{
  "best_global_step": 150,
  "best_metric": 0.8634624481201172,
  "best_model_checkpoint": "lora_deception_model/checkpoint-100",
  "epoch": 5.0,
  "eval_steps": 50,
  "global_step": 745,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 0.6688848555088043,
      "epoch": 0.06717044500419815,
      "grad_norm": 0.3304958939552307,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 0.8658,
      "mean_token_accuracy": 0.8207968935370445,
      "num_tokens": 63133.0,
      "step": 10
    },
    {
      "entropy": 0.6755495790392161,
      "epoch": 0.1343408900083963,
      "grad_norm": 0.32398757338523865,
      "learning_rate": 1.5200000000000002e-05,
      "loss": 0.8662,
      "mean_token_accuracy": 0.8197331622242927,
      "num_tokens": 124489.0,
      "step": 20
    },
    {
      "entropy": 0.734241085499525,
      "epoch": 0.20151133501259447,
      "grad_norm": 0.31472697854042053,
      "learning_rate": 2.32e-05,
      "loss": 0.7134,
      "mean_token_accuracy": 0.8222098298370838,
      "num_tokens": 189081.0,
      "step": 30
    },
    {
      "entropy": 0.8794498354196548,
      "epoch": 0.2686817800167926,
      "grad_norm": 0.23867088556289673,
      "learning_rate": 3.1200000000000006e-05,
      "loss": 0.6577,
      "mean_token_accuracy": 0.820378091186285,
      "num_tokens": 270096.0,
      "step": 40
    },
    {
      "entropy": 0.9822202995419502,
      "epoch": 0.33585222502099077,
      "grad_norm": 0.23442600667476654,
      "learning_rate": 3.9200000000000004e-05,
      "loss": 0.5764,
      "mean_token_accuracy": 0.8329788409173489,
      "num_tokens": 343034.0,
      "step": 50
    },
    {
      "epoch": 0.33585222502099077,
      "eval_entropy": 1.35109115924154,
      "eval_loss": 0.9188798666000366,
      "eval_mean_token_accuracy": 0.7514589822718075,
      "eval_num_tokens": 343034.0,
      "eval_runtime": 5.1522,
      "eval_samples_per_second": 10.869,
      "eval_steps_per_second": 10.869,
      "step": 50
    },
    {
      "entropy": 0.8484722189605236,
      "epoch": 0.40302267002518893,
      "grad_norm": 0.27580252289772034,
      "learning_rate": 3.948201438848921e-05,
      "loss": 0.4939,
      "mean_token_accuracy": 0.8525501079857349,
      "num_tokens": 407346.0,
      "step": 60
    },
    {
      "entropy": 0.7665611129254103,
      "epoch": 0.47019311502938704,
      "grad_norm": 0.32506343722343445,
      "learning_rate": 3.8906474820143886e-05,
      "loss": 0.4095,
      "mean_token_accuracy": 0.8701820805668831,
      "num_tokens": 466070.0,
      "step": 70
    },
    {
      "entropy": 0.7331306278705597,
      "epoch": 0.5373635600335852,
      "grad_norm": 0.3568798899650574,
      "learning_rate": 3.833093525179856e-05,
      "loss": 0.448,
      "mean_token_accuracy": 0.863949628919363,
      "num_tokens": 536560.0,
      "step": 80
    },
    {
      "entropy": 0.7565343648195266,
      "epoch": 0.6045340050377834,
      "grad_norm": 0.3249973952770233,
      "learning_rate": 3.775539568345324e-05,
      "loss": 0.4065,
      "mean_token_accuracy": 0.8672126568853855,
      "num_tokens": 597642.0,
      "step": 90
    },
    {
      "entropy": 0.6388500925153494,
      "epoch": 0.6717044500419815,
      "grad_norm": 0.36163443326950073,
      "learning_rate": 3.7179856115107914e-05,
      "loss": 0.3693,
