{
  "best_metric": 0.09644630551338196,
  "best_model_checkpoint": "finetuned-ai-real-beit/checkpoint-50",
  "epoch": 5.0,
  "eval_steps": 50,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 4.455732345581055,
      "learning_rate": 0.00018363636363636366,
      "loss": 0.3675,
      "step": 10
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 6.04647159576416,
      "learning_rate": 0.00016545454545454545,
      "loss": 0.1004,
      "step": 20
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 7.7111616134643555,
      "learning_rate": 0.00014727272727272728,
      "loss": 0.1074,
      "step": 30
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 3.5139763355255127,
      "learning_rate": 0.0001290909090909091,
      "loss": 0.0934,
      "step": 40
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 1.9594430923461914,
      "learning_rate": 0.00011090909090909092,
      "loss": 0.0724,
      "step": 50
    },
    {
      "epoch": 2.2727272727272725,
      "eval_accuracy": 0.9669421487603306,
      "eval_loss": 0.09644630551338196,
      "eval_runtime": 1.506,
      "eval_samples_per_second": 80.347,
      "eval_steps_per_second": 10.624,
      "step": 50
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 1.1000548601150513,
      "learning_rate": 9.272727272727273e-05,
      "loss": 0.0213,
      "step": 60
    },
    {
      "epoch": 3.1818181818181817,
      "grad_norm": 1.2705051898956299,
      "learning_rate": 7.454545454545455e-05,
      "loss": 0.0563,
      "step": 70
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.07004624605178833,
      "learning_rate": 5.636363636363636e-05,
      "loss": 0.0588,
      "step": 80
    },
    {
      "epoch": 4.090909090909091,
      "grad_norm": 6.447866916656494,
      "learning_rate": 3.818181818181819e-05,
      "loss": 0.0296,
      "step": 90
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 0.036224253475666046,
      "learning_rate": 2e-05,
      "loss": 0.0198,
      "step": 100
    },
    {
      "epoch": 4.545454545454545,
      "eval_accuracy": 0.9586776859504132,
      "eval_loss": 0.13395561277866364,
      "eval_runtime": 1.4421,
      "eval_samples_per_second": 83.904,
      "eval_steps_per_second": 11.095,
      "step": 100
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.009324366226792336,
      "learning_rate": 1.818181818181818e-06,
      "loss": 0.0103,
      "step": 110
    },
    {
      "epoch": 5.0,
      "step": 110,
      "total_flos": 2.633601533681664e+17,
      "train_loss": 0.08520049764351412,
      "train_runtime": 91.5555,
      "train_samples_per_second": 37.136,
      "train_steps_per_second": 1.201
    }
  ],
  "logging_steps": 10,
  "max_steps": 110,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.633601533681664e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}