|
--- |
|
license: other |
|
datasets: |
|
- Open-Orca/OpenOrca |
|
- ehartford/wizard_vicuna_70k_unfiltered |
|
tags: |
|
- code |
|
- prompt |
|
- reverse prompt |
|
widget: |
|
- text: "Photosynthesis is the process by which plants, algae and some bacteria convert carbon dioxide and water into glucose and oxygen, using the energy of sunlight. This process is fundamental to life on Earth, as it provides the basis for almost all food chains and also contributes to the carbon cycle by helping to regulate the concentration of carbon dioxide in the atmosphere. \n[REVERSED-PROMPT]" |
|
example_title: "reverse prompt" |
|
|
|
--- |
|
# PREVIEW - training will end 4/9 |
|
commit a87a7a188022bec44cffcb3ae9c250b8bacf7dd3 seems to be more stable than the lasts commits, the next one I will post only at 6/9 |
|
# core-prompt-reverser-opt-1.3b |
|
|
|
This model is a fine-tuned version of facebook/opt-1.3b on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.2950 |
|
- Accuracy: 0.7084 |
|
|
|
|
|
## 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: 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: 1.0 |
|
|
|
### Training results |
|
|
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.0.dev0 |
|
- Pytorch 2.1.0.dev20230605+cu121 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
