metadata
license: gemma
base_model: google/gemma-7b
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- masakhane/african-ultrachat
- untrachat_en
- sd
model-index:
- name: zephyr-7b-gemma-sft-african-ultraalpaca
results: []
zephyr-7b-gemma-sft-african-ultraalpaca
This model is a fine-tuned version of google/gemma-7b
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0034 | 1.0 | 23628 | 1.0630 |
| 0.6403 | 2.0 | 47257 | 0.8788 |
| 0.2976 | 3.0 | 70884 | 0.8875 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2