README.md
| 1 | --- |
| 2 | tags: |
| 3 | - generated_from_trainer |
| 4 | - summarization |
| 5 | - finance |
| 6 | model-index: |
| 7 | - name: T5-Base-10K-Summarization |
| 8 | results: [] |
| 9 | --- |
| 10 | |
| 11 | # T5-Base-10K-Summarization |
| 12 | |
| 13 | This model is a fine-tuned version of Google's T5-Base model tailored for summarizing financial 10K report sections. |
| 14 | |
| 15 | ## Model description |
| 16 | |
| 17 | T5-Base-10K-Summarization is optimized to condense lengthy 10K reports into manageable summaries, enabling quick insights into financial data and trends. |
| 18 | |
| 19 | ## Intended uses & limitations |
| 20 | |
| 21 | Ideal for use by financial analysts and regulatory agencies needing rapid insights from 10K reports. It may not be suited for summarizing non-financial documents or informal texts. |
| 22 | |
| 23 | ## Training and evaluation data |
| 24 | |
| 25 | Trained on a diverse collection of 10K reports from various industries, annotated for summarization to ensure broad applicability and accuracy. |
| 26 | |
| 27 | ## Training procedure |
| 28 | |
| 29 | ### Training hyperparameters |
| 30 | |
| 31 | The following hyperparameters were used during training: |
| 32 | - learning_rate: 5e-05 |
| 33 | - train_batch_size: 8 |
| 34 | - eval_batch_size: 8 |
| 35 | - seed: 42 |
| 36 | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| 37 | - lr_scheduler_type: linear |
| 38 | - num_epochs: 3.0 |
| 39 | |
| 40 | ### Framework versions |
| 41 | |
| 42 | - Transformers 4.40.0 |
| 43 | - Pytorch 2.2.1+cu121 |
| 44 | - Tokenizers 0.19.1 |
| 45 | |