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-2k
results: []
gemma7b-summarize-gpt4o-2k
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: 3.2983
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 |
---|---|---|---|
23.4809 | 1.0 | 13 | 8.2506 |
7.0034 | 2.0 | 26 | 3.5645 |
1.9278 | 3.0 | 39 | 2.7831 |
1.3284 | 4.0 | 52 | 2.7295 |
1.046 | 5.0 | 65 | 2.7647 |
0.8611 | 6.0 | 78 | 2.8629 |
0.7242 | 7.0 | 91 | 3.0405 |
0.6192 | 8.0 | 104 | 3.1549 |
0.5312 | 9.0 | 117 | 3.3041 |
0.5202 | 10.0 | 130 | 3.2983 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1