      "mean_token_accuracy": 0.8828025683760643,
      "num_tokens": 663210.0,
      "step": 100
    },
    {
      "epoch": 0.6717044500419815,
      "eval_entropy": 1.0956847156797136,
      "eval_loss": 0.8651557564735413,
      "eval_mean_token_accuracy": 0.7637390036668096,
      "eval_num_tokens": 663210.0,
      "eval_runtime": 4.9833,
      "eval_samples_per_second": 11.237,
      "eval_steps_per_second": 11.237,
      "step": 100
    },
    {
      "entropy": 0.6128827821463346,
      "epoch": 0.7388748950461796,
      "grad_norm": 0.29096513986587524,
      "learning_rate": 3.6604316546762595e-05,
      "loss": 0.3719,
      "mean_token_accuracy": 0.8851677082479,
      "num_tokens": 726617.0,
      "step": 110
    },
    {
      "entropy": 0.6564031228423118,
      "epoch": 0.8060453400503779,
      "grad_norm": 0.27515140175819397,
      "learning_rate": 3.602877697841727e-05,
      "loss": 0.3935,
      "mean_token_accuracy": 0.8752141006290912,
      "num_tokens": 800821.0,
      "step": 120
    },
    {
      "entropy": 0.6125180713832379,
      "epoch": 0.873215785054576,
      "grad_norm": 0.3126560151576996,
      "learning_rate": 3.545323741007194e-05,
      "loss": 0.3847,
      "mean_token_accuracy": 0.8818505816161633,
      "num_tokens": 868710.0,
      "step": 130
    },
    {
      "entropy": 0.6347699824720621,
      "epoch": 0.9403862300587741,
      "grad_norm": 0.23533445596694946,
      "learning_rate": 3.487769784172662e-05,
      "loss": 0.385,
      "mean_token_accuracy": 0.8835290059447288,
      "num_tokens": 935575.0,
      "step": 140
    },
    {
      "entropy": 0.579044715513157,
      "epoch": 1.0067170445004199,
      "grad_norm": 0.2643934488296509,
      "learning_rate": 3.43021582733813e-05,
      "loss": 0.3224,
      "mean_token_accuracy": 0.8946574262425869,
      "num_tokens": 996466.0,
      "step": 150
    },
    {
      "epoch": 1.0067170445004199,
      "eval_entropy": 0.9877308234572411,
      "eval_loss": 0.8634624481201172,
      "eval_mean_token_accuracy": 0.7611759411437171,
      "eval_num_tokens": 996466.0,
      "eval_runtime": 4.9854,
      "eval_samples_per_second": 11.233,
      "eval_steps_per_second": 11.233,
      "step": 150
    },
    {
      "entropy": 0.552555637806654,
      "epoch": 1.073887489504618,
      "grad_norm": 0.2633912265300751,
      "learning_rate": 3.372661870503598e-05,
      "loss": 0.3265,
      "mean_token_accuracy": 0.8968047671020031,
      "num_tokens": 1066789.0,
      "step": 160
    },
    {
      "entropy": 0.5594113569706678,
      "epoch": 1.141057934508816,
      "grad_norm": 0.2680589258670807,
      "learning_rate": 3.315107913669065e-05,
      "loss": 0.3519,
      "mean_token_accuracy": 0.8886663600802421,
      "num_tokens": 1138401.0,
      "step": 170
    },
    {
      "entropy": 0.5540055774152279,
      "epoch": 1.2082283795130142,
      "grad_norm": 0.27169251441955566,
      "learning_rate": 3.2575539568345325e-05,
      "loss": 0.3436,
      "mean_token_accuracy": 0.8913260444998741,
      "num_tokens": 1202735.0,
      "step": 180
    },
    {
      "entropy": 0.5612262919545173,
      "epoch": 1.2753988245172123,
      "grad_norm": 0.3151009976863861,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.351,
      "mean_token_accuracy": 0.8909851491451264,
