Lamini-fal-prompt-enchance
This model is a fine-tuned version of MBZUAI/LaMini-Flan-T5-248M on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9041
- Rouge1: 20.9035
- Rouge2: 9.3637
- Rougel: 17.2527
- Rougelsum: 17.2667
- Gen Len: 19.0
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-05
- train_batch_size: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.2667 | 1.0 | 1087 | 2.0387 | 20.8796 | 9.0801 | 17.1295 | 17.1457 | 19.0 |
| 2.1479 | 2.0 | 2174 | 1.9617 | 20.9168 | 9.2939 | 17.2554 | 17.2756 | 19.0 |
| 2.0904 | 3.0 | 3261 | 1.9266 | 20.9394 | 9.3389 | 17.2804 | 17.3005 | 19.0 |
| 2.0609 | 4.0 | 4348 | 1.9096 | 20.9855 | 9.3774 | 17.2773 | 17.2923 | 19.0 |
| 2.0464 | 5.0 | 5435 | 1.9041 | 20.9035 | 9.3637 | 17.2527 | 17.2667 | 19.0 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 31
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 gokaygokay/Lamini-fal-prompt-enchance
Base model
MBZUAI/LaMini-Flan-T5-248M