{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 309,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.032362459546925564,
      "grad_norm": 4.205862998962402,
      "learning_rate": 5.806451612903226e-06,
      "loss": 0.6004,
      "step": 10
    },
    {
      "epoch": 0.06472491909385113,
      "grad_norm": 2.067194700241089,
      "learning_rate": 1.2258064516129034e-05,
      "loss": 0.2484,
      "step": 20
    },
    {
      "epoch": 0.0970873786407767,
      "grad_norm": 0.9206975102424622,
      "learning_rate": 1.870967741935484e-05,
      "loss": 0.1354,
      "step": 30
    },
    {
      "epoch": 0.12944983818770225,
      "grad_norm": 0.8155682682991028,
      "learning_rate": 1.9959162014075553e-05,
      "loss": 0.1027,
      "step": 40
    },
    {
      "epoch": 0.16181229773462782,
      "grad_norm": 0.6652464270591736,
      "learning_rate": 1.9793829188147406e-05,
      "loss": 0.0861,
      "step": 50
    },
    {
      "epoch": 0.1941747572815534,
      "grad_norm": 0.6949710845947266,
      "learning_rate": 1.9503556665478066e-05,
      "loss": 0.0882,
      "step": 60
    },
    {
      "epoch": 0.22653721682847897,
      "grad_norm": 0.5845817923545837,
      "learning_rate": 1.9092047447238775e-05,
      "loss": 0.0684,
      "step": 70
    },
    {
      "epoch": 0.2588996763754045,
      "grad_norm": 0.5173789262771606,
      "learning_rate": 1.856455114887056e-05,
      "loss": 0.0639,
      "step": 80
    },
    {
      "epoch": 0.2912621359223301,
      "grad_norm": 0.593817412853241,
      "learning_rate": 1.792779703083777e-05,
      "loss": 0.0718,
      "step": 90
    },
    {
      "epoch": 0.32362459546925565,
      "grad_norm": 0.6153833866119385,
      "learning_rate": 1.7189908153577473e-05,
      "loss": 0.0653,
      "step": 100
    },
    {
      "epoch": 0.3559870550161812,
      "grad_norm": 0.6375450491905212,
      "learning_rate": 1.636029775176862e-05,
      "loss": 0.0632,
      "step": 110
    },
    {
      "epoch": 0.3883495145631068,
      "grad_norm": 0.4619232416152954,
      "learning_rate": 1.544954914987238e-05,
      "loss": 0.0614,
      "step": 120
    },
    {
      "epoch": 0.42071197411003236,
      "grad_norm": 0.4041443467140198,
      "learning_rate": 1.4469280750858854e-05,
      "loss": 0.0572,
      "step": 130
    },
    {
      "epoch": 0.45307443365695793,
      "grad_norm": 0.5032212734222412,
      "learning_rate": 1.3431997820456592e-05,
      "loss": 0.0532,
      "step": 140
    },
    {
      "epoch": 0.4854368932038835,
      "grad_norm": 0.4844492971897125,
      "learning_rate": 1.2350932957710322e-05,
      "loss": 0.0512,
      "step": 150
    },
    {
      "epoch": 0.517799352750809,
      "grad_norm": 0.5413029789924622,
      "learning_rate": 1.1239877286961123e-05,
      "loss": 0.0499,
      "step": 160
    },
    {
      "epoch": 0.5501618122977346,
      "grad_norm": 0.48275595903396606,
      "learning_rate": 1.01130045247298e-05,
      "loss": 0.0545,
      "step": 170
    },
    {
      "epoch": 0.5825242718446602,
      "grad_norm": 0.5238805413246155,
      "learning_rate": 8.98469016587892e-06,
      "loss": 0.048,
      "step": 180
    },
    {
      "epoch": 0.6148867313915858,
      "grad_norm": 0.5326752066612244,
      "learning_rate": 7.869328095692313e-06,
      "loss": 0.0476,
      "step": 190
    },
    {
      "epoch": 0.6472491909385113,
      "grad_norm": 0.4399051368236542,
      "learning_rate": 6.781146967348283e-06,
      "loss": 0.0483,
      "step": 200
    },
    {
      "epoch": 0.6796116504854369,
      "grad_norm": 0.42469847202301025,
      "learning_rate": 5.7340286872557515e-06,
      "loss": 0.0406,
      "step": 210
    },
    {
      "epoch": 0.7119741100323624,
      "grad_norm": 0.3958876430988312,
      "learning_rate": 4.7413313238324556e-06,
      "loss": 0.0469,
      "step": 220
    },
    {
      "epoch": 0.7443365695792881,
      "grad_norm": 0.49159300327301025,
      "learning_rate": 3.815718698874672e-06,
      "loss": 0.0473,
      "step": 230
    },
    {
      "epoch": 0.7766990291262136,
      "grad_norm": 0.41017910838127136,
      "learning_rate": 2.9689988354181742e-06,
      "loss": 0.0432,
      "step": 240
    },
    {
      "epoch": 0.8090614886731392,
      "grad_norm": 0.3570820391178131,
      "learning_rate": 2.211973323008041e-06,
      "loss": 0.0475,
      "step": 250
    },
    {
      "epoch": 0.8414239482200647,
      "grad_norm": 0.4732098877429962,
      "learning_rate": 1.5542995220217961e-06,
      "loss": 0.0459,
      "step": 260
    },
    {
      "epoch": 0.8737864077669902,
      "grad_norm": 0.42088189721107483,
      "learning_rate": 1.0043673649027519e-06,
      "loss": 0.0424,
      "step": 270
    },
    {
      "epoch": 0.9061488673139159,
      "grad_norm": 0.3217940926551819,
      "learning_rate": 5.691923259479093e-07,
      "loss": 0.0425,
      "step": 280
    },
    {
      "epoch": 0.9385113268608414,
      "grad_norm": 0.3519341051578522,
      "learning_rate": 2.5432592503288e-07,
      "loss": 0.043,
      "step": 290
    },
    {
      "epoch": 0.970873786407767,
      "grad_norm": 0.4310944378376007,
      "learning_rate": 6.378490697611761e-08,
      "loss": 0.0453,
      "step": 300
    },
    {
      "epoch": 1.0,
      "step": 309,
      "total_flos": 3.151751154761728e+17,
      "train_loss": 0.08207544491514805,
      "train_runtime": 2093.6474,
      "train_samples_per_second": 4.722,
      "train_steps_per_second": 0.148
    }
  ],
  "logging_steps": 10,
  "max_steps": 309,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.151751154761728e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}