|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: roberta-large-finetuned-chunking |
|
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-finetuned-chunking |
|
|
|
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.4192 |
|
- Precision: 0.3222 |
|
- Recall: 0.3161 |
|
- F1: 0.3191 |
|
- Accuracy: 0.8632 |
|
|
|
## 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: 6 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.0373 | 1.0 | 2498 | 0.9545 | 0.3166 | 0.2545 | 0.2822 | 0.8656 | |
|
| 0.0045 | 2.0 | 4996 | 1.1324 | 0.2667 | 0.3142 | 0.2885 | 0.8525 | |
|
| 0.0022 | 3.0 | 7494 | 1.3138 | 0.3349 | 0.3097 | 0.3218 | 0.8672 | |
|
| 0.0015 | 4.0 | 9992 | 1.3454 | 0.3261 | 0.3260 | 0.3260 | 0.8647 | |
|
| 0.0014 | 5.0 | 12490 | 1.3640 | 0.3064 | 0.3126 | 0.3095 | 0.8603 | |
|
| 0.0008 | 6.0 | 14988 | 1.4192 | 0.3222 | 0.3161 | 0.3191 | 0.8632 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.20.0 |
|
- Pytorch 1.11.0 |
|
- Datasets 2.3.2 |
|
- Tokenizers 0.12.1 |
|
|
