blenderbot-empathetic
This model is a fine-tuned version of facebook/blenderbot-400M-distill on the None dataset. It achieves the following results on the evaluation set:
- Loss: 6.2422
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-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 89.3751 | 1.0 | 920 | 6.0781 |
| 70.3343 | 2.0 | 1840 | 5.8086 |
| 42.7835 | 3.0 | 2760 | 6.2422 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 2.19.1
- Tokenizers 0.22.2
- Downloads last month
- 7
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Gasolinaaa/blenderbot-empathetic
Base model
facebook/blenderbot-400M-distill