{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 4000,
  "global_step": 9760,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010245901639344262,
      "grad_norm": 6.315417766571045,
      "learning_rate": 0.0,
      "loss": 4.1362,
      "step": 1
    },
    {
      "epoch": 0.4098360655737705,
      "grad_norm": 4.62825345993042,
      "learning_rate": 1.536501024590164e-05,
      "loss": 3.1603,
      "step": 4000
    },
    {
      "epoch": 0.4098360655737705,
      "eval_cosine_accuracy": 0.953901469707489,
      "eval_loss": 1.0815402269363403,
      "eval_runtime": 24.8505,
      "eval_samples_per_second": 380.595,
      "eval_steps_per_second": 1.489,
      "step": 4000
    },
    {
      "epoch": 0.819672131147541,
      "grad_norm": 4.6219048500061035,
      "learning_rate": 2.999728935936485e-05,
      "loss": 2.7017,
      "step": 8000
    },
    {
      "epoch": 0.819672131147541,
      "eval_cosine_accuracy": 0.9081200957298279,
      "eval_loss": 1.3302178382873535,
      "eval_runtime": 22.5389,
      "eval_samples_per_second": 419.629,
      "eval_steps_per_second": 1.642,
      "step": 8000
    }
  ],
  "logging_steps": 4000,
  "max_steps": 39040,
  "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
}