|
--- |
|
license: apache-2.0 |
|
base_model: google/t5-v1_1-small |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: T5_1_mrqa_v1 |
|
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. --> |
|
|
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/favcowboy/huggingface/runs/j31c1si7) |
|
# T5_1_mrqa_v1 |
|
|
|
This model is a fine-tuned version of [google/t5-v1_1-small](https://huggingface.co/google/t5-v1_1-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.7981 |
|
|
|
## 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 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 9 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 10.3869 | 1.0 | 500 | 4.9828 | |
|
| 6.7903 | 2.0 | 1000 | 3.4878 | |
|
| 5.8096 | 3.0 | 1500 | 3.1873 | |
|
| 5.2496 | 4.0 | 2000 | 3.0379 | |
|
| 4.9384 | 5.0 | 2500 | 2.9406 | |
|
| 4.6901 | 6.0 | 3000 | 2.8722 | |
|
| 4.5321 | 7.0 | 3500 | 2.8254 | |
|
| 4.4324 | 8.0 | 4000 | 2.8045 | |
|
| 4.3835 | 9.0 | 4500 | 2.7981 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.0.dev0 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
