{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014285714285714285,
      "grad_norm": 1.8742432594299316,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 2.6888,
      "step": 20
    },
    {
      "epoch": 0.02857142857142857,
      "grad_norm": 1.6443878412246704,
      "learning_rate": 2.857142857142857e-05,
      "loss": 2.289,
      "step": 40
    },
    {
      "epoch": 0.04285714285714286,
      "grad_norm": 1.8094583749771118,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 1.7939,
      "step": 60
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 1.4206470251083374,
      "learning_rate": 5.714285714285714e-05,
      "loss": 1.312,
      "step": 80
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 1.4811224937438965,
      "learning_rate": 7.142857142857143e-05,
      "loss": 1.0735,
      "step": 100
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 1.4770212173461914,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.9261,
      "step": 120
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.3422306776046753,
      "learning_rate": 0.0001,
      "loss": 0.882,
      "step": 140
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 1.5494495630264282,
      "learning_rate": 9.841269841269841e-05,
      "loss": 0.8599,
      "step": 160
    },
    {
      "epoch": 0.12857142857142856,
      "grad_norm": 1.4366521835327148,
      "learning_rate": 9.682539682539682e-05,
      "loss": 0.7784,
      "step": 180
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 1.731536865234375,
      "learning_rate": 9.523809523809524e-05,
      "loss": 0.7404,
      "step": 200
    },
    {
      "epoch": 0.15714285714285714,
      "grad_norm": 1.2290751934051514,
      "learning_rate": 9.365079365079366e-05,
      "loss": 0.6393,
      "step": 220
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 1.5464402437210083,
      "learning_rate": 9.206349206349206e-05,
      "loss": 0.6414,
      "step": 240
    },
    {
      "epoch": 0.18571428571428572,
      "grad_norm": 1.628503680229187,
      "learning_rate": 9.047619047619048e-05,
      "loss": 0.6233,
      "step": 260
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.8485362529754639,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.6558,
      "step": 280
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 1.4331471920013428,
      "learning_rate": 8.730158730158731e-05,
      "loss": 0.624,
      "step": 300
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 1.6106165647506714,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.6276,
      "step": 320
    },
    {
      "epoch": 0.24285714285714285,
      "grad_norm": 1.328774094581604,
      "learning_rate": 8.412698412698413e-05,
      "loss": 0.5928,
      "step": 340
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 1.4172090291976929,
      "learning_rate": 8.253968253968255e-05,
      "loss": 0.597,
      "step": 360
    },
    {
      "epoch": 0.2714285714285714,
      "grad_norm": 1.2621384859085083,
      "learning_rate": 8.095238095238096e-05,
      "loss": 0.6336,
      "step": 380
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 1.4633510112762451,
      "learning_rate": 7.936507936507937e-05,
      "loss": 0.6165,
      "step": 400
    },
    {
      "epoch": 0.3,
      "grad_norm": 1.5444340705871582,
      "learning_rate": 7.777777777777778e-05,
      "loss": 0.6204,
      "step": 420
    },
    {
      "epoch": 0.3142857142857143,
      "grad_norm": 1.758965253829956,
      "learning_rate": 7.619047619047618e-05,
      "loss": 0.6122,
      "step": 440
    },
    {
      "epoch": 0.32857142857142857,
      "grad_norm": 1.4885847568511963,
      "learning_rate": 7.460317460317461e-05,
      "loss": 0.5739,
      "step": 460
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 1.6695561408996582,
      "learning_rate": 7.301587301587302e-05,
      "loss": 0.5807,
      "step": 480
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 1.7690757513046265,
      "learning_rate": 7.142857142857143e-05,
      "loss": 0.5633,
      "step": 500
    },
    {
      "epoch": 0.37142857142857144,
      "grad_norm": 1.4946894645690918,
      "learning_rate": 6.984126984126984e-05,
      "loss": 0.5602,
      "step": 520
    },
    {
      "epoch": 0.38571428571428573,
      "grad_norm": 1.5215212106704712,
      "learning_rate": 6.825396825396825e-05,
      "loss": 0.5381,
      "step": 540
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.1956950426101685,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.5281,
      "step": 560
    },
    {
      "epoch": 0.4142857142857143,
      "grad_norm": 1.315496563911438,
      "learning_rate": 6.507936507936509e-05,
      "loss": 0.551,
      "step": 580
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.3885098695755005,
      "learning_rate": 6.349206349206349e-05,
      "loss": 0.5428,
      "step": 600
    },
    {
      "epoch": 0.44285714285714284,
      "grad_norm": 1.4572407007217407,
      "learning_rate": 6.19047619047619e-05,
      "loss": 0.5465,
      "step": 620
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 1.411399006843567,
      "learning_rate": 6.0317460317460316e-05,
      "loss": 0.5263,
      "step": 640
    },
    {
      "epoch": 0.4714285714285714,
      "grad_norm": 1.3295258283615112,
      "learning_rate": 5.873015873015873e-05,
      "loss": 0.5248,
      "step": 660
    },
    {
      "epoch": 0.4857142857142857,
      "grad_norm": 1.512662410736084,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.5213,
      "step": 680
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.3572126626968384,
      "learning_rate": 5.555555555555556e-05,
      "loss": 0.5003,
      "step": 700
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 1.4415481090545654,
      "learning_rate": 5.396825396825397e-05,
