|
--- |
|
license: apache-2.0 |
|
base_model: google-t5/t5-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: t5_base_amazon |
|
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. --> |
|
|
|
# t5_base_amazon |
|
|
|
This model is a fine-tuned version of [google-t5/t5-base](https://huggingface.co/google-t5/t5-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5565 |
|
- Accuracy: 0.8399 |
|
- F1 Macro: 0.8113 |
|
- F1 Micro: 0.8399 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- total_train_batch_size: 32 |
|
- total_eval_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
| 1.2275 | 0.13 | 50 | 1.0353 | 0.6950 | 0.6073 | 0.6950 | |
|
| 0.8341 | 0.26 | 100 | 0.8838 | 0.7385 | 0.6814 | 0.7385 | |
|
| 0.7773 | 0.39 | 150 | 0.7473 | 0.7833 | 0.7340 | 0.7833 | |
|
| 0.7188 | 0.53 | 200 | 0.7024 | 0.7925 | 0.7433 | 0.7925 | |
|
| 0.7483 | 0.66 | 250 | 0.7056 | 0.7872 | 0.7396 | 0.7872 | |
|
| 0.6228 | 0.79 | 300 | 0.6338 | 0.8129 | 0.7636 | 0.8129 | |
|
| 0.7089 | 0.92 | 350 | 0.6130 | 0.8208 | 0.7963 | 0.8208 | |
|
| 0.5055 | 1.05 | 400 | 0.5939 | 0.8300 | 0.8075 | 0.8300 | |
|
| 0.3942 | 1.18 | 450 | 0.6021 | 0.8241 | 0.7916 | 0.8241 | |
|
| 0.4248 | 1.32 | 500 | 0.5956 | 0.8300 | 0.8060 | 0.8300 | |
|
| 0.3595 | 1.45 | 550 | 0.6173 | 0.8175 | 0.7897 | 0.8175 | |
|
| 0.5263 | 1.58 | 600 | 0.6170 | 0.8162 | 0.7908 | 0.8162 | |
|
| 0.5153 | 1.71 | 650 | 0.6007 | 0.8327 | 0.8043 | 0.8327 | |
|
| 0.4237 | 1.84 | 700 | 0.5565 | 0.8399 | 0.8113 | 0.8399 | |
|
| 0.3852 | 1.97 | 750 | 0.5631 | 0.8439 | 0.8146 | 0.8439 | |
|
| 0.1916 | 2.11 | 800 | 0.5848 | 0.8439 | 0.8132 | 0.8439 | |
|
| 0.2108 | 2.24 | 850 | 0.6054 | 0.8432 | 0.8094 | 0.8432 | |
|
| 0.1752 | 2.37 | 900 | 0.6142 | 0.8439 | 0.8131 | 0.8439 | |
|
| 0.1502 | 2.5 | 950 | 0.6100 | 0.8452 | 0.8119 | 0.8452 | |
|
| 0.2253 | 2.63 | 1000 | 0.6084 | 0.8439 | 0.8228 | 0.8439 | |
|
| 0.2193 | 2.76 | 1050 | 0.6062 | 0.8485 | 0.8171 | 0.8485 | |
|
| 0.2182 | 2.89 | 1100 | 0.5966 | 0.8498 | 0.8182 | 0.8498 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|