1.2515229645387639e-06,
|
|
"loss": 0.1625,
|
|
"num_input_tokens_seen": 301381456,
|
|
"step": 3850,
|
|
"train_runtime": 50736.817,
|
|
"train_tokens_per_second": 5940.094
|
|
},
|
|
{
|
|
"epoch": 1.542,
|
|
"grad_norm": 0.7709718783267265,
|
|
"learning_rate": 1.2411462158780791e-06,
|
|
"loss": 0.1542,
|
|
"num_input_tokens_seen": 301831440,
|
|
"step": 3855,
|
|
"train_runtime": 50810.3613,
|
|
"train_tokens_per_second": 5940.352
|
|
},
|
|
{
|
|
"epoch": 1.544,
|
|
"grad_norm": 0.7260519140885252,
|
|
"learning_rate": 1.2308065655867346e-06,
|
|
"loss": 0.1687,
|
|
"num_input_tokens_seen": 302152880,
|
|
"step": 3860,
|
|
"train_runtime": 50855.3514,
|
|
"train_tokens_per_second": 5941.418
|
|
},
|
|
{
|
|
"epoch": 1.546,
|
|
"grad_norm": 0.794749393179828,
|
|
"learning_rate": 1.2205041157129017e-06,
|
|
"loss": 0.1646,
|
|
"num_input_tokens_seen": 302571152,
|
|
"step": 3865,
|
|
"train_runtime": 50925.2734,
|
|
"train_tokens_per_second": 5941.473
|
|
},
|
|
{
|
|
"epoch": 1.548,
|
|
"grad_norm": 0.9153778363944037,
|
|
"learning_rate": 1.2102389679376037e-06,
|
|
"loss": 0.153,
|
|
"num_input_tokens_seen": 302999424,
|
|
"step": 3870,
|
|
"train_runtime": 50992.9744,
|
|
"train_tokens_per_second": 5941.984
|
|
},
|
|
{
|
|
"epoch": 1.55,
|
|
"grad_norm": 0.7657976563472844,
|
|
"learning_rate": 1.200011223573702e-06,
|
|
"loss": 0.1668,
|
|
"num_input_tokens_seen": 303335568,
|
|
"step": 3875,
|
|
"train_runtime": 51047.9903,
|
|
"train_tokens_per_second": 5942.165
|
|
},
|
|
{
|
|
"epoch": 1.552,
|
|
"grad_norm": 0.5829441050334857,
|
|
"learning_rate": 1.1898209835649083e-06,
|
|
"loss": 0.1389,
|
|
"num_input_tokens_seen": 303743248,
|
|
"step": 3880,
|
|
"train_runtime": 51125.9327,
|
|
"train_tokens_per_second": 5941.08
|
|
},
|
|
{
|
|
"epoch": 1.554,
|
|
"grad_norm": 0.6985271990646709,
|
|
"learning_rate": 1.1796683484847731e-06,
|
|
"loss": 0.1514,
|
|
"num_input_tokens_seen": 304106352,
|
|
"step": 3885,
|
|
"train_runtime": 51195.1143,
|
|
"train_tokens_per_second": 5940.144
|
|
},
|
|
{
|
|
"epoch": 1.556,
|
|
"grad_norm": 0.9314518957225341,
|
|
"learning_rate": 1.16955341853571e-06,
|
|
"loss": 0.1616,
|
|
"num_input_tokens_seen": 304480976,
|
|
"step": 3890,
|
|
"train_runtime": 51259.4005,
|
|
"train_tokens_per_second": 5940.003
|
|
},
|
|
{
|
|
"epoch": 1.558,
|
|
"grad_norm": 0.5742395593745069,
|
|
"learning_rate": 1.159476293547992e-06,
|
|
"loss": 0.1694,
|
|
"num_input_tokens_seen": 304955440,
|
|
"step": 3895,
|
|
"train_runtime": 51330.1049,
|
|
"train_tokens_per_second": 5941.064
|
|
},
|
|
{
|
|
"epoch": 1.56,
|
|
"grad_norm": 0.7505585227992764,
|
|
"learning_rate": 1.149437072978773e-06,
|
|
"loss": 0.1439,
|
|
"num_input_tokens_seen": 305368592,
|
|
"step": 3900,
|
|
"train_runtime": 51404.1488,
|
|
"train_tokens_per_second": 5940.544
|
|
},
|
|
{
|
|
"epoch": 1.562,
|
|
"grad_norm": 0.9284631824732897,
|
|
"learning_rate": 1.1394358559111101e-06,
|
|
"loss": 0.1629,
|
|
"num_input_tokens_seen": 305674576,
|
|
"step": 3905,
|
|
"train_runtime": 51453.4355,
|
|
"train_tokens_per_second": 5940.8
|
|
},
|
|
{
|
|
"epoch": 1.564,
|
|
"grad_norm": 0.6202213613264032,
|
|
"learning_rate": 1.1294727410529754e-06,
|
|
"loss": 0.1417,
|
|
"num_input_tokens_seen": 306050064,
|
|
"step": 3910,
|
|
"train_runtime": 51508.3405,
|
|
"train_tokens_per_second": 5941.757
|
|
},
|
|
{
|
|
"epoch": 1.5659999999999998,
|
|
"grad_norm": 0.9103982557120633,
|
|
"learning_rate": 1.1195478267362924e-06,
|
|
"loss": 0.1683,
|
|
"num_input_tokens_seen": 306442352,
|
|
"step": 3915,
|
|
"train_runtime": 51576.8601,
|
|
"train_tokens_per_second": 5941.47
|
|
},
|
|
{
|
|
"epoch": 1.568,
|
|
"grad_norm": 0.7948430101693148,
|
|
"learning_rate": 1.109661210915956e-06,
|
|
"loss": 0.1539,
|
|
"num_input_tokens_seen": 306873936,
|
|
"step": 3920,
|
|
"train_runtime": 51648.5019,
|
|
"train_tokens_per_second": 5941.584
|
|
},
|
|
{
|
|
"epoch": 1.5699999999999998,
|
|
"grad_norm": 0.7063624876955984,
|
|
"learning_rate": 1.0998129911688766e-06,
|
|
"loss": 0.1469,
|
|
"num_input_tokens_seen": 307235072,
|
|
"step": 3925,
|
|
"train_runtime": 51712.6458,
|
|
"train_tokens_per_second": 5941.198
|
|
},
|
|
{
|
|
"epoch": 1.572,
|
|
"grad_norm": 0.6946879322873568,
|
|
"learning_rate": 1.090003264693003e-06,
|
|
"loss": 0.1545,
|
|
"num_input_tokens_seen": 307618096,
|
|
"step": 3930,
|
|
"train_runtime": 51787.7595,
|
|
"train_tokens_per_second": 5939.977
|
|
},
|
|
{
|
|
"epoch": 1.5739999999999998,
|
|
"grad_norm": 0.7173671885390808,
|
|
"learning_rate": 1.0802321283063794e-06,
|
|
"loss": 0.171,
|
|
"num_input_tokens_seen": 307988144,
|
|
"step": 3935,
|
|
"train_runtime": 51859.6588,
|
|
"train_tokens_per_second": 5938.877
|
|
},
|
|
{
|
|
"epoch": 1.576,
|
|
"grad_norm": 0.8435950312942204,
|
|
"learning_rate": 1.0704996784461753e-06,
|
|
"loss": 0.1768,
|
|
"num_input_tokens_seen": 308369536,
|
|
"step": 3940,
|
|
"train_runtime": 51929.6894,
|
|
"train_tokens_per_second": 5938.213
|
|
},
|
|
{
|
|
"epoch": 1.5779999999999998,
|
|
"grad_norm": 0.8068932664683814,
|
|
"learning_rate": 1.0608060111677409e-06,
|
|
"loss": 0.165,
|
|
"num_input_tokens_seen": 308753040,
|
|
"step": 3945,
|
|
"train_runtime": 51995.9574,
|
|
"train_tokens_per_second": 5938.02
|
|
},
|
|
{
|
|
"epoch": 1.58,
|
|
"grad_norm": 0.834555502724904,
|
|
"learning_rate": 1.0511512221436581e-06,
|
|
"loss": 0.1595,
|
|
"num_input_tokens_seen": 309055504,
|
|
"step": 3950,
|
|
"train_runtime": 52044.6503,
|
|
"train_tokens_per_second": 5938.276
|
|
},
|
|
{
|
|
"epoch": 1.5819999999999999,
|
|
"grad_norm": 0.8042325847254838,
|
|
"learning_rate": 1.0415354066627993e-06,
|
|
"loss": 0.1424,
|
|
"num_input_tokens_seen": 309452224,
|
|
"step": 3955,
|
|
"train_runtime": 52111.1572,
|
|
"train_tokens_per_second": 5938.31
|
|
},
|
|
{
|
|
"epoch": 1.584,
|
|
"grad_norm": 0.7316181513052099,
|
|
"learning_rate": 1.03195865962938e-06,
|
|
"loss": 0.1516,
|
|
"num_input_tokens_seen": 309809200,
|
|
"step": 3960,
|
|
"train_runtime": 52165.6744,
|
|
"train_tokens_per_second": 5938.947
|
|
},
|
|
{
|
|
"epoch": 1.5859999999999999,
|
|
"grad_norm": 0.7534254617656516,
|
|
"learning_rate": 1.0224210755620257e-06,
|
|
"loss": 0.162,
|
|
"num_input_tokens_seen": 310253648,
|
|
"step": 3965,
|
|
"train_runtime": 52238.0456,
|
|
"train_tokens_per_second": 5939.228
|
|
},
|
|
{
|
|
"epoch": 1.588,
|
|
"grad_norm": 0.6079151466242301,
|
|
"learning_rate": 1.0129227485928432e-06,
|
|
"loss": 0.1585,
|
|
"num_input_tokens_seen": 310700400,
|
|
"step": 3970,
|
|
"train_runtime": 52302.956,
|
|
"train_tokens_per_second": 5940.398
|
|
},
|
|
{
|
|
"epoch": 1.5899999999999999,
|
|
"grad_norm": 0.7267644896480594,
|
|
"learning_rate": 1.0034637724664832e-06,
|
|
"loss": 0.1463,
|
|
"num_input_tokens_seen": 311100192,
|
|
"step": 3975,
|
|
"train_runtime": 52374.6534,
|
|
"train_tokens_per_second": 5939.9
|
|
},
|
|
{
|
|
"epoch": 1.592,
|
|
"grad_norm": 0.698238858394852,
|
|
"learning_rate": 9.940442405392226e-07,
|
|
"loss": 0.1671,
|
|
"num_input_tokens_seen": 311518048,
|
|
"step": 3980,
|
|
"train_runtime": 52440.9233,
|
|
"train_tokens_per_second": 5940.362
|
|
},
|
|
{
|
|
"epoch": 1.5939999999999999,
|
|
"grad_norm": 0.9105156843444525,
|
|
"learning_rate": 9.84664245778037e-07,
|
|
"loss": 0.159,
|
|
"num_input_tokens_seen": 311819200,
|
|
"step": 3985,
|
|
"train_runtime": 52491.2791,
|
|
"train_tokens_per_second": 5940.4
|
|
},
|
|
{
|
|
"epoch": 1.596,
|
|
"grad_norm": 0.7075598572520726,
|
|
"learning_rate": 9.753238807596903e-07,
|
|
"loss": 0.1586,
|
|
"num_input_tokens_seen": 312203520,
|
|
"step": 3990,
|
|
"train_runtime": 52556.8555,
|
|
"train_tokens_per_second": 5940.301
|
|
},
|
|
{
|
|
"epoch": 1.5979999999999999,
|
|
"grad_norm": 0.7825496188469808,
|
|
"learning_rate": 9.66023237669812e-07,
