|
--- |
|
license: apache-2.0 |
|
base_model: google/flan-t5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: flan_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. --> |
|
|
|
# flan_t5_small_amazon |
|
|
|
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6518 |
|
- Accuracy: 0.8096 |
|
- F1 Macro: 0.7882 |
|
- F1 Micro: 0.8096 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
| 1.9282 | 0.13 | 50 | 1.5904 | 0.5738 | 0.4436 | 0.5738 | |
|
| 1.1323 | 0.26 | 100 | 1.1076 | 0.6634 | 0.5641 | 0.6634 | |
|
| 0.9976 | 0.39 | 150 | 0.9465 | 0.7207 | 0.6468 | 0.7207 | |
|
| 0.928 | 0.53 | 200 | 0.8840 | 0.7332 | 0.6860 | 0.7332 | |
|
| 0.974 | 0.66 | 250 | 0.8179 | 0.7523 | 0.7026 | 0.7523 | |
|
| 0.8206 | 0.79 | 300 | 0.7982 | 0.7675 | 0.7182 | 0.7675 | |
|
| 0.8863 | 0.92 | 350 | 0.7445 | 0.7773 | 0.7301 | 0.7773 | |
|
| 0.713 | 1.05 | 400 | 0.7428 | 0.7740 | 0.7391 | 0.7740 | |
|
| 0.6544 | 1.18 | 450 | 0.7234 | 0.7852 | 0.7379 | 0.7852 | |
|
| 0.6034 | 1.32 | 500 | 0.7140 | 0.7925 | 0.7648 | 0.7925 | |
|
| 0.588 | 1.45 | 550 | 0.7062 | 0.7931 | 0.7585 | 0.7931 | |
|
| 0.6035 | 1.58 | 600 | 0.7112 | 0.7925 | 0.7480 | 0.7925 | |
|
| 0.6616 | 1.71 | 650 | 0.6783 | 0.7938 | 0.7578 | 0.7938 | |
|
| 0.6334 | 1.84 | 700 | 0.6816 | 0.8004 | 0.7851 | 0.8004 | |
|
| 0.5872 | 1.97 | 750 | 0.6532 | 0.8037 | 0.7792 | 0.8037 | |
|
| 0.4134 | 2.11 | 800 | 0.6601 | 0.8070 | 0.7858 | 0.8070 | |
|
| 0.518 | 2.24 | 850 | 0.6772 | 0.8070 | 0.7858 | 0.8070 | |
|
| 0.3891 | 2.37 | 900 | 0.6752 | 0.8090 | 0.7866 | 0.8090 | |
|
| 0.3389 | 2.5 | 950 | 0.6639 | 0.8123 | 0.7914 | 0.8123 | |
|
| 0.4166 | 2.63 | 1000 | 0.6590 | 0.8169 | 0.8010 | 0.8169 | |
|
| 0.483 | 2.76 | 1050 | 0.6630 | 0.8149 | 0.7937 | 0.8149 | |
|
| 0.4582 | 2.89 | 1100 | 0.6518 | 0.8096 | 0.7882 | 0.8096 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
