|
--- |
|
base_model: ybelkada/flan-t5-xl-sharded-bf16 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: flan-xl-gen4 |
|
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-gen4 |
|
|
|
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: 0.6847 |
|
- Rouge1: 36.2186 |
|
- Rouge2: 27.5662 |
|
- Rougel: 32.6055 |
|
- Rougelsum: 32.8805 |
|
- Gen Len: 10.85 |
|
|
|
## 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 | 179 | 0.6847 | 36.2186 | 27.5662 | 32.6055 | 32.8805 | 10.85 | |
|
| No log | 2.0 | 358 | 0.6847 | 36.2186 | 27.5662 | 32.6055 | 32.8805 | 10.85 | |
|
| 0.7514 | 3.0 | 537 | 0.6847 | 36.2186 | 27.5662 | 32.6055 | 32.8805 | 10.85 | |
|
| 0.7514 | 4.0 | 716 | 0.6847 | 36.2186 | 27.5662 | 32.6055 | 32.8805 | 10.85 | |
|
| 0.7514 | 5.0 | 895 | 0.6847 | 36.2186 | 27.5662 | 32.6055 | 32.8805 | 10.85 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
