---
base_model: haryoaw/scenario-TCR-NER_data-univner_en
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_en66
  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_en66

This model is a fine-tuned version of [haryoaw/scenario-TCR-NER_data-univner_en](https://huggingface.co/haryoaw/scenario-TCR-NER_data-univner_en) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1455
- Precision: 0.8256
- Recall: 0.8333
- F1: 0.8295
- Accuracy: 0.9850

## 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 |
|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.0025        | 1.2755  | 500   | 0.1138          | 0.8395    | 0.8230 | 0.8312 | 0.9849   |
| 0.002         | 2.5510  | 1000  | 0.1150          | 0.8157    | 0.8292 | 0.8224 | 0.9849   |
| 0.0023        | 3.8265  | 1500  | 0.1137          | 0.8212    | 0.8416 | 0.8313 | 0.9852   |
| 0.0015        | 5.1020  | 2000  | 0.1171          | 0.8197    | 0.8520 | 0.8355 | 0.9851   |
| 0.001         | 6.3776  | 2500  | 0.1206          | 0.7990    | 0.8437 | 0.8207 | 0.9839   |
| 0.0013        | 7.6531  | 3000  | 0.1177          | 0.8233    | 0.8251 | 0.8242 | 0.9849   |
| 0.001         | 8.9286  | 3500  | 0.1177          | 0.8399    | 0.8199 | 0.8298 | 0.9855   |
| 0.0005        | 10.2041 | 4000  | 0.1209          | 0.8253    | 0.8313 | 0.8283 | 0.9851   |
| 0.0007        | 11.4796 | 4500  | 0.1285          | 0.8175    | 0.8116 | 0.8145 | 0.9843   |
| 0.0003        | 12.7551 | 5000  | 0.1335          | 0.8445    | 0.8095 | 0.8266 | 0.9850   |
| 0.0006        | 14.0306 | 5500  | 0.1371          | 0.7810    | 0.8344 | 0.8068 | 0.9829   |
| 0.0008        | 15.3061 | 6000  | 0.1322          | 0.8173    | 0.8427 | 0.8298 | 0.9844   |
| 0.0005        | 16.5816 | 6500  | 0.1271          | 0.8203    | 0.8364 | 0.8283 | 0.9850   |
| 0.0007        | 17.8571 | 7000  | 0.1200          | 0.8153    | 0.8499 | 0.8322 | 0.9854   |
| 0.0002        | 19.1327 | 7500  | 0.1321          | 0.8193    | 0.8354 | 0.8273 | 0.9846   |
| 0.0003        | 20.4082 | 8000  | 0.1355          | 0.8050    | 0.8375 | 0.8209 | 0.9846   |
| 0.0002        | 21.6837 | 8500  | 0.1413          | 0.808     | 0.8364 | 0.8220 | 0.9841   |
| 0.0003        | 22.9592 | 9000  | 0.1327          | 0.8321    | 0.8416 | 0.8369 | 0.9855   |
| 0.0001        | 24.2347 | 9500  | 0.1412          | 0.8276    | 0.8251 | 0.8263 | 0.9847   |
| 0.0001        | 25.5102 | 10000 | 0.1427          | 0.8199    | 0.8344 | 0.8271 | 0.9849   |
| 0.0001        | 26.7857 | 10500 | 0.1429          | 0.8304    | 0.8261 | 0.8282 | 0.9852   |
| 0.0001        | 28.0612 | 11000 | 0.1446          | 0.8250    | 0.8344 | 0.8296 | 0.9852   |
| 0.0001        | 29.3367 | 11500 | 0.1455          | 0.8256    | 0.8333 | 0.8295 | 0.9850   |


### Framework versions

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