|
--- |
|
license: apache-2.0 |
|
base_model: google/flan-t5-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: SQL_Final_RunPod_Last |
|
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. --> |
|
|
|
# SQL_Final_RunPod_Last |
|
|
|
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0215 |
|
- Bleu: 44.256 |
|
- Gen Len: 18.9114 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 24 |
|
- eval_batch_size: 24 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:| |
|
| 0.2055 | 0.12 | 1000 | 0.0917 | 42.8594 | 18.8938 | |
|
| 0.1187 | 0.23 | 2000 | 0.0709 | 43.1637 | 18.8915 | |
|
| 0.1007 | 0.35 | 3000 | 0.0602 | 43.4304 | 18.9088 | |
|
| 0.0869 | 0.46 | 4000 | 0.0559 | 43.4636 | 18.8961 | |
|
| 0.0792 | 0.58 | 5000 | 0.0497 | 43.5366 | 18.9063 | |
|
| 0.0736 | 0.69 | 6000 | 0.0464 | 43.5769 | 18.9016 | |
|
| 0.0672 | 0.81 | 7000 | 0.0435 | 43.7471 | 18.9068 | |
|
| 0.0635 | 0.93 | 8000 | 0.0403 | 43.781 | 18.9073 | |
|
| 0.0564 | 1.04 | 9000 | 0.0389 | 43.7054 | 18.9029 | |
|
| 0.0493 | 1.16 | 10000 | 0.0376 | 43.8362 | 18.9063 | |
|
| 0.0479 | 1.27 | 11000 | 0.0367 | 43.8514 | 18.9126 | |
|
| 0.0465 | 1.39 | 12000 | 0.0350 | 43.8365 | 18.9078 | |
|
| 0.0449 | 1.5 | 13000 | 0.0335 | 43.8878 | 18.9042 | |
|
| 0.0419 | 1.62 | 14000 | 0.0324 | 43.9035 | 18.9075 | |
|
| 0.0426 | 1.74 | 15000 | 0.0314 | 43.9272 | 18.906 | |
|
| 0.0405 | 1.85 | 16000 | 0.0302 | 44.0143 | 18.9087 | |
|
| 0.039 | 1.97 | 17000 | 0.0291 | 43.9392 | 18.9089 | |
|
| 0.0327 | 2.08 | 18000 | 0.0286 | 44.0248 | 18.9087 | |
|
| 0.0311 | 2.2 | 19000 | 0.0288 | 44.0732 | 18.9119 | |
|
| 0.0302 | 2.31 | 20000 | 0.0282 | 44.061 | 18.9055 | |
|
| 0.029 | 2.43 | 21000 | 0.0279 | 44.0681 | 18.9121 | |
|
| 0.0297 | 2.55 | 22000 | 0.0267 | 44.0958 | 18.91 | |
|
| 0.0284 | 2.66 | 23000 | 0.0259 | 44.1215 | 18.9121 | |
|
| 0.0272 | 2.78 | 24000 | 0.0259 | 44.0752 | 18.9113 | |
|
| 0.0273 | 2.89 | 25000 | 0.0253 | 44.1104 | 18.909 | |
|
| 0.0265 | 3.01 | 26000 | 0.0253 | 44.1262 | 18.9095 | |
|
| 0.0215 | 3.12 | 27000 | 0.0251 | 44.137 | 18.9119 | |
|
| 0.0215 | 3.24 | 28000 | 0.0246 | 44.1382 | 18.9096 | |
|
| 0.0215 | 3.36 | 29000 | 0.0244 | 44.1806 | 18.9088 | |
|
| 0.0206 | 3.47 | 30000 | 0.0237 | 44.169 | 18.911 | |
|
| 0.0202 | 3.59 | 31000 | 0.0243 | 44.1469 | 18.9096 | |
|
| 0.0204 | 3.7 | 32000 | 0.0231 | 44.1405 | 18.9116 | |
|
| 0.0193 | 3.82 | 33000 | 0.0230 | 44.1613 | 18.9116 | |
|
| 0.0196 | 3.94 | 34000 | 0.0226 | 44.197 | 18.9117 | |
|
| 0.0177 | 4.05 | 35000 | 0.0228 | 44.1942 | 18.9102 | |
|
| 0.0155 | 4.17 | 36000 | 0.0230 | 44.2241 | 18.9118 | |
|
| 0.0159 | 4.28 | 37000 | 0.0226 | 44.2219 | 18.9107 | |
|
| 0.0151 | 4.4 | 38000 | 0.0221 | 44.212 | 18.912 | |
|
| 0.0149 | 4.51 | 39000 | 0.0222 | 44.2743 | 18.9115 | |
|
| 0.0154 | 4.63 | 40000 | 0.0216 | 44.2636 | 18.9121 | |
|
| 0.0149 | 4.75 | 41000 | 0.0215 | 44.2805 | 18.913 | |
|
| 0.0146 | 4.86 | 42000 | 0.0216 | 44.2681 | 18.9125 | |
|
| 0.0145 | 4.98 | 43000 | 0.0215 | 44.256 | 18.9114 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
