{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0321285140562249,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008032128514056224,
      "grad_norm": 0.33232566714286804,
      "learning_rate": 1e-05,
      "loss": 1.2928,
      "step": 1
    },
    {
      "epoch": 0.008032128514056224,
      "eval_loss": 1.2809306383132935,
      "eval_runtime": 95.0521,
      "eval_samples_per_second": 2.209,
      "eval_steps_per_second": 1.105,
      "step": 1
    },
    {
      "epoch": 0.01606425702811245,
      "grad_norm": 0.2837705612182617,
      "learning_rate": 2e-05,
      "loss": 1.1181,
      "step": 2
    },
    {
      "epoch": 0.01606425702811245,
      "eval_loss": 1.2742336988449097,
      "eval_runtime": 16.7827,
      "eval_samples_per_second": 12.513,
      "eval_steps_per_second": 6.256,
      "step": 2
    },
    {
      "epoch": 0.024096385542168676,
      "grad_norm": 0.2786341607570648,
      "learning_rate": 3e-05,
      "loss": 1.1506,
      "step": 3
    },
    {
      "epoch": 0.0321285140562249,
      "grad_norm": 0.3296334147453308,
      "learning_rate": 4e-05,
      "loss": 1.3103,
      "step": 4
    },
    {
      "epoch": 0.0321285140562249,
      "eval_loss": 1.266922116279602,
      "eval_runtime": 16.846,
      "eval_samples_per_second": 12.466,
      "eval_steps_per_second": 6.233,
      "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": 3560411177680896.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}