{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 1000,
  "global_step": 2537,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00039416633819471815,
      "grad_norm": 6.644246578216553,
      "learning_rate": 0.0,
      "loss": 4.1042,
      "step": 1
    },
    {
      "epoch": 0.3941663381947182,
      "grad_norm": 4.322690963745117,
      "learning_rate": 3.276428102429416e-05,
      "loss": 3.3834,
      "step": 1000
    },
    {
      "epoch": 0.3941663381947182,
      "eval_cosine_accuracy": 0.9609843492507935,
      "eval_loss": 1.7424726486206055,
      "eval_runtime": 22.1887,
      "eval_samples_per_second": 428.552,
      "eval_steps_per_second": 1.713,
      "step": 1000
    },
    {
      "epoch": 0.7883326763894364,
      "grad_norm": 4.4025044441223145,
      "learning_rate": 4.82699467114388e-05,
      "loss": 2.5243,
      "step": 2000
    },
    {
      "epoch": 0.7883326763894364,
      "eval_cosine_accuracy": 0.967714786529541,
      "eval_loss": 1.6491715908050537,
      "eval_runtime": 22.146,
      "eval_samples_per_second": 429.378,
      "eval_steps_per_second": 1.716,
      "step": 2000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 15222,
  "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
}