|
--- |
|
license: apache-2.0 |
|
base_model: google/flan-t5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: maximo-t5-chat |
|
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. --> |
|
|
|
# maximo-t5-chat |
|
|
|
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.1443 |
|
- Rouge1: 27.8954 |
|
- Rouge2: 7.9325 |
|
- Rougel: 27.8954 |
|
- Rougelsum: 27.0723 |
|
- Gen Len: 12.5 |
|
|
|
## 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: 0.0005 |
|
- 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 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| |
|
| No log | 1.0 | 3 | 2.8565 | 15.4762 | 2.439 | 15.0794 | 15.4762 | 16.1667 | |
|
| No log | 2.0 | 6 | 2.5544 | 13.0291 | 2.439 | 12.6323 | 13.0291 | 16.1667 | |
|
| No log | 3.0 | 9 | 2.4527 | 14.6825 | 2.439 | 14.2857 | 14.2857 | 10.8333 | |
|
| No log | 4.0 | 12 | 2.3570 | 20.2381 | 2.439 | 19.8413 | 19.8413 | 11.1667 | |
|
| No log | 5.0 | 15 | 2.2745 | 27.1017 | 7.9325 | 27.1017 | 26.2787 | 11.3333 | |
|
| No log | 6.0 | 18 | 2.2170 | 27.8954 | 7.9325 | 27.8954 | 27.0723 | 13.1667 | |
|
| No log | 7.0 | 21 | 2.1860 | 27.8954 | 7.9325 | 27.8954 | 27.0723 | 12.6667 | |
|
| No log | 8.0 | 24 | 2.1568 | 27.8954 | 7.9325 | 27.8954 | 27.0723 | 12.5 | |
|
| No log | 9.0 | 27 | 2.1445 | 27.8954 | 7.9325 | 27.8954 | 27.0723 | 12.5 | |
|
| No log | 10.0 | 30 | 2.1443 | 27.8954 | 7.9325 | 27.8954 | 27.0723 | 12.5 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
