|
--- |
|
license: apache-2.0 |
|
base_model: google-t5/t5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: meeting_summarizer_model |
|
results: [] |
|
datasets: |
|
- huuuyeah/meetingbank |
|
language: |
|
- en |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# meeting_summarizer_model |
|
|
|
This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on the dataset "huuuyeah/meetingbank". |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.3916 |
|
- Rouge1: 0.3517 |
|
- Rouge2: 0.2684 |
|
- Rougel: 0.3353 |
|
- Rougelsum: 0.3363 |
|
- Gen Len: 18.7564 |
|
|
|
## 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: linear |
|
- num_epochs: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| No log | 1.0 | 324 | 2.9030 | 0.2906 | 0.1982 | 0.2662 | 0.2663 | 18.9687 | |
|
| 5.7333 | 2.0 | 648 | 2.5094 | 0.3313 | 0.2456 | 0.3132 | 0.3138 | 18.7506 | |
|
| 5.7333 | 3.0 | 972 | 2.4188 | 0.3514 | 0.2673 | 0.3345 | 0.335 | 18.7749 | |
|
| 3.9805 | 4.0 | 1296 | 2.3916 | 0.3517 | 0.2684 | 0.3353 | 0.3363 | 18.7564 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.2.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
