{
  "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": 2.0159542560577393,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 2.6872,
      "step": 20
    },
    {
      "epoch": 0.02857142857142857,
      "grad_norm": 1.690909743309021,
      "learning_rate": 2.857142857142857e-05,
      "loss": 2.281,
      "step": 40
    },
    {
      "epoch": 0.04285714285714286,
      "grad_norm": 1.8601027727127075,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 1.7851,
      "step": 60
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 1.4562734365463257,
      "learning_rate": 5.714285714285714e-05,
      "loss": 1.3021,
      "step": 80
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 1.4902580976486206,
      "learning_rate": 7.142857142857143e-05,
      "loss": 1.0692,
      "step": 100
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 1.4558128118515015,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.9234,
      "step": 120
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.373028039932251,
      "learning_rate": 0.0001,
      "loss": 0.8799,
      "step": 140
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 1.6163955926895142,
      "learning_rate": 9.841269841269841e-05,
      "loss": 0.857,
      "step": 160
    },
    {
      "epoch": 0.12857142857142856,
      "grad_norm": 1.4480136632919312,
      "learning_rate": 9.682539682539682e-05,
      "loss": 0.7656,
      "step": 180
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 1.6265840530395508,
      "learning_rate": 9.523809523809524e-05,
      "loss": 0.7326,
      "step": 200
    },
    {
      "epoch": 0.15714285714285714,
      "grad_norm": 1.2702994346618652,
      "learning_rate": 9.365079365079366e-05,
      "loss": 0.639,
      "step": 220
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 1.4225071668624878,
      "learning_rate": 9.206349206349206e-05,
      "loss": 0.6401,
      "step": 240
    },
    {
      "epoch": 0.18571428571428572,
      "grad_norm": 1.622852087020874,
      "learning_rate": 9.047619047619048e-05,
      "loss": 0.624,
      "step": 260
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.6511507034301758,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.6543,
      "step": 280
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 1.5115859508514404,
      "learning_rate": 8.730158730158731e-05,
      "loss": 0.6238,
      "step": 300
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 1.534798502922058,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.6277,
      "step": 320
    },
    {
      "epoch": 0.24285714285714285,
      "grad_norm": 1.3327252864837646,
      "learning_rate": 8.412698412698413e-05,
      "loss": 0.5918,
      "step": 340
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 1.4269055128097534,
      "learning_rate": 8.253968253968255e-05,
      "loss": 0.5968,
      "step": 360
    },
    {
      "epoch": 0.2714285714285714,
      "grad_norm": 1.2712342739105225,
      "learning_rate": 8.095238095238096e-05,
      "loss": 0.6326,
      "step": 380
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 1.500617265701294,
      "learning_rate": 7.936507936507937e-05,
      "loss": 0.6162,
      "step": 400
    },
    {
      "epoch": 0.3,
      "grad_norm": 1.5671484470367432,
      "learning_rate": 7.777777777777778e-05,
      "loss": 0.6206,
      "step": 420
    },
    {
      "epoch": 0.3142857142857143,
      "grad_norm": 1.8047889471054077,
      "learning_rate": 7.619047619047618e-05,
      "loss": 0.612,
      "step": 440
    },
    {
      "epoch": 0.32857142857142857,
      "grad_norm": 1.4521819353103638,
      "learning_rate": 7.460317460317461e-05,
      "loss": 0.5748,
      "step": 460
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 1.6426695585250854,
      "learning_rate": 7.301587301587302e-05,
      "loss": 0.5811,
      "step": 480
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 1.6789945363998413,
      "learning_rate": 7.142857142857143e-05,
      "loss": 0.5636,
      "step": 500
    },
    {
      "epoch": 0.37142857142857144,
      "grad_norm": 1.5078628063201904,
      "learning_rate": 6.984126984126984e-05,
      "loss": 0.5618,
      "step": 520
    },
    {
      "epoch": 0.38571428571428573,
      "grad_norm": 1.5368173122406006,
      "learning_rate": 6.825396825396825e-05,
      "loss": 0.5381,
      "step": 540
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.1794755458831787,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.528,
      "step": 560
    },
    {
      "epoch": 0.4142857142857143,
      "grad_norm": 1.31809401512146,
      "learning_rate": 6.507936507936509e-05,
      "loss": 0.5508,
      "step": 580
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.398769736289978,
      "learning_rate": 6.349206349206349e-05,
      "loss": 0.5435,
      "step": 600
    },
    {
      "epoch": 0.44285714285714284,
      "grad_norm": 1.49237859249115,
      "learning_rate": 6.19047619047619e-05,
      "loss": 0.5469,
      "step": 620
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 1.3688076734542847,
      "learning_rate": 6.0317460317460316e-05,
      "loss": 0.5257,
      "step": 640
    },
    {
      "epoch": 0.4714285714285714,
      "grad_norm": 1.427947998046875,
      "learning_rate": 5.873015873015873e-05,
      "loss": 0.5247,
      "step": 660
    },
    {
      "epoch": 0.4857142857142857,
      "grad_norm": 1.4817345142364502,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.5223,
      "step": 680
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.3692938089370728,
      "learning_rate": 5.555555555555556e-05,
      "loss": 0.5003,
      "step": 700
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 1.4122618436813354,
