---
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_full44
  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_full44

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: 0.3159
- Precision: 0.6317
- Recall: 0.6096
- F1: 0.6205
- Accuracy: 0.9636

## 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: 44
- 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 |
|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.3088        | 0.2910  | 500   | 0.2391          | 0.3299    | 0.2154 | 0.2606 | 0.9344   |
| 0.1992        | 0.5821  | 1000  | 0.1901          | 0.3635    | 0.3792 | 0.3712 | 0.9430   |
| 0.1511        | 0.8731  | 1500  | 0.1697          | 0.4865    | 0.4499 | 0.4675 | 0.9520   |
| 0.1103        | 1.1641  | 2000  | 0.1592          | 0.5109    | 0.5203 | 0.5155 | 0.9553   |
| 0.09          | 1.4552  | 2500  | 0.1498          | 0.5337    | 0.5649 | 0.5488 | 0.9578   |
| 0.0852        | 1.7462  | 3000  | 0.1489          | 0.5792    | 0.5224 | 0.5493 | 0.9592   |
| 0.0739        | 2.0373  | 3500  | 0.1468          | 0.5588    | 0.6070 | 0.5819 | 0.9606   |
| 0.0469        | 2.3283  | 4000  | 0.1673          | 0.5990    | 0.5625 | 0.5802 | 0.9612   |
| 0.0479        | 2.6193  | 4500  | 0.1578          | 0.5783    | 0.6139 | 0.5956 | 0.9612   |
| 0.0472        | 2.9104  | 5000  | 0.1568          | 0.6109    | 0.5914 | 0.6010 | 0.9627   |
| 0.0318        | 3.2014  | 5500  | 0.1806          | 0.6092    | 0.5807 | 0.5946 | 0.9622   |
| 0.0271        | 3.4924  | 6000  | 0.1910          | 0.5860    | 0.5659 | 0.5757 | 0.9605   |
| 0.0289        | 3.7835  | 6500  | 0.1811          | 0.5978    | 0.5990 | 0.5984 | 0.9626   |
| 0.0246        | 4.0745  | 7000  | 0.1958          | 0.6135    | 0.6027 | 0.6080 | 0.9630   |
| 0.0165        | 4.3655  | 7500  | 0.2066          | 0.6118    | 0.5927 | 0.6021 | 0.9621   |
| 0.0177        | 4.6566  | 8000  | 0.2033          | 0.5884    | 0.6018 | 0.5950 | 0.9608   |
| 0.0178        | 4.9476  | 8500  | 0.2051          | 0.5985    | 0.5956 | 0.5970 | 0.9620   |
| 0.0117        | 5.2386  | 9000  | 0.2181          | 0.5962    | 0.6174 | 0.6066 | 0.9619   |
| 0.0107        | 5.5297  | 9500  | 0.2247          | 0.5859    | 0.6119 | 0.5986 | 0.9610   |
| 0.013         | 5.8207  | 10000 | 0.2253          | 0.6049    | 0.5825 | 0.5935 | 0.9618   |
| 0.0106        | 6.1118  | 10500 | 0.2280          | 0.6130    | 0.6068 | 0.6099 | 0.9625   |
| 0.0071        | 6.4028  | 11000 | 0.2321          | 0.6006    | 0.6292 | 0.6146 | 0.9623   |
| 0.0077        | 6.6938  | 11500 | 0.2497          | 0.5847    | 0.6024 | 0.5934 | 0.9612   |
| 0.0085        | 6.9849  | 12000 | 0.2421          | 0.5838    | 0.6058 | 0.5946 | 0.9611   |
| 0.0053        | 7.2759  | 12500 | 0.2562          | 0.6189    | 0.5917 | 0.6050 | 0.9627   |
| 0.0057        | 7.5669  | 13000 | 0.2602          | 0.5918    | 0.6138 | 0.6026 | 0.9613   |
| 0.0065        | 7.8580  | 13500 | 0.2531          | 0.6077    | 0.6148 | 0.6112 | 0.9625   |
| 0.0048        | 8.1490  | 14000 | 0.2634          | 0.6182    | 0.6141 | 0.6161 | 0.9628   |
| 0.004         | 8.4400  | 14500 | 0.2736          | 0.6197    | 0.5969 | 0.6081 | 0.9622   |
| 0.0053        | 8.7311  | 15000 | 0.2579          | 0.6194    | 0.6119 | 0.6156 | 0.9633   |
| 0.0042        | 9.0221  | 15500 | 0.2770          | 0.6223    | 0.6211 | 0.6217 | 0.9633   |
| 0.003         | 9.3132  | 16000 | 0.2835          | 0.6010    | 0.6081 | 0.6046 | 0.9622   |
| 0.0031        | 9.6042  | 16500 | 0.2839          | 0.6408    | 0.5954 | 0.6173 | 0.9632   |
| 0.0035        | 9.8952  | 17000 | 0.2876          | 0.6209    | 0.5996 | 0.6101 | 0.9623   |
| 0.0034        | 10.1863 | 17500 | 0.2839          | 0.6215    | 0.6044 | 0.6128 | 0.9628   |
| 0.0026        | 10.4773 | 18000 | 0.2851          | 0.6053    | 0.6187 | 0.6119 | 0.9626   |
| 0.0032        | 10.7683 | 18500 | 0.2799          | 0.6120    | 0.6068 | 0.6094 | 0.9620   |
| 0.003         | 11.0594 | 19000 | 0.2912          | 0.6110    | 0.6306 | 0.6207 | 0.9629   |
| 0.0019        | 11.3504 | 19500 | 0.2963          | 0.6188    | 0.6201 | 0.6194 | 0.9629   |
| 0.0025        | 11.6414 | 20000 | 0.2876          | 0.6101    | 0.6240 | 0.6170 | 0.9628   |
| 0.0023        | 11.9325 | 20500 | 0.2940          | 0.6392    | 0.6001 | 0.6190 | 0.9631   |
| 0.0017        | 12.2235 | 21000 | 0.3056          | 0.6017    | 0.6177 | 0.6096 | 0.9625   |
| 0.0013        | 12.5146 | 21500 | 0.3127          | 0.6128    | 0.6018 | 0.6072 | 0.9628   |
| 0.002         | 12.8056 | 22000 | 0.3052          | 0.6160    | 0.6151 | 0.6156 | 0.9630   |
| 0.0018        | 13.0966 | 22500 | 0.3115          | 0.6279    | 0.5999 | 0.6136 | 0.9629   |
| 0.0015        | 13.3877 | 23000 | 0.3121          | 0.6125    | 0.6155 | 0.6140 | 0.9628   |
| 0.0013        | 13.6787 | 23500 | 0.3203          | 0.6193    | 0.6185 | 0.6189 | 0.9629   |
| 0.0015        | 13.9697 | 24000 | 0.3290          | 0.6329    | 0.6028 | 0.6175 | 0.9629   |
| 0.0012        | 14.2608 | 24500 | 0.3267          | 0.6123    | 0.6194 | 0.6158 | 0.9625   |
| 0.0011        | 14.5518 | 25000 | 0.3191          | 0.6213    | 0.6165 | 0.6189 | 0.9633   |
| 0.0011        | 14.8428 | 25500 | 0.3159          | 0.6317    | 0.6096 | 0.6205 | 0.9636   |


### Framework versions

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