{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 3465,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4329004329004329,
      "grad_norm": 5.537757873535156,
      "learning_rate": 4.278499278499279e-05,
      "loss": 0.7119,
      "step": 500
    },
    {
      "epoch": 0.8658008658008658,
      "grad_norm": 4.387680530548096,
      "learning_rate": 3.556998556998557e-05,
      "loss": 0.3833,
      "step": 1000
    },
    {
      "epoch": 1.2987012987012987,
      "grad_norm": 3.637988328933716,
      "learning_rate": 2.8354978354978357e-05,
      "loss": 0.2849,
      "step": 1500
    },
    {
      "epoch": 1.7316017316017316,
      "grad_norm": 3.036390781402588,
      "learning_rate": 2.113997113997114e-05,
      "loss": 0.2441,
      "step": 2000
    },
    {
      "epoch": 2.1645021645021645,
      "grad_norm": 2.361323356628418,
      "learning_rate": 1.3924963924963927e-05,
      "loss": 0.2078,
      "step": 2500
    },
    {
      "epoch": 2.5974025974025974,
      "grad_norm": 2.214087963104248,
      "learning_rate": 6.709956709956711e-06,
      "loss": 0.1685,
      "step": 3000
    },
    {
      "epoch": 3.0,
      "step": 3465,
      "total_flos": 2.368703361024e+17,
      "train_loss": 0.30996957313790807,
      "train_runtime": 15330.9154,
      "train_samples_per_second": 115.796,
      "train_steps_per_second": 0.226
    }
  ],
  "logging_steps": 500,
  "max_steps": 3465,
  "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": 2.368703361024e+17,
  "train_batch_size": 512,
  "trial_name": null,
  "trial_params": null
}