{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 96,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15625,
      "grad_norm": 1.1824947595596313,
      "learning_rate": 8e-05,
      "loss": 2.1224836349487304,
      "step": 5
    },
    {
      "epoch": 0.3125,
      "grad_norm": 0.45979633927345276,
      "learning_rate": 9.952402219937816e-05,
      "loss": 1.7379152297973632,
      "step": 10
    },
    {
      "epoch": 0.46875,
      "grad_norm": 0.5583250522613525,
      "learning_rate": 9.760588329553571e-05,
      "loss": 1.5223669052124023,
      "step": 15
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.4054713845252991,
      "learning_rate": 9.42728012826605e-05,
      "loss": 1.2529266357421875,
      "step": 20
    },
    {
      "epoch": 0.78125,
      "grad_norm": 0.41235220432281494,
      "learning_rate": 8.962384209755452e-05,
      "loss": 1.0075555801391602,
      "step": 25
    },
    {
      "epoch": 0.9375,
      "grad_norm": 0.4131007790565491,
      "learning_rate": 8.379718220723773e-05,
      "loss": 0.7767543792724609,
      "step": 30
    },
    {
      "epoch": 1.09375,
      "grad_norm": 0.28115367889404297,
      "learning_rate": 7.696600172495997e-05,
      "loss": 0.670633602142334,
      "step": 35
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.25491470098495483,
      "learning_rate": 6.933333714707094e-05,
      "loss": 0.6005853176116943,
      "step": 40
    },
    {
      "epoch": 1.40625,
      "grad_norm": 0.2761740982532501,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.5778088092803955,
      "step": 45
    },
    {
      "epoch": 1.5625,
      "grad_norm": 0.24875779449939728,
      "learning_rate": 5.258806764421048e-05,
      "loss": 0.538189172744751,
      "step": 50
    },
    {
      "epoch": 1.71875,
      "grad_norm": 0.25878462195396423,
      "learning_rate": 4.397316598723385e-05,
      "loss": 0.5227806568145752,
      "step": 55
    },
    {
      "epoch": 1.875,
      "grad_norm": 0.32230958342552185,
      "learning_rate": 3.553739402317162e-05,
      "loss": 0.5064546585083007,
      "step": 60
    },
    {
      "epoch": 2.03125,
      "grad_norm": 0.3282443583011627,
      "learning_rate": 2.7531479951641924e-05,
      "loss": 0.5330670356750489,
      "step": 65
    },
    {
      "epoch": 2.1875,
      "grad_norm": 0.2622469663619995,
      "learning_rate": 2.0193375726538737e-05,
      "loss": 0.4886016368865967,
      "step": 70
    },
    {
      "epoch": 2.34375,
      "grad_norm": 0.27460813522338867,
      "learning_rate": 1.3741184642831189e-05,
      "loss": 0.4667336463928223,
      "step": 75
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.2819143831729889,
      "learning_rate": 8.366678865639688e-06,
      "loss": 0.4716463088989258,
      "step": 80
    },
    {
      "epoch": 2.65625,
      "grad_norm": 0.260720431804657,
      "learning_rate": 4.229599573731685e-06,
      "loss": 0.46319150924682617,
      "step": 85
    },
    {
      "epoch": 2.8125,
      "grad_norm": 0.29859086871147156,
      "learning_rate": 1.4529091286973995e-06,
      "loss": 0.47528905868530275,
      "step": 90
    },
    {
      "epoch": 2.96875,
      "grad_norm": 0.42338818311691284,
      "learning_rate": 1.191363849376237e-07,
      "loss": 0.4699601173400879,
      "step": 95
    }
  ],
  "logging_steps": 5,
  "max_steps": 96,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.988693266849792e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}