Downloads · 30 days
66
24% of all-time downloads
old-full-lstm-1
CLMBR/old-full-lstm-1
old-full-lstm-1 is a machine learning model from CLMBR. 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
276
Public
Repo size
32.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt21.2 GB · 66%
At a glance
- Library
- transformers
- Model type
- rnn
- Access
- Public
- Created
- Jan 12, 2024
- Updated
- Jan 17, 2024
- SHA
- 254f4966
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. -->
full-lstm-1
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.9726
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: 32
- eval_batch_size: 32
- seed: 1
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 3052726
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.8036 | 0.03 | 76319 | 4.7692 |
| 4.5156 | 0.03 | 152638 | 4.4851 |
| 4.3728 | 1.03 | 228957 | 4.3496 |
| 4.2801 | 0.03 | 305276 | 4.2669 |
| 4.216 | 1.03 | 381595 | 4.2097 |
| 4.1643 | 0.03 | 457914 | 4.1683 |
| 4.1289 | 0.03 | 534233 | 4.1370 |
| 4.1016 | 0.03 | 610552 | 4.1116 |
| 4.0704 | 1.03 | 686871 | 4.0915 |
| 4.0474 | 0.03 | 763190 | 4.0756 |
| 4.0289 | 1.03 | 839509 | 4.0626 |
| 4.0114 | 0.03 | 915828 | 4.0512 |
| 3.9911 | 1.03 | 992147 | 4.0417 |
| 3.9793 | 0.03 | 1068467 | 4.0332 |
| 3.9657 | 1.03 | 1144787 | 4.0265 |
| 3.961 | 0.03 | 1221107 | 4.0183 |
| 3.942 | 1.03 | 1297427 | 4.0134 |
| 3.9346 | 0.03 | 1373747 | 4.0081 |
| 3.9222 | 1.03 | 1450067 | 4.0045 |
| 3.9166 | 0.03 | 1526387 | 4.0005 |
| 3.9154 | 1.03 | 1602707 | 3.9975 |
| 3.9098 | 0.03 | 1679027 | 3.9947 |
| 3.909 | 1.03 | 1755347 | 3.9925 |
| 3.9044 | 0.03 | 1831667 | 3.9899 |
| 3.8977 | 1.03 | 1907987 | 3.9880 |
| 3.8925 | 0.03 | 1984307 | 3.9862 |
| 3.8863 | 1.03 | 2060627 | 3.9841 |
| 3.8797 | 0.03 | 2136947 | 3.9827 |
| 3.8795 | 0.03 | 2213267 | 3.9815 |
| 3.8729 | 0.03 | 2289587 | 3.9806 |
| 3.8659 | 1.03 | 2365907 | 3.9793 |
| 3.862 | 0.03 | 2442227 | 3.9783 |
| 3.8541 | 1.03 | 2518547 | 3.9774 |
| 3.8528 | 0.03 | 2594867 | 3.9767 |
| 3.846 | 1.03 | 2671187 | 3.9760 |
| 3.8445 | 0.03 | 2747507 | 3.9748 |
| 3.848 | 0.03 | 2823827 | 3.9741 |
| 3.8471 | 0.03 | 2900147 | 3.9735 |
| 3.8508 | 1.03 | 2976467 | 3.9729 |
| 3.8512 | 0.02 | 3052726 | 3.9726 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Library
- transformers
- Type
- rnn
- Created
- Jan 12, 2024
- Updated
- Jan 17, 2024