Downloads · 30 days
20
31% of all-time downloads
chessgpt2-medium-s
dakwi/chessgpt2-medium-s
chessgpt2-medium-s is a text generation model from dakwi. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
65
Public
Parameters
303M
14.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.2 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- mit
- Model type
- gpt2
- Access
- Public
- Created
- Oct 10, 2024
- Updated
- Oct 11, 2024
- SHA
- 989081ae
Try a prompt
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. -->
chessgpt2-medium-s
This model is a fine-tuned version of gpt2-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0790
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: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.025
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.3553 | 0.2560 | 1000 | 1.7539 |
| 1.6483 | 0.5119 | 2000 | 1.4751 |
| 1.4597 | 0.7679 | 3000 | 1.3417 |
| 1.3504 | 1.0238 | 4000 | 1.2587 |
| 1.2717 | 1.2798 | 5000 | 1.2104 |
| 1.2263 | 1.5357 | 6000 | 1.1654 |
| 1.1899 | 1.7917 | 7000 | 1.1346 |
| 1.154 | 2.0476 | 8000 | 1.1105 |
| 1.1124 | 2.3036 | 9000 | 1.0941 |
| 1.1002 | 2.5595 | 10000 | 1.0835 |
| 1.093 | 2.8155 | 11000 | 1.0790 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1
- Task
- Text Generation
- Library
- transformers
- Type
- gpt2
- License
- mit
- Created
- Oct 10, 2024
- Updated
- Oct 11, 2024