---
base_model: haryoaw/scenario-TCR-NER_data-univner_half
library_name: transformers
license: mit
metrics:
- precision
- recall
- f1
- accuracy
tags:
- generated_from_trainer
model-index:
- name: scenario-kd-po-ner-full-mdeberta_data-univner_half55
  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-kd-po-ner-full-mdeberta_data-univner_half55

This model is a fine-tuned version of [haryoaw/scenario-TCR-NER_data-univner_half](https://huggingface.co/haryoaw/scenario-TCR-NER_data-univner_half) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 61.3798
- Precision: 0.7820
- Recall: 0.7775
- F1: 0.7798
- Accuracy: 0.9778

## 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: 8
- eval_batch_size: 32
- seed: 55
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 134.7409      | 0.5828 | 500  | 105.3598        | 0.6084    | 0.4377 | 0.5091 | 0.9490   |
| 96.012        | 1.1655 | 1000 | 90.6475         | 0.6858    | 0.7153 | 0.7003 | 0.9708   |
| 85.0907       | 1.7483 | 1500 | 84.2206         | 0.7177    | 0.7448 | 0.7310 | 0.9739   |
| 78.2732       | 2.3310 | 2000 | 79.7850         | 0.7312    | 0.7697 | 0.7500 | 0.9752   |
| 73.6913       | 2.9138 | 2500 | 76.1999         | 0.7601    | 0.7527 | 0.7564 | 0.9760   |
| 69.7676       | 3.4965 | 3000 | 73.2988         | 0.7666    | 0.7575 | 0.7620 | 0.9765   |
| 66.6414       | 4.0793 | 3500 | 70.8495         | 0.7711    | 0.7563 | 0.7636 | 0.9766   |
| 64.0181       | 4.6620 | 4000 | 68.8880         | 0.7808    | 0.7560 | 0.7682 | 0.9770   |
| 61.881        | 5.2448 | 4500 | 67.1248         | 0.7702    | 0.7703 | 0.7703 | 0.9771   |
| 60.1233       | 5.8275 | 5000 | 65.7057         | 0.7849    | 0.7521 | 0.7681 | 0.9766   |
| 58.4747       | 6.4103 | 5500 | 64.4473         | 0.7744    | 0.7736 | 0.7740 | 0.9774   |
| 57.511        | 6.9930 | 6000 | 63.5221         | 0.7731    | 0.7808 | 0.7770 | 0.9776   |
| 56.432        | 7.5758 | 6500 | 62.8477         | 0.7803    | 0.7723 | 0.7763 | 0.9776   |
| 55.7061       | 8.1585 | 7000 | 62.2029         | 0.7715    | 0.7794 | 0.7754 | 0.9776   |
| 55.1513       | 8.7413 | 7500 | 61.7137         | 0.7808    | 0.7797 | 0.7802 | 0.9783   |
| 54.7004       | 9.3240 | 8000 | 61.5394         | 0.7824    | 0.7817 | 0.7820 | 0.9782   |
| 54.5449       | 9.9068 | 8500 | 61.3798         | 0.7820    | 0.7775 | 0.7798 | 0.9778   |


### Framework versions

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