{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 2090,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.23923444976076555,
      "grad_norm": 1.7421875,
      "learning_rate": 1.8803827751196172e-05,
      "loss": 0.3483,
      "mean_token_accuracy": 0.9018868366479874,
      "step": 500
    },
    {
      "epoch": 0.4784688995215311,
      "grad_norm": 1.40625,
      "learning_rate": 1.7607655502392345e-05,
      "loss": 0.2415,
      "mean_token_accuracy": 0.9288070352077484,
      "step": 1000
    },
    {
      "epoch": 0.7177033492822966,
      "grad_norm": 1.5,
      "learning_rate": 1.641148325358852e-05,
      "loss": 0.2362,
      "mean_token_accuracy": 0.9295575091838837,
      "step": 1500
    },
    {
      "epoch": 0.9569377990430622,
      "grad_norm": 1.265625,
      "learning_rate": 1.5215311004784689e-05,
      "loss": 0.2303,
      "mean_token_accuracy": 0.9311141439676285,
      "step": 2000
    }
  ],
  "logging_steps": 500,
  "max_steps": 8360,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 1.3524271724249088e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}