---
base_model: jjzha/jobbert_knowledge_extraction
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: tok_train_info
  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. -->

# tok_train_info

This model is a fine-tuned version of [jjzha/jobbert_knowledge_extraction](https://huggingface.co/jjzha/jobbert_knowledge_extraction) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2616
- Precision: 0.5755
- Recall: 0.5980
- F1: 0.5865
- Accuracy: 0.9072

## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log        | 1.0   | 20   | 0.4390          | 0.3790    | 0.4608 | 0.4159 | 0.8845   |
| No log        | 2.0   | 40   | 0.2831          | 0.5321    | 0.5686 | 0.5498 | 0.9034   |
| No log        | 3.0   | 60   | 0.2616          | 0.5755    | 0.5980 | 0.5865 | 0.9072   |


### Framework versions

- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3