{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 424,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04716981132075472,
      "grad_norm": 10.339975900973732,
      "learning_rate": 1.5625e-06,
      "loss": 1.3185,
      "step": 10
    },
    {
      "epoch": 0.09433962264150944,
      "grad_norm": 8.639420811310895,
      "learning_rate": 3.125e-06,
      "loss": 1.1257,
      "step": 20
    },
    {
      "epoch": 0.14150943396226415,
      "grad_norm": 6.362701458039821,
      "learning_rate": 4.6875000000000004e-06,
      "loss": 1.041,
      "step": 30
    },
    {
      "epoch": 0.18867924528301888,
      "grad_norm": 7.474727688541833,
      "learning_rate": 6.25e-06,
      "loss": 1.0533,
      "step": 40
    },
    {
      "epoch": 0.2358490566037736,
      "grad_norm": 6.345846042465665,
      "learning_rate": 7.8125e-06,
      "loss": 1.0768,
      "step": 50
    },
    {
      "epoch": 0.2830188679245283,
      "grad_norm": 5.536260759387115,
      "learning_rate": 9.375000000000001e-06,
      "loss": 1.0677,
      "step": 60
    },
    {
      "epoch": 0.330188679245283,
      "grad_norm": 5.474059389864174,
      "learning_rate": 9.997285368432704e-06,
      "loss": 1.1041,
      "step": 70
    },
    {
      "epoch": 0.37735849056603776,
      "grad_norm": 5.295591714060799,
      "learning_rate": 9.980706626858607e-06,
      "loss": 1.1077,
      "step": 80
    },
    {
      "epoch": 0.42452830188679247,
      "grad_norm": 5.2022602380163585,
      "learning_rate": 9.949107209404664e-06,
      "loss": 1.1104,
      "step": 90
    },
    {
      "epoch": 0.4716981132075472,
      "grad_norm": 4.811376563501318,
      "learning_rate": 9.90258241271112e-06,
      "loss": 1.1154,
      "step": 100
    },
    {
      "epoch": 0.5188679245283019,
      "grad_norm": 4.533067523894548,
      "learning_rate": 9.841272544959892e-06,
      "loss": 1.1089,
      "step": 110
    },
    {
      "epoch": 0.5660377358490566,
      "grad_norm": 4.852818755597881,
      "learning_rate": 9.765362502737098e-06,
      "loss": 1.0997,
      "step": 120
    },
    {
      "epoch": 0.6132075471698113,
      "grad_norm": 4.312700282726922,
      "learning_rate": 9.675081213427076e-06,
      "loss": 1.0683,
      "step": 130
    },
    {
      "epoch": 0.660377358490566,
      "grad_norm": 4.226722206109523,
      "learning_rate": 9.570700944819584e-06,
      "loss": 1.0919,
      "step": 140
    },
    {
      "epoch": 0.7075471698113207,
      "grad_norm": 4.541295812983241,
      "learning_rate": 9.452536484012212e-06,
      "loss": 1.0755,
      "step": 150
    },
    {
      "epoch": 0.7547169811320755,
      "grad_norm": 4.097208867550537,
      "learning_rate": 9.320944188084241e-06,
      "loss": 1.0798,
      "step": 160
    },
    {
      "epoch": 0.8018867924528302,
      "grad_norm": 4.133382277384145,
      "learning_rate": 9.176320909404925e-06,
      "loss": 1.0506,
      "step": 170
    },
    {
      "epoch": 0.8490566037735849,
      "grad_norm": 4.618603673796325,
      "learning_rate": 9.019102798817196e-06,
      "loss": 1.0743,
      "step": 180
    },
    {
      "epoch": 0.8962264150943396,
      "grad_norm": 4.412642520748403,
      "learning_rate": 8.849763990306153e-06,
      "loss": 1.0651,
      "step": 190
    },
    {
      "epoch": 0.9433962264150944,
      "grad_norm": 4.247358369460362,
      "learning_rate": 8.66881517111902e-06,
      "loss": 1.0703,
      "step": 200
    },
    {
      "epoch": 0.9905660377358491,
      "grad_norm": 4.8340296279679364,
      "learning_rate": 8.476802041648832e-06,
      "loss": 1.0838,
      "step": 210
    },
    {
      "epoch": 1.0377358490566038,
      "grad_norm": 4.3846093359734155,
