{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.7160975609756097,
  "eval_steps": 500,
  "global_step": 880,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01951219512195122,
      "grad_norm": 0.14488260447978973,
      "learning_rate": 0.00019934683213585893,
      "loss": 0.6356,
      "step": 10
    },
    {
      "epoch": 0.03902439024390244,
      "grad_norm": 0.1634250283241272,
      "learning_rate": 0.00019804049640757677,
      "loss": 0.4368,
      "step": 20
    },
    {
      "epoch": 0.05853658536585366,
      "grad_norm": 0.1504327356815338,
      "learning_rate": 0.0001967341606792946,
      "loss": 0.407,
      "step": 30
    },
    {
      "epoch": 0.07804878048780488,
      "grad_norm": 0.16282524168491364,
      "learning_rate": 0.00019542782495101242,
      "loss": 0.3788,
      "step": 40
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.17505913972854614,
      "learning_rate": 0.00019412148922273026,
      "loss": 0.3705,
      "step": 50
    },
    {
      "epoch": 0.11707317073170732,
      "grad_norm": 0.18271876871585846,
      "learning_rate": 0.00019281515349444807,
      "loss": 0.3654,
      "step": 60
    },
    {
      "epoch": 0.13658536585365855,
      "grad_norm": 0.1547907590866089,
      "learning_rate": 0.0001915088177661659,
      "loss": 0.3845,
      "step": 70
    },
    {
      "epoch": 0.15609756097560976,
      "grad_norm": 0.1806977242231369,
      "learning_rate": 0.00019020248203788375,
      "loss": 0.362,
      "step": 80
    },
    {
      "epoch": 0.17560975609756097,
      "grad_norm": 0.16502083837985992,
      "learning_rate": 0.00018889614630960156,
      "loss": 0.3436,
      "step": 90
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.15947739779949188,
      "learning_rate": 0.0001875898105813194,
      "loss": 0.3221,
      "step": 100
    },
    {
      "epoch": 0.2146341463414634,
      "grad_norm": 0.16028478741645813,
      "learning_rate": 0.00018628347485303724,
      "loss": 0.3291,
      "step": 110
    },
    {
      "epoch": 0.23414634146341465,
      "grad_norm": 0.16755621135234833,
      "learning_rate": 0.00018497713912475508,
      "loss": 0.3454,
      "step": 120
    },
    {
      "epoch": 0.25365853658536586,
      "grad_norm": 0.17687192559242249,
      "learning_rate": 0.00018367080339647292,
      "loss": 0.3265,
      "step": 130
    },
    {
      "epoch": 0.2731707317073171,
      "grad_norm": 0.12853658199310303,
      "learning_rate": 0.00018236446766819073,
      "loss": 0.3136,
      "step": 140
    },
    {
      "epoch": 0.2926829268292683,
      "grad_norm": 0.15641653537750244,
      "learning_rate": 0.00018105813193990857,
      "loss": 0.3124,
      "step": 150
    },
    {
      "epoch": 0.3121951219512195,
      "grad_norm": 0.1840222179889679,
      "learning_rate": 0.00017975179621162638,
      "loss": 0.3308,
      "step": 160
    },
    {
      "epoch": 0.33170731707317075,
      "grad_norm": 0.16983111202716827,
      "learning_rate": 0.00017844546048334422,
      "loss": 0.3116,
      "step": 170
    },
    {
      "epoch": 0.35121951219512193,
      "grad_norm": 0.18679502606391907,
      "learning_rate": 0.00017713912475506206,
      "loss": 0.3458,
      "step": 180
    },
    {
      "epoch": 0.37073170731707317,
      "grad_norm": 0.1655397266149521,
      "learning_rate": 0.0001758327890267799,
      "loss": 0.3041,
      "step": 190
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 0.16899655759334564,
      "learning_rate": 0.00017452645329849774,
      "loss": 0.3179,
      "step": 200
    },
    {
      "epoch": 0.4097560975609756,
      "grad_norm": 0.14320065081119537,
      "learning_rate": 0.00017322011757021555,
      "loss": 0.2896,
      "step": 210
    },
    {
      "epoch": 0.4292682926829268,
      "grad_norm": 0.18079160153865814,
      "learning_rate": 0.0001719137818419334,
