{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.04,
  "eval_steps": 25,
  "global_step": 19,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "grad_norm": 0.09495715796947479,
      "learning_rate": 9.931806517013612e-05,
      "loss": 11.9258,
      "step": 1
    },
    {
      "epoch": 0.16,
      "eval_loss": 11.916019439697266,
      "eval_runtime": 0.1989,
      "eval_samples_per_second": 216.176,
      "eval_steps_per_second": 30.164,
      "step": 1
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.1044018417596817,
      "learning_rate": 9.729086208503174e-05,
      "loss": 11.9309,
      "step": 2
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.10026930272579193,
      "learning_rate": 9.397368756032445e-05,
      "loss": 11.9315,
      "step": 3
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.09114942699670792,
      "learning_rate": 8.945702546981969e-05,
      "loss": 11.9222,
      "step": 4
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.10115586966276169,
      "learning_rate": 8.386407858128706e-05,
      "loss": 11.9237,
      "step": 5
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.10670667141675949,
      "learning_rate": 7.734740790612136e-05,
      "loss": 11.9259,
      "step": 6
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.18786552548408508,
      "learning_rate": 7.008477123264848e-05,
      "loss": 20.862,
      "step": 7
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.1250055730342865,
      "learning_rate": 6.227427435703997e-05,
      "loss": 11.9305,
      "step": 8
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.12761305272579193,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 11.9259,
      "step": 9
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.10062720626592636,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 11.9193,
      "step": 10
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.1087232455611229,
      "learning_rate": 3.772572564296005e-05,
      "loss": 11.9236,
      "step": 11
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.12009818106889725,
      "learning_rate": 2.991522876735154e-05,
      "loss": 11.9267,
      "step": 12
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.22319898009300232,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 20.8653,
      "step": 13
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.12906824052333832,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 11.9242,
      "step": 14
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.12796084582805634,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 11.9255,
      "step": 15
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.12255435436964035,
      "learning_rate": 6.026312439675552e-06,
      "loss": 11.9267,
      "step": 16
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 0.11803531646728516,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 11.9246,
      "step": 17
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.12631937861442566,
      "learning_rate": 6.819348298638839e-07,
      "loss": 11.9239,
      "step": 18
    },
    {
      "epoch": 3.04,
      "grad_norm": 0.23046503961086273,
      "learning_rate": 0.0,
      "loss": 20.8562,
      "step": 19
    }
  ],
  "logging_steps": 1,
  "max_steps": 19,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 396147818496.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}