{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0024382810118866198,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006095702529716549,
      "grad_norm": 0.5167356133460999,
      "learning_rate": 1e-05,
      "loss": 1.4562,
      "step": 1
    },
    {
      "epoch": 0.0006095702529716549,
      "eval_loss": 2.036431074142456,
      "eval_runtime": 500.2738,
      "eval_samples_per_second": 5.523,
      "eval_steps_per_second": 2.762,
      "step": 1
    },
    {
      "epoch": 0.0012191405059433099,
      "grad_norm": 0.4348970651626587,
      "learning_rate": 2e-05,
      "loss": 1.5483,
      "step": 2
    },
    {
      "epoch": 0.0012191405059433099,
      "eval_loss": 2.0302329063415527,
      "eval_runtime": 178.5576,
      "eval_samples_per_second": 15.474,
      "eval_steps_per_second": 7.74,
      "step": 2
    },
    {
      "epoch": 0.001828710758914965,
      "grad_norm": 0.557339608669281,
      "learning_rate": 3e-05,
      "loss": 2.0254,
      "step": 3
    },
    {
      "epoch": 0.0024382810118866198,
      "grad_norm": 0.5236634016036987,
      "learning_rate": 4e-05,
      "loss": 1.9116,
      "step": 4
    },
    {
      "epoch": 0.0024382810118866198,
      "eval_loss": 1.9945498704910278,
      "eval_runtime": 150.032,
      "eval_samples_per_second": 18.416,
      "eval_steps_per_second": 9.211,
      "step": 4
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3540378989887488.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}