|
--- |
|
license: other |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: EnabledChat |
|
results: [] |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# EnabledChat |
|
|
|
This model is a fine-tuned version of [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1152 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.2849 | 0.06 | 200 | 1.2346 | |
|
| 1.2515 | 0.13 | 400 | 1.2077 | |
|
| 1.1859 | 0.19 | 600 | 1.1948 | |
|
| 1.2007 | 0.26 | 800 | 1.1845 | |
|
| 1.2085 | 0.32 | 1000 | 1.1763 | |
|
| 1.2036 | 0.38 | 1200 | 1.1710 | |
|
| 1.2134 | 0.45 | 1400 | 1.1655 | |
|
| 1.1869 | 0.51 | 1600 | 1.1610 | |
|
| 1.2017 | 0.58 | 1800 | 1.1573 | |
|
| 1.2139 | 0.64 | 2000 | 1.1537 | |
|
| 1.1302 | 0.7 | 2200 | 1.1510 | |
|
| 1.1799 | 0.77 | 2400 | 1.1480 | |
|
| 1.1518 | 0.83 | 2600 | 1.1461 | |
|
| 1.1752 | 0.9 | 2800 | 1.1434 | |
|
| 1.1584 | 0.96 | 3000 | 1.1415 | |
|
| 1.1311 | 1.02 | 3200 | 1.1400 | |
|
| 1.1595 | 1.09 | 3400 | 1.1374 | |
|
| 1.1721 | 1.15 | 3600 | 1.1365 | |
|
| 1.1597 | 1.22 | 3800 | 1.1355 | |
|
| 1.1718 | 1.28 | 4000 | 1.1335 | |
|
| 1.1639 | 1.34 | 4200 | 1.1315 | |
|
| 1.1448 | 1.41 | 4400 | 1.1312 | |
|
| 1.1645 | 1.47 | 4600 | 1.1296 | |
|
| 1.1562 | 1.54 | 4800 | 1.1282 | |
|
| 1.1619 | 1.6 | 5000 | 1.1273 | |
|
| 1.1794 | 1.66 | 5200 | 1.1270 | |
|
| 1.178 | 1.73 | 5400 | 1.1254 | |
|
| 1.1291 | 1.79 | 5600 | 1.1246 | |
|
| 1.1235 | 1.86 | 5800 | 1.1234 | |
|
| 1.1169 | 1.92 | 6000 | 1.1222 | |
|
| 1.1494 | 1.98 | 6200 | 1.1214 | |
|
| 1.1032 | 2.05 | 6400 | 1.1218 | |
|
| 1.1269 | 2.11 | 6600 | 1.1207 | |
|
| 1.1561 | 2.18 | 6800 | 1.1203 | |
|
| 1.152 | 2.24 | 7000 | 1.1199 | |
|
| 1.1335 | 2.3 | 7200 | 1.1191 | |
|
| 1.1341 | 2.37 | 7400 | 1.1184 | |
|
| 1.0963 | 2.43 | 7600 | 1.1180 | |
|
| 1.1179 | 2.5 | 7800 | 1.1172 | |
|
| 1.1176 | 2.56 | 8000 | 1.1170 | |
|
| 1.15 | 2.62 | 8200 | 1.1165 | |
|
| 1.073 | 2.69 | 8400 | 1.1164 | |
|
| 1.1737 | 2.75 | 8600 | 1.1156 | |
|
| 1.1251 | 2.82 | 8800 | 1.1156 | |
|
| 1.1548 | 2.88 | 9000 | 1.1154 | |
|
| 1.1046 | 2.94 | 9200 | 1.1152 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.30.0.dev0 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |