{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.79104,
  "eval_steps": 700,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00256,
      "grad_norm": 14.952803611755371,
      "learning_rate": 0.0,
      "loss": 1.0238,
      "step": 1
    },
    {
      "epoch": 0.128,
      "grad_norm": 3.0013201236724854,
      "learning_rate": 2.0851063829787235e-06,
      "loss": 0.8222,
      "step": 50
    },
    {
      "epoch": 0.256,
      "grad_norm": 2.3984222412109375,
      "learning_rate": 4.212765957446809e-06,
      "loss": 0.445,
      "step": 100
    },
    {
      "epoch": 0.384,
      "grad_norm": 2.368490695953369,
      "learning_rate": 6.3404255319148945e-06,
      "loss": 0.4149,
      "step": 150
    },
    {
      "epoch": 0.512,
      "grad_norm": 2.158310890197754,
      "learning_rate": 8.46808510638298e-06,
      "loss": 0.3995,
      "step": 200
    },
    {
      "epoch": 0.64,
      "grad_norm": 2.212986707687378,
      "learning_rate": 9.994504457428557e-06,
      "loss": 0.3701,
      "step": 250
    },
    {
      "epoch": 0.768,
      "grad_norm": 2.0821216106414795,
      "learning_rate": 9.885572470188207e-06,
      "loss": 0.3951,
      "step": 300
    },
    {
      "epoch": 0.896,
      "grad_norm": 2.1344685554504395,
      "learning_rate": 9.639951230825433e-06,
      "loss": 0.3777,
      "step": 350
    },
    {
      "epoch": 1.02304,
      "grad_norm": 2.2334532737731934,
      "learning_rate": 9.2645127658466e-06,
      "loss": 0.353,
      "step": 400
    },
    {
      "epoch": 1.15104,
      "grad_norm": 2.0466365814208984,
      "learning_rate": 8.76976114684395e-06,
      "loss": 0.3095,
      "step": 450
    },
    {
      "epoch": 1.27904,
      "grad_norm": 2.1597046852111816,
      "learning_rate": 8.169538606063647e-06,
      "loss": 0.3148,
      "step": 500
    },
    {
      "epoch": 1.40704,
      "grad_norm": 2.369905471801758,
      "learning_rate": 7.480638256432977e-06,
      "loss": 0.3089,
      "step": 550
    },
    {
      "epoch": 1.53504,
      "grad_norm": 2.1879630088806152,
      "learning_rate": 6.722334251421665e-06,
      "loss": 0.3123,
      "step": 600
    },
    {
      "epoch": 1.66304,
      "grad_norm": 1.9208930730819702,
      "learning_rate": 5.915842529992632e-06,
      "loss": 0.2917,
      "step": 650
    },
    {
      "epoch": 1.79104,
      "grad_norm": 1.9313366413116455,
      "learning_rate": 5.083727233997775e-06,
      "loss": 0.3105,
      "step": 700
    },
    {
      "epoch": 1.79104,
      "eval_loss": 0.3375703692436218,
      "eval_runtime": 78.8007,
      "eval_samples_per_second": 15.863,
      "eval_steps_per_second": 7.931,
      "step": 700
    }
  ],
  "logging_steps": 50,
  "max_steps": 1173,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 700,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2117424625575526e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}