|
--- |
|
license: apache-2.0 |
|
base_model: t5-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: amtibot_t5 |
|
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. --> |
|
|
|
# amtibot_t5 |
|
|
|
This model is a fine-tuned version of [t5-base](https://huggingface.co./t5-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.3926 |
|
- Rouge1: 0.3075 |
|
- Rouge2: 0.1254 |
|
- Rougel: 0.2587 |
|
- Rougelsum: 0.2591 |
|
- 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| No log | 0.92 | 9 | 2.9455 | 0.3081 | 0.128 | 0.265 | 0.2643 | 19.0 | |
|
| No log | 1.95 | 19 | 2.5732 | 0.3069 | 0.1305 | 0.2575 | 0.257 | 19.0 | |
|
| No log | 2.97 | 29 | 2.4209 | 0.3039 | 0.1243 | 0.2548 | 0.2559 | 19.0 | |
|
| No log | 3.69 | 36 | 2.3926 | 0.3075 | 0.1254 | 0.2587 | 0.2591 | 19.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
