|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: ViT-Bert_Mimic |
|
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. --> |
|
|
|
# ViT-Bert_Mimic |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2334 |
|
- Rouge1: 27.4942 |
|
- Rouge2: 21.9051 |
|
- Rougel: 26.9521 |
|
- Rougelsum: 27.0238 |
|
- Gen Len: 16.0 |
|
|
|
## 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: 5e-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 | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| |
|
| No log | 1.0 | 125 | 0.3533 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 | |
|
| No log | 2.0 | 250 | 0.3009 | 7.9737 | 1.5 | 7.7593 | 7.9222 | 16.38 | |
|
| No log | 3.0 | 375 | 0.2334 | 27.4942 | 21.9051 | 26.9521 | 27.0238 | 16.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.1 |
|
- Pytorch 1.13.1+cu117 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.1 |
|
|