      "loss": 0.3121,
      "step": 220
    },
    {
      "epoch": 0.44878048780487806,
      "grad_norm": 0.15252567827701569,
      "learning_rate": 0.00017060744611365123,
      "loss": 0.3054,
      "step": 230
    },
    {
      "epoch": 0.4682926829268293,
      "grad_norm": 0.1688212901353836,
      "learning_rate": 0.00016930111038536904,
      "loss": 0.316,
      "step": 240
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 0.1604667603969574,
      "learning_rate": 0.00016799477465708688,
      "loss": 0.3174,
      "step": 250
    },
    {
      "epoch": 0.5073170731707317,
      "grad_norm": 0.19493722915649414,
      "learning_rate": 0.0001666884389288047,
      "loss": 0.307,
      "step": 260
    },
    {
      "epoch": 0.526829268292683,
      "grad_norm": 0.13511119782924652,
      "learning_rate": 0.00016538210320052253,
      "loss": 0.2918,
      "step": 270
    },
    {
      "epoch": 0.5463414634146342,
      "grad_norm": 0.1683417409658432,
      "learning_rate": 0.00016407576747224037,
      "loss": 0.2704,
      "step": 280
    },
    {
      "epoch": 0.5658536585365853,
      "grad_norm": 0.16002771258354187,
      "learning_rate": 0.0001627694317439582,
      "loss": 0.3401,
      "step": 290
    },
    {
      "epoch": 0.5853658536585366,
      "grad_norm": 0.1851789504289627,
      "learning_rate": 0.00016146309601567605,
      "loss": 0.3134,
      "step": 300
    },
    {
      "epoch": 0.6048780487804878,
      "grad_norm": 0.18187113106250763,
      "learning_rate": 0.00016015676028739386,
      "loss": 0.2732,
      "step": 310
    },
    {
      "epoch": 0.624390243902439,
      "grad_norm": 0.13298119604587555,
      "learning_rate": 0.0001588504245591117,
      "loss": 0.3317,
      "step": 320
    },
    {
      "epoch": 0.6439024390243903,
      "grad_norm": 0.17413659393787384,
      "learning_rate": 0.00015754408883082954,
      "loss": 0.3176,
      "step": 330
    },
    {
      "epoch": 0.6634146341463415,
      "grad_norm": 0.17591014504432678,
      "learning_rate": 0.00015623775310254735,
      "loss": 0.3074,
      "step": 340
    },
    {
      "epoch": 0.6829268292682927,
      "grad_norm": 0.17484629154205322,
      "learning_rate": 0.0001549314173742652,
      "loss": 0.3033,
      "step": 350
    },
    {
      "epoch": 0.7024390243902439,
      "grad_norm": 0.17957189679145813,
      "learning_rate": 0.000153625081645983,
      "loss": 0.2995,
      "step": 360
    },
    {
      "epoch": 0.7219512195121951,
      "grad_norm": 0.1616777628660202,
      "learning_rate": 0.00015231874591770084,
      "loss": 0.2955,
      "step": 370
    },
    {
      "epoch": 0.7414634146341463,
      "grad_norm": 0.165989488363266,
      "learning_rate": 0.00015101241018941868,
      "loss": 0.278,
      "step": 380
    },
    {
      "epoch": 0.7609756097560976,
      "grad_norm": 0.15299169719219208,
      "learning_rate": 0.00014970607446113652,
      "loss": 0.2877,
      "step": 390
    },
    {
      "epoch": 0.7804878048780488,
      "grad_norm": 0.17317935824394226,
      "learning_rate": 0.00014839973873285436,
      "loss": 0.2888,
      "step": 400
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.17615154385566711,
      "learning_rate": 0.00014709340300457217,
      "loss": 0.298,
      "step": 410
    },
    {
      "epoch": 0.8195121951219512,
      "grad_norm": 0.15918245911598206,
      "learning_rate": 0.00014578706727629,
      "loss": 0.3118,
      "step": 420
    },
    {
      "epoch": 0.8390243902439024,
      "grad_norm": 0.1735045462846756,
      "learning_rate": 0.00014448073154800785,
      "loss": 0.2968,
      "step": 430
    },
    {
      "epoch": 0.8585365853658536,
      "grad_norm": 0.16569170355796814,
      "learning_rate": 0.00014317439581972566,
      "loss": 0.2902,
      "step": 440
    },
    {
      "epoch": 0.8780487804878049,
