{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000224621302522778,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.49242605045556e-05,
      "grad_norm": 12.354199409484863,
      "learning_rate": 1e-05,
      "loss": 33.4897,
      "step": 1
    },
    {
      "epoch": 4.49242605045556e-05,
      "eval_loss": 2.2456727027893066,
      "eval_runtime": 1710.6209,
      "eval_samples_per_second": 21.916,
      "eval_steps_per_second": 10.958,
      "step": 1
    },
    {
      "epoch": 8.98485210091112e-05,
      "grad_norm": 12.5243558883667,
      "learning_rate": 2e-05,
      "loss": 37.2758,
      "step": 2
    },
    {
      "epoch": 8.98485210091112e-05,
      "eval_loss": 2.2376697063446045,
      "eval_runtime": 1305.2304,
      "eval_samples_per_second": 28.723,
      "eval_steps_per_second": 14.361,
      "step": 2
    },
    {
      "epoch": 0.0001347727815136668,
      "grad_norm": 15.355352401733398,
      "learning_rate": 3e-05,
      "loss": 34.2527,
      "step": 3
    },
    {
      "epoch": 0.0001796970420182224,
      "grad_norm": 13.506675720214844,
      "learning_rate": 4e-05,
      "loss": 33.2262,
      "step": 4
    },
    {
      "epoch": 0.0001796970420182224,
      "eval_loss": 2.224916696548462,
      "eval_runtime": 1242.049,
      "eval_samples_per_second": 30.184,
      "eval_steps_per_second": 15.092,
      "step": 4
    },
    {
      "epoch": 0.000224621302522778,
      "grad_norm": 16.53463363647461,
      "learning_rate": 5e-05,
      "loss": 38.9078,
      "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": 3257466271825920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}