flan-t5-base-finetuned-frnet-300ct-7e
This model is a fine-tuned version of RohanHBTU/flan-t5-base-finetuned-frnet-300ct-4e on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4854
- Bleu: 43.2024
- Gen Len: 87.8205
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: 2
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 0.5653 | 1.0 | 17548 | 0.5172 | 41.7992 | 89.1587 |
| 0.5663 | 2.0 | 35096 | 0.4939 | 42.9805 | 88.0114 |
| 0.5107 | 3.0 | 52644 | 0.4854 | 43.2024 | 87.8205 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- 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.