---
library_name: transformers
license: mit
base_model: xlnet/xlnet-base-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: xlnet-base-cased-grammar-ner-generic
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# xlnet-base-cased-grammar-ner-generic

This model is a fine-tuned version of [xlnet/xlnet-base-cased](https://huggingface.co/xlnet/xlnet-base-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0907
- Accuracy: 0.9907
- F1 Macro: 0.9282
- F1 Micro: 0.9282
- Precision Macro: 0.9686
- Precision Micro: 0.9686
- Recall Macro: 0.8910
- Recall Micro: 0.8910

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 18

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro | Precision Macro | Precision Micro | Recall Macro | Recall Micro |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|:---------------:|:---------------:|:------------:|:------------:|
| 0.2156        | 1.0   | 93   | 0.1656          | 0.9273   | 0.4389   | 0.4389   | 0.3873          | 0.3873          | 0.5064       | 0.5064       |
| 0.136         | 2.0   | 186  | 0.1196          | 0.9611   | 0.5396   | 0.5396   | 0.8129          | 0.8129          | 0.4038       | 0.4038       |
| 0.0885        | 3.0   | 279  | 0.0983          | 0.9673   | 0.7120   | 0.7120   | 0.7031          | 0.7031          | 0.7212       | 0.7212       |
| 0.0585        | 4.0   | 372  | 0.0908          | 0.9760   | 0.7898   | 0.7898   | 0.8381          | 0.8381          | 0.7468       | 0.7468       |
| 0.0406        | 5.0   | 465  | 0.0952          | 0.9723   | 0.7365   | 0.7365   | 0.8084          | 0.8084          | 0.6763       | 0.6763       |
| 0.0323        | 6.0   | 558  | 0.0755          | 0.9826   | 0.8529   | 0.8529   | 0.87            | 0.87            | 0.8365       | 0.8365       |
| 0.0228        | 7.0   | 651  | 0.0682          | 0.9858   | 0.8724   | 0.8724   | 0.8795          | 0.8795          | 0.8654       | 0.8654       |
| 0.0127        | 8.0   | 744  | 0.0822          | 0.9866   | 0.8799   | 0.8799   | 0.9319          | 0.9319          | 0.8333       | 0.8333       |
| 0.0107        | 9.0   | 837  | 0.0802          | 0.9879   | 0.9008   | 0.9008   | 0.9142          | 0.9142          | 0.8878       | 0.8878       |
| 0.007         | 10.0  | 930  | 0.0866          | 0.9878   | 0.9042   | 0.9042   | 0.9505          | 0.9505          | 0.8622       | 0.8622       |
| 0.0049        | 11.0  | 1023 | 0.0815          | 0.9884   | 0.9005   | 0.9005   | 0.9169          | 0.9169          | 0.8846       | 0.8846       |
| 0.0045        | 12.0  | 1116 | 0.0931          | 0.9886   | 0.9082   | 0.9082   | 0.9477          | 0.9477          | 0.8718       | 0.8718       |
| 0.003         | 13.0  | 1209 | 0.0926          | 0.9891   | 0.9195   | 0.9195   | 0.9648          | 0.9648          | 0.8782       | 0.8782       |
| 0.0015        | 14.0  | 1302 | 0.0840          | 0.9900   | 0.9208   | 0.9208   | 0.9490          | 0.9490          | 0.8942       | 0.8942       |
| 0.0009        | 15.0  | 1395 | 0.0895          | 0.9907   | 0.9280   | 0.9280   | 0.9719          | 0.9719          | 0.8878       | 0.8878       |
| 0.0007        | 16.0  | 1488 | 0.0898          | 0.9907   | 0.9282   | 0.9282   | 0.9686          | 0.9686          | 0.8910       | 0.8910       |
| 0.0005        | 17.0  | 1581 | 0.0903          | 0.9907   | 0.9282   | 0.9282   | 0.9686          | 0.9686          | 0.8910       | 0.8910       |
| 0.0006        | 18.0  | 1674 | 0.0907          | 0.9907   | 0.9282   | 0.9282   | 0.9686          | 0.9686          | 0.8910       | 0.8910       |


### Framework versions

- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3