metadata
base_model: google/gemma-2b-it
datasets:
- generator
library_name: peft
license: gemma
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: new_genna_nodel
results: []
new_genna_nodel
This model is a fine-tuned version of google/gemma-2b-it on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 2.7368
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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.335 | 1.0 | 649 | 2.4869 |
| 2.1888 | 2.0 | 1298 | 2.5154 |
| 2.0938 | 3.0 | 1947 | 2.5809 |
| 1.9877 | 4.0 | 2596 | 2.6546 |
| 1.8859 | 5.0 | 3245 | 2.7368 |
Framework versions
- PEFT 0.12.1.dev0
- Transformers 4.45.0.dev0
- Pytorch 2.1.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1