flan-t5-base-sql
Browse files
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/flan-t5-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: flan-t5-base-sql
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# flan-t5-base-sql
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.2463
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 2e-06
|
| 38 |
+
- train_batch_size: 32
|
| 39 |
+
- eval_batch_size: 32
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 1
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| 36.07 | 0.032 | 100 | 28.3961 |
|
| 50 |
+
| 17.6704 | 0.064 | 200 | 7.5753 |
|
| 51 |
+
| 5.1571 | 0.096 | 300 | 4.2162 |
|
| 52 |
+
| 3.7573 | 0.128 | 400 | 2.9984 |
|
| 53 |
+
| 2.7831 | 0.16 | 500 | 1.7788 |
|
| 54 |
+
| 2.0308 | 0.192 | 600 | 1.2800 |
|
| 55 |
+
| 1.5731 | 0.224 | 700 | 0.9554 |
|
| 56 |
+
| 1.2735 | 0.256 | 800 | 0.7648 |
|
| 57 |
+
| 1.0347 | 0.288 | 900 | 0.6471 |
|
| 58 |
+
| 0.886 | 0.32 | 1000 | 0.5424 |
|
| 59 |
+
| 0.757 | 0.352 | 1100 | 0.4848 |
|
| 60 |
+
| 0.6731 | 0.384 | 1200 | 0.4293 |
|
| 61 |
+
| 0.6222 | 0.416 | 1300 | 0.3904 |
|
| 62 |
+
| 0.55 | 0.448 | 1400 | 0.3609 |
|
| 63 |
+
| 0.5226 | 0.48 | 1500 | 0.3372 |
|
| 64 |
+
| 0.4802 | 0.512 | 1600 | 0.3218 |
|
| 65 |
+
| 0.4653 | 0.544 | 1700 | 0.3076 |
|
| 66 |
+
| 0.4419 | 0.576 | 1800 | 0.2948 |
|
| 67 |
+
| 0.4252 | 0.608 | 1900 | 0.2865 |
|
| 68 |
+
| 0.4009 | 0.64 | 2000 | 0.2780 |
|
| 69 |
+
| 0.3977 | 0.672 | 2100 | 0.2716 |
|
| 70 |
+
| 0.3919 | 0.704 | 2200 | 0.2670 |
|
| 71 |
+
| 0.3788 | 0.736 | 2300 | 0.2618 |
|
| 72 |
+
| 0.3674 | 0.768 | 2400 | 0.2574 |
|
| 73 |
+
| 0.359 | 0.8 | 2500 | 0.2543 |
|
| 74 |
+
| 0.3477 | 0.832 | 2600 | 0.2524 |
|
| 75 |
+
| 0.3555 | 0.864 | 2700 | 0.2503 |
|
| 76 |
+
| 0.3461 | 0.896 | 2800 | 0.2482 |
|
| 77 |
+
| 0.3454 | 0.928 | 2900 | 0.2470 |
|
| 78 |
+
| 0.3526 | 0.96 | 3000 | 0.2464 |
|
| 79 |
+
| 0.3464 | 0.992 | 3100 | 0.2463 |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Framework versions
|
| 83 |
+
|
| 84 |
+
- Transformers 4.44.0
|
| 85 |
+
- Pytorch 2.3.1.post300
|
| 86 |
+
- Datasets 2.21.0
|
| 87 |
+
- Tokenizers 0.19.1
|