{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.29952,
  "eval_steps": 312,
  "global_step": 936,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.032,
      "grad_norm": 12.154169082641602,
      "learning_rate": 1.5814696485623005e-05,
      "loss": 0.6236,
      "step": 100
    },
    {
      "epoch": 0.064,
      "grad_norm": 9.922504425048828,
      "learning_rate": 3.17891373801917e-05,
      "loss": 0.3588,
      "step": 200
    },
    {
      "epoch": 0.096,
      "grad_norm": 3.1723761558532715,
      "learning_rate": 4.76038338658147e-05,
      "loss": 0.2728,
      "step": 300
    },
    {
      "epoch": 0.09984,
      "eval_loss": 0.30084338784217834,
      "eval_runtime": 22.6946,
      "eval_samples_per_second": 220.317,
      "eval_steps_per_second": 13.792,
      "step": 312
    },
    {
      "epoch": 0.128,
      "grad_norm": 3.547367572784424,
      "learning_rate": 4.8488620199146516e-05,
      "loss": 0.2796,
      "step": 400
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.3291678428649902,
      "learning_rate": 4.671052631578948e-05,
      "loss": 0.2329,
      "step": 500
    },
    {
      "epoch": 0.192,
      "grad_norm": 7.059551239013672,
      "learning_rate": 4.4932432432432435e-05,
      "loss": 0.2115,
      "step": 600
    },
    {
      "epoch": 0.19968,
      "eval_loss": 0.21099330484867096,
      "eval_runtime": 22.3651,
      "eval_samples_per_second": 223.563,
      "eval_steps_per_second": 13.995,
      "step": 624
    },
    {
      "epoch": 0.224,
      "grad_norm": 9.585307121276855,
      "learning_rate": 4.31543385490754e-05,
      "loss": 0.2362,
      "step": 700
    },
    {
      "epoch": 0.256,
      "grad_norm": 3.5654361248016357,
      "learning_rate": 4.137624466571835e-05,
      "loss": 0.192,
      "step": 800
    },
    {
      "epoch": 0.288,
      "grad_norm": 15.965906143188477,
      "learning_rate": 3.959815078236131e-05,
      "loss": 0.1919,
      "step": 900
    },
    {
      "epoch": 0.29952,
      "eval_loss": 0.19985319674015045,
      "eval_runtime": 22.2546,
      "eval_samples_per_second": 224.673,
      "eval_steps_per_second": 14.065,
      "step": 936
    }
  ],
  "logging_steps": 100,
  "max_steps": 3125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 312,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}