      "num_tokens": 1266476.0,
      "step": 190
    },
    {
      "entropy": 0.5354872807860375,
      "epoch": 1.3425692695214106,
      "grad_norm": 0.29847052693367004,
      "learning_rate": 3.142446043165468e-05,
      "loss": 0.3045,
      "mean_token_accuracy": 0.9023352213203907,
      "num_tokens": 1327389.0,
      "step": 200
    },
    {
      "epoch": 1.3425692695214106,
      "eval_entropy": 0.9606236421636173,
      "eval_loss": 0.8751164078712463,
      "eval_mean_token_accuracy": 0.7617330902389118,
      "eval_num_tokens": 1327389.0,
      "eval_runtime": 4.9901,
      "eval_samples_per_second": 11.222,
      "eval_steps_per_second": 11.222,
      "step": 200
    },
    {
      "entropy": 0.5093934688717127,
      "epoch": 1.4097397145256088,
      "grad_norm": 0.31276237964630127,
      "learning_rate": 3.084892086330935e-05,
      "loss": 0.2882,
      "mean_token_accuracy": 0.9080218151211739,
      "num_tokens": 1390647.0,
      "step": 210
    },
    {
      "entropy": 0.49913822263479235,
      "epoch": 1.4769101595298069,
      "grad_norm": 0.2638222575187683,
      "learning_rate": 3.027338129496403e-05,
      "loss": 0.32,
      "mean_token_accuracy": 0.9011362835764885,
      "num_tokens": 1458413.0,
      "step": 220
    },
    {
      "entropy": 0.5291724860668182,
      "epoch": 1.5440806045340052,
      "grad_norm": 0.7974303960800171,
      "learning_rate": 2.9697841726618707e-05,
      "loss": 0.3437,
      "mean_token_accuracy": 0.8957020588219166,
      "num_tokens": 1529069.0,
      "step": 230
    },
    {
      "entropy": 0.5148157492280007,
      "epoch": 1.611251049538203,
      "grad_norm": 0.3252256512641907,
      "learning_rate": 2.9122302158273384e-05,
      "loss": 0.3078,
      "mean_token_accuracy": 0.8965719811618328,
      "num_tokens": 1593891.0,
      "step": 240
    },
    {
      "entropy": 0.5439612463116645,
      "epoch": 1.6784214945424014,
      "grad_norm": 0.3167729079723358,
      "learning_rate": 2.854676258992806e-05,
      "loss": 0.3331,
      "mean_token_accuracy": 0.8926876865327358,
      "num_tokens": 1658563.0,
      "step": 250
    },
    {
      "epoch": 1.6784214945424014,
      "eval_entropy": 0.8733608674790178,
      "eval_loss": 0.8773566484451294,
      "eval_mean_token_accuracy": 0.7638165514383998,
      "eval_num_tokens": 1658563.0,
      "eval_runtime": 4.9846,
      "eval_samples_per_second": 11.235,
      "eval_steps_per_second": 11.235,
      "step": 250
    },
    {
      "entropy": 0.5023419760167599,
      "epoch": 1.7455919395465995,
      "grad_norm": 0.30670592188835144,
      "learning_rate": 2.7971223021582735e-05,
      "loss": 0.3503,
      "mean_token_accuracy": 0.8920910514891147,
      "num_tokens": 1735767.0,
      "step": 260
    },
    {
      "entropy": 0.5167030651122332,
      "epoch": 1.8127623845507976,
      "grad_norm": 0.25313618779182434,
      "learning_rate": 2.7395683453237412e-05,
      "loss": 0.3242,
      "mean_token_accuracy": 0.8931105189025402,
      "num_tokens": 1802895.0,
      "step": 270
    },
    {
      "entropy": 0.5199910126626491,
      "epoch": 1.879932829554996,
      "grad_norm": 0.3637166917324066,
      "learning_rate": 2.6820143884892086e-05,
      "loss": 0.3145,
      "mean_token_accuracy": 0.8975049994885922,
      "num_tokens": 1865468.0,
