{
  "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": 2.207634687423706,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 2.5979,
      "step": 20
    },
    {
      "epoch": 0.02857142857142857,
      "grad_norm": 1.5117173194885254,
      "learning_rate": 2.857142857142857e-05,
      "loss": 2.3131,
      "step": 40
    },
    {
      "epoch": 0.04285714285714286,
      "grad_norm": 1.7237502336502075,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 1.7843,
      "step": 60
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 1.895707130432129,
      "learning_rate": 5.714285714285714e-05,
      "loss": 1.2737,
      "step": 80
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 1.7597640752792358,
      "learning_rate": 7.142857142857143e-05,
      "loss": 1.0504,
      "step": 100
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 1.589367151260376,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.9498,
      "step": 120
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.5316022634506226,
      "learning_rate": 0.0001,
      "loss": 0.8856,
      "step": 140
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 1.638037919998169,
      "learning_rate": 9.841269841269841e-05,
      "loss": 0.8257,
      "step": 160
    },
    {
      "epoch": 0.12857142857142856,
      "grad_norm": 1.3244397640228271,
      "learning_rate": 9.682539682539682e-05,
      "loss": 0.7503,
      "step": 180
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 1.434253215789795,
      "learning_rate": 9.523809523809524e-05,
      "loss": 0.7035,
      "step": 200
    },
    {
      "epoch": 0.15714285714285714,
      "grad_norm": 1.5084493160247803,
      "learning_rate": 9.365079365079366e-05,
      "loss": 0.6422,
      "step": 220
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 1.704795002937317,
      "learning_rate": 9.206349206349206e-05,
      "loss": 0.6382,
      "step": 240
    },
    {
      "epoch": 0.18571428571428572,
      "grad_norm": 1.784338116645813,
      "learning_rate": 9.047619047619048e-05,
      "loss": 0.6329,
      "step": 260
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.8456165790557861,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.6412,
      "step": 280
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 1.192288875579834,
      "learning_rate": 8.730158730158731e-05,
      "loss": 0.591,
      "step": 300
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 1.7664241790771484,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.5889,
      "step": 320
    },
    {
      "epoch": 0.24285714285714285,
      "grad_norm": 1.4029046297073364,
      "learning_rate": 8.412698412698413e-05,
      "loss": 0.5976,
      "step": 340
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 1.2247138023376465,
      "learning_rate": 8.253968253968255e-05,
      "loss": 0.6098,
      "step": 360
    },
    {
      "epoch": 0.2714285714285714,
      "grad_norm": 1.9247369766235352,
      "learning_rate": 8.095238095238096e-05,
      "loss": 0.6056,
      "step": 380
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 1.2571682929992676,
      "learning_rate": 7.936507936507937e-05,
      "loss": 0.5946,
      "step": 400
    },
    {
      "epoch": 0.3,
      "grad_norm": 1.4346907138824463,
      "learning_rate": 7.777777777777778e-05,
      "loss": 0.5899,
      "step": 420
    },
    {
      "epoch": 0.3142857142857143,
      "grad_norm": 1.5911189317703247,
      "learning_rate": 7.619047619047618e-05,
      "loss": 0.5629,
      "step": 440
    },
    {
      "epoch": 0.32857142857142857,
      "grad_norm": 1.4303562641143799,
      "learning_rate": 7.460317460317461e-05,
      "loss": 0.6007,
      "step": 460
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 1.5196324586868286,
      "learning_rate": 7.301587301587302e-05,
      "loss": 0.5917,
      "step": 480
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 1.4185888767242432,
      "learning_rate": 7.142857142857143e-05,
      "loss": 0.5666,
      "step": 500
    },
    {
      "epoch": 0.37142857142857144,
      "grad_norm": 1.416913390159607,
      "learning_rate": 6.984126984126984e-05,
      "loss": 0.5468,
      "step": 520
    },
    {
      "epoch": 0.38571428571428573,
      "grad_norm": 1.3123226165771484,
      "learning_rate": 6.825396825396825e-05,
      "loss": 0.5381,
      "step": 540
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.4564621448516846,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.5255,
      "step": 560
    },
    {
      "epoch": 0.4142857142857143,
      "grad_norm": 1.3417844772338867,
      "learning_rate": 6.507936507936509e-05,
      "loss": 0.5563,
      "step": 580
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.168533205986023,
      "learning_rate": 6.349206349206349e-05,
      "loss": 0.5624,
      "step": 600
    },
    {
      "epoch": 0.44285714285714284,
      "grad_norm": 1.4705379009246826,
      "learning_rate": 6.19047619047619e-05,
      "loss": 0.5378,
      "step": 620
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 1.3392393589019775,
      "learning_rate": 6.0317460317460316e-05,
      "loss": 0.5751,
      "step": 640
    },
    {
      "epoch": 0.4714285714285714,
      "grad_norm": 1.2585370540618896,
      "learning_rate": 5.873015873015873e-05,
      "loss": 0.5262,
      "step": 660
    },
    {
      "epoch": 0.4857142857142857,
      "grad_norm": 1.7023590803146362,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.505,
      "step": 680
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.3246266841888428,
      "learning_rate": 5.555555555555556e-05,
      "loss": 0.5401,
      "step": 700
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 1.4986284971237183,
