metadata
base_model: unsloth/gemma-2-9b-it-bnb-4bit
library_name: peft
license: gemma
tags:
- generated_from_trainer
model-index:
- name: chatbot-arena-20240726
results: []
chatbot-arena-20240726
This model is a fine-tuned version of unsloth/gemma-2-9b-it-bnb-4bit on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3505
- Acc: 0.4
- Log Loss: 1.3503
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: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Acc | Log Loss |
|---|---|---|---|---|---|
| 1.3608 | 0.3333 | 2 | 1.5601 | 0.2 | 1.5602 |
| 1.4371 | 0.6667 | 4 | 1.6443 | 0.0 | 1.6444 |
| 1.4553 | 1.0 | 6 | 1.8381 | 0.4 | 1.8384 |
| 1.6976 | 1.3333 | 8 | 1.0593 | 0.4 | 1.0591 |
| 1.0222 | 1.6667 | 10 | 1.1011 | 0.0 | 1.1012 |
| 1.0382 | 2.0 | 12 | 1.3505 | 0.4 | 1.3503 |
Framework versions
- PEFT 0.11.1
- Transformers 4.42.4
- Pytorch 2.1.1+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1