      "step": 280
    },
    {
      "entropy": 0.5213575050234794,
      "epoch": 1.9471032745591939,
      "grad_norm": 0.3701685965061188,
      "learning_rate": 2.6244604316546767e-05,
      "loss": 0.3398,
      "mean_token_accuracy": 0.896855977922678,
      "num_tokens": 1932031.0,
      "step": 290
    },
    {
      "entropy": 0.4997344066070605,
      "epoch": 2.0134340890008398,
      "grad_norm": 0.331307590007782,
      "learning_rate": 2.566906474820144e-05,
      "loss": 0.2637,
      "mean_token_accuracy": 0.9088972090165827,
      "num_tokens": 1992713.0,
      "step": 300
    },
    {
      "epoch": 2.0134340890008398,
      "eval_entropy": 0.9004479699901172,
      "eval_loss": 0.8707331418991089,
      "eval_mean_token_accuracy": 0.7641822940536908,
      "eval_num_tokens": 1992713.0,
      "eval_runtime": 4.9809,
      "eval_samples_per_second": 11.243,
      "eval_steps_per_second": 11.243,
      "step": 300
    },
    {
      "entropy": 0.47825686521828176,
      "epoch": 2.0806045340050376,
      "grad_norm": 0.3079531192779541,
      "learning_rate": 2.5093525179856118e-05,
      "loss": 0.2863,
      "mean_token_accuracy": 0.908924800157547,
      "num_tokens": 2061833.0,
      "step": 310
    },
    {
      "entropy": 0.48984590619802476,
      "epoch": 2.147774979009236,
      "grad_norm": 0.2569948434829712,
      "learning_rate": 2.451798561151079e-05,
      "loss": 0.3162,
      "mean_token_accuracy": 0.903419229388237,
      "num_tokens": 2132082.0,
      "step": 320
    },
    {
      "entropy": 0.46938193738460543,
      "epoch": 2.2149454240134343,
      "grad_norm": 0.29792118072509766,
      "learning_rate": 2.394244604316547e-05,
      "loss": 0.2943,
      "mean_token_accuracy": 0.9081865437328815,
      "num_tokens": 2202270.0,
      "step": 330
    },
    {
      "entropy": 0.4853254608809948,
      "epoch": 2.282115869017632,
      "grad_norm": 0.26585960388183594,
      "learning_rate": 2.336690647482015e-05,
      "loss": 0.2682,
      "mean_token_accuracy": 0.9112951382994652,
      "num_tokens": 2263789.0,
      "step": 340
    },
    {
      "entropy": 0.49189864136278627,
      "epoch": 2.3492863140218305,
      "grad_norm": 0.2741142213344574,
      "learning_rate": 2.2791366906474823e-05,
      "loss": 0.313,
      "mean_token_accuracy": 0.8986666277050972,
      "num_tokens": 2334071.0,
      "step": 350
    },
    {
      "epoch": 2.3492863140218305,
      "eval_entropy": 0.8618932158819267,
      "eval_loss": 0.8953577280044556,
      "eval_mean_token_accuracy": 0.7628704607486725,
      "eval_num_tokens": 2334071.0,
      "eval_runtime": 4.984,
      "eval_samples_per_second": 11.236,
      "eval_steps_per_second": 11.236,
      "step": 350
    },
    {
      "entropy": 0.49905899055302144,
      "epoch": 2.4164567590260284,
      "grad_norm": 0.3090650141239166,
      "learning_rate": 2.22158273381295e-05,
      "loss": 0.2886,
      "mean_token_accuracy": 0.9060709603130818,
      "num_tokens": 2396966.0,
      "step": 360
    },
    {
      "entropy": 0.49515552036464217,
      "epoch": 2.4836272040302267,
      "grad_norm": 0.3477407991886139,
      "learning_rate": 2.1640287769784174e-05,
      "loss": 0.2685,
      "mean_token_accuracy": 0.9104222223162651,
      "num_tokens": 2457974.0,
      "step": 370
    },
    {