      "learning_rate": 5.396825396825397e-05,
      "loss": 0.5108,
      "step": 720
    },
    {
      "epoch": 0.5285714285714286,
      "grad_norm": 1.5356686115264893,
      "learning_rate": 5.2380952380952384e-05,
      "loss": 0.5036,
      "step": 740
    },
    {
      "epoch": 0.5428571428571428,
      "grad_norm": 1.670077919960022,
      "learning_rate": 5.0793650793650794e-05,
      "loss": 0.5584,
      "step": 760
    },
    {
      "epoch": 0.5571428571428572,
      "grad_norm": 1.5580649375915527,
      "learning_rate": 4.9206349206349204e-05,
      "loss": 0.5049,
      "step": 780
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.558235764503479,
      "learning_rate": 4.761904761904762e-05,
      "loss": 0.5181,
      "step": 800
    },
    {
      "epoch": 0.5857142857142857,
      "grad_norm": 1.753937840461731,
      "learning_rate": 4.603174603174603e-05,
      "loss": 0.5237,
      "step": 820
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.6312466859817505,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.5137,
      "step": 840
    },
    {
      "epoch": 0.6142857142857143,
      "grad_norm": 1.388678789138794,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.5176,
      "step": 860
    },
    {
      "epoch": 0.6285714285714286,
      "grad_norm": 1.627751350402832,
      "learning_rate": 4.126984126984127e-05,
      "loss": 0.4901,
      "step": 880
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 1.627482295036316,
      "learning_rate": 3.968253968253968e-05,
      "loss": 0.5166,
      "step": 900
    },
    {
      "epoch": 0.6571428571428571,
      "grad_norm": 1.5321110486984253,
      "learning_rate": 3.809523809523809e-05,
      "loss": 0.5197,
      "step": 920
    },
    {
      "epoch": 0.6714285714285714,
      "grad_norm": 1.7120718955993652,
      "learning_rate": 3.650793650793651e-05,
      "loss": 0.5043,
      "step": 940
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 1.5418710708618164,
      "learning_rate": 3.492063492063492e-05,
      "loss": 0.5025,
      "step": 960
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.376985788345337,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.4952,
      "step": 980
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.3709187507629395,
      "learning_rate": 3.1746031746031745e-05,
      "loss": 0.4808,
      "step": 1000
    },
    {
      "epoch": 0.7285714285714285,
      "grad_norm": 1.600040078163147,
      "learning_rate": 3.0158730158730158e-05,
      "loss": 0.4876,
      "step": 1020
    },
    {
      "epoch": 0.7428571428571429,
      "grad_norm": 1.501184105873108,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.4659,
      "step": 1040
    },
    {
      "epoch": 0.7571428571428571,
      "grad_norm": 1.4377880096435547,
      "learning_rate": 2.6984126984126984e-05,
      "loss": 0.4625,
      "step": 1060
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 1.2743709087371826,
      "learning_rate": 2.5396825396825397e-05,
      "loss": 0.4736,
      "step": 1080
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 1.6590967178344727,
      "learning_rate": 2.380952380952381e-05,
      "loss": 0.4854,
      "step": 1100
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.5961614847183228,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.4593,
      "step": 1120
    },
    {
      "epoch": 0.8142857142857143,
      "grad_norm": 1.3354884386062622,
      "learning_rate": 2.0634920634920636e-05,
      "loss": 0.4753,
      "step": 1140
    },
    {
      "epoch": 0.8285714285714286,
      "grad_norm": 1.3281641006469727,
      "learning_rate": 1.9047619047619046e-05,
      "loss": 0.4708,
      "step": 1160
    },
    {
      "epoch": 0.8428571428571429,
      "grad_norm": 1.233601450920105,
      "learning_rate": 1.746031746031746e-05,
      "loss": 0.4891,
      "step": 1180
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 1.3751627206802368,
      "learning_rate": 1.5873015873015872e-05,
      "loss": 0.4936,
      "step": 1200
    },
    {
      "epoch": 0.8714285714285714,
      "grad_norm": 1.4707367420196533,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.4635,
      "step": 1220
    },
    {
      "epoch": 0.8857142857142857,
      "grad_norm": 1.5429284572601318,
      "learning_rate": 1.2698412698412699e-05,
      "loss": 0.4773,
      "step": 1240
    },
    {
      "epoch": 0.9,
      "grad_norm": 1.4306563138961792,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.4517,
      "step": 1260
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 1.6000938415527344,
      "learning_rate": 9.523809523809523e-06,
      "loss": 0.453,
      "step": 1280
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 1.5970221757888794,
      "learning_rate": 7.936507936507936e-06,
      "loss": 0.4729,
      "step": 1300
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 1.4147007465362549,
      "learning_rate": 6.349206349206349e-06,
      "loss": 0.4797,
      "step": 1320
    },
    {
      "epoch": 0.9571428571428572,
      "grad_norm": 1.682041049003601,
      "learning_rate": 4.7619047619047615e-06,
      "loss": 0.4969,
      "step": 1340
    },
    {
      "epoch": 0.9714285714285714,
      "grad_norm": 1.436335563659668,
      "learning_rate": 3.1746031746031746e-06,
      "loss": 0.4906,
      "step": 1360
    },
    {
      "epoch": 0.9857142857142858,
      "grad_norm": 1.7256879806518555,
      "learning_rate": 1.5873015873015873e-06,
      "loss": 0.458,
      "step": 1380
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.6402218341827393,
      "learning_rate": 0.0,
      "loss": 0.4668,
      "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
}