---
library_name: transformers
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: scenario-non-kd-scr-ner-full-mdeberta_data-univner_full66
  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. -->

# scenario-non-kd-scr-ner-full-mdeberta_data-univner_full66

This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3189
- Precision: 0.6246
- Recall: 0.5741
- F1: 0.5983
- Accuracy: 0.9618

## 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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 66
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30

### Training results

| Training Loss | Epoch   | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.3108        | 0.2910  | 500   | 0.2429          | 0.3192    | 0.2232 | 0.2627 | 0.9338   |
| 0.1942        | 0.5821  | 1000  | 0.1982          | 0.4385    | 0.3207 | 0.3705 | 0.9447   |
| 0.1438        | 0.8731  | 1500  | 0.1652          | 0.4817    | 0.4732 | 0.4774 | 0.9522   |
| 0.1089        | 1.1641  | 2000  | 0.1553          | 0.5015    | 0.5252 | 0.5131 | 0.9558   |
| 0.0849        | 1.4552  | 2500  | 0.1575          | 0.5738    | 0.5229 | 0.5471 | 0.9587   |
| 0.0794        | 1.7462  | 3000  | 0.1483          | 0.5344    | 0.5574 | 0.5457 | 0.9588   |
| 0.071         | 2.0373  | 3500  | 0.1583          | 0.5706    | 0.5640 | 0.5673 | 0.9600   |
| 0.0435        | 2.3283  | 4000  | 0.1623          | 0.5559    | 0.5660 | 0.5609 | 0.9588   |
| 0.0471        | 2.6193  | 4500  | 0.1561          | 0.5563    | 0.5905 | 0.5729 | 0.9607   |
| 0.0462        | 2.9104  | 5000  | 0.1557          | 0.5755    | 0.5960 | 0.5856 | 0.9610   |
| 0.028         | 3.2014  | 5500  | 0.1784          | 0.5995    | 0.6136 | 0.6065 | 0.9623   |
| 0.026         | 3.4924  | 6000  | 0.1895          | 0.6169    | 0.5555 | 0.5846 | 0.9620   |
| 0.0257        | 3.7835  | 6500  | 0.1790          | 0.6020    | 0.6068 | 0.6044 | 0.9621   |
| 0.025         | 4.0745  | 7000  | 0.1943          | 0.6036    | 0.6048 | 0.6042 | 0.9625   |
| 0.0138        | 4.3655  | 7500  | 0.2013          | 0.5832    | 0.6203 | 0.6012 | 0.9619   |
| 0.0165        | 4.6566  | 8000  | 0.2146          | 0.6079    | 0.5865 | 0.5970 | 0.9621   |
| 0.0163        | 4.9476  | 8500  | 0.2123          | 0.6071    | 0.5827 | 0.5947 | 0.9615   |
| 0.0099        | 5.2386  | 9000  | 0.2290          | 0.6196    | 0.5957 | 0.6074 | 0.9627   |
| 0.0093        | 5.5297  | 9500  | 0.2274          | 0.6019    | 0.6143 | 0.6081 | 0.9616   |
| 0.0105        | 5.8207  | 10000 | 0.2326          | 0.6102    | 0.5806 | 0.5950 | 0.9618   |
| 0.0096        | 6.1118  | 10500 | 0.2335          | 0.6016    | 0.6198 | 0.6106 | 0.9617   |
| 0.0062        | 6.4028  | 11000 | 0.2542          | 0.6230    | 0.5866 | 0.6043 | 0.9626   |
| 0.0069        | 6.6938  | 11500 | 0.2510          | 0.6216    | 0.6066 | 0.6140 | 0.9627   |
| 0.0079        | 6.9849  | 12000 | 0.2457          | 0.5980    | 0.6067 | 0.6023 | 0.9620   |
| 0.0051        | 7.2759  | 12500 | 0.2603          | 0.6330    | 0.5842 | 0.6076 | 0.9626   |
| 0.0054        | 7.5669  | 13000 | 0.2627          | 0.6237    | 0.6025 | 0.6129 | 0.9625   |
| 0.0053        | 7.8580  | 13500 | 0.2680          | 0.5916    | 0.6227 | 0.6068 | 0.9617   |
| 0.0045        | 8.1490  | 14000 | 0.2709          | 0.6004    | 0.6068 | 0.6036 | 0.9619   |
| 0.0033        | 8.4400  | 14500 | 0.2873          | 0.6024    | 0.5940 | 0.5982 | 0.9616   |
| 0.0043        | 8.7311  | 15000 | 0.2806          | 0.6167    | 0.6032 | 0.6099 | 0.9624   |
| 0.0048        | 9.0221  | 15500 | 0.2733          | 0.6091    | 0.5918 | 0.6003 | 0.9623   |
| 0.0028        | 9.3132  | 16000 | 0.2804          | 0.5862    | 0.6188 | 0.6021 | 0.9618   |
| 0.0029        | 9.6042  | 16500 | 0.2829          | 0.6201    | 0.6019 | 0.6109 | 0.9624   |
| 0.0031        | 9.8952  | 17000 | 0.2828          | 0.6154    | 0.5989 | 0.6070 | 0.9620   |
| 0.0029        | 10.1863 | 17500 | 0.2876          | 0.6075    | 0.6094 | 0.6085 | 0.9625   |
| 0.0026        | 10.4773 | 18000 | 0.3005          | 0.6329    | 0.5859 | 0.6085 | 0.9623   |
| 0.0025        | 10.7683 | 18500 | 0.2942          | 0.6063    | 0.6201 | 0.6131 | 0.9619   |
| 0.0025        | 11.0594 | 19000 | 0.2948          | 0.6115    | 0.6102 | 0.6108 | 0.9622   |
| 0.0017        | 11.3504 | 19500 | 0.2995          | 0.6143    | 0.5965 | 0.6052 | 0.9621   |
| 0.002         | 11.6414 | 20000 | 0.2930          | 0.6022    | 0.6061 | 0.6042 | 0.9616   |
| 0.002         | 11.9325 | 20500 | 0.3087          | 0.6222    | 0.5910 | 0.6062 | 0.9624   |
| 0.0018        | 12.2235 | 21000 | 0.3114          | 0.5903    | 0.6217 | 0.6056 | 0.9617   |
| 0.0014        | 12.5146 | 21500 | 0.3189          | 0.6246    | 0.5741 | 0.5983 | 0.9618   |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.1.1+cu121
- Datasets 2.14.5
- Tokenizers 0.19.1