      "learning_rate": 8.274303669726427e-06,
      "loss": 0.8046,
      "step": 220
    },
    {
      "epoch": 1.0849056603773586,
      "grad_norm": 4.380739238799166,
      "learning_rate": 8.061930744283855e-06,
      "loss": 0.7034,
      "step": 230
    },
    {
      "epoch": 1.1320754716981132,
      "grad_norm": 4.109393167948876,
      "learning_rate": 7.84032373365578e-06,
      "loss": 0.6926,
      "step": 240
    },
    {
      "epoch": 1.179245283018868,
      "grad_norm": 4.447087911268458,
      "learning_rate": 7.610150954072953e-06,
      "loss": 0.678,
      "step": 250
    },
    {
      "epoch": 1.2264150943396226,
      "grad_norm": 4.290517597049971,
      "learning_rate": 7.372106554172802e-06,
      "loss": 0.663,
      "step": 260
    },
    {
      "epoch": 1.2735849056603774,
      "grad_norm": 4.606641884408385,
      "learning_rate": 7.1269084216053756e-06,
      "loss": 0.6857,
      "step": 270
    },
    {
      "epoch": 1.320754716981132,
      "grad_norm": 4.586125051930431,
      "learning_rate": 6.87529601804781e-06,
      "loss": 0.7059,
      "step": 280
    },
    {
      "epoch": 1.3679245283018868,
      "grad_norm": 4.767902764168844,
      "learning_rate": 6.618028149156479e-06,
      "loss": 0.6824,
      "step": 290
    },
    {
      "epoch": 1.4150943396226414,
      "grad_norm": 4.008793287021251,
      "learning_rate": 6.355880676182086e-06,
      "loss": 0.7055,
      "step": 300
    },
    {
      "epoch": 1.4622641509433962,
      "grad_norm": 4.473579632302127,
      "learning_rate": 6.0896441761489925e-06,
      "loss": 0.7075,
      "step": 310
    },
    {
      "epoch": 1.509433962264151,
      "grad_norm": 4.465283149780194,
      "learning_rate": 5.820121557655109e-06,
      "loss": 0.6737,
      "step": 320
    },
    {
      "epoch": 1.5566037735849056,
      "grad_norm": 4.044860663026542,
      "learning_rate": 5.548125639482587e-06,
      "loss": 0.6912,
      "step": 330
    },
    {
      "epoch": 1.6037735849056602,
      "grad_norm": 4.089100641637805,
      "learning_rate": 5.274476699321638e-06,
      "loss": 0.6713,
      "step": 340
    },
    {
      "epoch": 1.650943396226415,
      "grad_norm": 4.294865410065968,
      "learning_rate": 5e-06,
      "loss": 0.693,
      "step": 350
    },
    {
      "epoch": 1.6981132075471699,
      "grad_norm": 4.389938974240709,
      "learning_rate": 4.7255233006783626e-06,
      "loss": 0.6685,
      "step": 360
    },
    {
      "epoch": 1.7452830188679245,
      "grad_norm": 4.386476416942353,
      "learning_rate": 4.451874360517413e-06,
      "loss": 0.6964,
      "step": 370
    },
    {
      "epoch": 1.7924528301886793,
      "grad_norm": 4.293516930297213,
      "learning_rate": 4.179878442344892e-06,
      "loss": 0.6453,
      "step": 380
    },
    {
      "epoch": 1.8396226415094339,
      "grad_norm": 4.075161428655764,
      "learning_rate": 3.910355823851008e-06,
      "loss": 0.6543,
      "step": 390
    },
    {
      "epoch": 1.8867924528301887,
      "grad_norm": 4.8560048633206305,
      "learning_rate": 3.6441193238179152e-06,
      "loss": 0.6331,
      "step": 400
    },
    {
      "epoch": 1.9339622641509435,
      "grad_norm": 4.26649898385167,
      "learning_rate": 3.381971850843523e-06,
      "loss": 0.652,
      "step": 410
    },
    {
      "epoch": 1.9811320754716981,
      "grad_norm": 4.352787646334764,
      "learning_rate": 3.1247039819521907e-06,
      "loss": 0.6578,
      "step": 420
    }
  ],
  "logging_steps": 10,
  "max_steps": 636,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 424,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 10801965957120.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}