{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.974025974025974,
  "eval_steps": 25,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "grad_norm": 11.01017951965332,
      "learning_rate": 2.2361809045226133e-05,
      "loss": 2.5416,
      "step": 25
    },
    {
      "epoch": 0.16,
      "eval_loss": 1.7125414609909058,
      "eval_runtime": 5.0817,
      "eval_samples_per_second": 6.887,
      "eval_steps_per_second": 0.984,
      "step": 25
    },
    {
      "epoch": 0.32,
      "grad_norm": 10.009162902832031,
      "learning_rate": 1.9221105527638193e-05,
      "loss": 1.6162,
      "step": 50
    },
    {
      "epoch": 0.32,
      "eval_loss": 1.5332300662994385,
      "eval_runtime": 5.2881,
      "eval_samples_per_second": 6.619,
      "eval_steps_per_second": 0.946,
      "step": 50
    },
    {
      "epoch": 0.49,
      "grad_norm": 9.377760887145996,
      "learning_rate": 1.608040201005025e-05,
      "loss": 1.4794,
      "step": 75
    },
    {
      "epoch": 0.49,
      "eval_loss": 1.431817889213562,
      "eval_runtime": 5.1946,
      "eval_samples_per_second": 6.738,
      "eval_steps_per_second": 0.963,
      "step": 75
    },
    {
      "epoch": 0.65,
      "grad_norm": 14.868287086486816,
      "learning_rate": 1.2939698492462313e-05,
      "loss": 1.3783,
      "step": 100
    },
    {
      "epoch": 0.65,
      "eval_loss": 1.3400715589523315,
      "eval_runtime": 5.2323,
      "eval_samples_per_second": 6.689,
      "eval_steps_per_second": 0.956,
      "step": 100
    },
    {
      "epoch": 0.81,
      "grad_norm": 11.457832336425781,
      "learning_rate": 9.798994974874372e-06,
      "loss": 1.3071,
      "step": 125
    },
    {
      "epoch": 0.81,
      "eval_loss": 1.2986036539077759,
      "eval_runtime": 5.2307,
      "eval_samples_per_second": 6.691,
      "eval_steps_per_second": 0.956,
      "step": 125
    },
    {
      "epoch": 0.97,
      "grad_norm": 9.498678207397461,
      "learning_rate": 6.658291457286432e-06,
      "loss": 1.2695,
      "step": 150
    },
    {
      "epoch": 0.97,
      "eval_loss": 1.272000789642334,
      "eval_runtime": 5.2257,
      "eval_samples_per_second": 6.698,
      "eval_steps_per_second": 0.957,
      "step": 150
    }
  ],
  "logging_steps": 25,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "total_flos": 1036180979712000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}