textGeneration_06
This model is a fine-tuned version of t5-small on the xsum dataset. It achieves the following results on the evaluation set:
- Loss: 3.7405
- Rouge1: 12.1154
- Rouge2: 1.7291
- Rougel: 9.4055
- Rougelsum: 11.035
- Gen Len: 937.368
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 4.2168 | 1.0 | 1250 | 3.8405 | 12.1695 | 1.7457 | 9.3821 | 11.0907 | 896.12 |
| 4.1005 | 2.0 | 2500 | 3.7840 | 11.933 | 1.7034 | 9.3269 | 10.8944 | 938.399 |
| 4.0678 | 3.0 | 3750 | 3.7579 | 12.0066 | 1.7388 | 9.3301 | 10.9558 | 936.662 |
| 4.0411 | 4.0 | 5000 | 3.7445 | 12.0542 | 1.7188 | 9.4032 | 11.0116 | 932.645 |
| 4.0359 | 5.0 | 6250 | 3.7405 | 12.1154 | 1.7291 | 9.4055 | 11.035 | 937.368 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
- Downloads last month
- 4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Dataset used to train Seungjun/textGeneration_06
Evaluation results
- Rouge1 on xsumvalidation set self-reported12.115
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Seungjun/textGeneration_06") model = AutoModelForSeq2SeqLM.from_pretrained("Seungjun/textGeneration_06")