{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.28196813760045114,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 4.8589960518894536e-05,
      "loss": 0.6413,
      "step": 50
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.717992103778906e-05,
      "loss": 0.6068,
      "step": 100
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.576988155668359e-05,
      "loss": 0.5975,
      "step": 150
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.435984207557812e-05,
      "loss": 0.5683,
      "step": 200
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.294980259447265e-05,
      "loss": 0.5482,
      "step": 250
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.153976311336718e-05,
      "loss": 0.5216,
      "step": 300
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.0129723632261705e-05,
      "loss": 0.5204,
      "step": 350
    },
    {
      "epoch": 0.23,
      "learning_rate": 3.871968415115623e-05,
      "loss": 0.7592,
      "step": 400
    },
    {
      "epoch": 0.25,
      "learning_rate": 3.7309644670050766e-05,
      "loss": 0.954,
      "step": 450
    },
    {
      "epoch": 0.28,
      "learning_rate": 3.589960518894529e-05,
      "loss": 0.9491,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 1773,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 250,
  "total_flos": 1.3411773579264e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}