      "entropy": 0.5188349276781082,
      "epoch": 2.5507976490344246,
      "grad_norm": 0.2762923538684845,
      "learning_rate": 2.1064748201438848e-05,
      "loss": 0.2911,
      "mean_token_accuracy": 0.9037038788199425,
      "num_tokens": 2526344.0,
      "step": 380
    },
    {
      "entropy": 0.5011733949184418,
      "epoch": 2.617968094038623,
      "grad_norm": 0.2646786570549011,
      "learning_rate": 2.0489208633093525e-05,
      "loss": 0.3158,
      "mean_token_accuracy": 0.9090628199279308,
      "num_tokens": 2596395.0,
      "step": 390
    },
    {
      "entropy": 0.49840320982038977,
      "epoch": 2.6851385390428213,
      "grad_norm": 0.4310755431652069,
      "learning_rate": 1.9913669064748202e-05,
      "loss": 0.2887,
      "mean_token_accuracy": 0.9083616696298122,
      "num_tokens": 2657920.0,
      "step": 400
    },
    {
      "epoch": 2.6851385390428213,
      "eval_entropy": 0.8837019130587578,
      "eval_loss": 0.88917475938797,
      "eval_mean_token_accuracy": 0.763011426797935,
      "eval_num_tokens": 2657920.0,
      "eval_runtime": 4.9877,
      "eval_samples_per_second": 11.228,
      "eval_steps_per_second": 11.228,
      "step": 400
    },
    {
      "entropy": 0.4771813187748194,
      "epoch": 2.752308984047019,
      "grad_norm": 0.32867103815078735,
      "learning_rate": 1.933812949640288e-05,
      "loss": 0.2668,
      "mean_token_accuracy": 0.9088380873203278,
      "num_tokens": 2725640.0,
      "step": 410
    },
    {
      "entropy": 0.47720473557710646,
      "epoch": 2.8194794290512175,
      "grad_norm": 0.27547284960746765,
      "learning_rate": 1.8762589928057556e-05,
      "loss": 0.2725,
      "mean_token_accuracy": 0.9101646140217781,
      "num_tokens": 2789853.0,
      "step": 420
    },
    {
      "entropy": 0.45747280344367025,
      "epoch": 2.886649874055416,
      "grad_norm": 0.3139909505844116,
      "learning_rate": 1.8187050359712234e-05,
      "loss": 0.267,
      "mean_token_accuracy": 0.9148379288613796,
      "num_tokens": 2857093.0,
      "step": 430
    },
    {
      "entropy": 0.46566248275339606,
      "epoch": 2.9538203190596137,
      "grad_norm": 0.3694741427898407,
      "learning_rate": 1.7611510791366907e-05,
      "loss": 0.2995,
      "mean_token_accuracy": 0.901902287453413,
      "num_tokens": 2928087.0,
      "step": 440
    },
    {
      "entropy": 0.47634567490106894,
      "epoch": 3.0201511335012596,
      "grad_norm": 0.26703643798828125,
      "learning_rate": 1.7035971223021584e-05,
      "loss": 0.3174,
      "mean_token_accuracy": 0.9040401434596581,
      "num_tokens": 2993485.0,
      "step": 450
    },
    {
      "epoch": 3.0201511335012596,
      "eval_entropy": 0.8348773148443017,
      "eval_loss": 0.8874495625495911,
      "eval_mean_token_accuracy": 0.7612802609801292,
      "eval_num_tokens": 2993485.0,
      "eval_runtime": 4.9913,
      "eval_samples_per_second": 11.22,
      "eval_steps_per_second": 11.22,
      "step": 450
    },
    {
      "entropy": 0.44407146945595743,
      "epoch": 3.0873215785054575,
      "grad_norm": 0.27298107743263245,
      "learning_rate": 1.646043165467626e-05,
      "loss": 0.2888,
      "mean_token_accuracy": 0.9176116026937962,
      "num_tokens": 3062721.0,
      "step": 460
    },
    {
      "entropy": 0.4276166781783104,
