|
--- |
|
base_model: ybelkada/flan-t5-xl-sharded-bf16 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: flan-xl-gen5 |
|
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-xl-gen5 |
|
|
|
This model is a fine-tuned version of [ybelkada/flan-t5-xl-sharded-bf16](https://huggingface.co./ybelkada/flan-t5-xl-sharded-bf16) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7669 |
|
- Rouge1: 24.6538 |
|
- Rouge2: 17.821 |
|
- Rougel: 21.5884 |
|
- Rougelsum: 21.9045 |
|
- Gen Len: 13.0515 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| |
|
| No log | 1.0 | 328 | 24.8987 | 29.9366 | 22.9687 | 26.9975 | 27.1774 | 11.1203 | |
|
| 25.467 | 2.0 | 656 | 1.3504 | 51.142 | 49.8705 | 51.1588 | 51.1528 | 0.0 | |
|
| 25.467 | 3.0 | 984 | 0.8221 | 19.5594 | 12.7325 | 16.4586 | 16.7605 | 14.9278 | |
|
| 1.8759 | 4.0 | 1312 | 0.7783 | 21.8348 | 14.9645 | 18.7764 | 19.0709 | 14.1100 | |
|
| 0.8715 | 5.0 | 1640 | 0.7669 | 24.6538 | 17.821 | 21.5884 | 21.9045 | 13.0515 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
