{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 670,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14925373134328357,
      "grad_norm": 17.16141700744629,
      "learning_rate": 1.7065868263473055e-05,
      "loss": 7.3728,
      "step": 100
    },
    {
      "epoch": 0.29850746268656714,
      "grad_norm": 24.333465576171875,
      "learning_rate": 1.4071856287425152e-05,
      "loss": 5.4973,
      "step": 200
    },
    {
      "epoch": 0.44776119402985076,
      "grad_norm": 21.152509689331055,
      "learning_rate": 1.1077844311377246e-05,
      "loss": 4.8076,
      "step": 300
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 22.028194427490234,
      "learning_rate": 8.083832335329342e-06,
      "loss": 4.6389,
      "step": 400
    },
    {
      "epoch": 0.746268656716418,
      "grad_norm": 15.0093994140625,
      "learning_rate": 5.0898203592814375e-06,
      "loss": 4.4903,
      "step": 500
    },
    {
      "epoch": 0.8955223880597015,
      "grad_norm": 33.529720306396484,
      "learning_rate": 2.095808383233533e-06,
      "loss": 4.3542,
      "step": 600
    }
  ],
  "logging_steps": 100,
  "max_steps": 670,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6359481553751677e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}