|
|
"loss": 0.152,
|
|
"num_input_tokens_seen": 312507584,
|
|
"step": 3995,
|
|
"train_runtime": 52608.0978,
|
|
"train_tokens_per_second": 5940.294
|
|
},
|
|
{
|
|
"epoch": 1.6,
|
|
"grad_norm": 0.6339671908477715,
|
|
"learning_rate": 9.567624083019966e-07,
|
|
"loss": 0.139,
|
|
"num_input_tokens_seen": 312985888,
|
|
"step": 4000,
|
|
"train_runtime": 52685.0956,
|
|
"train_tokens_per_second": 5940.691
|
|
},
|
|
{
|
|
"epoch": 1.6019999999999999,
|
|
"grad_norm": 0.716981880518906,
|
|
"learning_rate": 9.475414840568903e-07,
|
|
"loss": 0.1412,
|
|
"num_input_tokens_seen": 313402192,
|
|
"step": 4005,
|
|
"train_runtime": 52756.5642,
|
|
"train_tokens_per_second": 5940.535
|
|
},
|
|
{
|
|
"epoch": 1.604,
|
|
"grad_norm": 0.622200241936413,
|
|
"learning_rate": 9.383605559412911e-07,
|
|
"loss": 0.1521,
|
|
"num_input_tokens_seen": 313892192,
|
|
"step": 4010,
|
|
"train_runtime": 52834.9055,
|
|
"train_tokens_per_second": 5941.0
|
|
},
|
|
{
|
|
"epoch": 1.6059999999999999,
|
|
"grad_norm": 0.721150749155636,
|
|
"learning_rate": 9.29219714567256e-07,
|
|
"loss": 0.1414,
|
|
"num_input_tokens_seen": 314322864,
|
|
"step": 4015,
|
|
"train_runtime": 52913.2498,
|
|
"train_tokens_per_second": 5940.343
|
|
},
|
|
{
|
|
"epoch": 1.608,
|
|
"grad_norm": 0.7598956843200992,
|
|
"learning_rate": 9.201190501511964e-07,
|
|
"loss": 0.1489,
|
|
"num_input_tokens_seen": 314726832,
|
|
"step": 4020,
|
|
"train_runtime": 52985.46,
|
|
"train_tokens_per_second": 5939.872
|
|
},
|
|
{
|
|
"epoch": 1.6099999999999999,
|
|
"grad_norm": 0.6907716743798843,
|
|
"learning_rate": 9.110586525129988e-07,
|
|
"loss": 0.1555,
|
|
"num_input_tokens_seen": 315177056,
|
|
"step": 4025,
|
|
"train_runtime": 53057.6311,
|
|
"train_tokens_per_second": 5940.278
|
|
},
|
|
{
|
|
"epoch": 1.612,
|
|
"grad_norm": 0.8293953448161336,
|
|
"learning_rate": 9.020386110751267e-07,
|
|
"loss": 0.1598,
|
|
"num_input_tokens_seen": 315552336,
|
|
"step": 4030,
|
|
"train_runtime": 53118.1875,
|
|
"train_tokens_per_second": 5940.57
|
|
},
|
|
{
|
|
"epoch": 1.6139999999999999,
|
|
"grad_norm": 0.7989124732357052,
|
|
"learning_rate": 8.930590148617513e-07,
|
|
"loss": 0.1819,
|
|
"num_input_tokens_seen": 315957232,
|
|
"step": 4035,
|
|
"train_runtime": 53184.6368,
|
|
"train_tokens_per_second": 5940.761
|
|
},
|
|
{
|
|
"epoch": 1.616,
|
|
"grad_norm": 0.6428285367505974,
|
|
"learning_rate": 8.841199524978583e-07,
|
|
"loss": 0.1531,
|
|
"num_input_tokens_seen": 316314048,
|
|
"step": 4040,
|
|
"train_runtime": 53251.1528,
|
|
"train_tokens_per_second": 5940.041
|
|
},
|
|
{
|
|
"epoch": 1.6179999999999999,
|
|
"grad_norm": 0.565472067050307,
|
|
"learning_rate": 8.752215122083874e-07,
|
|
"loss": 0.1489,
|
|
"num_input_tokens_seen": 316735184,
|
|
"step": 4045,
|
|
"train_runtime": 53313.806,
|
|
"train_tokens_per_second": 5940.96
|
|
},
|
|
{
|
|
"epoch": 1.62,
|
|
"grad_norm": 0.7114994088593782,
|
|
"learning_rate": 8.663637818173504e-07,
|
|
"loss": 0.156,
|
|
"num_input_tokens_seen": 317204928,
|
|
"step": 4050,
|
|
"train_runtime": 53385.791,
|
|
"train_tokens_per_second": 5941.748
|
|
},
|
|
{
|
|
"epoch": 1.6219999999999999,
|
|
"grad_norm": 0.9870198872186691,
|
|
"learning_rate": 8.575468487469696e-07,
|
|
"loss": 0.173,
|
|
"num_input_tokens_seen": 317577008,
|
|
"step": 4055,
|
|
"train_runtime": 53453.8591,
|
|
"train_tokens_per_second": 5941.143
|
|
},
|
|
{
|
|
"epoch": 1.624,
|
|
"grad_norm": 0.5697149919750604,
|
|
"learning_rate": 8.487708000168166e-07,
|
|
"loss": 0.1648,
|
|
"num_input_tokens_seen": 318002288,
|
|
"step": 4060,
|
|
"train_runtime": 53529.2946,
|
|
"train_tokens_per_second": 5940.715
|
|
},
|
|
{
|
|
"epoch": 1.626,
|
|
"grad_norm": 0.7805127506032401,
|
|
"learning_rate": 8.400357222429473e-07,
|
|
"loss": 0.1659,
|
|
"num_input_tokens_seen": 318419952,
|
|
"step": 4065,
|
|
"train_runtime": 53590.6658,
|
|
"train_tokens_per_second": 5941.705
|
|
},
|
|
{
|
|
"epoch": 1.6280000000000001,
|
|
"grad_norm": 0.9117245976736663,
|
|
"learning_rate": 8.313417016370557e-07,
|
|
"loss": 0.1496,
|
|
"num_input_tokens_seen": 318719648,
|
|
"step": 4070,
|
|
"train_runtime": 53632.4854,
|
|
"train_tokens_per_second": 5942.66
|
|
},
|
|
{
|
|
"epoch": 1.63,
|
|
"grad_norm": 0.7672928588910254,
|
|
"learning_rate": 8.226888240056114e-07,
|
|
"loss": 0.1544,
|
|
"num_input_tokens_seen": 319146480,
|
|
"step": 4075,
|
|
"train_runtime": 53707.4445,
|
|
"train_tokens_per_second": 5942.314
|
|
},
|
|
{
|
|
"epoch": 1.6320000000000001,
|
|
"grad_norm": 0.7629874400781869,
|
|
"learning_rate": 8.140771747490273e-07,
|
|
"loss": 0.1534,
|
|
"num_input_tokens_seen": 319534576,
|
|
"step": 4080,
|
|
"train_runtime": 53772.6392,
|
|
"train_tokens_per_second": 5942.326
|
|
},
|
|
{
|
|
"epoch": 1.634,
|
|
"grad_norm": 0.8995459844384383,
|
|
"learning_rate": 8.055068388608011e-07,
|
|
"loss": 0.1744,
|
|
"num_input_tokens_seen": 319929424,
|
|
"step": 4085,
|
|
"train_runtime": 53837.4544,
|
|
"train_tokens_per_second": 5942.507
|
|
},
|
|
{
|
|
"epoch": 1.6360000000000001,
|
|
"grad_norm": 0.6673984349910066,
|
|
"learning_rate": 7.969779009266915e-07,
|
|
"loss": 0.1493,
|
|
"num_input_tokens_seen": 320369280,
|
|
"step": 4090,
|
|
"train_runtime": 53909.9784,
|
|
"train_tokens_per_second": 5942.671
|
|
},
|
|
{
|
|
"epoch": 1.638,
|
|
"grad_norm": 0.768757939760275,
|
|
"learning_rate": 7.884904451238712e-07,
|
|
"loss": 0.1599,
|
|
"num_input_tokens_seen": 320707392,
|
|
"step": 4095,
|
|
"train_runtime": 53960.8577,
|
|
"train_tokens_per_second": 5943.334
|
|
},
|
|
{
|
|
"epoch": 1.6400000000000001,
|
|
"grad_norm": 0.766689309823999,
|
|
"learning_rate": 7.800445552201014e-07,
|
|
"loss": 0.1556,
|
|
"num_input_tokens_seen": 321094592,
|
|
"step": 4100,
|
|
"train_runtime": 54032.4023,
|
|
"train_tokens_per_second": 5942.63
|
|
},
|
|
{
|
|
"epoch": 1.642,
|
|
"grad_norm": 0.7188276700164136,
|
|
"learning_rate": 7.716403145729073e-07,
|
|
"loss": 0.1519,
|
|
"num_input_tokens_seen": 321483936,
|
|
"step": 4105,
|
|
"train_runtime": 54100.0683,
|
|
"train_tokens_per_second": 5942.394
|
|
},
|
|
{
|
|
"epoch": 1.6440000000000001,
|
|
"grad_norm": 0.5941087900324759,
|
|
"learning_rate": 7.632778061287494e-07,
|
|
"loss": 0.1624,
|
|
"num_input_tokens_seen": 321804816,
|
|
"step": 4110,
|
|
"train_runtime": 54144.5026,
|
|
"train_tokens_per_second": 5943.444
|
|
},
|
|
{
|
|
"epoch": 1.646,
|
|
"grad_norm": 0.6210913484441862,
|
|
"learning_rate": 7.549571124222127e-07,
|
|
"loss": 0.1407,
|
|
"num_input_tokens_seen": 322181776,
|
|
"step": 4115,
|
|
"train_runtime": 54211.1301,
|
|
"train_tokens_per_second": 5943.093
|
|
},
|
|
{
|
|
"epoch": 1.6480000000000001,
|
|
"grad_norm": 0.7369318767545302,
|
|
"learning_rate": 7.466783155751816e-07,
|
|
"loss": 0.1509,
|
|
"num_input_tokens_seen": 322569200,
|
|
"step": 4120,
|
|
"train_runtime": 54265.8725,
|
|
"train_tokens_per_second": 5944.237
|
|
},
|
|
{
|
|
"epoch": 1.65,
|
|
"grad_norm": 0.7262183535199628,
|
|
"learning_rate": 7.384414972960419e-07,
|
|
"loss": 0.1619,
|
|
"num_input_tokens_seen": 323008496,
|
|
"step": 4125,
|
|
"train_runtime": 54341.9195,
|
|
"train_tokens_per_second": 5944.002
|
|
},
|
|
{
|
|
"epoch": 1.6520000000000001,
|
|
"grad_norm": 0.8470333491964478,
|
|
"learning_rate": 7.302467388788614e-07,
|
|
"loss": 0.1539,
|
|
"num_input_tokens_seen": 323424624,
|
|
"step": 4130,
|
|
"train_runtime": 54419.5928,
|
|
"train_tokens_per_second": 5943.165
|
|
},
|
|
{
|
|
"epoch": 1.654,
|
|
"grad_norm": 0.6048524596853466,
|
|
"learning_rate": 7.220941212026005e-07,
|
|
"loss": 0.1369,
|
|
"num_input_tokens_seen": 323819312,
|
|
"step": 4135,
|
|
"train_runtime": 54491.291,
|
|
"train_tokens_per_second": 5942.588
|
|
},
|
|
{
|
|
"epoch": 1.6560000000000001,
|
|
"grad_norm": 0.7208157495659575,
