{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0334928229665072,
  "eval_steps": 6,
  "global_step": 27,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03827751196172249,
      "eval_loss": 1.614690899848938,
      "eval_runtime": 7.7076,
      "eval_samples_per_second": 22.964,
      "eval_steps_per_second": 2.984,
      "step": 1
    },
    {
      "epoch": 0.22966507177033493,
      "eval_loss": 1.6019983291625977,
      "eval_runtime": 6.6098,
      "eval_samples_per_second": 26.778,
      "eval_steps_per_second": 3.48,
      "step": 6
    },
    {
      "epoch": 0.3827751196172249,
      "grad_norm": 0.10793803632259369,
      "learning_rate": 7.679133974894983e-05,
      "loss": 1.5942,
      "step": 10
    },
    {
      "epoch": 0.45933014354066987,
      "eval_loss": 1.5849605798721313,
      "eval_runtime": 6.4803,
      "eval_samples_per_second": 27.314,
      "eval_steps_per_second": 3.549,
      "step": 12
    },
    {
      "epoch": 0.6889952153110048,
      "eval_loss": 1.5751739740371704,
      "eval_runtime": 6.4829,
      "eval_samples_per_second": 27.303,
      "eval_steps_per_second": 3.548,
      "step": 18
    },
    {
      "epoch": 0.7655502392344498,
      "grad_norm": 0.12132919579744339,
      "learning_rate": 1.8128800512565513e-05,
      "loss": 1.5682,
      "step": 20
    },
    {
      "epoch": 0.9186602870813397,
      "eval_loss": 1.5725187063217163,
      "eval_runtime": 6.4917,
      "eval_samples_per_second": 27.266,
      "eval_steps_per_second": 3.543,
      "step": 24
    }
  ],
  "logging_steps": 10,
  "max_steps": 27,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 7,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.643030806888448e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}