metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
base_model: rishiraj/CatPPT-base
model-index:
- name: catppt_2
results: []
catppt_2
This model is a fine-tuned version of rishiraj/CatPPT-base on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.3328
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 130
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7962 | 0.97 | 10 | 1.1737 |
| 1.0723 | 1.94 | 20 | 0.9357 |
| 0.8491 | 2.91 | 30 | 0.7148 |
| 0.6214 | 3.88 | 40 | 0.5303 |
| 0.4837 | 4.85 | 50 | 0.4475 |
| 0.4223 | 5.82 | 60 | 0.4044 |
| 0.3822 | 6.79 | 70 | 0.3762 |
| 0.3575 | 7.76 | 80 | 0.3568 |
| 0.3477 | 8.73 | 90 | 0.3449 |
| 0.3283 | 9.7 | 100 | 0.3368 |
| 0.3254 | 10.67 | 110 | 0.3337 |
| 0.3177 | 11.64 | 120 | 0.3328 |
| 0.3299 | 12.61 | 130 | 0.3328 |
Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.38.1
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0