Scarlet Chase Chatbot
This model is a fine-tuned version of openchat/openchat_3.5 on the Scarch 0.2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5505
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3688 | 0.99 | 23 | 1.2936 |
| 0.6937 | 1.99 | 46 | 0.7731 |
| 0.4616 | 2.98 | 69 | 0.5906 |
| 0.3754 | 3.98 | 92 | 0.5231 |
| 0.2555 | 4.97 | 115 | 0.5099 |
| 0.2235 | 5.97 | 138 | 0.5073 |
| 0.1517 | 6.96 | 161 | 0.5216 |
| 0.0767 | 8.0 | 185 | 0.5357 |
| 0.073 | 8.99 | 208 | 0.5503 |
| 0.0886 | 9.95 | 230 | 0.5505 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 20
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for amgadhasan/scachase-openchat-0.2
Base model
openchat/openchat_3.5