metadata
license: gemma
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: google/gemma-7b
datasets:
- generator
model-index:
- name: gemma7b-summarize-gpt4o-1k
results: []
gemma7b-summarize-gpt4o-1k
This model is a fine-tuned version of google/gemma-7b on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 2.8104
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
- distributed_type: multi-GPU
- num_devices: 2
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 37.3003 | 0.9231 | 6 | 12.3240 |
| 21.0453 | 2.0 | 13 | 7.5884 |
| 17.809 | 2.9231 | 19 | 5.6549 |
| 3.5386 | 4.0 | 26 | 3.1607 |
| 2.02 | 4.9231 | 32 | 2.8709 |
| 1.732 | 6.0 | 39 | 2.7893 |
| 1.4072 | 6.9231 | 45 | 2.7970 |
| 1.3061 | 8.0 | 52 | 2.8125 |
| 1.2613 | 8.9231 | 58 | 2.8098 |
| 1.2304 | 9.2308 | 60 | 2.8104 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1