{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.230769230769231,
  "eval_steps": 25,
  "global_step": 275,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.38,
      "learning_rate": 2.29933110367893e-05,
      "loss": 1.9196,
      "step": 25
    },
    {
      "epoch": 0.38,
      "eval_loss": 1.4835141897201538,
      "eval_runtime": 4.4399,
      "eval_samples_per_second": 4.505,
      "eval_steps_per_second": 0.676,
      "step": 25
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.090301003344482e-05,
      "loss": 0.9398,
      "step": 50
    },
    {
      "epoch": 0.77,
      "eval_loss": 1.353461503982544,
      "eval_runtime": 4.4353,
      "eval_samples_per_second": 4.509,
      "eval_steps_per_second": 0.676,
      "step": 50
    },
    {
      "epoch": 1.15,
      "learning_rate": 1.8812709030100337e-05,
      "loss": 0.7795,
      "step": 75
    },
    {
      "epoch": 1.15,
      "eval_loss": 1.4102122783660889,
      "eval_runtime": 4.4451,
      "eval_samples_per_second": 4.499,
      "eval_steps_per_second": 0.675,
      "step": 75
    },
    {
      "epoch": 1.54,
      "learning_rate": 1.6722408026755853e-05,
      "loss": 0.6915,
      "step": 100
    },
    {
      "epoch": 1.54,
      "eval_loss": 1.3842780590057373,
      "eval_runtime": 4.44,
      "eval_samples_per_second": 4.505,
      "eval_steps_per_second": 0.676,
      "step": 100
    },
    {
      "epoch": 1.92,
      "learning_rate": 1.4632107023411373e-05,
      "loss": 0.706,
      "step": 125
    },
    {
      "epoch": 1.92,
      "eval_loss": 1.4492868185043335,
      "eval_runtime": 4.4412,
      "eval_samples_per_second": 4.503,
      "eval_steps_per_second": 0.675,
      "step": 125
    },
    {
      "epoch": 2.31,
      "learning_rate": 1.254180602006689e-05,
      "loss": 0.4767,
      "step": 150
    },
    {
      "epoch": 2.31,
      "eval_loss": 1.5637826919555664,
      "eval_runtime": 4.4377,
      "eval_samples_per_second": 4.507,
      "eval_steps_per_second": 0.676,
      "step": 150
    },
    {
      "epoch": 2.69,
      "learning_rate": 1.045150501672241e-05,
      "loss": 0.4167,
      "step": 175
    },
    {
      "epoch": 2.69,
      "eval_loss": 1.6361162662506104,
      "eval_runtime": 4.4339,
      "eval_samples_per_second": 4.511,
      "eval_steps_per_second": 0.677,
      "step": 175
    },
    {
      "epoch": 3.08,
      "learning_rate": 8.361204013377926e-06,
      "loss": 0.8085,
      "step": 200
    },
    {
      "epoch": 3.08,
      "eval_loss": 1.869662880897522,
      "eval_runtime": 4.4356,
      "eval_samples_per_second": 4.509,
      "eval_steps_per_second": 0.676,
      "step": 200
    },
    {
      "epoch": 3.46,
      "learning_rate": 6.270903010033445e-06,
      "loss": 1.1709,
      "step": 225
    },
    {
      "epoch": 3.46,
      "eval_loss": 2.216012954711914,
      "eval_runtime": 4.4388,
      "eval_samples_per_second": 4.506,
      "eval_steps_per_second": 0.676,
      "step": 225
    },
    {
      "epoch": 3.85,
      "learning_rate": 4.180602006688963e-06,
      "loss": 1.4037,
      "step": 250
    },
    {
      "epoch": 3.85,
      "eval_loss": 2.300891399383545,
      "eval_runtime": 4.436,
      "eval_samples_per_second": 4.509,
      "eval_steps_per_second": 0.676,
      "step": 250
    },
    {
      "epoch": 4.23,
      "learning_rate": 2.0903010033444816e-06,
      "loss": 1.5494,
      "step": 275
    },
    {
      "epoch": 4.23,
      "eval_loss": 2.494781494140625,
      "eval_runtime": 4.4383,
      "eval_samples_per_second": 4.506,
      "eval_steps_per_second": 0.676,
      "step": 275
    }
  ],
  "logging_steps": 25,
  "max_steps": 300,
  "num_train_epochs": 5,
  "save_steps": 25,
  "total_flos": 1519732103577600.0,
  "trial_name": null,
  "trial_params": null
}