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-80k
results: []
gemma7b-summarize-gpt4o-80k
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: 2.9801
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: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- total_eval_batch_size: 4
- 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 |
|---|---|---|---|
| 0.9152 | 0.9982 | 275 | 2.1950 |
| 0.8104 | 2.0 | 551 | 2.1405 |
| 0.7914 | 2.9982 | 826 | 2.1592 |
| 0.6978 | 4.0 | 1102 | 2.2176 |
| 0.6386 | 4.9982 | 1377 | 2.3272 |
| 0.5725 | 6.0 | 1653 | 2.4713 |
| 0.5089 | 6.9982 | 1928 | 2.6491 |
| 0.4678 | 8.0 | 2204 | 2.8434 |
| 0.433 | 8.9982 | 2479 | 2.9604 |
| 0.4229 | 9.9819 | 2750 | 2.9801 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1