|
--- |
|
tags: |
|
- generated_from_trainer |
|
- summarization |
|
- finance |
|
model-index: |
|
- name: T5-Large-10K-Summarization |
|
results: [] |
|
--- |
|
|
|
# T5-Large-10K-Summarization |
|
|
|
This model is a fine-tuned version of Google's T5-Large model, designed to summarize sections of financial 10K reports efficiently. |
|
|
|
## Model description |
|
|
|
T5-Large-10K-Summarization excels in distilling complex financial information into clear, concise summaries, aiding in faster decision-making processes. |
|
|
|
## Intended uses & limitations |
|
|
|
This model is specifically designed for financial professionals needing quick summaries of extensive financial reports. It is not intended for use with general news articles or non-financial documents. |
|
|
|
## Training and evaluation data |
|
|
|
The model was trained on a large corpus of financial reports, each section manually summarized to train the model effectively. |
|
|
|
## 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: 3.0 |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.0 |
|
- Pytorch 2.2.1+cu121 |
|
- Tokenizers 0.19.1 |
|
|
