<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
kobart_16_5.6e-5_datav2_min30_lp5.0_temperature1.0
This model is a fine-tuned version of gogamza/kobart-base-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.7174
- Rouge1: 35.7621
- Rouge2: 12.8914
- Rougel: 23.6695
- Bleu1: 29.9954
- Bleu2: 17.513
- Bleu3: 10.317
- Bleu4: 5.8532
- Gen Len: 49.3147
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: 5.6e-05
- train_batch_size: 16
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Bleu1 | Bleu2 | Bleu3 | Bleu4 | Gen Len |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.9617 | 1.89 | 5000 | 2.6146 | 35.2828 | 12.4993 | 22.9894 | 29.2237 | 16.8919 | 9.7826 | 5.4461 | 48.0676 |
| 1.5272 | 3.78 | 10000 | 2.7174 | 35.7621 | 12.8914 | 23.6695 | 29.9954 | 17.513 | 10.317 | 5.8532 | 49.3147 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu117
- Datasets 2.7.1
- Tokenizers 0.13.2
