{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1076923076923077,
  "eval_steps": 10,
  "global_step": 35,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006153846153846154,
      "eval_loss": 1.4845428466796875,
      "eval_runtime": 1.2728,
      "eval_samples_per_second": 89.569,
      "eval_steps_per_second": 4.714,
      "step": 2
    },
    {
      "epoch": 0.03076923076923077,
      "grad_norm": 15.541728973388672,
      "learning_rate": 6.060606060606061e-06,
      "loss": 1.4404,
      "step": 10
    },
    {
      "epoch": 0.03076923076923077,
      "eval_loss": 0.9616736769676208,
      "eval_runtime": 1.1678,
      "eval_samples_per_second": 97.621,
      "eval_steps_per_second": 5.138,
      "step": 10
    },
    {
      "epoch": 0.06153846153846154,
      "grad_norm": 12.678512573242188,
      "learning_rate": 1.2121212121212122e-05,
      "loss": 0.8308,
      "step": 20
    },
    {
      "epoch": 0.06153846153846154,
      "eval_loss": 0.7126240134239197,
      "eval_runtime": 1.1678,
      "eval_samples_per_second": 97.621,
      "eval_steps_per_second": 5.138,
      "step": 20
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 10.91329574584961,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.8042,
      "step": 30
    },
    {
      "epoch": 0.09230769230769231,
      "eval_loss": 0.7227696180343628,
      "eval_runtime": 1.17,
      "eval_samples_per_second": 97.438,
      "eval_steps_per_second": 5.128,
      "step": 30
    }
  ],
  "logging_steps": 10,
  "max_steps": 325,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "total_flos": 2144353824800768.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}