metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: rishiraj/CatPPT
model-index:
- name: cat_no_robots_english
results: []
cat_no_robots_english
This model is a fine-tuned version of rishiraj/CatPPT on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7261
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: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 8
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6225 | 0.12 | 100 | 1.7549 |
| 1.4886 | 0.24 | 200 | 1.7485 |
| 1.6488 | 0.37 | 300 | 1.7422 |
| 1.7647 | 0.49 | 400 | 1.7345 |
| 1.7318 | 0.61 | 500 | 1.7324 |
| 1.6355 | 0.73 | 600 | 1.7296 |
| 1.5116 | 0.86 | 700 | 1.7271 |
| 1.4797 | 0.98 | 800 | 1.7261 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.0
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0