|
|
"learning_rate": 7.139837247303027e-07,
|
|
"loss": 0.1485,
|
|
"num_input_tokens_seen": 324175520,
|
|
"step": 4140,
|
|
"train_runtime": 54555.9717,
|
|
"train_tokens_per_second": 5942.072
|
|
},
|
|
{
|
|
"epoch": 1.658,
|
|
"grad_norm": 0.7299239304434404,
|
|
"learning_rate": 7.059156295083064e-07,
|
|
"loss": 0.1655,
|
|
"num_input_tokens_seen": 324614832,
|
|
"step": 4145,
|
|
"train_runtime": 54627.3036,
|
|
"train_tokens_per_second": 5942.355
|
|
},
|
|
{
|
|
"epoch": 1.6600000000000001,
|
|
"grad_norm": 0.9935145604315183,
|
|
"learning_rate": 6.978899151654556e-07,
|
|
"loss": 0.1412,
|
|
"num_input_tokens_seen": 324951920,
|
|
"step": 4150,
|
|
"train_runtime": 54685.9186,
|
|
"train_tokens_per_second": 5942.15
|
|
},
|
|
{
|
|
"epoch": 1.662,
|
|
"grad_norm": 0.8883944989326571,
|
|
"learning_rate": 6.89906660912309e-07,
|
|
"loss": 0.1551,
|
|
"num_input_tokens_seen": 325298624,
|
|
"step": 4155,
|
|
"train_runtime": 54741.2048,
|
|
"train_tokens_per_second": 5942.482
|
|
},
|
|
{
|
|
"epoch": 1.6640000000000001,
|
|
"grad_norm": 0.7536602299661465,
|
|
"learning_rate": 6.819659455403654e-07,
|
|
"loss": 0.1623,
|
|
"num_input_tokens_seen": 325665392,
|
|
"step": 4160,
|
|
"train_runtime": 54810.8193,
|
|
"train_tokens_per_second": 5941.626
|
|
},
|
|
{
|
|
"epoch": 1.666,
|
|
"grad_norm": 0.7390816162314212,
|
|
"learning_rate": 6.74067847421277e-07,
|
|
"loss": 0.1769,
|
|
"num_input_tokens_seen": 326069408,
|
|
"step": 4165,
|
|
"train_runtime": 54877.0655,
|
|
"train_tokens_per_second": 5941.816
|
|
},
|
|
{
|
|
"epoch": 1.6680000000000001,
|
|
"grad_norm": 0.7142739148749228,
|
|
"learning_rate": 6.662124445060863e-07,
|
|
"loss": 0.1513,
|
|
"num_input_tokens_seen": 326501792,
|
|
"step": 4170,
|
|
"train_runtime": 54943.262,
|
|
"train_tokens_per_second": 5942.527
|
|
},
|
|
{
|
|
"epoch": 1.67,
|
|
"grad_norm": 0.709829468162806,
|
|
"learning_rate": 6.583998143244463e-07,
|
|
"loss": 0.1415,
|
|
"num_input_tokens_seen": 326889952,
|
|
"step": 4175,
|
|
"train_runtime": 54998.976,
|
|
"train_tokens_per_second": 5943.564
|
|
},
|
|
{
|
|
"epoch": 1.6720000000000002,
|
|
"grad_norm": 0.7086934697038104,
|
|
"learning_rate": 6.506300339838656e-07,
|
|
"loss": 0.1585,
|
|
"num_input_tokens_seen": 327314752,
|
|
"step": 4180,
|
|
"train_runtime": 55073.4666,
|
|
"train_tokens_per_second": 5943.239
|
|
},
|
|
{
|
|
"epoch": 1.674,
|
|
"grad_norm": 0.8651443191899251,
|
|
"learning_rate": 6.429031801689362e-07,
|
|
"loss": 0.1578,
|
|
"num_input_tokens_seen": 327750640,
|
|
"step": 4185,
|
|
"train_runtime": 55146.6911,
|
|
"train_tokens_per_second": 5943.251
|
|
},
|
|
{
|
|
"epoch": 1.6760000000000002,
|
|
"grad_norm": 0.7485967641548902,
|
|
"learning_rate": 6.352193291405884e-07,
|
|
"loss": 0.1551,
|
|
"num_input_tokens_seen": 328201488,
|
|
"step": 4190,
|
|
"train_runtime": 55218.7329,
|
|
"train_tokens_per_second": 5943.662
|
|
},
|
|
{
|
|
"epoch": 1.678,
|
|
"grad_norm": 0.8576333442466543,
|
|
"learning_rate": 6.275785567353293e-07,
|
|
"loss": 0.1493,
|
|
"num_input_tokens_seen": 328593632,
|
|
"step": 4195,
|
|
"train_runtime": 55285.6055,
|
|
"train_tokens_per_second": 5943.566
|
|
},
|
|
{
|
|
"epoch": 1.6800000000000002,
|
|
"grad_norm": 0.8229876103761707,
|
|
"learning_rate": 6.199809383644956e-07,
|
|
"loss": 0.1413,
|
|
"num_input_tokens_seen": 328971728,
|
|
"step": 4200,
|
|
"train_runtime": 55350.2329,
|
|
"train_tokens_per_second": 5943.457
|
|
},
|
|
{
|
|
"epoch": 1.682,
|
|
"grad_norm": 0.8672846202378146,
|
|
"learning_rate": 6.124265490135161e-07,
|
|
"loss": 0.1523,
|
|
"num_input_tokens_seen": 329316976,
|
|
"step": 4205,
|
|
"train_runtime": 55420.5103,
|
|
"train_tokens_per_second": 5942.15
|
|
},
|
|
{
|
|
"epoch": 1.6840000000000002,
|
|
"grad_norm": 0.6764392878911452,
|
|
"learning_rate": 6.049154632411625e-07,
|
|
"loss": 0.1524,
|
|
"num_input_tokens_seen": 329709072,
|
|
"step": 4210,
|
|
"train_runtime": 55498.2896,
|
|
"train_tokens_per_second": 5940.887
|
|
},
|
|
{
|
|
"epoch": 1.686,
|
|
"grad_norm": 0.7260497027533451,
|
|
"learning_rate": 5.974477551788194e-07,
|
|
"loss": 0.1547,
|
|
"num_input_tokens_seen": 330101328,
|
|
"step": 4215,
|
|
"train_runtime": 55569.0068,
|
|
"train_tokens_per_second": 5940.386
|
|
},
|
|
{
|
|
"epoch": 1.688,
|
|
"grad_norm": 0.8171423073707977,
|
|
"learning_rate": 5.900234985297498e-07,
|
|
"loss": 0.1523,
|
|
"num_input_tokens_seen": 330512448,
|
|
"step": 4220,
|
|
"train_runtime": 55637.0123,
|
|
"train_tokens_per_second": 5940.514
|
|
},
|
|
{
|
|
"epoch": 1.69,
|
|
"grad_norm": 1.024639936468752,
|
|
"learning_rate": 5.826427665683715e-07,
|
|
"loss": 0.1618,
|
|
"num_input_tokens_seen": 330900992,
|
|
"step": 4225,
|
|
"train_runtime": 55703.5638,
|
|
"train_tokens_per_second": 5940.392
|
|
},
|
|
{
|
|
"epoch": 1.692,
|
|
"grad_norm": 0.8852343006997153,
|
|
"learning_rate": 5.753056321395267e-07,
|
|
"loss": 0.1562,
|
|
"num_input_tokens_seen": 331273936,
|
|
"step": 4230,
|
|
"train_runtime": 55772.1025,
|
|
"train_tokens_per_second": 5939.779
|
|
},
|
|
{
|
|
"epoch": 1.694,
|
|
"grad_norm": 0.767093047294307,
|
|
"learning_rate": 5.680121676577721e-07,
|
|
"loss": 0.1613,
|
|
"num_input_tokens_seen": 331678640,
|
|
"step": 4235,
|
|
"train_runtime": 55838.5256,
|
|
"train_tokens_per_second": 5939.961
|
|
},
|
|
{
|
|
"epoch": 1.696,
|
|
"grad_norm": 0.7178529915448881,
|
|
"learning_rate": 5.607624451066568e-07,
|
|
"loss": 0.1549,
|
|
"num_input_tokens_seen": 332056128,
|
|
"step": 4240,
|
|
"train_runtime": 55913.9961,
|
|
"train_tokens_per_second": 5938.694
|
|
},
|
|
{
|
|
"epoch": 1.698,
|
|
"grad_norm": 0.7810027171387974,
|
|
"learning_rate": 5.535565360380146e-07,
|
|
"loss": 0.1523,
|
|
"num_input_tokens_seen": 332493344,
|
|
"step": 4245,
|
|
"train_runtime": 55986.6819,
|
|
"train_tokens_per_second": 5938.794
|
|
},
|
|
{
|
|
"epoch": 1.7,
|
|
"grad_norm": 0.7914847631148596,
|
|
"learning_rate": 5.46394511571261e-07,
|
|
"loss": 0.158,
|
|
"num_input_tokens_seen": 332902464,
|
|
"step": 4250,
|
|
"train_runtime": 56062.3376,
|
|
"train_tokens_per_second": 5938.077
|
|
},
|
|
{
|
|
"epoch": 1.702,
|
|
"grad_norm": 0.7572169430163048,
|
|
"learning_rate": 5.392764423926844e-07,
|
|
"loss": 0.1306,
|
|
"num_input_tokens_seen": 333240368,
|
|
"step": 4255,
|
|
"train_runtime": 56127.3816,
|
|
"train_tokens_per_second": 5937.216
|
|
},
|
|
{
|
|
"epoch": 1.704,
|
|
"grad_norm": 0.7207793402198224,
|
|
"learning_rate": 5.322023987547547e-07,
|
|
"loss": 0.1574,
|
|
"num_input_tokens_seen": 333619536,
|
|
"step": 4260,
|
|
"train_runtime": 56183.0207,
|
|
"train_tokens_per_second": 5938.085
|
|
},
|
|
{
|
|
"epoch": 1.706,
|
|
"grad_norm": 0.7125248872457159,
|
|
"learning_rate": 5.251724504754258e-07,
|
|
"loss": 0.1523,
|
|
"num_input_tokens_seen": 334030848,
|
|
"step": 4265,
|
|
"train_runtime": 56252.3873,
|
|
"train_tokens_per_second": 5938.074
|
|
},
|
|
{
|
|
"epoch": 1.708,
|
|
"grad_norm": 0.5960843885640255,
|
|
"learning_rate": 5.181866669374507e-07,
|
|
"loss": 0.1614,
|
|
"num_input_tokens_seen": 334524720,
|
|
"step": 4270,
|
|
"train_runtime": 56331.0264,
|
|
"train_tokens_per_second": 5938.552
|
|
},
|
|
{
|
|
"epoch": 1.71,
|
|
"grad_norm": 0.600671230966292,
|
|
"learning_rate": 5.112451170876903e-07,
|
|
"loss": 0.1472,
|
|
"num_input_tokens_seen": 335002128,
|
|
"step": 4275,
|
|
"train_runtime": 56409.2368,
|
|
"train_tokens_per_second": 5938.781
|
|
},
|
|
{
|
|
"epoch": 1.712,
|
|
"grad_norm": 0.7897492866217319,
|
|
"learning_rate": 5.043478694364423e-07,
|
|
"loss": 0.1363,
|
|
"num_input_tokens_seen": 335363280,
|
|
"step": 4280,
|
|
"train_runtime": 56472.0488,
|
|
"train_tokens_per_second": 5938.571
|
|
},
|
|
{
|
|
"epoch": 1.714,
|
|
"grad_norm": 0.713337408458915,
|
|
"learning_rate": 4.97494992056754e-07,
