{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 19.902439024390244,
  "eval_steps": 500,
  "global_step": 1020,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 4.256475448608398,
      "learning_rate": 9.80392156862745e-05,
      "loss": 1.8243,
      "step": 20
    },
    {
      "epoch": 0.7804878048780488,
      "grad_norm": 3.3582167625427246,
      "learning_rate": 0.000196078431372549,
      "loss": 1.358,
      "step": 40
    },
    {
      "epoch": 1.170731707317073,
      "grad_norm": 2.848921775817871,
      "learning_rate": 0.00029411764705882356,
      "loss": 1.0892,
      "step": 60
    },
    {
      "epoch": 1.5609756097560976,
      "grad_norm": 3.141003370285034,
      "learning_rate": 0.000392156862745098,
      "loss": 0.9606,
      "step": 80
    },
    {
      "epoch": 1.951219512195122,
      "grad_norm": 2.106764078140259,
      "learning_rate": 0.0004901960784313725,
      "loss": 0.9963,
      "step": 100
    },
    {
      "epoch": 2.341463414634146,
      "grad_norm": 1.790688157081604,
      "learning_rate": 0.0004995258321842611,
      "loss": 0.7703,
      "step": 120
    },
    {
      "epoch": 2.7317073170731705,
      "grad_norm": 1.8451107740402222,
      "learning_rate": 0.0004978890426632721,
      "loss": 0.7723,
      "step": 140
    },
    {
      "epoch": 3.1219512195121952,
      "grad_norm": 1.552288293838501,
      "learning_rate": 0.0004950914404289423,
      "loss": 0.7005,
      "step": 160
    },
    {
      "epoch": 3.5121951219512195,
      "grad_norm": 1.4375431537628174,
      "learning_rate": 0.0004911461260693639,
      "loss": 0.5082,
      "step": 180
    },
    {
      "epoch": 3.902439024390244,
      "grad_norm": 1.4421968460083008,
      "learning_rate": 0.0004860715746692661,
      "loss": 0.563,
      "step": 200
    },
    {
      "epoch": 4.2926829268292686,
      "grad_norm": 1.249590516090393,
      "learning_rate": 0.0004798915492950456,
      "loss": 0.3945,
      "step": 220
    },
    {
      "epoch": 4.682926829268292,
      "grad_norm": 1.2297637462615967,
      "learning_rate": 0.0004726349897172791,
      "loss": 0.3679,
      "step": 240
    },
    {
      "epoch": 5.073170731707317,
      "grad_norm": 0.9739590883255005,
      "learning_rate": 0.00046433587689181054,
      "loss": 0.3572,
      "step": 260
    },
    {
      "epoch": 5.463414634146342,
      "grad_norm": 1.0546987056732178,
      "learning_rate": 0.00045503307383401896,
      "loss": 0.2272,
      "step": 280
    },
    {
      "epoch": 5.853658536585366,
      "grad_norm": 1.131352424621582,
      "learning_rate": 0.0004447701436314176,
      "loss": 0.2635,
      "step": 300
    },
    {
      "epoch": 6.2439024390243905,
      "grad_norm": 0.8285700082778931,
      "learning_rate": 0.00043359514544679713,
      "loss": 0.1999,
      "step": 320
    },
    {
      "epoch": 6.634146341463414,
      "grad_norm": 0.8312835097312927,
      "learning_rate": 0.00042156040946718344,
      "loss": 0.1749,
      "step": 340
    },
    {
      "epoch": 7.024390243902439,
      "grad_norm": 0.6575689911842346,
      "learning_rate": 0.0004087222918524807,
      "loss": 0.1888,
      "step": 360
    },
    {
      "epoch": 7.414634146341464,
      "grad_norm": 0.8747310042381287,
      "learning_rate": 0.0003951409108313223,
      "loss": 0.1192,
      "step": 380
    },
    {
      "epoch": 7.804878048780488,
      "grad_norm": 0.688596248626709,
      "learning_rate": 0.00038087986517993766,
      "loss": 0.1361,
      "step": 400
    },
    {
      "epoch": 8.195121951219512,
      "grad_norm": 0.6887462139129639,
      "learning_rate": 0.00036600593640234084,
      "loss": 0.1098,
      "step": 420
    },
    {
      "epoch": 8.585365853658537,
      "grad_norm": 0.7194873094558716,
      "learning_rate": 0.0003505887760064681,
      "loss": 0.0964,
      "step": 440
    },
    {
      "epoch": 8.975609756097562,
      "grad_norm": 0.681694746017456,
      "learning_rate": 0.0003347005793406853,
      "loss": 0.1006,
      "step": 460
    },
    {
      "epoch": 9.365853658536585,
      "grad_norm": 0.5795145630836487,
      "learning_rate": 0.0003184157475180208,
      "loss": 0.0672,
      "step": 480
    },
    {
      "epoch": 9.75609756097561,
      "grad_norm": 0.5477526783943176,
      "learning_rate": 0.00030181053901126245,
      "loss": 0.0741,
      "step": 500
    },
    {
      "epoch": 10.146341463414634,
      "grad_norm": 0.46498867869377136,
      "learning_rate": 0.00028496271255042615,
      "loss": 0.0625,
      "step": 520
    },
    {
      "epoch": 10.536585365853659,
      "grad_norm": 0.5062224268913269,
