{
  "best_metric": 0.8963138930200525,
  "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v1/checkpoint-1600",
  "epoch": 0.8528784648187633,
  "eval_steps": 100,
  "global_step": 1600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.053304904051172705,
      "eval_accuracy": 0.6684599798377034,
      "eval_f1": 0.6684599798377034,
      "eval_loss": 0.9209221005439758,
      "eval_precision": 0.6684599798377034,
      "eval_recall": 0.6684599798377034,
      "eval_runtime": 41.8743,
      "eval_samples_per_second": 38.377,
      "eval_steps_per_second": 2.412,
      "step": 100
    },
    {
      "epoch": 0.10660980810234541,
      "eval_accuracy": 0.8154451176300318,
      "eval_f1": 0.8154451176300318,
      "eval_loss": 0.6488999724388123,
      "eval_precision": 0.8154451176300318,
      "eval_recall": 0.8154451176300318,
      "eval_runtime": 44.2144,
      "eval_samples_per_second": 36.346,
      "eval_steps_per_second": 2.284,
      "step": 200
    },
    {
      "epoch": 0.15991471215351813,
      "eval_accuracy": 0.7420323994130975,
      "eval_f1": 0.7420323994130975,
      "eval_loss": 0.7198283076286316,
      "eval_precision": 0.7420323994130975,
      "eval_recall": 0.7420323994130975,
      "eval_runtime": 41.064,
      "eval_samples_per_second": 39.134,
      "eval_steps_per_second": 2.46,
      "step": 300
    },
    {
      "epoch": 0.21321961620469082,
      "eval_accuracy": 0.7961212532564105,
      "eval_f1": 0.7961212532564104,
      "eval_loss": 0.5486767292022705,
      "eval_precision": 0.7961212532564105,
      "eval_recall": 0.7961212532564105,
      "eval_runtime": 43.0362,
      "eval_samples_per_second": 37.341,
      "eval_steps_per_second": 2.347,
      "step": 400
    },
    {
      "epoch": 0.26652452025586354,
      "grad_norm": 8.946574211120605,
      "learning_rate": 1.4722814498933904e-05,
      "loss": 0.736,
      "step": 500
    },
    {
      "epoch": 0.26652452025586354,
      "eval_accuracy": 0.8669088803936639,
      "eval_f1": 0.8669088803936638,
      "eval_loss": 0.44298624992370605,
      "eval_precision": 0.8669088803936639,
      "eval_recall": 0.8669088803936639,
      "eval_runtime": 42.8219,
      "eval_samples_per_second": 37.527,
      "eval_steps_per_second": 2.359,
      "step": 500
    },
    {
      "epoch": 0.31982942430703626,
      "eval_accuracy": 0.8614091648617086,
      "eval_f1": 0.8614091648617086,
      "eval_loss": 0.4405972361564636,
      "eval_precision": 0.8614091648617086,
      "eval_recall": 0.8614091648617086,
      "eval_runtime": 46.0068,
      "eval_samples_per_second": 34.93,
      "eval_steps_per_second": 2.195,
      "step": 600
    },
    {
      "epoch": 0.373134328358209,
      "eval_accuracy": 0.865092277441185,
      "eval_f1": 0.865092277441185,
      "eval_loss": 0.41120249032974243,
      "eval_precision": 0.865092277441185,
      "eval_recall": 0.865092277441185,
      "eval_runtime": 43.2183,
      "eval_samples_per_second": 37.183,
      "eval_steps_per_second": 2.337,
      "step": 700
    },
    {
      "epoch": 0.42643923240938164,
      "eval_accuracy": 0.8710710970485193,
      "eval_f1": 0.8710710970485193,
      "eval_loss": 0.41007000207901,
      "eval_precision": 0.8710710970485193,
      "eval_recall": 0.8710710970485193,
      "eval_runtime": 41.5981,
      "eval_samples_per_second": 38.632,
      "eval_steps_per_second": 2.428,
      "step": 800
    },
    {
      "epoch": 0.47974413646055436,
