Downloads · 30 days
9
10% of all-time downloads
roberta2gpt2-roberta-base-gpt2-cnn-dailymail-seed42
tomvoelker/roberta2gpt2-roberta-base-gpt2-cnn-dailymail-seed42
roberta2gpt2-roberta-base-gpt2-cnn-dailymail-seed42 is a machine learning model from tomvoelker. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
93
Public
Parameters
277M
15.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.1 GB · 100%
At a glance
- Library
- transformers
- Model type
- encoder-decoder
- Access
- Public
- Created
- Mar 15, 2025
- Updated
- Mar 16, 2025
- SHA
- 608cbaba
Model card
From the Hugging Face model README
<!-- 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. -->
roberta2gpt2-roberta-base-gpt2-cnn-dailymail-seed42
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.0931
- Rouge1: 0.1549
- Rouge2: 0.0158
- Rougel: 0.1017
- Rougelsum: 0.1453
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 3.4365 | 0.2229 | 2000 | 3.2391 | 0.1383 | 0.0109 | 0.0905 | 0.1307 |
| 3.341 | 0.4458 | 4000 | 3.1842 | 0.1344 | 0.0099 | 0.0884 | 0.1262 |
| 3.2829 | 0.6687 | 6000 | 3.1547 | 0.1481 | 0.0137 | 0.0976 | 0.1391 |
| 3.2371 | 0.8916 | 8000 | 3.1359 | 0.1491 | 0.0128 | 0.0981 | 0.1401 |
| 3.1202 | 1.1145 | 10000 | 3.1200 | 0.1527 | 0.0147 | 0.0993 | 0.1438 |
| 3.112 | 1.3374 | 12000 | 3.1102 | 0.1529 | 0.0144 | 0.1004 | 0.1438 |
| 3.0934 | 1.5603 | 14000 | 3.1048 | 0.1462 | 0.0151 | 0.0967 | 0.1373 |
| 3.0837 | 1.7832 | 16000 | 3.0971 | 0.1538 | 0.0170 | 0.1014 | 0.1445 |
| 3.0701 | 2.0061 | 18000 | 3.0958 | 0.1533 | 0.0160 | 0.1016 | 0.1438 |
| 3.0083 | 2.2290 | 20000 | 3.0984 | 0.1554 | 0.0166 | 0.1019 | 0.1460 |
| 2.9929 | 2.4519 | 22000 | 3.0943 | 0.1559 | 0.0159 | 0.1022 | 0.1463 |
| 2.9884 | 2.6748 | 24000 | 3.0929 | 0.1558 | 0.0165 | 0.1027 | 0.1463 |
| 2.9865 | 2.8977 | 26000 | 3.0931 | 0.1549 | 0.0158 | 0.1017 | 0.1453 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1
- Library
- transformers
- Type
- encoder-decoder
- Created
- Mar 15, 2025
- Updated
- Mar 16, 2025