Downloads · 30 days
10
3% of all-time downloads
nekta_ai_v2
webstels/nekta_ai_v2
nekta_ai_v2 is a text generation model from webstels. Use it when you need the model to write or continue text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
370
Public
Repo size
1.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin501 MB · 99%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- gpt2
- Access
- Public
- Created
- Jun 15, 2023
- Updated
- Jun 15, 2023
- SHA
- ae084cdf
Try a prompt
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. -->
nekta_ai_v2
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3819
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 1 | 2.7725 |
| No log | 2.0 | 2 | 2.0761 |
| No log | 3.0 | 3 | 1.6521 |
| No log | 4.0 | 4 | 1.3916 |
| No log | 5.0 | 5 | 1.2775 |
| No log | 6.0 | 6 | 1.1982 |
| No log | 7.0 | 7 | 1.1158 |
| No log | 8.0 | 8 | 1.0482 |
| No log | 9.0 | 9 | 1.0100 |
| No log | 10.0 | 10 | 0.9798 |
| No log | 11.0 | 11 | 0.9576 |
| No log | 12.0 | 12 | 0.9373 |
| No log | 13.0 | 13 | 0.9129 |
| No log | 14.0 | 14 | 0.8900 |
| No log | 15.0 | 15 | 0.8704 |
| No log | 16.0 | 16 | 0.8561 |
| No log | 17.0 | 17 | 0.8436 |
| No log | 18.0 | 18 | 0.8343 |
| No log | 19.0 | 19 | 0.8197 |
| No log | 20.0 | 20 | 0.7882 |
| No log | 21.0 | 21 | 0.7567 |
| No log | 22.0 | 22 | 0.7370 |
| No log | 23.0 | 23 | 0.7239 |
| No log | 24.0 | 24 | 0.7099 |
| No log | 25.0 | 25 | 0.6934 |
| No log | 26.0 | 26 | 0.6758 |
| No log | 27.0 | 27 | 0.6582 |
| No log | 28.0 | 28 | 0.6439 |
| No log | 29.0 | 29 | 0.6290 |
| No log | 30.0 | 30 | 0.6120 |
| No log | 31.0 | 31 | 0.5951 |
| No log | 32.0 | 32 | 0.5779 |
| No log | 33.0 | 33 | 0.5587 |
| No log | 34.0 | 34 | 0.5395 |
| No log | 35.0 | 35 | 0.5184 |
| No log | 36.0 | 36 | 0.4945 |
| No log | 37.0 | 37 | 0.4751 |
| No log | 38.0 | 38 | 0.4597 |
| No log | 39.0 | 39 | 0.4462 |
| No log | 40.0 | 40 | 0.4361 |
| No log | 41.0 | 41 | 0.4264 |
| No log | 42.0 | 42 | 0.4184 |
| No log | 43.0 | 43 | 0.4111 |
| No log | 44.0 | 44 | 0.4064 |
| No log | 45.0 | 45 | 0.4006 |
| No log | 46.0 | 46 | 0.3948 |
| No log | 47.0 | 47 | 0.3892 |
| No log | 48.0 | 48 | 0.3857 |
| No log | 49.0 | 49 | 0.3833 |
| No log | 50.0 | 50 | 0.3819 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cpu
- Tokenizers 0.13.3
- Task
- Text Generation
- Library
- transformers
- Type
- gpt2
- Created
- Jun 15, 2023
- Updated
- Jun 15, 2023