|
--- |
|
license: apache-2.0 |
|
base_model: google/long-t5-tglobal-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: Word-selector |
|
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. --> |
|
|
|
# Word-selector |
|
|
|
This model is a fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.1303 |
|
- Rouge1: 0.3216 |
|
- Rouge2: 0.0621 |
|
- Rougel: 0.2469 |
|
- Rougelsum: 0.2469 |
|
- Gen Len: 48.8488 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 12 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| No log | 1.0 | 400 | 2.2490 | 0.1594 | 0.0161 | 0.1319 | 0.1321 | 69.2094 | |
|
| 2.7083 | 2.0 | 800 | 2.1665 | 0.2025 | 0.0287 | 0.1648 | 0.1647 | 69.5888 | |
|
| 2.369 | 3.0 | 1200 | 2.1296 | 0.2381 | 0.0344 | 0.1878 | 0.1878 | 57.9775 | |
|
| 2.2185 | 4.0 | 1600 | 2.0890 | 0.2525 | 0.0399 | 0.1986 | 0.1984 | 60.2588 | |
|
| 2.1014 | 5.0 | 2000 | 2.0731 | 0.2795 | 0.0484 | 0.2199 | 0.2199 | 49.5737 | |
|
| 2.1014 | 6.0 | 2400 | 2.0601 | 0.2862 | 0.0525 | 0.2249 | 0.2246 | 54.4206 | |
|
| 1.9992 | 7.0 | 2800 | 2.0592 | 0.3004 | 0.0533 | 0.2351 | 0.2351 | 49.9325 | |
|
| 1.9232 | 8.0 | 3200 | 2.0529 | 0.3033 | 0.0558 | 0.2366 | 0.2368 | 49.8744 | |
|
| 1.8534 | 9.0 | 3600 | 2.0600 | 0.3024 | 0.0573 | 0.2366 | 0.2366 | 50.355 | |
|
| 1.795 | 10.0 | 4000 | 2.0715 | 0.3082 | 0.0561 | 0.2392 | 0.2392 | 47.2162 | |
|
| 1.795 | 11.0 | 4400 | 2.0657 | 0.3137 | 0.0595 | 0.2437 | 0.2439 | 50.3438 | |
|
| 1.73 | 12.0 | 4800 | 2.0759 | 0.3142 | 0.0597 | 0.2434 | 0.2433 | 51.1619 | |
|
| 1.6844 | 13.0 | 5200 | 2.0818 | 0.3172 | 0.0605 | 0.2458 | 0.2458 | 48.9956 | |
|
| 1.6398 | 14.0 | 5600 | 2.0942 | 0.3149 | 0.0599 | 0.2428 | 0.243 | 47.3812 | |
|
| 1.6063 | 15.0 | 6000 | 2.1047 | 0.3171 | 0.0609 | 0.243 | 0.243 | 51.685 | |
|
| 1.6063 | 16.0 | 6400 | 2.1095 | 0.3234 | 0.0622 | 0.248 | 0.248 | 50.1588 | |
|
| 1.5659 | 17.0 | 6800 | 2.1180 | 0.3212 | 0.0627 | 0.2479 | 0.2478 | 49.0894 | |
|
| 1.5456 | 18.0 | 7200 | 2.1212 | 0.3208 | 0.0616 | 0.2455 | 0.2456 | 48.8688 | |
|
| 1.5177 | 19.0 | 7600 | 2.1275 | 0.3214 | 0.0628 | 0.2467 | 0.2467 | 48.4125 | |
|
| 1.5161 | 20.0 | 8000 | 2.1303 | 0.3216 | 0.0621 | 0.2469 | 0.2469 | 48.8488 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.1.1+cu121 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.15.1 |
|
|