      "epoch": 3.154492023509656,
      "grad_norm": 0.2755906879901886,
      "learning_rate": 1.5884892086330935e-05,
      "loss": 0.2419,
      "mean_token_accuracy": 0.9195634700357914,
      "num_tokens": 3129709.0,
      "step": 470
    },
    {
      "entropy": 0.4346423916518688,
      "epoch": 3.2216624685138537,
      "grad_norm": 0.39296212792396545,
      "learning_rate": 1.5309352517985613e-05,
      "loss": 0.233,
      "mean_token_accuracy": 0.9278727151453495,
      "num_tokens": 3189161.0,
      "step": 480
    },
    {
      "entropy": 0.44294624738395216,
      "epoch": 3.288832913518052,
      "grad_norm": 0.39035606384277344,
      "learning_rate": 1.473381294964029e-05,
      "loss": 0.2781,
      "mean_token_accuracy": 0.9181225150823593,
      "num_tokens": 3255403.0,
      "step": 490
    },
    {
      "entropy": 0.4794738654047251,
      "epoch": 3.3560033585222504,
      "grad_norm": 0.3938174545764923,
      "learning_rate": 1.4158273381294965e-05,
      "loss": 0.2942,
      "mean_token_accuracy": 0.9075012236833573,
      "num_tokens": 3320554.0,
      "step": 500
    },
    {
      "epoch": 3.3560033585222504,
      "eval_entropy": 0.817679978374924,
      "eval_loss": 0.9140912294387817,
      "eval_mean_token_accuracy": 0.761023474591119,
      "eval_num_tokens": 3320554.0,
      "eval_runtime": 4.9833,
      "eval_samples_per_second": 11.238,
      "eval_steps_per_second": 11.238,
      "step": 500
    },
    {
      "entropy": 0.4701398782432079,
      "epoch": 3.4231738035264483,
      "grad_norm": 0.4412434697151184,
      "learning_rate": 1.3582733812949642e-05,
      "loss": 0.2707,
      "mean_token_accuracy": 0.9106249861419201,
      "num_tokens": 3384303.0,
      "step": 510
    },
    {
      "entropy": 0.45122345685958865,
      "epoch": 3.4903442485306466,
      "grad_norm": 0.26691338419914246,
      "learning_rate": 1.3007194244604318e-05,
      "loss": 0.258,
      "mean_token_accuracy": 0.9156571164727211,
      "num_tokens": 3451764.0,
      "step": 520
    },
    {
      "entropy": 0.4313320998102427,
      "epoch": 3.5575146935348445,
      "grad_norm": 0.34582847356796265,
      "learning_rate": 1.2431654676258993e-05,
      "loss": 0.2612,
      "mean_token_accuracy": 0.916472752392292,
      "num_tokens": 3522461.0,
      "step": 530
    },
    {
      "entropy": 0.43578826524317266,
      "epoch": 3.624685138539043,
      "grad_norm": 0.4498523771762848,
      "learning_rate": 1.185611510791367e-05,
      "loss": 0.2834,
      "mean_token_accuracy": 0.9140046447515487,
      "num_tokens": 3591502.0,
      "step": 540
    },
    {
      "entropy": 0.4625163245946169,
      "epoch": 3.6918555835432407,
      "grad_norm": 0.3399084806442261,
      "learning_rate": 1.1280575539568346e-05,
      "loss": 0.2906,
      "mean_token_accuracy": 0.9062492586672306,
      "num_tokens": 3659203.0,
      "step": 550
    },
    {
      "epoch": 3.6918555835432407,
      "eval_entropy": 0.8242657040911061,
      "eval_loss": 0.9106144905090332,
      "eval_mean_token_accuracy": 0.7601779720612934,
      "eval_num_tokens": 3659203.0,
      "eval_runtime": 4.9925,
      "eval_samples_per_second": 11.217,
      "eval_steps_per_second": 11.217,
      "step": 550
    },
    {
      "entropy": 0.44798229187726973,
