{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5360983102918588,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07680491551459294,
      "grad_norm": 0.15998965501785278,
      "learning_rate": 0.0002,
      "loss": 0.8173,
      "step": 50
    },
    {
      "epoch": 0.15360983102918588,
      "grad_norm": 0.1599128544330597,
      "learning_rate": 0.00019965952472163515,
      "loss": 0.5618,
      "step": 100
    },
    {
      "epoch": 0.2304147465437788,
      "grad_norm": 0.1505613625049591,
      "learning_rate": 0.0001986404173548442,
      "loss": 0.5308,
      "step": 150
    },
    {
      "epoch": 0.30721966205837176,
      "grad_norm": 0.13830986618995667,
      "learning_rate": 0.0001969496175169149,
      "loss": 0.5155,
      "step": 200
    },
    {
      "epoch": 0.38402457757296465,
      "grad_norm": 0.12936702370643616,
      "learning_rate": 0.00019459863871875693,
      "loss": 0.5085,
      "step": 250
    },
    {
      "epoch": 0.4608294930875576,
      "grad_norm": 0.1287979781627655,
      "learning_rate": 0.00019160348996358483,
      "loss": 0.4953,
      "step": 300
    },
    {
      "epoch": 0.5376344086021505,
      "grad_norm": 0.13770239055156708,
      "learning_rate": 0.0001879845667335219,
      "loss": 0.4883,
      "step": 350
    },
    {
      "epoch": 0.6144393241167435,
      "grad_norm": 0.12349069118499756,
      "learning_rate": 0.00018376651210645086,
      "loss": 0.4828,
      "step": 400
    },
    {
      "epoch": 0.6912442396313364,
      "grad_norm": 0.1296069324016571,
      "learning_rate": 0.0001789780489488379,
      "loss": 0.4793,
      "step": 450
    },
    {
      "epoch": 0.7680491551459293,
      "grad_norm": 0.14504997432231903,
      "learning_rate": 0.0001736517843272136,
      "loss": 0.4772,
      "step": 500
    },
    {
      "epoch": 0.8448540706605223,
      "grad_norm": 0.13662400841712952,
      "learning_rate": 0.00016782398747017174,
      "loss": 0.4714,
      "step": 550
    },
    {
      "epoch": 0.9216589861751152,
      "grad_norm": 0.13271653652191162,
      "learning_rate": 0.0001615343427928555,
      "loss": 0.4658,
      "step": 600
    },
    {
      "epoch": 0.9984639016897081,
      "grad_norm": 0.13312594592571259,
      "learning_rate": 0.00015482567966571136,
      "loss": 0.464,
      "step": 650
    },
    {
      "epoch": 1.075268817204301,
      "grad_norm": 0.13460350036621094,
      "learning_rate": 0.00014774368076765274,
      "loss": 0.4452,
      "step": 700
    },
    {
      "epoch": 1.1520737327188941,
      "grad_norm": 0.12317976355552673,
      "learning_rate": 0.00014033657100960355,
      "loss": 0.446,
      "step": 750
    },
    {
      "epoch": 1.228878648233487,
      "grad_norm": 0.12744882702827454,
      "learning_rate": 0.0001326547891466988,
      "loss": 0.443,
      "step": 800
    },
    {
      "epoch": 1.30568356374808,
      "grad_norm": 0.13042095303535461,
      "learning_rate": 0.00012475064431530065,
      "loss": 0.4436,
      "step": 850
    },
    {
      "epoch": 1.3824884792626728,
      "grad_norm": 0.12759792804718018,
      "learning_rate": 0.00011667795983364332,
      "loss": 0.4436,
      "step": 900
    },
    {
      "epoch": 1.4592933947772657,
      "grad_norm": 0.1353318691253662,
      "learning_rate": 0.00010849170669164763,
      "loss": 0.4385,
      "step": 950
    },
    {
      "epoch": 1.5360983102918588,
      "grad_norm": 0.13270655274391174,
      "learning_rate": 0.00010024762922565933,
      "loss": 0.4358,
      "step": 1000
    }
  ],
  "logging_steps": 50,
  "max_steps": 1953,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.8344214986752e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}