Downloads · 30 days
7
23% of all-time downloads
t5-small-finetuned-manimml-1.1
keenhas/t5-small-finetuned-manimml-1.1
t5-small-finetuned-manimml-1.1 is a machine learning model from keenhas. 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
31
Public
Parameters
60.5M
485 MB 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
- Mar 26, 2024
- Updated
- Mar 26, 2024
- SHA
- 56e95ac4
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. -->
t5-small-finetuned-manimml-1.1
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0666
- Rouge1: 29.0954
- Rouge2: 22.9204
- Rougel: 29.0159
- Rougelsum: 29.1088
- Gen Len: 19.0
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: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 51 | 0.4260 | 25.6666 | 14.8192 | 25.0334 | 25.0395 | 19.0 |
| No log | 2.0 | 102 | 0.2263 | 28.3534 | 19.9722 | 27.7234 | 27.7846 | 19.0 |
| No log | 3.0 | 153 | 0.1529 | 28.2871 | 21.5089 | 28.1105 | 28.1893 | 19.0 |
| No log | 4.0 | 204 | 0.1180 | 28.8519 | 22.6105 | 28.7357 | 28.8292 | 19.0 |
| No log | 5.0 | 255 | 0.1001 | 29.0422 | 22.7932 | 28.9131 | 29.0146 | 19.0 |
| No log | 6.0 | 306 | 0.0915 | 29.0461 | 22.8255 | 28.9195 | 29.0204 | 19.0 |
| No log | 7.0 | 357 | 0.0853 | 29.0679 | 22.8469 | 28.9357 | 29.0362 | 19.0 |
| No log | 8.0 | 408 | 0.0779 | 29.0442 | 22.9108 | 28.9699 | 29.0709 | 19.0 |
| No log | 9.0 | 459 | 0.0752 | 29.0642 | 22.91 | 28.989 | 29.0853 | 19.0 |
| 0.395 | 10.0 | 510 | 0.0720 | 29.0642 | 22.9216 | 28.989 | 29.0853 | 19.0 |
| 0.395 | 11.0 | 561 | 0.0697 | 29.0642 | 22.9216 | 28.989 | 29.0853 | 19.0 |
| 0.395 | 12.0 | 612 | 0.0683 | 29.0642 | 22.9216 | 28.989 | 29.0853 | 19.0 |
| 0.395 | 13.0 | 663 | 0.0676 | 29.0954 | 22.9204 | 29.0159 | 29.1088 | 19.0 |
| 0.395 | 14.0 | 714 | 0.0669 | 29.0954 | 22.9204 | 29.0159 | 29.1088 | 19.0 |
| 0.395 | 15.0 | 765 | 0.0666 | 29.0954 | 22.9204 | 29.0159 | 29.1088 | 19.0 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Created
- Mar 26, 2024
- Updated
- Mar 26, 2024