{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001464611328768628,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002929222657537256,
      "grad_norm": 0.014375661499798298,
      "learning_rate": 1e-05,
      "loss": 10.3723,
      "step": 1
    },
    {
      "epoch": 0.0002929222657537256,
      "eval_loss": 10.373385429382324,
      "eval_runtime": 20.7884,
      "eval_samples_per_second": 276.596,
      "eval_steps_per_second": 138.298,
      "step": 1
    },
    {
      "epoch": 0.0005858445315074512,
      "grad_norm": 0.015149828046560287,
      "learning_rate": 2e-05,
      "loss": 10.3752,
      "step": 2
    },
    {
      "epoch": 0.0005858445315074512,
      "eval_loss": 10.373380661010742,
      "eval_runtime": 10.5137,
      "eval_samples_per_second": 546.905,
      "eval_steps_per_second": 273.452,
      "step": 2
    },
    {
      "epoch": 0.0008787667972611768,
      "grad_norm": 0.017868561670184135,
      "learning_rate": 3e-05,
      "loss": 10.3739,
      "step": 3
    },
    {
      "epoch": 0.0011716890630149024,
      "grad_norm": 0.016535909846425056,
      "learning_rate": 4e-05,
      "loss": 10.3738,
      "step": 4
    },
    {
      "epoch": 0.0011716890630149024,
      "eval_loss": 10.373360633850098,
      "eval_runtime": 10.6903,
      "eval_samples_per_second": 537.871,
      "eval_steps_per_second": 268.936,
      "step": 4
    },
    {
      "epoch": 0.001464611328768628,
      "grad_norm": 0.016503650695085526,
      "learning_rate": 5e-05,
      "loss": 10.3732,
      "step": 5
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 381461790720.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}