{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 2000,
  "global_step": 5352,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001868460388639761,
      "grad_norm": 4.329383373260498,
      "learning_rate": 0.0,
      "loss": 2.3475,
      "step": 1
    },
    {
      "epoch": 0.37369207772795215,
      "grad_norm": 1.3929723501205444,
      "learning_rate": 4.6683792620270904e-05,
      "loss": 1.4174,
      "step": 2000
    },
    {
      "epoch": 0.37369207772795215,
      "eval_cosine_accuracy": 0.9179443717002869,
      "eval_loss": 0.44630110263824463,
      "eval_runtime": 28.0643,
      "eval_samples_per_second": 336.976,
      "eval_steps_per_second": 1.318,
      "step": 2000
    },
    {
      "epoch": 0.7473841554559043,
      "grad_norm": 1.1317882537841797,
      "learning_rate": 4.886145894517875e-05,
      "loss": 0.7274,
      "step": 4000
    },
    {
      "epoch": 0.7473841554559043,
      "eval_cosine_accuracy": 0.9551655054092407,
      "eval_loss": 0.38517987728118896,
      "eval_runtime": 27.0397,
      "eval_samples_per_second": 349.745,
      "eval_steps_per_second": 1.368,
      "step": 4000
    }
  ],
  "logging_steps": 2000,
  "max_steps": 21408,
  "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
}