      "learning_rate": 5.396825396825397e-05,
      "loss": 0.5535,
      "step": 720
    },
    {
      "epoch": 0.5285714285714286,
      "grad_norm": 1.4148932695388794,
      "learning_rate": 5.2380952380952384e-05,
      "loss": 0.5262,
      "step": 740
    },
    {
      "epoch": 0.5428571428571428,
      "grad_norm": 1.3666108846664429,
      "learning_rate": 5.0793650793650794e-05,
      "loss": 0.5345,
      "step": 760
    },
    {
      "epoch": 0.5571428571428572,
      "grad_norm": 1.4528700113296509,
      "learning_rate": 4.9206349206349204e-05,
      "loss": 0.5136,
      "step": 780
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.563751459121704,
      "learning_rate": 4.761904761904762e-05,
      "loss": 0.5196,
      "step": 800
    },
    {
      "epoch": 0.5857142857142857,
      "grad_norm": 1.4110444784164429,
      "learning_rate": 4.603174603174603e-05,
      "loss": 0.5281,
      "step": 820
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.769435167312622,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.5482,
      "step": 840
    },
    {
      "epoch": 0.6142857142857143,
      "grad_norm": 1.4131271839141846,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.5366,
      "step": 860
    },
    {
      "epoch": 0.6285714285714286,
      "grad_norm": 1.459429144859314,
      "learning_rate": 4.126984126984127e-05,
      "loss": 0.5013,
      "step": 880
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 1.6418342590332031,
      "learning_rate": 3.968253968253968e-05,
      "loss": 0.5086,
      "step": 900
    },
    {
      "epoch": 0.6571428571428571,
      "grad_norm": 1.6576707363128662,
      "learning_rate": 3.809523809523809e-05,
      "loss": 0.5244,
      "step": 920
    },
    {
      "epoch": 0.6714285714285714,
      "grad_norm": 1.6548312902450562,
      "learning_rate": 3.650793650793651e-05,
      "loss": 0.4733,
      "step": 940
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 1.6226400136947632,
      "learning_rate": 3.492063492063492e-05,
      "loss": 0.5237,
      "step": 960
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.4631938934326172,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.5316,
      "step": 980
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.3383113145828247,
      "learning_rate": 3.1746031746031745e-05,
      "loss": 0.501,
      "step": 1000
    },
    {
      "epoch": 0.7285714285714285,
      "grad_norm": 1.4526844024658203,
      "learning_rate": 3.0158730158730158e-05,
      "loss": 0.5204,
      "step": 1020
    },
    {
      "epoch": 0.7428571428571429,
      "grad_norm": 1.2494806051254272,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.4956,
      "step": 1040
    },
    {
      "epoch": 0.7571428571428571,
      "grad_norm": 1.5174272060394287,
      "learning_rate": 2.6984126984126984e-05,
      "loss": 0.4821,
      "step": 1060
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 1.4890474081039429,
      "learning_rate": 2.5396825396825397e-05,
      "loss": 0.482,
      "step": 1080
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 1.7602328062057495,
      "learning_rate": 2.380952380952381e-05,
      "loss": 0.4809,
      "step": 1100
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.3647661209106445,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.4983,
      "step": 1120
    },
    {
      "epoch": 0.8142857142857143,
      "grad_norm": 1.386948585510254,
      "learning_rate": 2.0634920634920636e-05,
      "loss": 0.4851,
      "step": 1140
    },
    {
      "epoch": 0.8285714285714286,
      "grad_norm": 1.5154744386672974,
      "learning_rate": 1.9047619047619046e-05,
      "loss": 0.4645,
      "step": 1160
    },
    {
      "epoch": 0.8428571428571429,
      "grad_norm": 1.5008195638656616,
      "learning_rate": 1.746031746031746e-05,
      "loss": 0.4867,
      "step": 1180
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 1.5143955945968628,
      "learning_rate": 1.5873015873015872e-05,
      "loss": 0.4727,
      "step": 1200
    },
    {
      "epoch": 0.8714285714285714,
      "grad_norm": 1.4292445182800293,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.477,
      "step": 1220
    },
    {
      "epoch": 0.8857142857142857,
      "grad_norm": 1.619745135307312,
      "learning_rate": 1.2698412698412699e-05,
      "loss": 0.4788,
      "step": 1240
    },
    {
      "epoch": 0.9,
      "grad_norm": 1.4151842594146729,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.4824,
      "step": 1260
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 1.4590322971343994,
      "learning_rate": 9.523809523809523e-06,
      "loss": 0.476,
      "step": 1280
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 1.579836130142212,
      "learning_rate": 7.936507936507936e-06,
      "loss": 0.458,
      "step": 1300
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 1.5796328783035278,
      "learning_rate": 6.349206349206349e-06,
      "loss": 0.4921,
      "step": 1320
    },
    {
      "epoch": 0.9571428571428572,
      "grad_norm": 1.5328384637832642,
      "learning_rate": 4.7619047619047615e-06,
      "loss": 0.4796,
      "step": 1340
    },
    {
      "epoch": 0.9714285714285714,
      "grad_norm": 1.5657676458358765,
      "learning_rate": 3.1746031746031746e-06,
      "loss": 0.494,
      "step": 1360
    },
    {
      "epoch": 0.9857142857142858,
      "grad_norm": 1.5250962972640991,
      "learning_rate": 1.5873015873015873e-06,
      "loss": 0.4833,
      "step": 1380
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.6834768056869507,
      "learning_rate": 0.0,
      "loss": 0.4744,
      "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
}