|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: t5-small-mse-summarization |
|
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. --> |
|
|
|
# t5-small-mse-summarization |
|
|
|
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.2293 |
|
- Rouge1: 40.0683 |
|
- Rouge2: 20.2468 |
|
- Rougel: 34.0606 |
|
- Rougelsum: 38.0836 |
|
- Bleurt: -0.8806 |
|
- Gen Len: 18.649 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 256 |
|
- 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 | Bleurt | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|:-------:| |
|
| 1.768 | 1.0 | 267 | 1.4680 | 36.028 | 16.6997 | 30.4417 | 33.8528 | -0.9554 | 18.557 | |
|
| 1.5588 | 2.0 | 534 | 1.3877 | 37.4937 | 18.2652 | 32.1414 | 35.621 | -0.9248 | 18.646 | |
|
| 1.503 | 3.0 | 801 | 1.3469 | 38.1407 | 18.7353 | 32.5747 | 36.3185 | -0.9069 | 18.649 | |
|
| 1.4721 | 4.0 | 1068 | 1.3226 | 38.1918 | 18.5221 | 32.4574 | 36.3975 | -0.9071 | 18.661 | |
|
| 1.4402 | 5.0 | 1335 | 1.3061 | 38.672 | 18.8355 | 32.734 | 36.7534 | -0.9074 | 18.696 | |
|
| 1.4141 | 6.0 | 1602 | 1.2909 | 38.9248 | 19.0159 | 33.0053 | 36.98 | -0.9066 | 18.677 | |
|
| 1.4034 | 7.0 | 1869 | 1.2779 | 39.3301 | 19.2995 | 33.2336 | 37.3958 | -0.9047 | 18.68 | |
|
| 1.3864 | 8.0 | 2136 | 1.2686 | 39.5046 | 19.5836 | 33.4436 | 37.46 | -0.8928 | 18.681 | |
|
| 1.3801 | 9.0 | 2403 | 1.2599 | 39.6226 | 19.6625 | 33.6596 | 37.6379 | -0.8954 | 18.686 | |
|
| 1.3714 | 10.0 | 2670 | 1.2555 | 39.4381 | 19.5523 | 33.4644 | 37.4258 | -0.8983 | 18.721 | |
|
| 1.3586 | 11.0 | 2937 | 1.2493 | 39.6582 | 19.7031 | 33.5629 | 37.5895 | -0.8951 | 18.707 | |
|
| 1.3482 | 12.0 | 3204 | 1.2436 | 39.6473 | 19.6636 | 33.631 | 37.643 | -0.8945 | 18.7 | |
|
| 1.3448 | 13.0 | 3471 | 1.2407 | 39.6741 | 19.686 | 33.6859 | 37.6884 | -0.8922 | 18.661 | |
|
| 1.3458 | 14.0 | 3738 | 1.2382 | 39.7934 | 19.879 | 33.8368 | 37.8078 | -0.8863 | 18.658 | |
|
| 1.3315 | 15.0 | 4005 | 1.2343 | 39.812 | 19.935 | 33.8546 | 37.8262 | -0.8859 | 18.666 | |
|
| 1.3374 | 16.0 | 4272 | 1.2335 | 39.7989 | 19.9576 | 33.8681 | 37.803 | -0.885 | 18.657 | |
|
| 1.3301 | 17.0 | 4539 | 1.2315 | 39.9386 | 20.0602 | 33.941 | 37.9452 | -0.8853 | 18.656 | |
|
| 1.3295 | 18.0 | 4806 | 1.2303 | 40.0492 | 20.1841 | 34.0707 | 38.0749 | -0.8823 | 18.651 | |
|
| 1.3284 | 19.0 | 5073 | 1.2294 | 40.0335 | 20.2042 | 34.061 | 38.0575 | -0.881 | 18.649 | |
|
| 1.3249 | 20.0 | 5340 | 1.2293 | 40.0683 | 20.2468 | 34.0606 | 38.0836 | -0.8806 | 18.649 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.21.2 |
|
- Pytorch 1.12.1+cu113 |
|
- Datasets 2.4.0 |
|
- Tokenizers 0.12.1 |
|
|
