NDC_summarization_v1
This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.7368
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: 1.5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 39.59 | 0.08 | 100 | 38.3634 |
| 35.1013 | 0.16 | 200 | 33.4366 |
| 31.1938 | 0.24 | 300 | 29.1901 |
| 28.0987 | 0.32 | 400 | 25.8563 |
| 25.51 | 0.4 | 500 | 23.3870 |
| 23.5813 | 0.48 | 600 | 21.2345 |
| 21.6388 | 0.56 | 700 | 19.0511 |
| 19.7263 | 0.64 | 800 | 16.5095 |
| 17.7356 | 0.72 | 900 | 14.0403 |
| 15.9213 | 0.8 | 1000 | 11.4215 |
| 14.0669 | 0.88 | 1100 | 9.0435 |
| 12.4244 | 0.97 | 1200 | 7.0559 |
| 11.1694 | 1.05 | 1300 | 5.8898 |
| 9.9044 | 1.13 | 1400 | 5.3474 |
| 9.1553 | 1.21 | 1500 | 5.1055 |
| 8.6953 | 1.29 | 1600 | 4.9913 |
| 8.3372 | 1.37 | 1700 | 4.9194 |
| 7.9119 | 1.45 | 1800 | 4.8677 |
| 7.92 | 1.53 | 1900 | 4.8362 |
| 7.6597 | 1.61 | 2000 | 4.8150 |
| 7.6866 | 1.69 | 2100 | 4.7991 |
| 7.5191 | 1.77 | 2200 | 4.7857 |
| 7.6137 | 1.85 | 2300 | 4.7761 |
| 7.52 | 1.93 | 2400 | 4.7696 |
| 7.4387 | 2.01 | 2500 | 4.7635 |
| 7.4528 | 2.09 | 2600 | 4.7584 |
| 7.465 | 2.17 | 2700 | 4.7547 |
| 7.4059 | 2.25 | 2800 | 4.7520 |
| 7.2306 | 2.33 | 2900 | 4.7489 |
| 7.4756 | 2.41 | 3000 | 4.7490 |
| 7.3419 | 2.49 | 3100 | 4.7473 |
| 7.2891 | 2.57 | 3200 | 4.7453 |
| 7.2044 | 2.65 | 3300 | 4.7446 |
| 7.2625 | 2.74 | 3400 | 4.7441 |
| 7.2725 | 2.82 | 3500 | 4.7416 |
| 7.3309 | 2.9 | 3600 | 4.7423 |
| 7.3053 | 2.98 | 3700 | 4.7404 |
| 7.3913 | 3.06 | 3800 | 4.7408 |
| 7.2447 | 3.14 | 3900 | 4.7390 |
| 7.3025 | 3.22 | 4000 | 4.7393 |
| 7.3103 | 3.3 | 4100 | 4.7383 |
| 7.1809 | 3.38 | 4200 | 4.7381 |
| 7.2931 | 3.46 | 4300 | 4.7383 |
| 7.4078 | 3.54 | 4400 | 4.7385 |
| 7.3231 | 3.62 | 4500 | 4.7383 |
| 7.23 | 3.7 | 4600 | 4.7376 |
| 7.2222 | 3.78 | 4700 | 4.7372 |
| 7.3525 | 3.86 | 4800 | 4.7379 |
| 7.2597 | 3.94 | 4900 | 4.7372 |
| 7.3281 | 4.02 | 5000 | 4.7376 |
| 7.2656 | 4.1 | 5100 | 4.7370 |
| 7.3769 | 4.18 | 5200 | 4.7378 |
| 7.3637 | 4.26 | 5300 | 4.7367 |
| 7.2869 | 4.34 | 5400 | 4.7367 |
| 7.2634 | 4.42 | 5500 | 4.7369 |
| 7.3225 | 4.51 | 5600 | 4.7367 |
| 7.2394 | 4.59 | 5700 | 4.7369 |
| 7.2691 | 4.67 | 5800 | 4.7371 |
| 7.3459 | 4.75 | 5900 | 4.7368 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 0
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for huyenquinn282/NDC_summarization_v1
Base model
google/flan-t5-base