      "epoch": 3.759026028547439,
      "grad_norm": 0.28008008003234863,
      "learning_rate": 1.0705035971223023e-05,
      "loss": 0.2947,
      "mean_token_accuracy": 0.9083551168441772,
      "num_tokens": 3735002.0,
      "step": 560
    },
    {
      "entropy": 0.438993413746357,
      "epoch": 3.8261964735516374,
      "grad_norm": 0.33622145652770996,
      "learning_rate": 1.0129496402877699e-05,
      "loss": 0.2536,
      "mean_token_accuracy": 0.9168887868523597,
      "num_tokens": 3798345.0,
      "step": 570
    },
    {
      "entropy": 0.43377807587385175,
      "epoch": 3.8933669185558353,
      "grad_norm": 0.41980335116386414,
      "learning_rate": 9.553956834532376e-06,
      "loss": 0.2414,
      "mean_token_accuracy": 0.925646186619997,
      "num_tokens": 3859139.0,
      "step": 580
    },
    {
      "entropy": 0.43494608998298645,
      "epoch": 3.9605373635600336,
      "grad_norm": 0.29723235964775085,
      "learning_rate": 8.978417266187051e-06,
      "loss": 0.2619,
      "mean_token_accuracy": 0.9199615843594074,
      "num_tokens": 3923018.0,
      "step": 590
    },
    {
      "entropy": 0.42559608741651606,
      "epoch": 4.0268681780016795,
      "grad_norm": 0.32702481746673584,
      "learning_rate": 8.402877697841727e-06,
      "loss": 0.2393,
      "mean_token_accuracy": 0.9227683498889585,
      "num_tokens": 3985896.0,
      "step": 600
    },
    {
      "epoch": 4.0268681780016795,
      "eval_entropy": 0.790077348372766,
      "eval_loss": 0.929413378238678,
      "eval_mean_token_accuracy": 0.7607843939747129,
      "eval_num_tokens": 3985896.0,
      "eval_runtime": 4.9875,
      "eval_samples_per_second": 11.228,
      "eval_steps_per_second": 11.228,
      "step": 600
    },
    {
      "entropy": 0.4118167482316494,
      "epoch": 4.094038623005877,
      "grad_norm": 0.3099454641342163,
      "learning_rate": 7.827338129496404e-06,
      "loss": 0.2197,
      "mean_token_accuracy": 0.9286121532320977,
      "num_tokens": 4046640.0,
      "step": 610
    },
    {
      "entropy": 0.42818755134940145,
      "epoch": 4.161209068010075,
      "grad_norm": 0.3183671236038208,
      "learning_rate": 7.25179856115108e-06,
      "loss": 0.2681,
      "mean_token_accuracy": 0.9148878164589405,
      "num_tokens": 4115433.0,
      "step": 620
    },
    {
      "entropy": 0.4235291346907616,
      "epoch": 4.228379513014274,
      "grad_norm": 0.3553420603275299,
      "learning_rate": 6.6762589928057564e-06,
      "loss": 0.2386,
      "mean_token_accuracy": 0.9219062335789203,
      "num_tokens": 4177541.0,
      "step": 630
    },
    {
      "entropy": 0.43433762453496455,
      "epoch": 4.295549958018472,
      "grad_norm": 0.47075527906417847,
      "learning_rate": 6.100719424460432e-06,
      "loss": 0.2696,
      "mean_token_accuracy": 0.9177930898964405,
      "num_tokens": 4248216.0,
      "step": 640
    },
    {
      "entropy": 0.43204528763890265,
      "epoch": 4.36272040302267,
      "grad_norm": 0.34699931740760803,
      "learning_rate": 5.525179856115108e-06,
      "loss": 0.2697,
      "mean_token_accuracy": 0.9196366496384144,
      "num_tokens": 4319252.0,
      "step": 650
    },
    {
      "epoch": 4.36272040302267,
      "eval_entropy": 0.7843316655073848,
      "eval_loss": 0.9468327164649963,
