opt-2.7b-realtime-chat-v2
This model is a fine-tuned version of facebook/opt-2.7b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0888
- Accuracy: 0.6870
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: 3e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 128
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.0974 | 0.5 | 51 | 2.1267 | 0.6826 |
2.0842 | 1.0 | 102 | 2.0968 | 0.6859 |
1.9624 | 1.49 | 153 | 2.0936 | 0.6863 |
1.9476 | 1.99 | 204 | 2.0888 | 0.6870 |
1.888 | 2.49 | 255 | 2.0993 | 0.6864 |
1.8687 | 2.99 | 306 | 2.0994 | 0.6865 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.1+cu118
- Datasets 2.7.1
- Tokenizers 0.12.1
- Downloads last month
- 7
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.