{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.04,
  "eval_steps": 3,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "eval_loss": 5.956454753875732,
      "eval_runtime": 0.3943,
      "eval_samples_per_second": 15.218,
      "eval_steps_per_second": 7.609,
      "step": 1
    },
    {
      "epoch": 0.24,
      "eval_loss": 5.943696975708008,
      "eval_runtime": 0.3931,
      "eval_samples_per_second": 15.261,
      "eval_steps_per_second": 7.631,
      "step": 3
    },
    {
      "epoch": 0.4,
      "grad_norm": 10.887984275817871,
      "learning_rate": 5e-05,
      "loss": 6.0911,
      "step": 5
    },
    {
      "epoch": 0.48,
      "eval_loss": 5.283447742462158,
      "eval_runtime": 0.4178,
      "eval_samples_per_second": 14.361,
      "eval_steps_per_second": 7.18,
      "step": 6
    },
    {
      "epoch": 0.72,
      "eval_loss": 3.5568253993988037,
      "eval_runtime": 0.3981,
      "eval_samples_per_second": 15.072,
      "eval_steps_per_second": 7.536,
      "step": 9
    },
    {
      "epoch": 0.8,
      "grad_norm": 5.7051615715026855,
      "learning_rate": 0.0001,
      "loss": 4.2865,
      "step": 10
    },
    {
      "epoch": 0.96,
      "eval_loss": 2.183289051055908,
      "eval_runtime": 0.4018,
      "eval_samples_per_second": 14.934,
      "eval_steps_per_second": 7.467,
      "step": 12
    }
  ],
  "logging_steps": 5,
  "max_steps": 13,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 4,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2404433522589696.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}