{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 1000.0,
  "global_step": 7494,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.200160128102482,
      "grad_norm": 2.155690908432007,
      "learning_rate": 4.6663997864958635e-05,
      "loss": 4.4221,
      "step": 500
    },
    {
      "epoch": 0.400320256204964,
      "grad_norm": 1.6321208477020264,
      "learning_rate": 4.332799572991727e-05,
      "loss": 4.1746,
      "step": 1000
    },
    {
      "epoch": 0.600480384307446,
      "grad_norm": 2.751591920852661,
      "learning_rate": 3.99919935948759e-05,
      "loss": 4.1681,
      "step": 1500
    },
    {
      "epoch": 0.800640512409928,
      "grad_norm": 1.6891682147979736,
      "learning_rate": 3.665599145983454e-05,
      "loss": 4.1559,
      "step": 2000
    },
    {
      "epoch": 1.00080064051241,
      "grad_norm": 2.1806092262268066,
      "learning_rate": 3.3319989324793174e-05,
      "loss": 4.1615,
      "step": 2500
    },
    {
      "epoch": 1.200960768614892,
      "grad_norm": 2.332911491394043,
      "learning_rate": 2.9983987189751807e-05,
      "loss": 4.1495,
      "step": 3000
    },
    {
      "epoch": 1.4011208967173738,
      "grad_norm": 2.650616407394409,
      "learning_rate": 2.6647985054710433e-05,
      "loss": 4.1441,
      "step": 3500
    },
    {
      "epoch": 1.601281024819856,
      "grad_norm": 1.7507755756378174,
      "learning_rate": 2.331198291966907e-05,
      "loss": 4.1309,
      "step": 4000
    },
    {
      "epoch": 1.801441152922338,
      "grad_norm": 1.7960165739059448,
      "learning_rate": 1.9975980784627705e-05,
      "loss": 4.151,
      "step": 4500
    },
    {
      "epoch": 2.00160128102482,
      "grad_norm": 2.081895112991333,
      "learning_rate": 1.6639978649586335e-05,
      "loss": 4.1392,
      "step": 5000
    },
    {
      "epoch": 2.2017614091273017,
      "grad_norm": 2.4643125534057617,
      "learning_rate": 1.330397651454497e-05,
      "loss": 4.141,
      "step": 5500
    },
    {
      "epoch": 2.401921537229784,
      "grad_norm": 2.676142692565918,
      "learning_rate": 9.967974379503602e-06,
      "loss": 4.1454,
      "step": 6000
    },
    {
      "epoch": 2.602081665332266,
      "grad_norm": 2.038424015045166,
      "learning_rate": 6.631972244462237e-06,
      "loss": 4.1188,
      "step": 6500
    },
    {
      "epoch": 2.8022417934347477,
      "grad_norm": 2.213303565979004,
      "learning_rate": 3.29597010942087e-06,
      "loss": 4.1281,
      "step": 7000
    },
    {
      "epoch": 3.0,
      "step": 7494,
      "total_flos": 3.595290103775232e+16,
      "train_loss": 4.164535013427408,
      "train_runtime": 5790.6888,
      "train_samples_per_second": 2.588,
      "train_steps_per_second": 1.294
    }
  ],
  "logging_steps": 500,
  "max_steps": 7494,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 3.595290103775232e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}