|
--- |
|
license: apache-2.0 |
|
base_model: google/flan-t5-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: flan-t5-base-finetuned-FOMC |
|
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. --> |
|
|
|
# flan-t5-base-finetuned-FOMC |
|
|
|
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.2531 |
|
- Rouge1: 33.7697 |
|
- Rouge2: 20.9968 |
|
- Rougel: 30.2984 |
|
- Rougelsum: 30.5446 |
|
- Gen Len: 19.0 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| |
|
| No log | 1.0 | 10 | 2.6231 | 31.9634 | 19.4463 | 28.9802 | 29.3026 | 19.0 | |
|
| No log | 2.0 | 20 | 2.5645 | 31.6125 | 19.0593 | 28.572 | 28.9666 | 19.0 | |
|
| No log | 3.0 | 30 | 2.5120 | 31.9437 | 19.4395 | 28.9629 | 29.2817 | 19.0 | |
|
| No log | 4.0 | 40 | 2.4752 | 30.874 | 18.8778 | 27.8613 | 28.3752 | 19.0 | |
|
| No log | 5.0 | 50 | 2.4449 | 30.4001 | 18.425 | 27.2624 | 27.939 | 19.0 | |
|
| No log | 6.0 | 60 | 2.4177 | 31.0542 | 19.1125 | 27.9874 | 28.6255 | 19.0 | |
|
| No log | 7.0 | 70 | 2.3935 | 31.0542 | 19.1125 | 27.9874 | 28.6255 | 19.0 | |
|
| No log | 8.0 | 80 | 2.3778 | 31.0542 | 19.1125 | 27.9874 | 28.6255 | 19.0 | |
|
| No log | 9.0 | 90 | 2.3565 | 31.0542 | 19.1125 | 27.9874 | 28.6255 | 19.0 | |
|
| No log | 10.0 | 100 | 2.3415 | 31.0542 | 19.1125 | 27.9874 | 28.6255 | 19.0 | |
|
| No log | 11.0 | 110 | 2.3296 | 32.2319 | 19.728 | 29.1471 | 29.4452 | 19.0 | |
|
| No log | 12.0 | 120 | 2.3206 | 32.5462 | 19.9463 | 29.5345 | 29.6243 | 19.0 | |
|
| No log | 13.0 | 130 | 2.3123 | 32.5462 | 19.9463 | 29.5345 | 29.6243 | 19.0 | |
|
| No log | 14.0 | 140 | 2.3034 | 32.5462 | 19.9463 | 29.5345 | 29.3859 | 19.0 | |
|
| No log | 15.0 | 150 | 2.2966 | 32.5462 | 19.9463 | 29.5345 | 29.3859 | 19.0 | |
|
| No log | 16.0 | 160 | 2.2882 | 32.5462 | 19.9463 | 29.5345 | 29.3859 | 19.0 | |
|
| No log | 17.0 | 170 | 2.2813 | 32.5462 | 19.9463 | 29.5345 | 29.3859 | 19.0 | |
|
| No log | 18.0 | 180 | 2.2772 | 33.7697 | 20.9968 | 30.2984 | 30.5446 | 19.0 | |
|
| No log | 19.0 | 190 | 2.2728 | 33.7697 | 20.9968 | 30.2984 | 30.5446 | 19.0 | |
|
| No log | 20.0 | 200 | 2.2683 | 33.7697 | 20.9968 | 30.2984 | 30.5446 | 19.0 | |
|
| No log | 21.0 | 210 | 2.2643 | 33.7697 | 20.9968 | 30.2984 | 30.5446 | 19.0 | |
|
| No log | 22.0 | 220 | 2.2627 | 33.7697 | 20.9968 | 30.2984 | 30.5446 | 19.0 | |
|
| No log | 23.0 | 230 | 2.2615 | 33.7697 | 20.9968 | 30.2984 | 30.5446 | 19.0 | |
|
| No log | 24.0 | 240 | 2.2586 | 33.7697 | 20.9968 | 30.2984 | 30.5446 | 19.0 | |
|
| No log | 25.0 | 250 | 2.2573 | 33.7697 | 20.9968 | 30.2984 | 30.5446 | 19.0 | |
|
| No log | 26.0 | 260 | 2.2560 | 33.7697 | 20.9968 | 30.2984 | 30.5446 | 19.0 | |
|
| No log | 27.0 | 270 | 2.2552 | 33.7697 | 20.9968 | 30.2984 | 30.5446 | 19.0 | |
|
| No log | 28.0 | 280 | 2.2542 | 33.7697 | 20.9968 | 30.2984 | 30.5446 | 19.0 | |
|
| No log | 29.0 | 290 | 2.2533 | 33.7697 | 20.9968 | 30.2984 | 30.5446 | 19.0 | |
|
| No log | 30.0 | 300 | 2.2531 | 33.7697 | 20.9968 | 30.2984 | 30.5446 | 19.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.1 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
