{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 1000,
  "global_step": 3090,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00032362459546925567,
      "grad_norm": 6.685443878173828,
      "learning_rate": 0.0,
      "loss": 3.4534,
      "step": 1
    },
    {
      "epoch": 0.32362459546925565,
      "grad_norm": 5.621844291687012,
      "learning_rate": 2.9741100323624596e-05,
      "loss": 2.5414,
      "step": 1000
    },
    {
      "epoch": 0.32362459546925565,
      "eval_cosine_accuracy": 0.9566726088523865,
      "eval_loss": 0.3535313606262207,
      "eval_runtime": 156.4326,
      "eval_samples_per_second": 60.787,
      "eval_steps_per_second": 0.243,
      "step": 1000
    },
    {
      "epoch": 0.6472491909385113,
      "grad_norm": 5.640726566314697,
      "learning_rate": 2.614527148507731e-05,
      "loss": 1.4768,
      "step": 2000
    },
    {
      "epoch": 0.6472491909385113,
      "eval_cosine_accuracy": 0.9636133909225464,
      "eval_loss": 0.30959078669548035,
      "eval_runtime": 148.7133,
      "eval_samples_per_second": 63.942,
      "eval_steps_per_second": 0.256,
      "step": 2000
    },
    {
      "epoch": 0.970873786407767,
      "grad_norm": 6.189350128173828,
      "learning_rate": 2.2549442646530026e-05,
      "loss": 1.1557,
      "step": 3000
    },
    {
      "epoch": 0.970873786407767,
      "eval_cosine_accuracy": 0.9629824161529541,
      "eval_loss": 0.3100142478942871,
      "eval_runtime": 148.5055,
      "eval_samples_per_second": 64.031,
      "eval_steps_per_second": 0.256,
      "step": 3000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 9270,
  "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
}