|
|
"loss": 0.1498,
|
|
"num_input_tokens_seen": 335742592,
|
|
"step": 4285,
|
|
"train_runtime": 56529.5353,
|
|
"train_tokens_per_second": 5939.242
|
|
},
|
|
{
|
|
"epoch": 1.716,
|
|
"grad_norm": 0.7037126573434743,
|
|
"learning_rate": 4.90686552583759e-07,
|
|
"loss": 0.1634,
|
|
"num_input_tokens_seen": 336140320,
|
|
"step": 4290,
|
|
"train_runtime": 56600.6357,
|
|
"train_tokens_per_second": 5938.808
|
|
},
|
|
{
|
|
"epoch": 1.718,
|
|
"grad_norm": 0.8443463514807014,
|
|
"learning_rate": 4.839226182140072e-07,
|
|
"loss": 0.1917,
|
|
"num_input_tokens_seen": 336507328,
|
|
"step": 4295,
|
|
"train_runtime": 56654.5729,
|
|
"train_tokens_per_second": 5939.632
|
|
},
|
|
{
|
|
"epoch": 1.72,
|
|
"grad_norm": 1.0013401230261276,
|
|
"learning_rate": 4.772032557047984e-07,
|
|
"loss": 0.1577,
|
|
"num_input_tokens_seen": 336833552,
|
|
"step": 4300,
|
|
"train_runtime": 56708.961,
|
|
"train_tokens_per_second": 5939.688
|
|
},
|
|
{
|
|
"epoch": 1.722,
|
|
"grad_norm": 0.699289177727206,
|
|
"learning_rate": 4.705285313735297e-07,
|
|
"loss": 0.1688,
|
|
"num_input_tokens_seen": 337243936,
|
|
"step": 4305,
|
|
"train_runtime": 56780.841,
|
|
"train_tokens_per_second": 5939.397
|
|
},
|
|
{
|
|
"epoch": 1.724,
|
|
"grad_norm": 0.6382446993190217,
|
|
"learning_rate": 4.63898511097034e-07,
|
|
"loss": 0.1492,
|
|
"num_input_tokens_seen": 337576960,
|
|
"step": 4310,
|
|
"train_runtime": 56828.6195,
|
|
"train_tokens_per_second": 5940.263
|
|
},
|
|
{
|
|
"epoch": 1.726,
|
|
"grad_norm": 0.6731685332908478,
|
|
"learning_rate": 4.5731326031093645e-07,
|
|
"loss": 0.1489,
|
|
"num_input_tokens_seen": 338007872,
|
|
"step": 4315,
|
|
"train_runtime": 56894.8513,
|
|
"train_tokens_per_second": 5940.922
|
|
},
|
|
{
|
|
"epoch": 1.728,
|
|
"grad_norm": 0.8249670314108284,
|
|
"learning_rate": 4.5077284400900147e-07,
|
|
"loss": 0.1482,
|
|
"num_input_tokens_seen": 338365776,
|
|
"step": 4320,
|
|
"train_runtime": 56955.9474,
|
|
"train_tokens_per_second": 5940.833
|
|
},
|
|
{
|
|
"epoch": 1.73,
|
|
"grad_norm": 0.7572160236894864,
|
|
"learning_rate": 4.4427732674250045e-07,
|
|
"loss": 0.1511,
|
|
"num_input_tokens_seen": 338719792,
|
|
"step": 4325,
|
|
"train_runtime": 57014.6652,
|
|
"train_tokens_per_second": 5940.924
|
|
},
|
|
{
|
|
"epoch": 1.732,
|
|
"grad_norm": 0.8662514504682324,
|
|
"learning_rate": 4.378267726195645e-07,
|
|
"loss": 0.1515,
|
|
"num_input_tokens_seen": 339222768,
|
|
"step": 4330,
|
|
"train_runtime": 57085.4318,
|
|
"train_tokens_per_second": 5942.37
|
|
},
|
|
{
|
|
"epoch": 1.734,
|
|
"grad_norm": 0.7967484320616307,
|
|
"learning_rate": 4.31421245304558e-07,
|
|
"loss": 0.1491,
|
|
"num_input_tokens_seen": 339620128,
|
|
"step": 4335,
|
|
"train_runtime": 57154.2908,
|
|
"train_tokens_per_second": 5942.163
|
|
},
|
|
{
|
|
"epoch": 1.736,
|
|
"grad_norm": 0.7230310745243409,
|
|
"learning_rate": 4.250608080174512e-07,
|
|
"loss": 0.1569,
|
|
"num_input_tokens_seen": 340054832,
|
|
"step": 4340,
|
|
"train_runtime": 57216.2681,
|
|
"train_tokens_per_second": 5943.324
|
|
},
|
|
{
|
|
"epoch": 1.738,
|
|
"grad_norm": 0.8202911450038648,
|
|
"learning_rate": 4.1874552353319107e-07,
|
|
"loss": 0.1376,
|
|
"num_input_tokens_seen": 340418352,
|
|
"step": 4345,
|
|
"train_runtime": 57275.9738,
|
|
"train_tokens_per_second": 5943.476
|
|
},
|
|
{
|
|
"epoch": 1.74,
|
|
"grad_norm": 0.8915159863034795,
|
|
"learning_rate": 4.1247545418108715e-07,
|
|
"loss": 0.1614,
|
|
"num_input_tokens_seen": 340772864,
|
|
"step": 4350,
|
|
"train_runtime": 57325.0151,
|
|
"train_tokens_per_second": 5944.575
|
|
},
|
|
{
|
|
"epoch": 1.742,
|
|
"grad_norm": 1.1138211845776396,
|
|
"learning_rate": 4.062506618441908e-07,
|
|
"loss": 0.1438,
|
|
"num_input_tokens_seen": 341127504,
|
|
"step": 4355,
|
|
"train_runtime": 57380.8059,
|
|
"train_tokens_per_second": 5944.976
|
|
},
|
|
{
|
|
"epoch": 1.744,
|
|
"grad_norm": 0.8276021440688629,
|
|
"learning_rate": 4.000712079586916e-07,
|
|
"loss": 0.1392,
|
|
"num_input_tokens_seen": 341489712,
|
|
"step": 4360,
|
|
"train_runtime": 57452.2781,
|
|
"train_tokens_per_second": 5943.885
|
|
},
|
|
{
|
|
"epoch": 1.746,
|
|
"grad_norm": 0.7055913168922511,
|
|
"learning_rate": 3.9393715351330243e-07,
|
|
"loss": 0.1662,
|
|
"num_input_tokens_seen": 341885936,
|
|
"step": 4365,
|
|
"train_runtime": 57522.6858,
|
|
"train_tokens_per_second": 5943.497
|
|
},
|
|
{
|
|
"epoch": 1.748,
|
|
"grad_norm": 0.8171241351970536,
|
|
"learning_rate": 3.8784855904866637e-07,
|
|
"loss": 0.1566,
|
|
"num_input_tokens_seen": 342278816,
|
|
"step": 4370,
|
|
"train_runtime": 57592.7929,
|
|
"train_tokens_per_second": 5943.084
|
|
},
|
|
{
|
|
"epoch": 1.75,
|
|
"grad_norm": 0.864986013671374,
|
|
"learning_rate": 3.818054846567515e-07,
|
|
"loss": 0.1537,
|
|
"num_input_tokens_seen": 342626672,
|
|
"step": 4375,
|
|
"train_runtime": 57658.2449,
|
|
"train_tokens_per_second": 5942.371
|
|
},
|
|
{
|
|
"epoch": 1.752,
|
|
"grad_norm": 0.8397705491034702,
|
|
"learning_rate": 3.758079899802619e-07,
|
|
"loss": 0.1457,
|
|
"num_input_tokens_seen": 343003552,
|
|
"step": 4380,
|
|
"train_runtime": 57730.3141,
|
|
"train_tokens_per_second": 5941.481
|
|
},
|
|
{
|
|
"epoch": 1.754,
|
|
"grad_norm": 0.606195325507811,
|
|
"learning_rate": 3.698561342120499e-07,
|
|
"loss": 0.1544,
|
|
"num_input_tokens_seen": 343410656,
|
|
"step": 4385,
|
|
"train_runtime": 57796.3476,
|
|
"train_tokens_per_second": 5941.736
|
|
},
|
|
{
|
|
"epoch": 1.756,
|
|
"grad_norm": 0.7166334905460093,
|
|
"learning_rate": 3.6394997609452755e-07,
|
|
"loss": 0.1624,
|
|
"num_input_tokens_seen": 343837312,
|
|
"step": 4390,
|
|
"train_runtime": 57859.2761,
|
|
"train_tokens_per_second": 5942.648
|
|
},
|
|
{
|
|
"epoch": 1.758,
|
|
"grad_norm": 0.8647929127941133,
|
|
"learning_rate": 3.5808957391909315e-07,
|
|
"loss": 0.15,
|
|
"num_input_tokens_seen": 344159872,
|
|
"step": 4395,
|
|
"train_runtime": 57914.5614,
|
|
"train_tokens_per_second": 5942.545
|
|
},
|
|
{
|
|
"epoch": 1.76,
|
|
"grad_norm": 0.9348681784850232,
|
|
"learning_rate": 3.5227498552554805e-07,
|
|
"loss": 0.1628,
|
|
"num_input_tokens_seen": 344547168,
|
|
"step": 4400,
|
|
"train_runtime": 57968.6739,
|
|
"train_tokens_per_second": 5943.679
|
|
},
|
|
{
|
|
"epoch": 1.762,
|
|
"grad_norm": 0.7753520639920026,
|
|
"learning_rate": 3.465062683015341e-07,
|
|
"loss": 0.1535,
|
|
"num_input_tokens_seen": 344875120,
|
|
"step": 4405,
|
|
"train_runtime": 58019.9217,
|
|
"train_tokens_per_second": 5944.081
|
|
},
|
|
{
|
|
"epoch": 1.764,
|
|
"grad_norm": 0.7447918677525194,
|
|
"learning_rate": 3.407834791819603e-07,
|
|
"loss": 0.1603,
|
|
"num_input_tokens_seen": 345297504,
|
|
"step": 4410,
|
|
"train_runtime": 58097.9733,
|
|
"train_tokens_per_second": 5943.366
|
|
},
|
|
{
|
|
"epoch": 1.766,
|
|
"grad_norm": 0.6727183628099077,
|
|
"learning_rate": 3.351066746484455e-07,
|
|
"loss": 0.1461,
|
|
"num_input_tokens_seen": 345745392,
|
|
"step": 4415,
|
|
"train_runtime": 58171.9462,
|
|
"train_tokens_per_second": 5943.507
|
|
},
|
|
{
|
|
"epoch": 1.768,
|
|
"grad_norm": 0.7901735394650911,
|
|
"learning_rate": 3.294759107287582e-07,
|
|
"loss": 0.1437,
|
|
"num_input_tokens_seen": 346174448,
|
|
"step": 4420,
|
|
"train_runtime": 58247.1768,
|
|
"train_tokens_per_second": 5943.197
|
|
},
|
|
{
|
|
"epoch": 1.77,
|
|
"grad_norm": 0.743079403545147,
|
|
"learning_rate": 3.2389124299626483e-07,
|
|
"loss": 0.1532,
|
|
"num_input_tokens_seen": 346527968,
|
|
"step": 4425,
|
|
"train_runtime": 58310.3091,
|
|
"train_tokens_per_second": 5942.825
|
|
},
|
|
{
|
|
"epoch": 1.772,
|
|
"grad_norm": 0.8627906548317175,
|
|
"learning_rate": 3.18352726569382e-07,
|
|
"loss": 0.1495,
|
|
"num_input_tokens_seen": 346910736,
|
|
"step": 4430,
|
|
"train_runtime": 58369.9461,
|
