{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 2000,
  "global_step": 5352,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001868460388639761,
      "grad_norm": 8.692222595214844,
      "learning_rate": 0.0,
      "loss": 2.3163,
      "step": 1
    },
    {
      "epoch": 0.37369207772795215,
      "grad_norm": 5.377971172332764,
      "learning_rate": 7.46776303494674e-06,
      "loss": 1.7964,
      "step": 2000
    },
    {
      "epoch": 0.37369207772795215,
      "eval_cosine_accuracy": 0.9531564116477966,
      "eval_loss": 0.7834969162940979,
      "eval_runtime": 24.5425,
      "eval_samples_per_second": 385.332,
      "eval_steps_per_second": 1.508,
      "step": 2000
    },
    {
      "epoch": 0.7473841554559043,
      "grad_norm": 4.06288480758667,
      "learning_rate": 1.4943001308166699e-05,
      "loss": 1.1503,
      "step": 4000
    },
    {
      "epoch": 0.7473841554559043,
      "eval_cosine_accuracy": 0.9590779542922974,
      "eval_loss": 0.7469472885131836,
      "eval_runtime": 24.2666,
      "eval_samples_per_second": 389.712,
      "eval_steps_per_second": 1.525,
      "step": 4000
    }
  ],
  "logging_steps": 2000,
  "max_steps": 16056,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}