{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.018017206432142698,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.00019510565162951537,
      "loss": 6.2051,
      "step": 100
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.9004,
      "step": 200
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.7042,
      "step": 300
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.6277,
      "step": 400
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 0.6574,
      "step": 500
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.6373,
      "step": 600
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.5668,
      "step": 700
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.6167,
      "step": 800
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.5712,
      "step": 900
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0,
      "loss": 0.6059,
      "step": 1000
    }
  ],
  "max_steps": 1000,
  "num_train_epochs": 1,
  "total_flos": 2739029409792000.0,
  "trial_name": null,
  "trial_params": null
}