|
"train_tokens_per_second": 5943.311
|
|
},
|
|
{
|
|
"epoch": 1.774,
|
|
"grad_norm": 0.6456202888499875,
|
|
"learning_rate": 3.128604161110299e-07,
|
|
"loss": 0.1711,
|
|
"num_input_tokens_seen": 347352048,
|
|
"step": 4435,
|
|
"train_runtime": 58444.482,
|
|
"train_tokens_per_second": 5943.282
|
|
},
|
|
{
|
|
"epoch": 1.776,
|
|
"grad_norm": 0.5122814232672431,
|
|
"learning_rate": 3.07414365828097e-07,
|
|
"loss": 0.1553,
|
|
"num_input_tokens_seen": 347744080,
|
|
"step": 4440,
|
|
"train_runtime": 58519.0723,
|
|
"train_tokens_per_second": 5942.406
|
|
},
|
|
{
|
|
"epoch": 1.778,
|
|
"grad_norm": 0.8240295635717674,
|
|
"learning_rate": 3.0201462947089865e-07,
|
|
"loss": 0.1396,
|
|
"num_input_tokens_seen": 348104384,
|
|
"step": 4445,
|
|
"train_runtime": 58582.8049,
|
|
"train_tokens_per_second": 5942.091
|
|
},
|
|
{
|
|
"epoch": 1.78,
|
|
"grad_norm": 0.7665936966292872,
|
|
"learning_rate": 2.9666126033265517e-07,
|
|
"loss": 0.1562,
|
|
"num_input_tokens_seen": 348543616,
|
|
"step": 4450,
|
|
"train_runtime": 58652.2254,
|
|
"train_tokens_per_second": 5942.547
|
|
},
|
|
{
|
|
"epoch": 1.782,
|
|
"grad_norm": 0.6084946557555823,
|
|
"learning_rate": 2.913543112489564e-07,
|
|
"loss": 0.1575,
|
|
"num_input_tokens_seen": 349003296,
|
|
"step": 4455,
|
|
"train_runtime": 58719.9976,
|
|
"train_tokens_per_second": 5943.517
|
|
},
|
|
{
|
|
"epoch": 1.784,
|
|
"grad_norm": 0.8687973913487665,
|
|
"learning_rate": 2.8609383459724915e-07,
|
|
"loss": 0.1686,
|
|
"num_input_tokens_seen": 349434512,
|
|
"step": 4460,
|
|
"train_runtime": 58792.6994,
|
|
"train_tokens_per_second": 5943.502
|
|
},
|
|
{
|
|
"epoch": 1.786,
|
|
"grad_norm": 0.662138989236767,
|
|
"learning_rate": 2.8087988229631325e-07,
|
|
"loss": 0.1445,
|
|
"num_input_tokens_seen": 349754592,
|
|
"step": 4465,
|
|
"train_runtime": 58844.7605,
|
|
"train_tokens_per_second": 5943.683
|
|
},
|
|
{
|
|
"epoch": 1.788,
|
|
"grad_norm": 0.7920562578833943,
|
|
"learning_rate": 2.757125058057536e-07,
|
|
"loss": 0.1537,
|
|
"num_input_tokens_seen": 350108128,
|
|
"step": 4470,
|
|
"train_runtime": 58910.4267,
|
|
"train_tokens_per_second": 5943.059
|
|
},
|
|
{
|
|
"epoch": 1.79,
|
|
"grad_norm": 0.7024284896626523,
|
|
"learning_rate": 2.7059175612548947e-07,
|
|
"loss": 0.1422,
|
|
"num_input_tokens_seen": 350460560,
|
|
"step": 4475,
|
|
"train_runtime": 58977.6689,
|
|
"train_tokens_per_second": 5942.259
|
|
},
|
|
{
|
|
"epoch": 1.792,
|
|
"grad_norm": 0.8137243003503767,
|
|
"learning_rate": 2.655176837952528e-07,
|
|
"loss": 0.1512,
|
|
"num_input_tokens_seen": 350845008,
|
|
"step": 4480,
|
|
"train_runtime": 59043.6586,
|
|
"train_tokens_per_second": 5942.129
|
|
},
|
|
{
|
|
"epoch": 1.794,
|
|
"grad_norm": 0.7560864281422484,
|
|
"learning_rate": 2.604903388940899e-07,
|
|
"loss": 0.1478,
|
|
"num_input_tokens_seen": 351184624,
|
|
"step": 4485,
|
|
"train_runtime": 59112.3808,
|
|
"train_tokens_per_second": 5940.966
|
|
},
|
|
{
|
|
"epoch": 1.796,
|
|
"grad_norm": 0.8069650877273468,
|
|
"learning_rate": 2.555097710398635e-07,
|
|
"loss": 0.1612,
|
|
"num_input_tokens_seen": 351541888,
|
|
"step": 4490,
|
|
"train_runtime": 59182.0092,
|
|
"train_tokens_per_second": 5940.013
|
|
},
|
|
{
|
|
"epoch": 1.798,
|
|
"grad_norm": 0.7183049262552866,
|
|
"learning_rate": 2.505760293887699e-07,
|
|
"loss": 0.1533,
|
|
"num_input_tokens_seen": 351887408,
|
|
"step": 4495,
|
|
"train_runtime": 59243.7428,
|
|
"train_tokens_per_second": 5939.655
|
|
},
|
|
{
|
|
"epoch": 1.8,
|
|
"grad_norm": 0.7511724736236108,
|
|
"learning_rate": 2.456891626348451e-07,
|
|
"loss": 0.1601,
|
|
"num_input_tokens_seen": 352230768,
|
|
"step": 4500,
|
|
"train_runtime": 59301.2527,
|
|
"train_tokens_per_second": 5939.685
|
|
},
|
|
{
|
|
"epoch": 1.802,
|
|
"grad_norm": 0.7259328768604065,
|
|
"learning_rate": 2.40849219009493e-07,
|
|
"loss": 0.1495,
|
|
"num_input_tokens_seen": 352616368,
|
|
"step": 4505,
|
|
"train_runtime": 59366.9718,
|
|
"train_tokens_per_second": 5939.605
|
|
},
|
|
{
|
|
"epoch": 1.804,
|
|
"grad_norm": 0.9394609888477692,
|
|
"learning_rate": 2.3605624628100178e-07,
|
|
"loss": 0.1568,
|
|
"num_input_tokens_seen": 352985856,
|
|
"step": 4510,
|
|
"train_runtime": 59431.266,
|
|
"train_tokens_per_second": 5939.397
|
|
},
|
|
{
|
|
"epoch": 1.806,
|
|
"grad_norm": 0.7391015469588591,
|
|
"learning_rate": 2.3131029175407883e-07,
|
|
"loss": 0.1472,
|
|
"num_input_tokens_seen": 353348672,
|
|
"step": 4515,
|
|
"train_runtime": 59502.8726,
|
|
"train_tokens_per_second": 5938.346
|
|
},
|
|
{
|
|
"epoch": 1.808,
|
|
"grad_norm": 0.603477443612716,
|
|
"learning_rate": 2.2661140226937773e-07,
|
|
"loss": 0.1692,
|
|
"num_input_tokens_seen": 353810608,
|
|
"step": 4520,
|
|
"train_runtime": 59575.7737,
|
|
"train_tokens_per_second": 5938.834
|
|
},
|
|
{
|
|
"epoch": 1.81,
|
|
"grad_norm": 0.6815745937140112,
|
|
"learning_rate": 2.2195962420304083e-07,
|
|
"loss": 0.1548,
|
|
"num_input_tokens_seen": 354265984,
|
|
"step": 4525,
|
|
"train_runtime": 59649.1361,
|
|
"train_tokens_per_second": 5939.164
|
|
},
|
|
{
|
|
"epoch": 1.812,
|
|
"grad_norm": 0.7542355426396135,
|
|
"learning_rate": 2.1735500346624083e-07,
|
|
"loss": 0.1466,
|
|
"num_input_tokens_seen": 354663520,
|
|
"step": 4530,
|
|
"train_runtime": 59714.9232,
|
|
"train_tokens_per_second": 5939.278
|
|
},
|
|
{
|
|
"epoch": 1.814,
|
|
"grad_norm": 0.6765073618424478,
|
|
"learning_rate": 2.127975855047243e-07,
|
|
"loss": 0.1529,
|
|
"num_input_tokens_seen": 355100976,
|
|
"step": 4535,
|
|
"train_runtime": 59788.9534,
|
|
"train_tokens_per_second": 5939.241
|
|
},
|
|
{
|
|
"epoch": 1.8159999999999998,
|
|
"grad_norm": 0.8250422516813881,
|
|
"learning_rate": 2.0828741529836771e-07,
|
|
"loss": 0.1474,
|
|
"num_input_tokens_seen": 355468432,
|
|
"step": 4540,
|
|
"train_runtime": 59850.4732,
|
|
"train_tokens_per_second": 5939.275
|
|
},
|
|
{
|
|
"epoch": 1.818,
|
|
"grad_norm": 0.7034354581468405,
|
|
"learning_rate": 2.0382453736072838e-07,
|
|
"loss": 0.1685,
|
|
"num_input_tokens_seen": 355871536,
|
|
"step": 4545,
|
|
"train_runtime": 59928.1524,
|
|
"train_tokens_per_second": 5938.303
|
|
},
|
|
{
|
|
"epoch": 1.8199999999999998,
|
|
"grad_norm": 0.7583244472846854,
|
|
"learning_rate": 1.9940899573861195e-07,
|
|
"loss": 0.1495,
|
|
"num_input_tokens_seen": 356268624,
|
|
"step": 4550,
|
|
"train_runtime": 59999.8101,
|
|
"train_tokens_per_second": 5937.829
|
|
},
|
|
{
|
|
"epoch": 1.822,
|
|
"grad_norm": 0.8512363766568244,
|
|
"learning_rate": 1.9504083401162999e-07,
|
|
"loss": 0.1574,
|
|
"num_input_tokens_seen": 356731600,
|
|
"step": 4555,
|
|
"train_runtime": 60076.8179,
|
|
"train_tokens_per_second": 5937.924
|
|
},
|
|
{
|
|
"epoch": 1.8239999999999998,
|
|
"grad_norm": 0.8250539539288417,
|
|
"learning_rate": 1.907200952917765e-07,
|
|
"loss": 0.1614,
|
|
"num_input_tokens_seen": 357148736,
|
|
"step": 4560,
|
|
"train_runtime": 60155.2921,
|
|
"train_tokens_per_second": 5937.112
|
|
},
|
|
{
|
|
"epoch": 1.826,
|
|
"grad_norm": 0.8555656498953154,
|
|
"learning_rate": 1.8644682222299703e-07,
|
|
"loss": 0.1668,
|
|
"num_input_tokens_seen": 357530208,
|
|
"step": 4565,
|
|
"train_runtime": 60221.8596,
|
|
"train_tokens_per_second": 5936.884
|
|
},
|
|
{
|
|
"epoch": 1.8279999999999998,
|
|
"grad_norm": 0.7686445662924045,
|
|
"learning_rate": 1.8222105698077253e-07,
|
|
"loss": 0.1758,
|
|
"num_input_tokens_seen": 357929040,
|
|
"step": 4570,
|
|
"train_runtime": 60300.1902,
|
|
"train_tokens_per_second": 5935.786
|
|
},
|
|
{
|
|
"epoch": 1.83,
|
|
"grad_norm": 0.6708183387478129,
|
|
"learning_rate": 1.7804284127169946e-07,
|
|
"loss": 0.1532,
|
|
"num_input_tokens_seen": 358378688,
|
|
"step": 4575,
|
|
"train_runtime": 60368.5478,
|
|
"train_tokens_per_second": 5936.513
|
|
},
|
|
{
|
|
