|
--- |
|
license: apache-2.0 |
|
base_model: gayanin/bart-with-woz-noise-data-0.1-v2 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: bart-with-woz-pubmed-noise-data-0.1-v2 |
|
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. --> |
|
|
|
# bart-with-woz-pubmed-noise-data-0.1-v2 |
|
|
|
This model is a fine-tuned version of [gayanin/bart-with-woz-noise-data-0.1-v2](https://huggingface.co./gayanin/bart-with-woz-noise-data-0.1-v2) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2136 |
|
|
|
## 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: 5e-05 |
|
- 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_steps: 10 |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 0.395 | 0.11 | 500 | 0.3361 | |
|
| 0.3239 | 0.21 | 1000 | 0.2993 | |
|
| 0.2485 | 0.32 | 1500 | 0.2899 | |
|
| 0.3632 | 0.43 | 2000 | 0.2650 | |
|
| 0.3141 | 0.54 | 2500 | 0.2555 | |
|
| 0.2913 | 0.64 | 3000 | 0.2537 | |
|
| 0.2587 | 0.75 | 3500 | 0.2474 | |
|
| 0.2745 | 0.86 | 4000 | 0.2408 | |
|
| 0.2725 | 0.96 | 4500 | 0.2362 | |
|
| 0.2025 | 1.07 | 5000 | 0.2468 | |
|
| 0.2088 | 1.18 | 5500 | 0.2368 | |
|
| 0.1912 | 1.28 | 6000 | 0.2447 | |
|
| 0.2098 | 1.39 | 6500 | 0.2311 | |
|
| 0.1839 | 1.5 | 7000 | 0.2336 | |
|
| 0.2407 | 1.61 | 7500 | 0.2280 | |
|
| 0.1692 | 1.71 | 8000 | 0.2229 | |
|
| 0.1965 | 1.82 | 8500 | 0.2220 | |
|
| 0.2013 | 1.93 | 9000 | 0.2175 | |
|
| 0.1455 | 2.03 | 9500 | 0.2243 | |
|
| 0.1466 | 2.14 | 10000 | 0.2235 | |
|
| 0.1493 | 2.25 | 10500 | 0.2223 | |
|
| 0.1224 | 2.35 | 11000 | 0.2207 | |
|
| 0.1491 | 2.46 | 11500 | 0.2173 | |
|
| 0.1484 | 2.57 | 12000 | 0.2175 | |
|
| 0.1582 | 2.68 | 12500 | 0.2175 | |
|
| 0.1592 | 2.78 | 13000 | 0.2137 | |
|
| 0.1467 | 2.89 | 13500 | 0.2153 | |
|
| 0.1637 | 3.0 | 14000 | 0.2136 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.1 |
|
|
