{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.040096230954290296,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 4.99999449047447e-05,
      "loss": 2.7413,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.9999779619221645e-05,
      "loss": 2.6684,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999950414415935e-05,
      "loss": 2.6511,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999911848077199e-05,
      "loss": 2.72,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999862263075944e-05,
      "loss": 2.7222,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999801659630722e-05,
      "loss": 2.7479,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999730038008649e-05,
      "loss": 2.6063,
      "step": 35
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9996473985254055e-05,
      "loss": 2.576,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999553741545237e-05,
      "loss": 2.579,
      "step": 45
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999449067480945e-05,
      "loss": 2.5114,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9993333767938954e-05,
      "loss": 2.6174,
      "step": 55
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9992066699940085e-05,
      "loss": 2.6581,
      "step": 60
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9990689476397586e-05,
      "loss": 2.586,
      "step": 65
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.998920210338175e-05,
      "loss": 2.4642,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9987604587448343e-05,
      "loss": 2.6262,
      "step": 75
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.998589693563861e-05,
      "loss": 2.5678,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.998407915547924e-05,
      "loss": 2.5597,
      "step": 85
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9982151254982304e-05,
      "loss": 2.6578,
      "step": 90
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.998011324264527e-05,
      "loss": 2.4825,
      "step": 95
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.997796512745091e-05,
      "loss": 2.6197,
      "step": 100
    }
  ],
  "logging_steps": 5,
  "max_steps": 7482,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 1277352456683520.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}