{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.898550724637681,
  "eval_steps": 500,
  "global_step": 24,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.927536231884058,
      "eval_loss": 0.9510279893875122,
      "eval_runtime": 6.7662,
      "eval_samples_per_second": 34.14,
      "eval_steps_per_second": 0.591,
      "step": 8
    },
    {
      "epoch": 1.2173913043478262,
      "grad_norm": 6.295067185902384,
      "learning_rate": 5e-06,
      "loss": 1.0808,
      "step": 10
    },
    {
      "epoch": 1.9130434782608696,
      "eval_loss": 0.9052095413208008,
      "eval_runtime": 6.913,
      "eval_samples_per_second": 33.415,
      "eval_steps_per_second": 0.579,
      "step": 16
    },
    {
      "epoch": 2.4347826086956523,
      "grad_norm": 1.432996146425255,
      "learning_rate": 5e-06,
      "loss": 0.9702,
      "step": 20
    },
    {
      "epoch": 2.898550724637681,
      "eval_loss": 0.8778269290924072,
      "eval_runtime": 5.24,
      "eval_samples_per_second": 44.084,
      "eval_steps_per_second": 0.763,
      "step": 24
    },
    {
      "epoch": 2.898550724637681,
      "step": 24,
      "total_flos": 39991514234880.0,
      "train_loss": 0.9956328272819519,
      "train_runtime": 1019.8781,
      "train_samples_per_second": 12.875,
      "train_steps_per_second": 0.024
    }
  ],
  "logging_steps": 10,
  "max_steps": 24,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 39991514234880.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}