{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0064865566114228265,
  "eval_steps": 10,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 7.601585865020752,
      "learning_rate": 0.00016,
      "loss": 1.629,
      "step": 5
    },
    {
      "epoch": 0.0,
      "grad_norm": 6.085068702697754,
      "learning_rate": 0.00012,
      "loss": 0.7239,
      "step": 10
    },
    {
      "epoch": 0.0,
      "eval_loss": 0.6832157969474792,
      "eval_runtime": 7374.2039,
      "eval_samples_per_second": 0.481,
      "eval_steps_per_second": 0.481,
      "step": 10
    },
    {
      "epoch": 0.0,
      "grad_norm": 3.401209831237793,
      "learning_rate": 8e-05,
      "loss": 0.6425,
      "step": 15
    },
    {
      "epoch": 0.01,
      "grad_norm": 3.414715051651001,
      "learning_rate": 4e-05,
      "loss": 0.7502,
      "step": 20
    },
    {
      "epoch": 0.01,
      "eval_loss": 0.6290897130966187,
      "eval_runtime": 7374.3989,
      "eval_samples_per_second": 0.481,
      "eval_steps_per_second": 0.481,
      "step": 20
    },
    {
      "epoch": 0.01,
      "grad_norm": 2.3705151081085205,
      "learning_rate": 0.0,
      "loss": 0.5581,
      "step": 25
    },
    {
      "epoch": 0.01,
      "step": 25,
      "total_flos": 832443140849664.0,
      "train_loss": 0.8607504749298096,
      "train_runtime": 15509.9229,
      "train_samples_per_second": 0.013,
      "train_steps_per_second": 0.002
    }
  ],
  "logging_steps": 5,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "total_flos": 832443140849664.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}