|
--- |
|
license: apache-2.0 |
|
base_model: google-t5/t5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: t5_small_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_small_amazon |
|
|
|
This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7014 |
|
- Accuracy: 0.7767 |
|
- F1 Macro: 0.7273 |
|
- F1 Micro: 0.7767 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
| 2.1202 | 0.13 | 50 | 1.8088 | 0.5329 | 0.3841 | 0.5329 | |
|
| 1.1993 | 0.26 | 100 | 1.1746 | 0.6614 | 0.5439 | 0.6614 | |
|
| 1.0698 | 0.39 | 150 | 1.0116 | 0.6884 | 0.6004 | 0.6884 | |
|
| 0.8999 | 0.53 | 200 | 0.9428 | 0.7174 | 0.6539 | 0.7174 | |
|
| 1.1022 | 0.66 | 250 | 0.8932 | 0.7246 | 0.6716 | 0.7246 | |
|
| 0.8337 | 0.79 | 300 | 0.8664 | 0.7286 | 0.6789 | 0.7286 | |
|
| 0.9594 | 0.92 | 350 | 0.8445 | 0.7503 | 0.6994 | 0.7503 | |
|
| 0.803 | 1.05 | 400 | 0.8048 | 0.7530 | 0.6996 | 0.7530 | |
|
| 0.7271 | 1.18 | 450 | 0.7776 | 0.7602 | 0.7019 | 0.7602 | |
|
| 0.6694 | 1.32 | 500 | 0.7674 | 0.7609 | 0.7084 | 0.7609 | |
|
| 0.6109 | 1.45 | 550 | 0.7648 | 0.7609 | 0.7081 | 0.7609 | |
|
| 0.6575 | 1.58 | 600 | 0.7527 | 0.7628 | 0.7117 | 0.7628 | |
|
| 0.777 | 1.71 | 650 | 0.7419 | 0.7694 | 0.7218 | 0.7694 | |
|
| 0.6362 | 1.84 | 700 | 0.7272 | 0.7800 | 0.7301 | 0.7800 | |
|
| 0.648 | 1.97 | 750 | 0.7137 | 0.7813 | 0.7356 | 0.7813 | |
|
| 0.4981 | 2.11 | 800 | 0.7154 | 0.7767 | 0.7258 | 0.7767 | |
|
| 0.4955 | 2.24 | 850 | 0.7233 | 0.7800 | 0.7318 | 0.7800 | |
|
| 0.4451 | 2.37 | 900 | 0.7182 | 0.7780 | 0.7280 | 0.7780 | |
|
| 0.421 | 2.5 | 950 | 0.7117 | 0.7747 | 0.7262 | 0.7747 | |
|
| 0.4853 | 2.63 | 1000 | 0.7092 | 0.7760 | 0.7272 | 0.7760 | |
|
| 0.5442 | 2.76 | 1050 | 0.7114 | 0.7740 | 0.7272 | 0.7740 | |
|
| 0.4863 | 2.89 | 1100 | 0.7014 | 0.7767 | 0.7273 | 0.7767 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