      "eval_mean_token_accuracy": 0.7589835811938558,
      "eval_num_tokens": 4319252.0,
      "eval_runtime": 4.9823,
      "eval_samples_per_second": 11.24,
      "eval_steps_per_second": 11.24,
      "step": 650
    },
    {
      "entropy": 0.4113185711205006,
      "epoch": 4.429890848026869,
      "grad_norm": 0.3835369050502777,
      "learning_rate": 4.9496402877697845e-06,
      "loss": 0.2489,
      "mean_token_accuracy": 0.9217935107648373,
      "num_tokens": 4389439.0,
      "step": 660
    },
    {
      "entropy": 0.4268360245972872,
      "epoch": 4.4970612930310665,
      "grad_norm": 0.32893145084381104,
      "learning_rate": 4.374100719424461e-06,
      "loss": 0.2546,
      "mean_token_accuracy": 0.9204200245440006,
      "num_tokens": 4454296.0,
      "step": 670
    },
    {
      "entropy": 0.43092771619558334,
      "epoch": 4.564231738035264,
      "grad_norm": 0.35402655601501465,
      "learning_rate": 3.798561151079137e-06,
      "loss": 0.2528,
      "mean_token_accuracy": 0.9206391289830208,
      "num_tokens": 4516174.0,
      "step": 680
    },
    {
      "entropy": 0.40939035564661025,
      "epoch": 4.631402183039462,
      "grad_norm": 0.32696768641471863,
      "learning_rate": 3.223021582733813e-06,
      "loss": 0.2567,
      "mean_token_accuracy": 0.9263360798358917,
      "num_tokens": 4586677.0,
      "step": 690
    },
    {
      "entropy": 0.42081440389156344,
      "epoch": 4.698572628043661,
      "grad_norm": 0.3911837637424469,
      "learning_rate": 2.6474820143884894e-06,
      "loss": 0.21,
      "mean_token_accuracy": 0.9308864399790764,
      "num_tokens": 4643628.0,
      "step": 700
    },
    {
      "epoch": 4.698572628043661,
      "eval_entropy": 0.7831281987684113,
      "eval_loss": 0.9461870789527893,
      "eval_mean_token_accuracy": 0.7588864458458764,
      "eval_num_tokens": 4643628.0,
      "eval_runtime": 4.9942,
      "eval_samples_per_second": 11.213,
      "eval_steps_per_second": 11.213,
      "step": 700
    },
    {
      "entropy": 0.43728532269597054,
      "epoch": 4.765743073047859,
      "grad_norm": 0.30957573652267456,
      "learning_rate": 2.0719424460431657e-06,
      "loss": 0.2575,
      "mean_token_accuracy": 0.9134377054870129,
      "num_tokens": 4712648.0,
      "step": 710
    },
    {
      "entropy": 0.4240421138703823,
      "epoch": 4.832913518052057,
      "grad_norm": 0.4323979318141937,
      "learning_rate": 1.4964028776978418e-06,
      "loss": 0.2681,
      "mean_token_accuracy": 0.9151543125510215,
      "num_tokens": 4786100.0,
      "step": 720
    },
    {
      "entropy": 0.42574540376663206,
      "epoch": 4.900083963056256,
      "grad_norm": 0.41679295897483826,
      "learning_rate": 9.208633093525181e-07,
      "loss": 0.2643,
      "mean_token_accuracy": 0.9235311761498451,
      "num_tokens": 4853429.0,
      "step": 730
    },
    {
      "entropy": 0.42149149887263776,
      "epoch": 4.9672544080604535,
      "grad_norm": 0.3193954825401306,
      "learning_rate": 3.4532374100719426e-07,
      "loss": 0.2576,
      "mean_token_accuracy": 0.9235921517014504,
      "num_tokens": 4921420.0,
      "step": 740
    }
  ],
  "logging_steps": 10,
  "max_steps": 745,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.54582046359552e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}