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-4k
results: []
gemma7b-summarize-gpt4o-4k
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: 4.0658
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 |
---|---|---|---|
16.725 | 0.9804 | 25 | 6.5520 |
1.5122 | 2.0 | 51 | 2.6626 |
1.1154 | 2.9804 | 76 | 2.5917 |
0.9204 | 4.0 | 102 | 2.6570 |
0.779 | 4.9804 | 127 | 2.7498 |
0.6207 | 6.0 | 153 | 2.9976 |
0.4762 | 6.9804 | 178 | 3.4668 |
0.3908 | 8.0 | 204 | 3.8246 |
0.3418 | 8.9804 | 229 | 4.0561 |
0.3252 | 9.8039 | 250 | 4.0658 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1