      "grad_norm": 0.14971968531608582,
      "learning_rate": 0.0001418680600914435,
      "loss": 0.2909,
      "step": 450
    },
    {
      "epoch": 0.8975609756097561,
      "grad_norm": 0.17511232197284698,
      "learning_rate": 0.00014056172436316132,
      "loss": 0.2913,
      "step": 460
    },
    {
      "epoch": 0.9170731707317074,
      "grad_norm": 0.1714879721403122,
      "learning_rate": 0.00013925538863487918,
      "loss": 0.3032,
      "step": 470
    },
    {
      "epoch": 0.9365853658536586,
      "grad_norm": 0.15486101806163788,
      "learning_rate": 0.00013794905290659702,
      "loss": 0.2714,
      "step": 480
    },
    {
      "epoch": 0.9560975609756097,
      "grad_norm": 0.1515657603740692,
      "learning_rate": 0.00013664271717831483,
      "loss": 0.2663,
      "step": 490
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 0.1795472502708435,
      "learning_rate": 0.00013533638145003267,
      "loss": 0.2761,
      "step": 500
    },
    {
      "epoch": 0.9951219512195122,
      "grad_norm": 0.18285898864269257,
      "learning_rate": 0.00013403004572175048,
      "loss": 0.2709,
      "step": 510
    },
    {
      "epoch": 1.0136585365853659,
      "grad_norm": 0.16601520776748657,
      "learning_rate": 0.00013272370999346832,
      "loss": 0.2678,
      "step": 520
    },
    {
      "epoch": 1.033170731707317,
      "grad_norm": 0.16676375269889832,
      "learning_rate": 0.00013141737426518616,
      "loss": 0.2521,
      "step": 530
    },
    {
      "epoch": 1.0526829268292683,
      "grad_norm": 0.1423233151435852,
      "learning_rate": 0.00013011103853690398,
      "loss": 0.243,
      "step": 540
    },
    {
      "epoch": 1.0721951219512196,
      "grad_norm": 0.24877290427684784,
      "learning_rate": 0.00012880470280862181,
      "loss": 0.2348,
      "step": 550
    },
    {
      "epoch": 1.0917073170731708,
      "grad_norm": 0.18094764649868011,
      "learning_rate": 0.00012749836708033965,
      "loss": 0.2349,
      "step": 560
    },
    {
      "epoch": 1.111219512195122,
      "grad_norm": 0.1786268949508667,
      "learning_rate": 0.0001261920313520575,
      "loss": 0.2508,
      "step": 570
    },
    {
      "epoch": 1.1307317073170733,
      "grad_norm": 0.21345548331737518,
      "learning_rate": 0.00012488569562377533,
      "loss": 0.277,
      "step": 580
    },
    {
      "epoch": 1.1502439024390243,
      "grad_norm": 0.23655258119106293,
      "learning_rate": 0.00012357935989549314,
      "loss": 0.249,
      "step": 590
    },
    {
      "epoch": 1.1697560975609755,
      "grad_norm": 0.1962760090827942,
      "learning_rate": 0.00012227302416721098,
      "loss": 0.2649,
      "step": 600
    },
    {
      "epoch": 1.1892682926829268,
      "grad_norm": 0.18105126917362213,
      "learning_rate": 0.00012096668843892882,
      "loss": 0.2673,
      "step": 610
    },
    {
      "epoch": 1.208780487804878,
      "grad_norm": 0.16958513855934143,
      "learning_rate": 0.00011966035271064664,
      "loss": 0.2409,
      "step": 620
    },
    {
      "epoch": 1.2282926829268292,
      "grad_norm": 0.22808077931404114,
      "learning_rate": 0.00011835401698236447,
      "loss": 0.2564,
      "step": 630
    },
    {
      "epoch": 1.2478048780487805,
      "grad_norm": 0.162706196308136,
      "learning_rate": 0.0001170476812540823,
      "loss": 0.2497,
      "step": 640
    },
    {
      "epoch": 1.2673170731707317,
      "grad_norm": 0.16657714545726776,
      "learning_rate": 0.00011574134552580014,
      "loss": 0.2664,
      "step": 650
    },
    {
      "epoch": 1.286829268292683,
      "grad_norm": 0.20304907858371735,
      "learning_rate": 0.00011443500979751798,
      "loss": 0.251,
      "step": 660
    },
    {
      "epoch": 1.3063414634146342,
      "grad_norm": 0.18894435465335846,