      "eval_accuracy": 0.8397596494555182,
      "eval_f1": 0.8397596494555181,
      "eval_loss": 0.469059020280838,
      "eval_precision": 0.8397596494555182,
      "eval_recall": 0.8397596494555182,
      "eval_runtime": 42.8271,
      "eval_samples_per_second": 37.523,
      "eval_steps_per_second": 2.358,
      "step": 900
    },
    {
      "epoch": 0.5330490405117271,
      "grad_norm": 1.78385591506958,
      "learning_rate": 9.392324093816631e-06,
      "loss": 0.4575,
      "step": 1000
    },
    {
      "epoch": 0.5330490405117271,
      "eval_accuracy": 0.8009322566800083,
      "eval_f1": 0.8009322566800084,
      "eval_loss": 0.4894373416900635,
      "eval_precision": 0.8009322566800083,
      "eval_recall": 0.8009322566800083,
      "eval_runtime": 45.5517,
      "eval_samples_per_second": 35.279,
      "eval_steps_per_second": 2.217,
      "step": 1000
    },
    {
      "epoch": 0.5863539445628998,
      "eval_accuracy": 0.8552706438959147,
      "eval_f1": 0.8552706438959147,
      "eval_loss": 0.427526593208313,
      "eval_precision": 0.8552706438959147,
      "eval_recall": 0.8552706438959147,
      "eval_runtime": 41.1754,
      "eval_samples_per_second": 39.028,
      "eval_steps_per_second": 2.453,
      "step": 1100
    },
    {
      "epoch": 0.6396588486140725,
      "eval_accuracy": 0.88568377134758,
      "eval_f1": 0.88568377134758,
      "eval_loss": 0.3613550066947937,
      "eval_precision": 0.88568377134758,
      "eval_recall": 0.88568377134758,
      "eval_runtime": 43.3876,
      "eval_samples_per_second": 37.038,
      "eval_steps_per_second": 2.328,
      "step": 1200
    },
    {
      "epoch": 0.6929637526652452,
      "eval_accuracy": 0.8431832473274976,
      "eval_f1": 0.8431832473274976,
      "eval_loss": 0.45708218216896057,
      "eval_precision": 0.8431832473274976,
      "eval_recall": 0.8431832473274976,
      "eval_runtime": 43.4109,
      "eval_samples_per_second": 37.018,
      "eval_steps_per_second": 2.327,
      "step": 1300
    },
    {
      "epoch": 0.746268656716418,
      "eval_accuracy": 0.8377234571351573,
      "eval_f1": 0.8377234571351573,
      "eval_loss": 0.4477834701538086,
      "eval_precision": 0.8377234571351573,
      "eval_recall": 0.8377234571351573,
      "eval_runtime": 41.9819,
      "eval_samples_per_second": 38.278,
      "eval_steps_per_second": 2.406,
      "step": 1400
    },
    {
      "epoch": 0.7995735607675906,
      "grad_norm": 3.844151496887207,
      "learning_rate": 4.061833688699361e-06,
      "loss": 0.3718,
      "step": 1500
    },
    {
      "epoch": 0.7995735607675906,
      "eval_accuracy": 0.8324133869663729,
      "eval_f1": 0.8324133869663729,
      "eval_loss": 0.43807488679885864,
      "eval_precision": 0.8324133869663729,
      "eval_recall": 0.8324133869663729,
      "eval_runtime": 44.8422,
      "eval_samples_per_second": 35.837,
      "eval_steps_per_second": 2.252,
      "step": 1500
    },
    {
      "epoch": 0.8528784648187633,
      "eval_accuracy": 0.8963138930200525,
      "eval_f1": 0.8963138930200525,
      "eval_loss": 0.3266744911670685,
      "eval_precision": 0.8963138930200525,
      "eval_recall": 0.8963138930200525,
      "eval_runtime": 42.399,
      "eval_samples_per_second": 37.902,
      "eval_steps_per_second": 2.382,
      "step": 1600
    }
  ],
  "logging_steps": 500,
  "max_steps": 1876,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3560604657254400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}