{
  "best_global_step": 20,
  "best_metric": 0.3384554982185364,
  "best_model_checkpoint": "/content/models/gemma_qlora_lmh_inst/checkpoint-20",
  "epoch": 1.25,
  "eval_steps": 20,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.7708985269069673,
      "epoch": 1.25,
      "grad_norm": 3.859375,
      "learning_rate": 4.0625000000000005e-06,
      "loss": 0.773,
      "mean_token_accuracy": 0.8001608535647392,
      "num_tokens": 64265.0,
      "step": 20
    },
    {
      "epoch": 1.25,
      "eval_entropy": 1.772031757980585,
      "eval_loss": 0.3384554982185364,
      "eval_mean_token_accuracy": 0.8753308840095997,
      "eval_num_tokens": 64265.0,
      "eval_runtime": 6.0558,
      "eval_samples_per_second": 82.565,
      "eval_steps_per_second": 5.284,
      "step": 20
    }
  ],
  "logging_steps": 20,
  "max_steps": 32,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1003143202652160.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}