punctuation-test-4
This model is a fine-tuned version of facebook/bart-base on the wmt16 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3411
- Bleu: 39.1294
- Gen Len: 18.4812
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 0.3331 | 1.0 | 625 | 0.3411 | 39.1294 | 18.4812 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Dataset used to train mikeadimech/punctuation-test-4
Evaluation results
- Bleu on wmt16self-reported39.129
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("mikeadimech/punctuation-test-4") model = AutoModelForSeq2SeqLM.from_pretrained("mikeadimech/punctuation-test-4")