|
--- |
|
license: apache-2.0 |
|
base_model: google/long-t5-tglobal-xl |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- learn3r/gov_report_memsum_oracle |
|
model-index: |
|
- name: longt5_xl_govreport_4096_memsum_e10 |
|
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. --> |
|
|
|
# longt5_xl_govreport_4096_memsum_e10 |
|
|
|
This model is a fine-tuned version of [google/long-t5-tglobal-xl](https://huggingface.co/google/long-t5-tglobal-xl) on the learn3r/gov_report_memsum_oracle dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.2380 |
|
|
|
## 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: 0.001 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 32 |
|
- total_train_batch_size: 256 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant |
|
- num_epochs: 10.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.4775 | 1.0 | 68 | 1.2713 | |
|
| 1.3081 | 1.99 | 136 | 1.2380 | |
|
| 1.1811 | 2.99 | 204 | 1.2456 | |
|
| 1.0752 | 3.99 | 272 | 1.2426 | |
|
| 0.9663 | 5.0 | 341 | 1.2901 | |
|
| 0.8607 | 6.0 | 409 | 1.3396 | |
|
| 0.7462 | 6.99 | 477 | 1.3747 | |
|
| 0.7084 | 7.99 | 545 | 1.4659 | |
|
| 0.6155 | 8.99 | 613 | 1.5037 | |
|
| 0.5435 | 9.97 | 680 | 1.5582 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.0.dev0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
