RichardErkhov/RamAnanth1_-_distilgpt2-sd-prompts-gguf
0453
Quantization made by Richard Erkhov.
distilgpt2-sd-prompts - GGUF
- Model creator: https://huggingface.co/RamAnanth1/
- Original model: https://huggingface.co/RamAnanth1/distilgpt2-sd-prompts/
Original model description: --- license: apache-2.0 tags:
- generatedfromtrainer datasets: Gustavosta/Stable-Diffusion-Prompts widget:
- text: A detective of wolfhound model-index:
- name: distilgpt2-sd-prompts results: [] ---
<!-- 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. -->
distilgpt2-sd-prompts
This model is a fine-tuned version of distilgpt2 on Stable-Diffusion-Prompts. It achieves the following results on the evaluation set:
- Loss: 0.9450
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: 0.0005
- trainbatchsize: 32
- evalbatchsize: 32
- seed: 42
- gradientaccumulationsteps: 8
- totaltrainbatch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lrschedulertype: cosine
- lrschedulerwarmup_steps: 500
- num_epochs: 8
- mixedprecisiontraining: Native AMP
Training results
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1