|
--- |
|
license: apache-2.0 |
|
base_model: google/t5-efficient-tiny |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: medication-single-t5-tiny |
|
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. --> |
|
|
|
# medication-single-t5-tiny |
|
|
|
This model is a fine-tuned version of [google/t5-efficient-tiny](https://huggingface.co/google/t5-efficient-tiny) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0212 |
|
|
|
## 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: 0.004 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.03 |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.321 | 0.08 | 100 | 0.6658 | |
|
| 0.5928 | 0.16 | 200 | 0.3980 | |
|
| 0.4394 | 0.23 | 300 | 0.2642 | |
|
| 0.3582 | 0.31 | 400 | 0.2266 | |
|
| 0.3174 | 0.39 | 500 | 0.1874 | |
|
| 0.2776 | 0.47 | 600 | 0.1702 | |
|
| 0.2286 | 0.55 | 700 | 0.1357 | |
|
| 0.2052 | 0.63 | 800 | 0.1147 | |
|
| 0.1962 | 0.7 | 900 | 0.0933 | |
|
| 0.1641 | 0.78 | 1000 | 0.0771 | |
|
| 0.1613 | 0.86 | 1100 | 0.0759 | |
|
| 0.1482 | 0.94 | 1200 | 0.0677 | |
|
| 0.1128 | 1.02 | 1300 | 0.0574 | |
|
| 0.1139 | 1.09 | 1400 | 0.0509 | |
|
| 0.1021 | 1.17 | 1500 | 0.0465 | |
|
| 0.1013 | 1.25 | 1600 | 0.0449 | |
|
| 0.0854 | 1.33 | 1700 | 0.0394 | |
|
| 0.0839 | 1.41 | 1800 | 0.0375 | |
|
| 0.0972 | 1.49 | 1900 | 0.0377 | |
|
| 0.0775 | 1.56 | 2000 | 0.0352 | |
|
| 0.0682 | 1.64 | 2100 | 0.0324 | |
|
| 0.0676 | 1.72 | 2200 | 0.0310 | |
|
| 0.0633 | 1.8 | 2300 | 0.0284 | |
|
| 0.0608 | 1.88 | 2400 | 0.0279 | |
|
| 0.0571 | 1.95 | 2500 | 0.0270 | |
|
| 0.0557 | 2.03 | 2600 | 0.0259 | |
|
| 0.0561 | 2.11 | 2700 | 0.0273 | |
|
| 0.0542 | 2.19 | 2800 | 0.0247 | |
|
| 0.0542 | 2.27 | 2900 | 0.0241 | |
|
| 0.0514 | 2.35 | 3000 | 0.0248 | |
|
| 0.0471 | 2.42 | 3100 | 0.0240 | |
|
| 0.042 | 2.5 | 3200 | 0.0225 | |
|
| 0.0547 | 2.58 | 3300 | 0.0221 | |
|
| 0.0462 | 2.66 | 3400 | 0.0216 | |
|
| 0.0444 | 2.74 | 3500 | 0.0216 | |
|
| 0.0434 | 2.81 | 3600 | 0.0213 | |
|
| 0.0374 | 2.89 | 3700 | 0.0213 | |
|
| 0.0404 | 2.97 | 3800 | 0.0212 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.7 |
|
- Tokenizers 0.14.1 |
|
|
