{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 1000,
  "global_step": 2758,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00036258158085569254,
      "grad_norm": 7.228061676025391,
      "learning_rate": 0.0,
      "loss": 4.1707,
      "step": 1
    },
    {
      "epoch": 0.36258158085569253,
      "grad_norm": 5.762327194213867,
      "learning_rate": 3.018126888217523e-06,
      "loss": 3.7074,
      "step": 1000
    },
    {
      "epoch": 0.36258158085569253,
      "eval_cosine_accuracy": 0.943001389503479,
      "eval_loss": 0.5847920179367065,
      "eval_runtime": 35.6274,
      "eval_samples_per_second": 266.902,
      "eval_steps_per_second": 1.067,
      "step": 1000
    },
    {
      "epoch": 0.7251631617113851,
      "grad_norm": 7.7132134437561035,
      "learning_rate": 6.0392749244713e-06,
      "loss": 2.5733,
      "step": 2000
    },
    {
      "epoch": 0.7251631617113851,
      "eval_cosine_accuracy": 0.9467872381210327,
      "eval_loss": 0.5230411887168884,
      "eval_runtime": 35.5129,
      "eval_samples_per_second": 267.762,
      "eval_steps_per_second": 1.07,
      "step": 2000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 16548,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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
}