"epoch": 1.8319999999999999,
|
|
"grad_norm": 0.5960294001456247,
|
|
"learning_rate": 1.7391221633308032e-07,
|
|
"loss": 0.1459,
|
|
"num_input_tokens_seen": 358789536,
|
|
"step": 4580,
|
|
"train_runtime": 60433.7718,
|
|
"train_tokens_per_second": 5936.905
|
|
},
|
|
{
|
|
"epoch": 1.834,
|
|
"grad_norm": 0.946956247138258,
|
|
"learning_rate": 1.6982922293251548e-07,
|
|
"loss": 0.1522,
|
|
"num_input_tokens_seen": 359199840,
|
|
"step": 4585,
|
|
"train_runtime": 60494.8739,
|
|
"train_tokens_per_second": 5937.691
|
|
},
|
|
{
|
|
"epoch": 1.8359999999999999,
|
|
"grad_norm": 0.6711965164950642,
|
|
"learning_rate": 1.6579390136750086e-07,
|
|
"loss": 0.1687,
|
|
"num_input_tokens_seen": 359666192,
|
|
"step": 4590,
|
|
"train_runtime": 60571.8885,
|
|
"train_tokens_per_second": 5937.84
|
|
},
|
|
{
|
|
"epoch": 1.838,
|
|
"grad_norm": 0.9426140630055698,
|
|
"learning_rate": 1.6180629146503256e-07,
|
|
"loss": 0.1542,
|
|
"num_input_tokens_seen": 360085104,
|
|
"step": 4595,
|
|
"train_runtime": 60642.0984,
|
|
"train_tokens_per_second": 5937.873
|
|
},
|
|
{
|
|
"epoch": 1.8399999999999999,
|
|
"grad_norm": 0.7909187217499214,
|
|
"learning_rate": 1.5786643258120905e-07,
|
|
"loss": 0.1516,
|
|
"num_input_tokens_seen": 360529536,
|
|
"step": 4600,
|
|
"train_runtime": 60717.1389,
|
|
"train_tokens_per_second": 5937.854
|
|
},
|
|
{
|
|
"epoch": 1.842,
|
|
"grad_norm": 0.7383782742890509,
|
|
"learning_rate": 1.5397436360084784e-07,
|
|
"loss": 0.1744,
|
|
"num_input_tokens_seen": 360968864,
|
|
"step": 4605,
|
|
"train_runtime": 60791.8093,
|
|
"train_tokens_per_second": 5937.788
|
|
},
|
|
{
|
|
"epoch": 1.8439999999999999,
|
|
"grad_norm": 0.7497496609918477,
|
|
"learning_rate": 1.5013012293709828e-07,
|
|
"loss": 0.1603,
|
|
"num_input_tokens_seen": 361417600,
|
|
"step": 4610,
|
|
"train_runtime": 60861.6883,
|
|
"train_tokens_per_second": 5938.343
|
|
},
|
|
{
|
|
"epoch": 1.846,
|
|
"grad_norm": 0.668995274398484,
|
|
"learning_rate": 1.463337485310634e-07,
|
|
"loss": 0.1525,
|
|
"num_input_tokens_seen": 361839200,
|
|
"step": 4615,
|
|
"train_runtime": 60937.5334,
|
|
"train_tokens_per_second": 5937.871
|
|
},
|
|
{
|
|
"epoch": 1.8479999999999999,
|
|
"grad_norm": 0.792692843548526,
|
|
"learning_rate": 1.425852778514264e-07,
|
|
"loss": 0.1512,
|
|
"num_input_tokens_seen": 362259616,
|
|
"step": 4620,
|
|
"train_runtime": 61012.2498,
|
|
"train_tokens_per_second": 5937.49
|
|
},
|
|
{
|
|
"epoch": 1.85,
|
|
"grad_norm": 0.82569595179028,
|
|
"learning_rate": 1.388847478940797e-07,
|
|
"loss": 0.1478,
|
|
"num_input_tokens_seen": 362678496,
|
|
"step": 4625,
|
|
"train_runtime": 61080.254,
|
|
"train_tokens_per_second": 5937.737
|
|
},
|
|
{
|
|
"epoch": 1.8519999999999999,
|
|
"grad_norm": 1.1467063040896035,
|
|
"learning_rate": 1.3523219518175924e-07,
|
|
"loss": 0.1567,
|
|
"num_input_tokens_seen": 363027968,
|
|
"step": 4630,
|
|
"train_runtime": 61124.8998,
|
|
"train_tokens_per_second": 5939.118
|
|
},
|
|
{
|
|
"epoch": 1.854,
|
|
"grad_norm": 0.6253577254652782,
|
|
"learning_rate": 1.3162765576368587e-07,
|
|
"loss": 0.1484,
|
|
"num_input_tokens_seen": 363395040,
|
|
"step": 4635,
|
|
"train_runtime": 61192.9957,
|
|
"train_tokens_per_second": 5938.507
|
|
},
|
|
{
|
|
"epoch": 1.8559999999999999,
|
|
"grad_norm": 0.7446648872982482,
|
|
"learning_rate": 1.2807116521520947e-07,
|
|
"loss": 0.1595,
|
|
"num_input_tokens_seen": 363789744,
|
|
"step": 4640,
|
|
"train_runtime": 61264.3065,
|
|
"train_tokens_per_second": 5938.037
|
|
},
|
|
{
|
|
"epoch": 1.858,
|
|
"grad_norm": 0.7912008499572333,
|
|
"learning_rate": 1.2456275863745426e-07,
|
|
"loss": 0.1655,
|
|
"num_input_tokens_seen": 364247552,
|
|
"step": 4645,
|
|
"train_runtime": 61342.3354,
|
|
"train_tokens_per_second": 5937.947
|
|
},
|
|
{
|
|
"epoch": 1.8599999999999999,
|
|
"grad_norm": 0.6141134582638248,
|
|
"learning_rate": 1.21102470656978e-07,
|
|
"loss": 0.1425,
|
|
"num_input_tokens_seen": 364725648,
|
|
"step": 4650,
|
|
"train_runtime": 61419.385,
|
|
"train_tokens_per_second": 5938.282
|
|
},
|
|
{
|
|
"epoch": 1.862,
|
|
"grad_norm": 0.589110086213904,
|
|
"learning_rate": 1.1769033542542552e-07,
|
|
"loss": 0.1431,
|
|
"num_input_tokens_seen": 365182608,
|
|
"step": 4655,
|
|
"train_runtime": 61496.9331,
|
|
"train_tokens_per_second": 5938.225
|
|
},
|
|
{
|
|
"epoch": 1.8639999999999999,
|
|
"grad_norm": 0.6925283853283911,
|
|
"learning_rate": 1.1432638661919515e-07,
|
|
"loss": 0.1512,
|
|
"num_input_tokens_seen": 365552736,
|
|
"step": 4660,
|
|
"train_runtime": 61565.7418,
|
|
"train_tokens_per_second": 5937.6
|
|
},
|
|
{
|
|
"epoch": 1.866,
|
|
"grad_norm": 0.8422806070328288,
|
|
"learning_rate": 1.1101065743910122e-07,
|
|
"loss": 0.1497,
|
|
"num_input_tokens_seen": 365922048,
|
|
"step": 4665,
|
|
"train_runtime": 61624.0983,
|
|
"train_tokens_per_second": 5937.97
|
|
},
|
|
{
|
|
"epoch": 1.8679999999999999,
|
|
"grad_norm": 0.8392981689860877,
|
|
"learning_rate": 1.0774318061005484e-07,
|
|
"loss": 0.154,
|
|
"num_input_tokens_seen": 366317200,
|
|
"step": 4670,
|
|
"train_runtime": 61687.543,
|
|
"train_tokens_per_second": 5938.269
|
|
},
|
|
{
|
|
"epoch": 1.87,
|
|
"grad_norm": 0.8625802105358468,
|
|
"learning_rate": 1.0452398838073141e-07,
|
|
"loss": 0.157,
|
|
"num_input_tokens_seen": 366742816,
|
|
"step": 4675,
|
|
"train_runtime": 61762.5292,
|
|
"train_tokens_per_second": 5937.95
|
|
},
|
|
{
|
|
"epoch": 1.8719999999999999,
|
|
"grad_norm": 0.7200055447393615,
|
|
"learning_rate": 1.0135311252325863e-07,
|
|
"loss": 0.1532,
|
|
"num_input_tokens_seen": 367106336,
|
|
"step": 4680,
|
|
"train_runtime": 61821.9722,
|
|
"train_tokens_per_second": 5938.121
|
|
},
|
|
{
|
|
"epoch": 1.874,
|
|
"grad_norm": 0.880386998336964,
|
|
"learning_rate": 9.823058433290178e-08,
|
|
"loss": 0.1573,
|
|
"num_input_tokens_seen": 367428640,
|
|
"step": 4685,
|
|
"train_runtime": 61875.3672,
|
|
"train_tokens_per_second": 5938.205
|
|
},
|
|
{
|
|
"epoch": 1.876,
|
|
"grad_norm": 0.556646340581699,
|
|
"learning_rate": 9.515643462775337e-08,
|
|
"loss": 0.1385,
|
|
"num_input_tokens_seen": 367814192,
|
|
"step": 4690,
|
|
"train_runtime": 61940.6093,
|
|
"train_tokens_per_second": 5938.175
|
|
},
|
|
{
|
|
"epoch": 1.8780000000000001,
|
|
"grad_norm": 0.5784712410273231,
|
|
"learning_rate": 9.213069374842953e-08,
|
|
"loss": 0.1574,
|
|
"num_input_tokens_seen": 368216192,
|
|
"step": 4695,
|
|
"train_runtime": 62008.5173,
|
|
"train_tokens_per_second": 5938.155
|
|
},
|
|
{
|
|
"epoch": 1.88,
|
|
"grad_norm": 0.6875768403843328,
|
|
"learning_rate": 8.915339155777136e-08,
|
|
"loss": 0.1661,
|
|
"num_input_tokens_seen": 368698608,
|
|
"step": 4700,
|
|
"train_runtime": 62087.325,
|
|
"train_tokens_per_second": 5938.388
|
|
},
|
|
{
|
|
"epoch": 1.8820000000000001,
|
|
"grad_norm": 0.6784742989249009,
|
|
"learning_rate": 8.622455744054958e-08,
|
|
"loss": 0.1657,
|
|
"num_input_tokens_seen": 369162816,
|
|
"step": 4705,
|
|
"train_runtime": 62163.2518,
|
|
"train_tokens_per_second": 5938.602
|
|
},
|
|
{
|
|
"epoch": 1.884,
|
|
"grad_norm": 0.7324550742521656,
|
|
"learning_rate": 8.334422030317424e-08,
|
|
"loss": 0.1618,
|
|
"num_input_tokens_seen": 369534656,
|
|
"step": 4710,
|
|
"train_runtime": 62226.4914,
|
|
"train_tokens_per_second": 5938.542
|
|
},
|
|
{
|
|
"epoch": 1.8860000000000001,
|
|
"grad_norm": 0.6097184043787661,
|
|
"learning_rate": 8.051240857341102e-08,
|
|
"loss": 0.147,
|
|
"num_input_tokens_seen": 369905840,
|
|
"step": 4715,
|
|
"train_runtime": 62289.2274,
|
|
"train_tokens_per_second": 5938.52
|
|
},
|
|
{
|
|
"epoch": 1.888,
|
|
"grad_norm": 0.666015011240103,
|
|
"learning_rate": 7.772915020009708e-08,
|
|
"loss": 0.1517,
|
|
"num_input_tokens_seen": 370319248,
|
|
"step": 4720,
|
|
"train_runtime": 62362.8182,
|
|