      "learning_rate": 0.00026795116299483193,
      "loss": 0.0516,
      "step": 540
    },
    {
      "epoch": 10.926829268292684,
      "grad_norm": 0.4446791410446167,
      "learning_rate": 0.0002508555518849238,
      "loss": 0.0574,
      "step": 560
    },
    {
      "epoch": 11.317073170731707,
      "grad_norm": 0.4164929986000061,
      "learning_rate": 0.0002337559344038817,
      "loss": 0.0448,
      "step": 580
    },
    {
      "epoch": 11.707317073170731,
      "grad_norm": 0.48985204100608826,
      "learning_rate": 0.00021673238449588668,
      "loss": 0.0402,
      "step": 600
    },
    {
      "epoch": 12.097560975609756,
      "grad_norm": 0.37333598732948303,
      "learning_rate": 0.0001998646198965312,
      "loss": 0.0393,
      "step": 620
    },
    {
      "epoch": 12.487804878048781,
      "grad_norm": 0.34097352623939514,
      "learning_rate": 0.0001832316288312821,
      "loss": 0.0285,
      "step": 640
    },
    {
      "epoch": 12.878048780487806,
      "grad_norm": 0.3413819670677185,
      "learning_rate": 0.00016691130013008512,
      "loss": 0.0307,
      "step": 660
    },
    {
      "epoch": 13.268292682926829,
      "grad_norm": 0.27664974331855774,
      "learning_rate": 0.0001509800584902108,
      "loss": 0.0272,
      "step": 680
    },
    {
      "epoch": 13.658536585365853,
      "grad_norm": 0.2621878981590271,
      "learning_rate": 0.00013551250659532853,
      "loss": 0.0213,
      "step": 700
    },
    {
      "epoch": 14.048780487804878,
      "grad_norm": 0.22704452276229858,
      "learning_rate": 0.0001205810757666894,
      "loss": 0.0212,
      "step": 720
    },
    {
      "epoch": 14.439024390243903,
      "grad_norm": 0.17278432846069336,
      "learning_rate": 0.00010625568678234838,
      "loss": 0.0161,
      "step": 740
    },
    {
      "epoch": 14.829268292682928,
      "grad_norm": 0.1445775330066681,
      "learning_rate": 9.260342245273506e-05,
      "loss": 0.0159,
      "step": 760
    },
    {
      "epoch": 15.21951219512195,
      "grad_norm": 0.14733894169330597,
      "learning_rate": 7.968821348583643e-05,
      "loss": 0.0137,
      "step": 780
    },
    {
      "epoch": 15.609756097560975,
      "grad_norm": 0.15792453289031982,
      "learning_rate": 6.75705391130183e-05,
      "loss": 0.0112,
      "step": 800
    },
    {
      "epoch": 16.0,
      "grad_norm": 0.21093232929706573,
      "learning_rate": 5.6307143877391305e-05,
      "loss": 0.0129,
      "step": 820
    },
    {
      "epoch": 16.390243902439025,
      "grad_norm": 0.15143983066082,
      "learning_rate": 4.59507719109446e-05,
      "loss": 0.0092,
      "step": 840
    },
    {
      "epoch": 16.78048780487805,
      "grad_norm": 0.16431018710136414,
      "learning_rate": 3.654991994477039e-05,
      "loss": 0.0088,
      "step": 860
    },
    {
      "epoch": 17.170731707317074,
      "grad_norm": 0.10315347462892532,
      "learning_rate": 2.8148610208981464e-05,
      "loss": 0.0093,
      "step": 880
    },
    {
      "epoch": 17.5609756097561,
      "grad_norm": 0.10833552479743958,
      "learning_rate": 2.07861842857843e-05,
      "loss": 0.0075,
      "step": 900
    },
    {
      "epoch": 17.951219512195124,
      "grad_norm": 0.1411917805671692,
      "learning_rate": 1.4497118881050458e-05,
      "loss": 0.0084,
      "step": 920
    },
    {
      "epoch": 18.341463414634145,
      "grad_norm": 0.10689696669578552,
      "learning_rate": 9.310864377089696e-06,
      "loss": 0.0067,
      "step": 940
    },
    {
      "epoch": 18.73170731707317,
      "grad_norm": 0.10839959979057312,
      "learning_rate": 5.251706922648869e-06,
      "loss": 0.0071,
      "step": 960
    },
    {
      "epoch": 19.121951219512194,
      "grad_norm": 0.13111558556556702,
      "learning_rate": 2.3386547059396633e-06,
      "loss": 0.0074,
      "step": 980
    },
    {
      "epoch": 19.51219512195122,
      "grad_norm": 0.14715228974819183,
      "learning_rate": 5.853489432556536e-07,
      "loss": 0.0066,
      "step": 1000
    },
    {
      "epoch": 19.902439024390244,
      "grad_norm": 0.13206566870212555,
      "learning_rate": 0.0,
      "loss": 0.007,
      "step": 1020
    },
    {
      "epoch": 19.902439024390244,
      "step": 1020,
      "total_flos": 1.7419395455334912e+17,
      "train_loss": 0.2547569075197566,
      "train_runtime": 35555.2849,
      "train_samples_per_second": 0.922,
      "train_steps_per_second": 0.029
    }
  ],
  "logging_steps": 20,
  "max_steps": 1020,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7419395455334912e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}