{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 1000,
  "global_step": 3531,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002832058906825262,
      "grad_norm": 5.138741493225098,
      "learning_rate": 0.0,
      "loss": 2.7345,
      "step": 1
    },
    {
      "epoch": 0.2832058906825262,
      "grad_norm": 3.8642654418945312,
      "learning_rate": 1.0608849557522124e-05,
      "loss": 2.3628,
      "step": 1000
    },
    {
      "epoch": 0.2832058906825262,
      "eval_cosine_accuracy": 0.9549968242645264,
      "eval_loss": 1.1044740676879883,
      "eval_runtime": 24.643,
      "eval_samples_per_second": 384.125,
      "eval_steps_per_second": 1.501,
      "step": 1000
    },
    {
      "epoch": 0.5664117813650524,
      "grad_norm": 3.815659999847412,
      "learning_rate": 2.1228318584070797e-05,
      "loss": 1.8255,
      "step": 2000
    },
    {
      "epoch": 0.5664117813650524,
      "eval_cosine_accuracy": 0.965983510017395,
      "eval_loss": 1.0202418565750122,
      "eval_runtime": 23.6988,
      "eval_samples_per_second": 399.43,
      "eval_steps_per_second": 1.561,
      "step": 2000
    },
    {
      "epoch": 0.8496176720475785,
      "grad_norm": 3.5664591789245605,
      "learning_rate": 2.953801221347022e-05,
      "loss": 1.6176,
      "step": 3000
    },
    {
      "epoch": 0.8496176720475785,
      "eval_cosine_accuracy": 0.9692584276199341,
      "eval_loss": 0.9256343841552734,
      "eval_runtime": 27.6579,
      "eval_samples_per_second": 342.253,
      "eval_steps_per_second": 1.338,
      "step": 3000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 14124,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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
}