{
  "best_metric": 5.105292802909389e-05,
  "best_model_checkpoint": "/content/donut_finetuned/checkpoint-65",
  "epoch": 13.0,
  "eval_steps": 500,
  "global_step": 65,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 9.464871406555176,
      "eval_runtime": 4.0077,
      "eval_samples_per_second": 3.743,
      "eval_steps_per_second": 1.996,
      "step": 5
    },
    {
      "epoch": 2.0,
      "grad_norm": 46.585044860839844,
      "learning_rate": 2.4e-05,
      "loss": 10.4972,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_loss": 6.029897689819336,
      "eval_runtime": 3.4276,
      "eval_samples_per_second": 4.376,
      "eval_steps_per_second": 2.334,
      "step": 10
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.0910725593566895,
      "eval_runtime": 3.4674,
      "eval_samples_per_second": 4.326,
      "eval_steps_per_second": 2.307,
      "step": 15
    },
    {
      "epoch": 4.0,
      "grad_norm": 11.026430130004883,
      "learning_rate": 2.9418925439074784e-05,
      "loss": 3.1451,
      "step": 20
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.37007761001586914,
      "eval_runtime": 4.5507,
      "eval_samples_per_second": 3.296,
      "eval_steps_per_second": 1.758,
      "step": 20
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.020941253751516342,
      "eval_runtime": 3.4626,
      "eval_samples_per_second": 4.332,
      "eval_steps_per_second": 2.31,
      "step": 25
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.41835108399391174,
      "learning_rate": 2.7135254915624213e-05,
      "loss": 0.1413,
      "step": 30
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.0015195924788713455,
      "eval_runtime": 3.3155,
      "eval_samples_per_second": 4.524,
      "eval_steps_per_second": 2.413,
      "step": 30
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.000456114619737491,
      "eval_runtime": 3.3952,
      "eval_samples_per_second": 4.418,
      "eval_steps_per_second": 2.356,
      "step": 35
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.04658687859773636,
      "learning_rate": 2.3387893552061202e-05,
      "loss": 0.0024,
      "step": 40
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.00013167245197109878,
      "eval_runtime": 4.4677,
      "eval_samples_per_second": 3.357,
      "eval_steps_per_second": 1.791,
      "step": 40
    },
    {
      "epoch": 9.0,
      "eval_loss": 7.056079630274326e-05,
      "eval_runtime": 3.3248,
      "eval_samples_per_second": 4.512,
      "eval_steps_per_second": 2.406,
      "step": 45
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.029017027467489243,
      "learning_rate": 1.8628828433995013e-05,
      "loss": 0.0009,
      "step": 50
    },
    {
      "epoch": 10.0,
      "eval_loss": 5.423852053354494e-05,
      "eval_runtime": 3.3999,
      "eval_samples_per_second": 4.412,
      "eval_steps_per_second": 2.353,
      "step": 50
    },
    {
      "epoch": 11.0,
      "eval_loss": 5.392546518123709e-05,
      "eval_runtime": 3.3083,
      "eval_samples_per_second": 4.534,
      "eval_steps_per_second": 2.418,
      "step": 55
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.020294995978474617,
      "learning_rate": 1.3432073050985201e-05,
      "loss": 0.0013,
      "step": 60
    },
    {
      "epoch": 12.0,
      "eval_loss": 6.161272176541388e-05,
      "eval_runtime": 3.3432,
      "eval_samples_per_second": 4.487,
      "eval_steps_per_second": 2.393,
      "step": 60
    },
    {
      "epoch": 13.0,
      "eval_loss": 5.105292802909389e-05,
      "eval_runtime": 3.3625,
      "eval_samples_per_second": 4.461,
      "eval_steps_per_second": 2.379,
      "step": 65
    }
  ],
  "logging_steps": 10,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.251988117061632e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}