{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00754539023815138,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001886347559537845,
      "grad_norm": 0.18235556781291962,
      "learning_rate": 1e-05,
      "loss": 1.6598,
      "step": 1
    },
    {
      "epoch": 0.001886347559537845,
      "eval_loss": 1.5936278104782104,
      "eval_runtime": 187.1146,
      "eval_samples_per_second": 4.772,
      "eval_steps_per_second": 2.389,
      "step": 1
    },
    {
      "epoch": 0.00377269511907569,
      "grad_norm": 0.17051847279071808,
      "learning_rate": 2e-05,
      "loss": 1.4168,
      "step": 2
    },
    {
      "epoch": 0.00377269511907569,
      "eval_loss": 1.5858415365219116,
      "eval_runtime": 41.9344,
      "eval_samples_per_second": 21.295,
      "eval_steps_per_second": 10.659,
      "step": 2
    },
    {
      "epoch": 0.005659042678613535,
      "grad_norm": 0.17427842319011688,
      "learning_rate": 3e-05,
      "loss": 1.5282,
      "step": 3
    },
    {
      "epoch": 0.00754539023815138,
      "grad_norm": 0.17862240970134735,
      "learning_rate": 4e-05,
      "loss": 1.5516,
      "step": 4
    },
    {
      "epoch": 0.00754539023815138,
      "eval_loss": 1.5797351598739624,
      "eval_runtime": 27.0879,
      "eval_samples_per_second": 32.967,
      "eval_steps_per_second": 16.502,
      "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": 3833799301398528.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}