metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: DanSumT5-largeV_38143V_15157V_96478
results: []
DanSumT5-largeV_38143V_15157V_96478
This model is a fine-tuned version of emilstabil/DanSumT5-largeV_38143V_15157 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9819
- Rouge1: 35.982
- Rouge2: 12.5438
- Rougel: 22.7137
- Rougelsum: 33.5334
- Gen Len: 124.173
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 11
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 0.99 | 118 | 1.9875 | 35.6378 | 12.3785 | 22.4666 | 33.224 | 123.1814 |
| No log | 2.0 | 237 | 1.9991 | 35.9161 | 12.5761 | 22.7594 | 33.6048 | 123.5865 |
| No log | 3.0 | 356 | 1.9994 | 36.0651 | 12.7545 | 22.9642 | 33.6968 | 123.6203 |
| No log | 4.0 | 475 | 1.9980 | 35.9273 | 12.6691 | 22.818 | 33.609 | 123.4515 |
| 1.4198 | 4.99 | 593 | 2.0076 | 35.5438 | 12.2242 | 22.5019 | 33.237 | 123.7257 |
| 1.4198 | 6.0 | 712 | 2.0032 | 36.0019 | 12.7386 | 22.9014 | 33.7588 | 124.5443 |
| 1.4198 | 7.0 | 831 | 2.0001 | 35.8585 | 12.7149 | 22.8298 | 33.6196 | 124.4008 |
| 1.4198 | 8.0 | 950 | 1.9945 | 35.6975 | 12.4727 | 22.6524 | 33.3949 | 124.5316 |
| 1.4397 | 8.99 | 1068 | 1.9898 | 35.944 | 12.6829 | 22.9022 | 33.5212 | 124.1181 |
| 1.4397 | 10.0 | 1187 | 1.9843 | 36.0341 | 12.5681 | 22.7855 | 33.5415 | 124.0084 |
| 1.4397 | 10.93 | 1298 | 1.9819 | 35.982 | 12.5438 | 22.7137 | 33.5334 | 124.173 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.12.1+git7548e2f
- Datasets 2.13.2
- Tokenizers 0.13.3