Downloads · 30 days
8
22% of all-time downloads
tf-cnn-ft-trial-2-model
harish3742/tf-cnn-ft-trial-2-model
tf-cnn-ft-trial-2-model is a machine learning model from harish3742. 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. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
37
Public
Parameters
60.5M
19.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors242 MB · 99%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- t5
- Access
- Public
- Created
- Apr 8, 2024
- Updated
- Apr 8, 2024
- SHA
- 9e320652
Base models
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. -->
tf-cnn-ft-trial-2-model
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7041
- Rouge1: 0.2385
- Rouge2: 0.1049
- Rougel: 0.1981
- Rougelsum: 0.1981
- Gen Len: 18.9608
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.9308 | 1.0 | 8075 | 1.7221 | 0.2374 | 0.1043 | 0.1969 | 0.1969 | 18.9559 |
| 1.9019 | 2.0 | 16150 | 1.7127 | 0.2387 | 0.1052 | 0.1982 | 0.1981 | 18.9622 |
| 1.8967 | 3.0 | 24225 | 1.7089 | 0.2379 | 0.1047 | 0.1976 | 0.1976 | 18.9588 |
| 1.8963 | 4.0 | 32300 | 1.7062 | 0.2388 | 0.1053 | 0.1984 | 0.1984 | 18.9628 |
| 1.8773 | 5.0 | 40375 | 1.7041 | 0.2385 | 0.1049 | 0.1981 | 0.1981 | 18.9608 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Created
- Apr 8, 2024
- Updated
- Apr 8, 2024