---
base_model: microsoft/mdeberta-v3-base
library_name: transformers
license: mit
metrics:
- precision
- recall
- f1
- accuracy
tags:
- generated_from_trainer
model-index:
- name: scenario-non-kd-pre-ner-full-mdeberta_data-univner_half66
  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-pre-ner-full-mdeberta_data-univner_half66

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: 0.1996
- Precision: 0.7561
- Recall: 0.7723
- F1: 0.7641
- Accuracy: 0.9755

## 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 |
|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.304         | 0.5828  | 500   | 0.1829          | 0.3627    | 0.3414 | 0.3517 | 0.9389   |
| 0.155         | 1.1655  | 1000  | 0.1258          | 0.5315    | 0.6722 | 0.5937 | 0.9577   |
| 0.0973        | 1.7483  | 1500  | 0.1032          | 0.6320    | 0.7086 | 0.6681 | 0.9670   |
| 0.0707        | 2.3310  | 2000  | 0.1055          | 0.6478    | 0.7443 | 0.6927 | 0.9683   |
| 0.0584        | 2.9138  | 2500  | 0.1007          | 0.6755    | 0.7436 | 0.7079 | 0.9698   |
| 0.0431        | 3.4965  | 3000  | 0.1186          | 0.6613    | 0.7552 | 0.7051 | 0.9686   |
| 0.0392        | 4.0793  | 3500  | 0.1087          | 0.6946    | 0.7627 | 0.7270 | 0.9718   |
| 0.0273        | 4.6620  | 4000  | 0.1095          | 0.7451    | 0.7286 | 0.7367 | 0.9736   |
| 0.0233        | 5.2448  | 4500  | 0.1259          | 0.6876    | 0.7772 | 0.7297 | 0.9719   |
| 0.0189        | 5.8275  | 5000  | 0.1201          | 0.7222    | 0.7526 | 0.7371 | 0.9730   |
| 0.0161        | 6.4103  | 5500  | 0.1339          | 0.7334    | 0.7342 | 0.7338 | 0.9734   |
| 0.0153        | 6.9930  | 6000  | 0.1338          | 0.7226    | 0.7533 | 0.7376 | 0.9737   |
| 0.0109        | 7.5758  | 6500  | 0.1320          | 0.7345    | 0.7634 | 0.7486 | 0.9742   |
| 0.0108        | 8.1585  | 7000  | 0.1427          | 0.7189    | 0.7617 | 0.7397 | 0.9728   |
| 0.0089        | 8.7413  | 7500  | 0.1423          | 0.7268    | 0.7647 | 0.7453 | 0.9738   |
| 0.0075        | 9.3240  | 8000  | 0.1471          | 0.7332    | 0.7638 | 0.7482 | 0.9740   |
| 0.0071        | 9.9068  | 8500  | 0.1501          | 0.7502    | 0.7466 | 0.7484 | 0.9744   |
| 0.0064        | 10.4895 | 9000  | 0.1558          | 0.7133    | 0.7813 | 0.7458 | 0.9734   |
| 0.0058        | 11.0723 | 9500  | 0.1495          | 0.7514    | 0.7599 | 0.7556 | 0.9750   |
| 0.0047        | 11.6550 | 10000 | 0.1632          | 0.7146    | 0.7627 | 0.7379 | 0.9727   |
| 0.0043        | 12.2378 | 10500 | 0.1707          | 0.7259    | 0.7699 | 0.7472 | 0.9740   |
| 0.0039        | 12.8205 | 11000 | 0.1648          | 0.7415    | 0.7608 | 0.7510 | 0.9742   |
| 0.0041        | 13.4033 | 11500 | 0.1717          | 0.7247    | 0.7693 | 0.7463 | 0.9739   |
| 0.0036        | 13.9860 | 12000 | 0.1711          | 0.7251    | 0.7687 | 0.7463 | 0.9737   |
| 0.0029        | 14.5688 | 12500 | 0.1757          | 0.7275    | 0.7751 | 0.7505 | 0.9741   |
| 0.0026        | 15.1515 | 13000 | 0.1817          | 0.7527    | 0.7563 | 0.7545 | 0.9744   |
| 0.0027        | 15.7343 | 13500 | 0.1779          | 0.7534    | 0.7554 | 0.7544 | 0.9750   |
| 0.0028        | 16.3170 | 14000 | 0.1826          | 0.7505    | 0.7578 | 0.7541 | 0.9747   |
| 0.0026        | 16.8998 | 14500 | 0.1793          | 0.7573    | 0.7681 | 0.7627 | 0.9755   |
| 0.0022        | 17.4825 | 15000 | 0.1803          | 0.7460    | 0.7722 | 0.7589 | 0.9753   |
| 0.002         | 18.0653 | 15500 | 0.1858          | 0.7331    | 0.7807 | 0.7561 | 0.9746   |
| 0.0018        | 18.6480 | 16000 | 0.1875          | 0.7451    | 0.7624 | 0.7536 | 0.9740   |
| 0.0018        | 19.2308 | 16500 | 0.1896          | 0.7484    | 0.7661 | 0.7572 | 0.9749   |
| 0.0014        | 19.8135 | 17000 | 0.1862          | 0.7592    | 0.7689 | 0.7640 | 0.9755   |
| 0.0018        | 20.3963 | 17500 | 0.1936          | 0.7559    | 0.7567 | 0.7563 | 0.9749   |
| 0.0014        | 20.9790 | 18000 | 0.1908          | 0.7514    | 0.7680 | 0.7596 | 0.9751   |
| 0.0012        | 21.5618 | 18500 | 0.1956          | 0.7464    | 0.7692 | 0.7576 | 0.9751   |
| 0.0015        | 22.1445 | 19000 | 0.1986          | 0.7352    | 0.7751 | 0.7546 | 0.9746   |
| 0.0012        | 22.7273 | 19500 | 0.1936          | 0.7277    | 0.7804 | 0.7531 | 0.9746   |
| 0.001         | 23.3100 | 20000 | 0.1975          | 0.7358    | 0.7781 | 0.7564 | 0.9749   |
| 0.0011        | 23.8928 | 20500 | 0.1956          | 0.7485    | 0.7749 | 0.7615 | 0.9754   |
| 0.001         | 24.4755 | 21000 | 0.1950          | 0.7522    | 0.7728 | 0.7624 | 0.9754   |
| 0.0009        | 25.0583 | 21500 | 0.1958          | 0.7522    | 0.7713 | 0.7616 | 0.9755   |
| 0.0006        | 25.6410 | 22000 | 0.1998          | 0.7454    | 0.7741 | 0.7595 | 0.9751   |
| 0.0006        | 26.2238 | 22500 | 0.2026          | 0.7496    | 0.7725 | 0.7609 | 0.9753   |
| 0.0008        | 26.8065 | 23000 | 0.1991          | 0.7609    | 0.7638 | 0.7623 | 0.9755   |
| 0.0006        | 27.3893 | 23500 | 0.1962          | 0.7547    | 0.7772 | 0.7658 | 0.9758   |
| 0.0006        | 27.9720 | 24000 | 0.1995          | 0.7551    | 0.7728 | 0.7638 | 0.9755   |
| 0.0005        | 28.5548 | 24500 | 0.2003          | 0.7538    | 0.7738 | 0.7636 | 0.9754   |
| 0.0006        | 29.1375 | 25000 | 0.1996          | 0.7574    | 0.7694 | 0.7634 | 0.9755   |
| 0.0005        | 29.7203 | 25500 | 0.1996          | 0.7561    | 0.7723 | 0.7641 | 0.9755   |


### Framework versions

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