{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2165674066053059,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02707092582566324,
      "grad_norm": 0.9713733196258545,
      "learning_rate": 9.910124526258799e-05,
      "loss": 3.4945,
      "step": 250
    },
    {
      "epoch": 0.05414185165132648,
      "grad_norm": 0.9521434307098389,
      "learning_rate": 9.819888106839921e-05,
      "loss": 3.5097,
      "step": 500
    },
    {
      "epoch": 0.05414185165132648,
      "eval_loss": 2.95473575592041,
      "eval_runtime": 87.829,
      "eval_samples_per_second": 112.15,
      "eval_steps_per_second": 7.014,
      "step": 500
    },
    {
      "epoch": 0.08121277747698971,
      "grad_norm": 0.9334385395050049,
      "learning_rate": 9.729651687421044e-05,
      "loss": 3.4922,
      "step": 750
    },
    {
      "epoch": 0.10828370330265295,
      "grad_norm": 1.2239603996276855,
      "learning_rate": 9.639415268002166e-05,
      "loss": 3.477,
      "step": 1000
    },
    {
      "epoch": 0.10828370330265295,
      "eval_loss": 2.9319565296173096,
      "eval_runtime": 87.8964,
      "eval_samples_per_second": 112.064,
      "eval_steps_per_second": 7.008,
      "step": 1000
    },
    {
      "epoch": 0.1353546291283162,
      "grad_norm": 1.1727226972579956,
      "learning_rate": 9.549178848583288e-05,
      "loss": 3.493,
      "step": 1250
    },
    {
      "epoch": 0.16242555495397942,
      "grad_norm": 0.966973602771759,
      "learning_rate": 9.458942429164411e-05,
      "loss": 3.5013,
      "step": 1500
    },
    {
      "epoch": 0.16242555495397942,
      "eval_loss": 2.9275825023651123,
      "eval_runtime": 87.899,
      "eval_samples_per_second": 112.06,
      "eval_steps_per_second": 7.008,
      "step": 1500
    },
    {
      "epoch": 0.18949648077964265,
      "grad_norm": 0.9813922047615051,
      "learning_rate": 9.368706009745533e-05,
      "loss": 3.4907,
      "step": 1750
    },
    {
      "epoch": 0.2165674066053059,
      "grad_norm": 1.027085542678833,
      "learning_rate": 9.278469590326656e-05,
      "loss": 3.4588,
      "step": 2000
    },
    {
      "epoch": 0.2165674066053059,
      "eval_loss": 2.9044992923736572,
      "eval_runtime": 87.8776,
      "eval_samples_per_second": 112.088,
      "eval_steps_per_second": 7.01,
      "step": 2000
    }
  ],
  "logging_steps": 250,
  "max_steps": 27705,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 722108153856000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}