      "learning_rate": 0.00011312867406923579,
      "loss": 0.223,
      "step": 670
    },
    {
      "epoch": 1.3258536585365854,
      "grad_norm": 0.17584313452243805,
      "learning_rate": 0.00011182233834095363,
      "loss": 0.265,
      "step": 680
    },
    {
      "epoch": 1.3453658536585364,
      "grad_norm": 0.23363268375396729,
      "learning_rate": 0.00011051600261267146,
      "loss": 0.2593,
      "step": 690
    },
    {
      "epoch": 1.3648780487804877,
      "grad_norm": 0.17345435917377472,
      "learning_rate": 0.0001092096668843893,
      "loss": 0.2745,
      "step": 700
    },
    {
      "epoch": 1.384390243902439,
      "grad_norm": 0.20228204131126404,
      "learning_rate": 0.00010790333115610713,
      "loss": 0.2329,
      "step": 710
    },
    {
      "epoch": 1.4039024390243902,
      "grad_norm": 0.16685593128204346,
      "learning_rate": 0.00010659699542782495,
      "loss": 0.2427,
      "step": 720
    },
    {
      "epoch": 1.4234146341463414,
      "grad_norm": 0.18634216487407684,
      "learning_rate": 0.0001052906596995428,
      "loss": 0.2323,
      "step": 730
    },
    {
      "epoch": 1.4429268292682926,
      "grad_norm": 0.2305642068386078,
      "learning_rate": 0.00010398432397126061,
      "loss": 0.2537,
      "step": 740
    },
    {
      "epoch": 1.4624390243902439,
      "grad_norm": 0.19238169491291046,
      "learning_rate": 0.00010267798824297845,
      "loss": 0.2549,
      "step": 750
    },
    {
      "epoch": 1.481951219512195,
      "grad_norm": 0.170588880777359,
      "learning_rate": 0.00010137165251469629,
      "loss": 0.2364,
      "step": 760
    },
    {
      "epoch": 1.5014634146341463,
      "grad_norm": 0.18197551369667053,
      "learning_rate": 0.00010006531678641412,
      "loss": 0.2499,
      "step": 770
    },
    {
      "epoch": 1.5209756097560976,
      "grad_norm": 0.18300370872020721,
      "learning_rate": 9.875898105813195e-05,
      "loss": 0.2495,
      "step": 780
    },
    {
      "epoch": 1.5404878048780488,
      "grad_norm": 0.23338189721107483,
      "learning_rate": 9.745264532984978e-05,
      "loss": 0.2596,
      "step": 790
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.21071650087833405,
      "learning_rate": 9.61463096015676e-05,
      "loss": 0.2487,
      "step": 800
    },
    {
      "epoch": 1.5795121951219513,
      "grad_norm": 0.1906578093767166,
      "learning_rate": 9.483997387328543e-05,
      "loss": 0.2611,
      "step": 810
    },
    {
      "epoch": 1.5990243902439025,
      "grad_norm": 0.20316530764102936,
      "learning_rate": 9.353363814500327e-05,
      "loss": 0.2685,
      "step": 820
    },
    {
      "epoch": 1.6185365853658538,
      "grad_norm": 0.24779777228832245,
      "learning_rate": 9.222730241672111e-05,
      "loss": 0.2293,
      "step": 830
    },
    {
      "epoch": 1.638048780487805,
      "grad_norm": 0.1795492023229599,
      "learning_rate": 9.092096668843894e-05,
      "loss": 0.2755,
      "step": 840
    },
    {
      "epoch": 1.6575609756097562,
      "grad_norm": 0.22917696833610535,
      "learning_rate": 8.961463096015676e-05,
      "loss": 0.2726,
      "step": 850
    },
    {
      "epoch": 1.6770731707317075,
      "grad_norm": 0.17289987206459045,
      "learning_rate": 8.830829523187459e-05,
      "loss": 0.2512,
      "step": 860
    },
    {
      "epoch": 1.6965853658536585,
      "grad_norm": 0.189191073179245,
      "learning_rate": 8.700195950359243e-05,
      "loss": 0.2419,
      "step": 870
    },
    {
      "epoch": 1.7160975609756097,
      "grad_norm": 0.21344304084777832,
      "learning_rate": 8.569562377531027e-05,
      "loss": 0.2329,
      "step": 880
    }
  ],
  "logging_steps": 10,
  "max_steps": 1536,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.906907157573632e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}