{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 16.363636363636363,
  "eval_steps": 25,
  "global_step": 225,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.82,
      "learning_rate": 2.3797595190380762e-05,
      "loss": 1.5248,
      "step": 25
    },
    {
      "epoch": 1.82,
      "eval_loss": 1.3447530269622803,
      "eval_runtime": 4.2355,
      "eval_samples_per_second": 6.611,
      "eval_steps_per_second": 0.944,
      "step": 25
    },
    {
      "epoch": 3.64,
      "learning_rate": 2.2545090180360722e-05,
      "loss": 1.1125,
      "step": 50
    },
    {
      "epoch": 3.64,
      "eval_loss": 1.1437653303146362,
      "eval_runtime": 4.2057,
      "eval_samples_per_second": 6.658,
      "eval_steps_per_second": 0.951,
      "step": 50
    },
    {
      "epoch": 5.45,
      "learning_rate": 2.1292585170340683e-05,
      "loss": 0.8854,
      "step": 75
    },
    {
      "epoch": 5.45,
      "eval_loss": 1.1170519590377808,
      "eval_runtime": 4.2075,
      "eval_samples_per_second": 6.655,
      "eval_steps_per_second": 0.951,
      "step": 75
    },
    {
      "epoch": 7.27,
      "learning_rate": 2.0040080160320643e-05,
      "loss": 0.6729,
      "step": 100
    },
    {
      "epoch": 7.27,
      "eval_loss": 1.2089412212371826,
      "eval_runtime": 4.2061,
      "eval_samples_per_second": 6.657,
      "eval_steps_per_second": 0.951,
      "step": 100
    },
    {
      "epoch": 9.09,
      "learning_rate": 1.87875751503006e-05,
      "loss": 0.4656,
      "step": 125
    },
    {
      "epoch": 9.09,
      "eval_loss": 1.3860394954681396,
      "eval_runtime": 4.2101,
      "eval_samples_per_second": 6.651,
      "eval_steps_per_second": 0.95,
      "step": 125
    },
    {
      "epoch": 10.91,
      "learning_rate": 1.7535070140280564e-05,
      "loss": 0.2738,
      "step": 150
    },
    {
      "epoch": 10.91,
      "eval_loss": 1.6905710697174072,
      "eval_runtime": 4.209,
      "eval_samples_per_second": 6.652,
      "eval_steps_per_second": 0.95,
      "step": 150
    },
    {
      "epoch": 12.73,
      "learning_rate": 1.628256513026052e-05,
      "loss": 0.1355,
      "step": 175
    },
    {
      "epoch": 12.73,
      "eval_loss": 2.1363654136657715,
      "eval_runtime": 4.21,
      "eval_samples_per_second": 6.651,
      "eval_steps_per_second": 0.95,
      "step": 175
    },
    {
      "epoch": 14.55,
      "learning_rate": 1.5030060120240483e-05,
      "loss": 0.0744,
      "step": 200
    },
    {
      "epoch": 14.55,
      "eval_loss": 2.503084421157837,
      "eval_runtime": 4.2097,
      "eval_samples_per_second": 6.651,
      "eval_steps_per_second": 0.95,
      "step": 200
    },
    {
      "epoch": 16.36,
      "learning_rate": 1.3777555110220442e-05,
      "loss": 0.0535,
      "step": 225
    },
    {
      "epoch": 16.36,
      "eval_loss": 2.633431911468506,
      "eval_runtime": 4.2087,
      "eval_samples_per_second": 6.653,
      "eval_steps_per_second": 0.95,
      "step": 225
    }
  ],
  "logging_steps": 25,
  "max_steps": 500,
  "num_train_epochs": 39,
  "save_steps": 25,
  "total_flos": 3.94366669553664e+16,
  "trial_name": null,
  "trial_params": null
}