{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8571428571428572,
  "eval_steps": 500,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 443.46893310546875,
      "learning_rate": 2e-05,
      "loss": 4.351,
      "step": 1
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 435.6300354003906,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 4.3347,
      "step": 2
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 10.48087215423584,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 1.58,
      "step": 3
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 10.523934364318848,
      "learning_rate": 6.909830056250527e-06,
      "loss": 1.3946,
      "step": 4
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 6.847975254058838,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 0.9153,
      "step": 5
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 6.616868019104004,
      "learning_rate": 0.0,
      "loss": 0.7993,
      "step": 6
    },
    {
      "epoch": 1.8571428571428572,
      "step": 6,
      "total_flos": 9637412825202688.0,
      "train_loss": 2.229151020447413,
      "train_runtime": 212.6127,
      "train_samples_per_second": 2.079,
      "train_steps_per_second": 0.028
    }
  ],
  "logging_steps": 1,
  "max_steps": 6,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 9637412825202688.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}