|
--- |
|
license: apache-2.0 |
|
base_model: google-t5/t5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: t5_small_twitter |
|
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_twitter |
|
|
|
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: 0.4976 |
|
- Accuracy: 0.7445 |
|
- F1 Macro: 0.6956 |
|
- F1 Micro: 0.7445 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
| 0.4779 | 0.18 | 50 | 0.5151 | 0.7564 | 0.7177 | 0.7564 | |
|
| 0.5123 | 0.37 | 100 | 0.5060 | 0.7528 | 0.6987 | 0.7528 | |
|
| 0.4617 | 0.55 | 150 | 0.5287 | 0.7270 | 0.6149 | 0.7270 | |
|
| 0.4942 | 0.74 | 200 | 0.4976 | 0.7445 | 0.6956 | 0.7445 | |
|
| 0.4783 | 0.92 | 250 | 0.4978 | 0.7574 | 0.7124 | 0.7574 | |
|
| 0.4369 | 1.1 | 300 | 0.5052 | 0.7601 | 0.7124 | 0.7601 | |
|
| 0.439 | 1.29 | 350 | 0.5092 | 0.7564 | 0.7224 | 0.7564 | |
|
| 0.4417 | 1.47 | 400 | 0.5228 | 0.7546 | 0.6808 | 0.7546 | |
|
| 0.47 | 1.65 | 450 | 0.5087 | 0.7693 | 0.7235 | 0.7693 | |
|
| 0.4415 | 1.84 | 500 | 0.5106 | 0.7647 | 0.7262 | 0.7647 | |
|
| 0.4297 | 2.02 | 550 | 0.5023 | 0.7629 | 0.7291 | 0.7629 | |
|
| 0.4366 | 2.21 | 600 | 0.5225 | 0.7555 | 0.7127 | 0.7555 | |
|
| 0.3623 | 2.39 | 650 | 0.5226 | 0.7583 | 0.7157 | 0.7583 | |
|
| 0.3337 | 2.57 | 700 | 0.5313 | 0.7574 | 0.7144 | 0.7574 | |
|
| 0.4158 | 2.76 | 750 | 0.5385 | 0.7601 | 0.7211 | 0.7601 | |
|
| 0.4003 | 2.94 | 800 | 0.5350 | 0.7546 | 0.7058 | 0.7546 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|