bart_lfqa-fleece2instructions-r1
This model is a fine-tuned version of vblagoje/bart_lfqa on the pszemraj/fleece2instructions dataset. It achieves the following results on the evaluation set:
- Loss: 1.1890
- Rouge1: 0.0334
- Rouge2: 0.0299
- Rougel: 0.0334
- Rougelsum: 0.0334
- Gen Len: 255.9156
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: 6e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 2.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.9558 | 1.0 | 362 | 1.2120 | 0.0 | 0.0 | 0.0 | 0.0 | 256.0 |
| 0.757 | 2.0 | 724 | 1.1890 | 0.0 | 0.0 | 0.0 | 0.0 | 256.0 |
Framework versions
- Transformers 4.25.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.0
- Tokenizers 0.13.2
- Downloads last month
- 4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Dataset used to train AleBurzio/bart_lfqa-fleece2instructions-r1
Evaluation results
- Rouge1 on pszemraj/fleece2instructionsself-reported0.033