      "loss": 0.5529,
      "step": 720
    },
    {
      "epoch": 0.5285714285714286,
      "grad_norm": 1.4465086460113525,
      "learning_rate": 5.2380952380952384e-05,
      "loss": 0.5266,
      "step": 740
    },
    {
      "epoch": 0.5428571428571428,
      "grad_norm": 1.3659744262695312,
      "learning_rate": 5.0793650793650794e-05,
      "loss": 0.533,
      "step": 760
    },
    {
      "epoch": 0.5571428571428572,
      "grad_norm": 1.5549241304397583,
      "learning_rate": 4.9206349206349204e-05,
      "loss": 0.5139,
      "step": 780
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.5689399242401123,
      "learning_rate": 4.761904761904762e-05,
      "loss": 0.5188,
      "step": 800
    },
    {
      "epoch": 0.5857142857142857,
      "grad_norm": 1.3908042907714844,
      "learning_rate": 4.603174603174603e-05,
      "loss": 0.529,
      "step": 820
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.7993814945220947,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.548,
      "step": 840
    },
    {
      "epoch": 0.6142857142857143,
      "grad_norm": 1.5198805332183838,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.5367,
      "step": 860
    },
    {
      "epoch": 0.6285714285714286,
      "grad_norm": 1.4617140293121338,
      "learning_rate": 4.126984126984127e-05,
      "loss": 0.5016,
      "step": 880
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 1.6662240028381348,
      "learning_rate": 3.968253968253968e-05,
      "loss": 0.5078,
      "step": 900
    },
    {
      "epoch": 0.6571428571428571,
      "grad_norm": 1.617306113243103,
      "learning_rate": 3.809523809523809e-05,
      "loss": 0.5237,
      "step": 920
    },
    {
      "epoch": 0.6714285714285714,
      "grad_norm": 1.7389674186706543,
      "learning_rate": 3.650793650793651e-05,
      "loss": 0.4726,
      "step": 940
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 1.54181706905365,
      "learning_rate": 3.492063492063492e-05,
      "loss": 0.5232,
      "step": 960
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.4722188711166382,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.532,
      "step": 980
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.3351426124572754,
      "learning_rate": 3.1746031746031745e-05,
      "loss": 0.5015,
      "step": 1000
    },
    {
      "epoch": 0.7285714285714285,
      "grad_norm": 1.491120457649231,
      "learning_rate": 3.0158730158730158e-05,
      "loss": 0.5201,
      "step": 1020
    },
    {
      "epoch": 0.7428571428571429,
      "grad_norm": 1.24501633644104,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.4943,
      "step": 1040
    },
    {
      "epoch": 0.7571428571428571,
      "grad_norm": 1.4944851398468018,
      "learning_rate": 2.6984126984126984e-05,
      "loss": 0.4821,
      "step": 1060
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 1.513795256614685,
      "learning_rate": 2.5396825396825397e-05,
      "loss": 0.481,
      "step": 1080
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 1.8671048879623413,
      "learning_rate": 2.380952380952381e-05,
      "loss": 0.48,
      "step": 1100
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.3706579208374023,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.4979,
      "step": 1120
    },
    {
      "epoch": 0.8142857142857143,
      "grad_norm": 1.3706722259521484,
      "learning_rate": 2.0634920634920636e-05,
      "loss": 0.4842,
      "step": 1140
    },
    {
      "epoch": 0.8285714285714286,
      "grad_norm": 1.5844509601593018,
      "learning_rate": 1.9047619047619046e-05,
      "loss": 0.4647,
      "step": 1160
    },
    {
      "epoch": 0.8428571428571429,
      "grad_norm": 1.4700433015823364,
      "learning_rate": 1.746031746031746e-05,
      "loss": 0.4861,
      "step": 1180
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 1.5295989513397217,
      "learning_rate": 1.5873015873015872e-05,
      "loss": 0.4719,
      "step": 1200
    },
    {
      "epoch": 0.8714285714285714,
      "grad_norm": 1.4497429132461548,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.4761,
      "step": 1220
    },
    {
      "epoch": 0.8857142857142857,
      "grad_norm": 1.5591635704040527,
      "learning_rate": 1.2698412698412699e-05,
      "loss": 0.4787,
      "step": 1240
    },
    {
      "epoch": 0.9,
      "grad_norm": 1.410678744316101,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.4824,
      "step": 1260
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 1.4857158660888672,
      "learning_rate": 9.523809523809523e-06,
      "loss": 0.4757,
      "step": 1280
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 1.626083493232727,
      "learning_rate": 7.936507936507936e-06,
      "loss": 0.4571,
      "step": 1300
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 1.595832109451294,
      "learning_rate": 6.349206349206349e-06,
      "loss": 0.4909,
      "step": 1320
    },
    {
      "epoch": 0.9571428571428572,
      "grad_norm": 1.5187280178070068,
      "learning_rate": 4.7619047619047615e-06,
      "loss": 0.4785,
      "step": 1340
    },
    {
      "epoch": 0.9714285714285714,
      "grad_norm": 1.7050893306732178,
      "learning_rate": 3.1746031746031746e-06,
      "loss": 0.4933,
      "step": 1360
    },
    {
      "epoch": 0.9857142857142858,
      "grad_norm": 1.5147182941436768,
      "learning_rate": 1.5873015873015873e-06,
      "loss": 0.4833,
      "step": 1380
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.7184252738952637,
      "learning_rate": 0.0,
      "loss": 0.4739,
      "step": 1400
    }
  ],
  "logging_steps": 20,
  "max_steps": 1400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8419093040332800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}