---
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: RoBERTa-large-PM-M3-Voc-hf-finetuned-ner
  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. -->

# RoBERTa-large-PM-M3-Voc-hf-finetuned-ner

This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2997
- Precision: 0.7370
- Recall: 0.8282
- F1: 0.7800
- Accuracy: 0.9266

## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 20

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log        | 1.0   | 23   | 1.2765          | 1.0       | 0.0021 | 0.0041 | 0.7090   |
| No log        | 2.0   | 46   | 0.8236          | 0.4543    | 0.3562 | 0.3993 | 0.7750   |
| No log        | 3.0   | 69   | 0.6200          | 0.5096    | 0.5362 | 0.5226 | 0.8046   |
| No log        | 4.0   | 92   | 0.5748          | 0.5196    | 0.6359 | 0.5719 | 0.8128   |
| No log        | 5.0   | 115  | 0.5690          | 0.5048    | 0.6983 | 0.5860 | 0.8151   |
| No log        | 6.0   | 138  | 0.4617          | 0.5851    | 0.6997 | 0.6373 | 0.8557   |
| No log        | 7.0   | 161  | 0.4558          | 0.5852    | 0.7367 | 0.6523 | 0.8585   |
| No log        | 8.0   | 184  | 0.3995          | 0.6241    | 0.7535 | 0.6827 | 0.8832   |
| No log        | 9.0   | 207  | 0.3679          | 0.6446    | 0.7549 | 0.6954 | 0.8926   |
| No log        | 10.0  | 230  | 0.3332          | 0.6867    | 0.7724 | 0.7270 | 0.9059   |
| No log        | 11.0  | 253  | 0.3346          | 0.6805    | 0.7902 | 0.7313 | 0.9068   |
| No log        | 12.0  | 276  | 0.3303          | 0.6900    | 0.8012 | 0.7414 | 0.9100   |
| No log        | 13.0  | 299  | 0.3104          | 0.7041    | 0.8029 | 0.7503 | 0.9171   |
| No log        | 14.0  | 322  | 0.3194          | 0.7037    | 0.8149 | 0.7552 | 0.9158   |
| No log        | 15.0  | 345  | 0.2978          | 0.7342    | 0.8125 | 0.7714 | 0.9255   |
| No log        | 16.0  | 368  | 0.2993          | 0.7347    | 0.8221 | 0.7759 | 0.9266   |
| No log        | 17.0  | 391  | 0.3009          | 0.7346    | 0.8255 | 0.7774 | 0.9258   |
| No log        | 18.0  | 414  | 0.3006          | 0.7341    | 0.8255 | 0.7772 | 0.9259   |
| No log        | 19.0  | 437  | 0.2988          | 0.7379    | 0.8272 | 0.7800 | 0.9267   |
| No log        | 20.0  | 460  | 0.2997          | 0.7370    | 0.8282 | 0.7800 | 0.9266   |


### Framework versions

- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3