"train_tokens_per_second": 5938.142
|
|
},
|
|
{
|
|
"epoch": 1.8900000000000001,
|
|
"grad_norm": 0.5763015175555796,
|
|
"learning_rate": 7.499447265286952e-08,
|
|
"loss": 0.1539,
|
|
"num_input_tokens_seen": 370800368,
|
|
"step": 4725,
|
|
"train_runtime": 62435.7298,
|
|
"train_tokens_per_second": 5938.913
|
|
},
|
|
{
|
|
"epoch": 1.892,
|
|
"grad_norm": 0.729225466922384,
|
|
"learning_rate": 7.230840292189179e-08,
|
|
"loss": 0.1681,
|
|
"num_input_tokens_seen": 371215312,
|
|
"step": 4730,
|
|
"train_runtime": 62509.6841,
|
|
"train_tokens_per_second": 5938.525
|
|
},
|
|
{
|
|
"epoch": 1.8940000000000001,
|
|
"grad_norm": 0.8534774644572202,
|
|
"learning_rate": 6.967096751758773e-08,
|
|
"loss": 0.1502,
|
|
"num_input_tokens_seen": 371507376,
|
|
"step": 4735,
|
|
"train_runtime": 62556.5965,
|
|
"train_tokens_per_second": 5938.74
|
|
},
|
|
{
|
|
"epoch": 1.896,
|
|
"grad_norm": 0.7212851430574398,
|
|
"learning_rate": 6.708219247038017e-08,
|
|
"loss": 0.1561,
|
|
"num_input_tokens_seen": 371934544,
|
|
"step": 4740,
|
|
"train_runtime": 62634.5867,
|
|
"train_tokens_per_second": 5938.166
|
|
},
|
|
{
|
|
"epoch": 1.8980000000000001,
|
|
"grad_norm": 0.7288850535855359,
|
|
"learning_rate": 6.454210333043275e-08,
|
|
"loss": 0.1426,
|
|
"num_input_tokens_seen": 372310320,
|
|
"step": 4745,
|
|
"train_runtime": 62693.8078,
|
|
"train_tokens_per_second": 5938.55
|
|
},
|
|
{
|
|
"epoch": 1.9,
|
|
"grad_norm": 0.6806533435057149,
|
|
"learning_rate": 6.205072516740129e-08,
|
|
"loss": 0.1511,
|
|
"num_input_tokens_seen": 372661872,
|
|
"step": 4750,
|
|
"train_runtime": 62751.1379,
|
|
"train_tokens_per_second": 5938.727
|
|
},
|
|
{
|
|
"epoch": 1.9020000000000001,
|
|
"grad_norm": 0.8388251018260441,
|
|
"learning_rate": 5.960808257018113e-08,
|
|
"loss": 0.1648,
|
|
"num_input_tokens_seen": 373084368,
|
|
"step": 4755,
|
|
"train_runtime": 62817.8123,
|
|
"train_tokens_per_second": 5939.149
|
|
},
|
|
{
|
|
"epoch": 1.904,
|
|
"grad_norm": 0.7612503184122242,
|
|
"learning_rate": 5.7214199646669076e-08,
|
|
"loss": 0.149,
|
|
"num_input_tokens_seen": 373490144,
|
|
"step": 4760,
|
|
"train_runtime": 62895.9564,
|
|
"train_tokens_per_second": 5938.222
|
|
},
|
|
{
|
|
"epoch": 1.9060000000000001,
|
|
"grad_norm": 0.8318839418867255,
|
|
"learning_rate": 5.4869100023523526e-08,
|
|
"loss": 0.1523,
|
|
"num_input_tokens_seen": 373829536,
|
|
"step": 4765,
|
|
"train_runtime": 62953.8814,
|
|
"train_tokens_per_second": 5938.149
|
|
},
|
|
{
|
|
"epoch": 1.908,
|
|
"grad_norm": 0.6487161452783756,
|
|
"learning_rate": 5.2572806845930244e-08,
|
|
"loss": 0.1497,
|
|
"num_input_tokens_seen": 374173664,
|
|
"step": 4770,
|
|
"train_runtime": 63016.7985,
|
|
"train_tokens_per_second": 5937.681
|
|
},
|
|
{
|
|
"epoch": 1.9100000000000001,
|
|
"grad_norm": 0.6868042103732213,
|
|
"learning_rate": 5.032534277737644e-08,
|
|
"loss": 0.1747,
|
|
"num_input_tokens_seen": 374591792,
|
|
"step": 4775,
|
|
"train_runtime": 63083.9208,
|
|
"train_tokens_per_second": 5937.992
|
|
},
|
|
{
|
|
"epoch": 1.912,
|
|
"grad_norm": 0.6714323255807126,
|
|
"learning_rate": 4.81267299994248e-08,
|
|
"loss": 0.1591,
|
|
"num_input_tokens_seen": 375056544,
|
|
"step": 4780,
|
|
"train_runtime": 63161.5792,
|
|
"train_tokens_per_second": 5938.049
|
|
},
|
|
{
|
|
"epoch": 1.9140000000000001,
|
|
"grad_norm": 0.7346006160868402,
|
|
"learning_rate": 4.597699021149649e-08,
|
|
"loss": 0.1481,
|
|
"num_input_tokens_seen": 375473328,
|
|
"step": 4785,
|
|
"train_runtime": 63232.1122,
|
|
"train_tokens_per_second": 5938.017
|
|
},
|
|
{
|
|
"epoch": 1.916,
|
|
"grad_norm": 0.7674342092143264,
|
|
"learning_rate": 4.387614463065404e-08,
|
|
"loss": 0.1595,
|
|
"num_input_tokens_seen": 375937584,
|
|
"step": 4790,
|
|
"train_runtime": 63307.4543,
|
|
"train_tokens_per_second": 5938.283
|
|
},
|
|
{
|
|
"epoch": 1.9180000000000001,
|
|
"grad_norm": 0.6504531700444212,
|
|
"learning_rate": 4.1824213991396024e-08,
|
|
"loss": 0.1659,
|
|
"num_input_tokens_seen": 376345344,
|
|
"step": 4795,
|
|
"train_runtime": 63373.775,
|
|
"train_tokens_per_second": 5938.503
|
|
},
|
|
{
|
|
"epoch": 1.92,
|
|
"grad_norm": 0.7779660047411081,
|
|
"learning_rate": 3.9821218545449956e-08,
|
|
"loss": 0.1663,
|
|
"num_input_tokens_seen": 376703552,
|
|
"step": 4800,
|
|
"train_runtime": 63436.4972,
|
|
"train_tokens_per_second": 5938.278
|
|
},
|
|
{
|
|
"epoch": 1.9220000000000002,
|
|
"grad_norm": 0.7659507878224847,
|
|
"learning_rate": 3.786717806157136e-08,
|
|
"loss": 0.1634,
|
|
"num_input_tokens_seen": 377097632,
|
|
"step": 4805,
|
|
"train_runtime": 63506.7502,
|
|
"train_tokens_per_second": 5937.914
|
|
},
|
|
{
|
|
"epoch": 1.924,
|
|
"grad_norm": 0.6866853917620325,
|
|
"learning_rate": 3.5962111825350585e-08,
|
|
"loss": 0.1494,
|
|
"num_input_tokens_seen": 377493120,
|
|
"step": 4810,
|
|
"train_runtime": 63576.3896,
|
|
"train_tokens_per_second": 5937.631
|
|
},
|
|
{
|
|
"epoch": 1.9260000000000002,
|
|
"grad_norm": 0.9366824273788991,
|
|
"learning_rate": 3.410603863902406e-08,
|
|
"loss": 0.1455,
|
|
"num_input_tokens_seen": 377869200,
|
|
"step": 4815,
|
|
"train_runtime": 63638.3721,
|
|
"train_tokens_per_second": 5937.757
|
|
},
|
|
{
|
|
"epoch": 1.928,
|
|
"grad_norm": 0.7079656619304824,
|
|
"learning_rate": 3.2298976821282804e-08,
|
|
"loss": 0.153,
|
|
"num_input_tokens_seen": 378239120,
|
|
"step": 4820,
|
|
"train_runtime": 63700.2916,
|
|
"train_tokens_per_second": 5937.793
|
|
},
|
|
{
|
|
"epoch": 1.9300000000000002,
|
|
"grad_norm": 0.7664230296718139,
|
|
"learning_rate": 3.054094420709863e-08,
|
|
"loss": 0.1493,
|
|
"num_input_tokens_seen": 378639088,
|
|
"step": 4825,
|
|
"train_runtime": 63769.9795,
|
|
"train_tokens_per_second": 5937.576
|
|
},
|
|
{
|
|
"epoch": 1.932,
|
|
"grad_norm": 0.9685887343358113,
|
|
"learning_rate": 2.8831958147543805e-08,
|
|
"loss": 0.1456,
|
|
"num_input_tokens_seen": 378986240,
|
|
"step": 4830,
|
|
"train_runtime": 63820.3507,
|
|
"train_tokens_per_second": 5938.329
|
|
},
|
|
{
|
|
"epoch": 1.9340000000000002,
|
|
"grad_norm": 0.7015259491861456,
|
|
"learning_rate": 2.7172035509619442e-08,
|
|
"loss": 0.1509,
|
|
"num_input_tokens_seen": 379402800,
|
|
"step": 4835,
|
|
"train_runtime": 63891.4301,
|
|
"train_tokens_per_second": 5938.242
|
|
},
|
|
{
|
|
"epoch": 1.936,
|
|
"grad_norm": 0.6597504242438265,
|
|
"learning_rate": 2.556119267609347e-08,
|
|
"loss": 0.1631,
|
|
"num_input_tokens_seen": 379748272,
|
|
"step": 4840,
|
|
"train_runtime": 63949.7096,
|
|
"train_tokens_per_second": 5938.233
|
|
},
|
|
{
|
|
"epoch": 1.938,
|
|
"grad_norm": 0.771655430556284,
|
|
"learning_rate": 2.3999445545332955e-08,
|
|
"loss": 0.1486,
|
|
"num_input_tokens_seen": 380120432,
|
|
"step": 4845,
|
|
"train_runtime": 64013.1612,
|
|
"train_tokens_per_second": 5938.161
|
|
},
|
|
{
|
|
"epoch": 1.94,
|
|
"grad_norm": 0.8493098216978953,
|
|
"learning_rate": 2.2486809531152563e-08,
|
|
"loss": 0.1553,
|
|
"num_input_tokens_seen": 380466704,
|
|
"step": 4850,
|
|
"train_runtime": 64076.5096,
|
|
"train_tokens_per_second": 5937.694
|
|
},
|
|
{
|
|
"epoch": 1.942,
|
|
"grad_norm": 1.042184396192737,
|
|
"learning_rate": 2.1023299562658584e-08,
|
|
"loss": 0.159,
|
|
"num_input_tokens_seen": 380797952,
|
|
"step": 4855,
|
|
"train_runtime": 64120.7263,
|
|
"train_tokens_per_second": 5938.765
|
|
},
|
|
{
|
|
"epoch": 1.944,
|
|
"grad_norm": 0.8065241432185793,
|
|
"learning_rate": 1.9608930084104027e-08,
|
|
"loss": 0.151,
|
|
"num_input_tokens_seen": 381229408,
|
|
"step": 4860,
|
|
"train_runtime": 64182.8175,
|
|
"train_tokens_per_second": 5939.742
|
|
},
|
|
{
|
|
"epoch": 1.946,
|
|
"grad_norm": 0.6905242206927509,
|
|
"learning_rate": 1.8243715054744315e-08,
|
|
"loss": 0.1501,
|
|
"num_input_tokens_seen": 381589840,
|
|
"step": 4865,
