<!-- 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. -->
outputs
This model is a fine-tuned version of facebook/opt-1.3b on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6286
- Accuracy: 0.7095
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: 2e-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
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7716 | 0.05 | 20 | 1.1077 | 0.2355 |
| 0.7058 | 0.09 | 40 | 0.8183 | 0.5443 |
| 0.6877 | 0.14 | 60 | 0.8182 | 0.5443 |
| 0.6154 | 0.18 | 80 | 0.7467 | 0.6070 |
| 0.6188 | 0.23 | 100 | 0.7712 | 0.5810 |
| 0.549 | 0.28 | 120 | 0.9027 | 0.4847 |
| 0.5617 | 0.32 | 140 | 0.7137 | 0.6300 |
| 0.5573 | 0.37 | 160 | 0.7936 | 0.5642 |
| 0.5382 | 0.41 | 180 | 0.7245 | 0.6346 |
| 0.5121 | 0.46 | 200 | 0.7282 | 0.6422 |
| 0.5577 | 0.51 | 220 | 0.7301 | 0.6376 |
| 0.4909 | 0.55 | 240 | 0.6293 | 0.6957 |
| 0.5057 | 0.6 | 260 | 0.6421 | 0.6896 |
| 0.4774 | 0.64 | 280 | 0.6944 | 0.6697 |
| 0.4786 | 0.69 | 300 | 0.7043 | 0.6682 |
| 0.4403 | 0.74 | 320 | 0.6020 | 0.7217 |
| 0.5914 | 0.78 | 340 | 0.5944 | 0.7217 |
| 0.459 | 0.83 | 360 | 0.6188 | 0.7171 |
| 0.4654 | 0.87 | 380 | 0.6424 | 0.7110 |
| 0.3851 | 0.92 | 400 | 0.6387 | 0.7095 |
| 0.4811 | 0.97 | 420 | 0.6286 | 0.7095 |
Framework versions
- Transformers 4.29.0.dev0
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.2
