{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02184002184002184,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004368004368004368,
      "grad_norm": 0.013037811033427715,
      "learning_rate": 1e-05,
      "loss": 10.379,
      "step": 1
    },
    {
      "epoch": 0.004368004368004368,
      "eval_loss": 10.378809928894043,
      "eval_runtime": 8.7224,
      "eval_samples_per_second": 44.254,
      "eval_steps_per_second": 22.127,
      "step": 1
    },
    {
      "epoch": 0.008736008736008737,
      "grad_norm": 0.01289339642971754,
      "learning_rate": 2e-05,
      "loss": 10.38,
      "step": 2
    },
    {
      "epoch": 0.008736008736008737,
      "eval_loss": 10.378806114196777,
      "eval_runtime": 0.8615,
      "eval_samples_per_second": 448.072,
      "eval_steps_per_second": 224.036,
      "step": 2
    },
    {
      "epoch": 0.013104013104013105,
      "grad_norm": 0.01416063029319048,
      "learning_rate": 3e-05,
      "loss": 10.3787,
      "step": 3
    },
    {
      "epoch": 0.017472017472017473,
      "grad_norm": 0.012885983102023602,
      "learning_rate": 4e-05,
      "loss": 10.379,
      "step": 4
    },
    {
      "epoch": 0.017472017472017473,
      "eval_loss": 10.378789901733398,
      "eval_runtime": 0.9387,
      "eval_samples_per_second": 411.194,
      "eval_steps_per_second": 205.597,
      "step": 4
    },
    {
      "epoch": 0.02184002184002184,
      "grad_norm": 0.012850123457610607,
      "learning_rate": 5e-05,
      "loss": 10.3789,
      "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": 517236326400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}