|
|
"train_runtime": 64248.1914,
|
|
"train_tokens_per_second": 5939.309
|
|
},
|
|
{
|
|
"epoch": 1.948,
|
|
"grad_norm": 1.1071577342385468,
|
|
"learning_rate": 1.6927667948700155e-08,
|
|
"loss": 0.1671,
|
|
"num_input_tokens_seen": 382043232,
|
|
"step": 4870,
|
|
"train_runtime": 64319.1009,
|
|
"train_tokens_per_second": 5939.81
|
|
},
|
|
{
|
|
"epoch": 1.95,
|
|
"grad_norm": 0.7597420246133529,
|
|
"learning_rate": 1.5660801754825983e-08,
|
|
"loss": 0.1458,
|
|
"num_input_tokens_seen": 382438480,
|
|
"step": 4875,
|
|
"train_runtime": 64397.2202,
|
|
"train_tokens_per_second": 5938.742
|
|
},
|
|
{
|
|
"epoch": 1.952,
|
|
"grad_norm": 0.8326844892590033,
|
|
"learning_rate": 1.4443128976579513e-08,
|
|
"loss": 0.1399,
|
|
"num_input_tokens_seen": 382832560,
|
|
"step": 4880,
|
|
"train_runtime": 64465.7391,
|
|
"train_tokens_per_second": 5938.543
|
|
},
|
|
{
|
|
"epoch": 1.954,
|
|
"grad_norm": 0.7694840871608274,
|
|
"learning_rate": 1.3274661631899055e-08,
|
|
"loss": 0.141,
|
|
"num_input_tokens_seen": 383181280,
|
|
"step": 4885,
|
|
"train_runtime": 64519.1075,
|
|
"train_tokens_per_second": 5939.036
|
|
},
|
|
{
|
|
"epoch": 1.956,
|
|
"grad_norm": 0.7620739132390568,
|
|
"learning_rate": 1.2155411253085835e-08,
|
|
"loss": 0.1554,
|
|
"num_input_tokens_seen": 383546752,
|
|
"step": 4890,
|
|
"train_runtime": 64591.6143,
|
|
"train_tokens_per_second": 5938.027
|
|
},
|
|
{
|
|
"epoch": 1.958,
|
|
"grad_norm": 0.6225036043903326,
|
|
"learning_rate": 1.1085388886689085e-08,
|
|
"loss": 0.1543,
|
|
"num_input_tokens_seen": 383933440,
|
|
"step": 4895,
|
|
"train_runtime": 64649.7676,
|
|
"train_tokens_per_second": 5938.667
|
|
},
|
|
{
|
|
"epoch": 1.96,
|
|
"grad_norm": 0.5857614160553338,
|
|
"learning_rate": 1.0064605093397794e-08,
|
|
"loss": 0.1515,
|
|
"num_input_tokens_seen": 384386960,
|
|
"step": 4900,
|
|
"train_runtime": 64726.6587,
|
|
"train_tokens_per_second": 5938.619
|
|
},
|
|
{
|
|
"epoch": 1.962,
|
|
"grad_norm": 1.1240815802110373,
|
|
"learning_rate": 9.09306994793635e-09,
|
|
"loss": 0.1521,
|
|
"num_input_tokens_seen": 384734336,
|
|
"step": 4905,
|
|
"train_runtime": 64782.2287,
|
|
"train_tokens_per_second": 5938.887
|
|
},
|
|
{
|
|
"epoch": 1.964,
|
|
"grad_norm": 0.8013089128003337,
|
|
"learning_rate": 8.17079303896351e-09,
|
|
"loss": 0.1519,
|
|
"num_input_tokens_seen": 385162112,
|
|
"step": 4910,
|
|
"train_runtime": 64857.3513,
|
|
"train_tokens_per_second": 5938.604
|
|
},
|
|
{
|
|
"epoch": 1.966,
|
|
"grad_norm": 0.6537534676205653,
|
|
"learning_rate": 7.297783468980246e-09,
|
|
"loss": 0.162,
|
|
"num_input_tokens_seen": 385595168,
|
|
"step": 4915,
|
|
"train_runtime": 64929.6603,
|
|
"train_tokens_per_second": 5938.66
|
|
},
|
|
{
|
|
"epoch": 1.968,
|
|
"grad_norm": 0.6968813478617545,
|
|
"learning_rate": 6.4740498542387174e-09,
|
|
"loss": 0.1453,
|
|
"num_input_tokens_seen": 385979072,
|
|
"step": 4920,
|
|
"train_runtime": 64993.5203,
|
|
"train_tokens_per_second": 5938.732
|
|
},
|
|
{
|
|
"epoch": 1.97,
|
|
"grad_norm": 0.5697832535681487,
|
|
"learning_rate": 5.699600324657328e-09,
|
|
"loss": 0.1494,
|
|
"num_input_tokens_seen": 386395168,
|
|
"step": 4925,
|
|
"train_runtime": 65058.8548,
|
|
"train_tokens_per_second": 5939.163
|
|
},
|
|
{
|
|
"epoch": 1.972,
|
|
"grad_norm": 1.2111230864901055,
|
|
"learning_rate": 4.9744425237396865e-09,
|
|
"loss": 0.1559,
|
|
"num_input_tokens_seen": 386844528,
|
|
"step": 4930,
|
|
"train_runtime": 65135.2593,
|
|
"train_tokens_per_second": 5939.096
|
|
},
|
|
{
|
|
"epoch": 1.974,
|
|
"grad_norm": 0.6928071348228707,
|
|
"learning_rate": 4.298583608501328e-09,
|
|
"loss": 0.1714,
|
|
"num_input_tokens_seen": 387236864,
|
|
"step": 4935,
|
|
"train_runtime": 65190.3296,
|
|
"train_tokens_per_second": 5940.097
|
|
},
|
|
{
|
|
"epoch": 1.976,
|
|
"grad_norm": 0.7145374932720133,
|
|
"learning_rate": 3.672030249396441e-09,
|
|
"loss": 0.1646,
|
|
"num_input_tokens_seen": 387642192,
|
|
"step": 4940,
|
|
"train_runtime": 65254.881,
|
|
"train_tokens_per_second": 5940.432
|
|
},
|
|
{
|
|
"epoch": 1.978,
|
|
"grad_norm": 0.7769545179947129,
|
|
"learning_rate": 3.094788630254031e-09,
|
|
"loss": 0.162,
|
|
"num_input_tokens_seen": 388059072,
|
|
"step": 4945,
|
|
"train_runtime": 65317.3613,
|
|
"train_tokens_per_second": 5941.132
|
|
},
|
|
{
|
|
"epoch": 1.98,
|
|
"grad_norm": 0.7741033021358061,
|
|
"learning_rate": 2.5668644482151892e-09,
|
|
"loss": 0.1452,
|
|
"num_input_tokens_seen": 388484560,
|
|
"step": 4950,
|
|
"train_runtime": 65386.4344,
|
|
"train_tokens_per_second": 5941.363
|
|
},
|
|
{
|
|
"epoch": 1.982,
|
|
"grad_norm": 0.8277423778894699,
|
|
"learning_rate": 2.088262913679251e-09,
|
|
"loss": 0.1581,
|
|
"num_input_tokens_seen": 388827712,
|
|
"step": 4955,
|
|
"train_runtime": 65440.5816,
|
|
"train_tokens_per_second": 5941.691
|
|
},
|
|
{
|
|
"epoch": 1.984,
|
|
"grad_norm": 0.6775847367683332,
|
|
"learning_rate": 1.6589887502493907e-09,
|
|
"loss": 0.1581,
|
|
"num_input_tokens_seen": 389247824,
|
|
"step": 4960,
|
|
"train_runtime": 65518.1435,
|
|
"train_tokens_per_second": 5941.069
|
|
},
|
|
{
|
|
"epoch": 1.986,
|
|
"grad_norm": 0.7178108510620933,
|
|
"learning_rate": 1.2790461946887712e-09,
|
|
"loss": 0.157,
|
|
"num_input_tokens_seen": 389639584,
|
|
"step": 4965,
|
|
"train_runtime": 65595.8645,
|
|
"train_tokens_per_second": 5940.002
|
|
},
|
|
{
|
|
"epoch": 1.988,
|
|
"grad_norm": 0.6854334829602473,
|
|
"learning_rate": 9.484389968766882e-10,
|
|
"loss": 0.158,
|
|
"num_input_tokens_seen": 390047648,
|
|
"step": 4970,
|
|
"train_runtime": 65660.0021,
|
|
"train_tokens_per_second": 5940.415
|
|
},
|
|
{
|
|
"epoch": 1.99,
|
|
"grad_norm": 0.7191417155028322,
|
|
"learning_rate": 6.671704197735995e-10,
|
|
"loss": 0.1632,
|
|
"num_input_tokens_seen": 390419856,
|
|
"step": 4975,
|
|
"train_runtime": 65717.6775,
|
|
"train_tokens_per_second": 5940.865
|
|
},
|
|
{
|
|
"epoch": 1.992,
|
|
"grad_norm": 0.6423440131309586,
|
|
"learning_rate": 4.3524323938559655e-10,
|
|
"loss": 0.153,
|
|
"num_input_tokens_seen": 390808512,
|
|
"step": 4980,
|
|
"train_runtime": 65785.3488,
|
|
"train_tokens_per_second": 5940.662
|
|
},
|
|
{
|
|
"epoch": 1.994,
|
|
"grad_norm": 0.5750505572416644,
|
|
"learning_rate": 2.5265974474109054e-10,
|
|
"loss": 0.1537,
|
|
"num_input_tokens_seen": 391214192,
|
|
"step": 4985,
|
|
"train_runtime": 65844.0384,
|
|
"train_tokens_per_second": 5941.528
|
|
},
|
|
{
|
|
"epoch": 1.996,
|
|
"grad_norm": 0.8744993490514669,
|
|
"learning_rate": 1.1942173786527732e-10,
|
|
"loss": 0.1569,
|
|
"num_input_tokens_seen": 391600608,
|
|
"step": 4990,
|
|
"train_runtime": 65916.6129,
|
|
"train_tokens_per_second": 5940.848
|
|
},
|
|
{
|
|
"epoch": 1.998,
|
|
"grad_norm": 0.7063071436578877,
|
|
"learning_rate": 3.55305337634837e-11,
|
|
"loss": 0.1555,
|
|
"num_input_tokens_seen": 391994016,
|
|
"step": 4995,
|
|
"train_runtime": 65990.8234,
|
|
"train_tokens_per_second": 5940.129
|
|
},
|
|
{
|
|
"epoch": 2.0,
|
|
"grad_norm": 0.7623938207114338,
|
|
"learning_rate": 9.869604078449612e-13,
|
|
"loss": 0.1515,
|
|
"num_input_tokens_seen": 392342880,
|
|
"step": 5000,
|
|
"train_runtime": 66052.8886,
|
|
"train_tokens_per_second": 5939.829
|
|
},
|
|
{
|
|
"epoch": 2.0,
|
|
"num_input_tokens_seen": 392342880,
|
|
"step": 5000,
|
|
"total_flos": 725576951136256.0,
|
|
"train_loss": 0.20804190348386764,
|
|
"train_runtime": 66170.2748,
|
|
"train_samples_per_second": 0.605,
|
|
"train_steps_per_second": 0.076
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 5000,
|
|
"num_input_tokens_seen": 392342880,
|
|
"num_train_epochs": 2,
|
|
"save_steps": 500,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 725576951136256.0,
|
|
"train_batch_size": 2,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|