{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 1000,
  "global_step": 2363,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00042319085907744394,
      "grad_norm": 8.33436107635498,
      "learning_rate": 0.0,
      "loss": 4.1437,
      "step": 1
    },
    {
      "epoch": 0.4231908590774439,
      "grad_norm": 4.534207820892334,
      "learning_rate": 2.8641065830721004e-05,
      "loss": 3.6457,
      "step": 1000
    },
    {
      "epoch": 0.4231908590774439,
      "eval_cosine_accuracy": 0.9362708926200867,
      "eval_loss": 0.9829329252243042,
      "eval_runtime": 62.6077,
      "eval_samples_per_second": 151.882,
      "eval_steps_per_second": 0.607,
      "step": 1000
    },
    {
      "epoch": 0.8463817181548878,
      "grad_norm": 8.568726539611816,
      "learning_rate": 2.393887147335423e-05,
      "loss": 2.6898,
      "step": 2000
    },
    {
      "epoch": 0.8463817181548878,
      "eval_cosine_accuracy": 0.9378483295440674,
      "eval_loss": 0.9382773041725159,
      "eval_runtime": 58.9559,
      "eval_samples_per_second": 161.29,
      "eval_steps_per_second": 0.645,
      "step": 2000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 7089,
  "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
}