gemma7b-summarize-gemini1_5flash-16k
This model is a fine-tuned version of google/gemma-7b on the llama-duo/synth_summarize_dataset_dedup dataset. It achieves the following results on the evaluation set:
- Loss: 2.6632
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: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 16
- 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 |
|---|---|---|---|
| 20.3933 | 0.9811 | 26 | 7.9476 |
| 5.2781 | 2.0 | 53 | 4.2830 |
| 1.5712 | 2.9811 | 79 | 2.9235 |
| 1.2696 | 4.0 | 106 | 2.7524 |
| 1.1842 | 4.9811 | 132 | 2.7035 |
| 1.1359 | 6.0 | 159 | 2.6779 |
| 1.1053 | 6.9811 | 185 | 2.6764 |
| 1.0828 | 8.0 | 212 | 2.6683 |
| 1.0853 | 8.9811 | 238 | 2.6656 |
| 1.0794 | 9.8113 | 260 | 2.6632 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for llama-duo/gemma7b-summarize-gemini1_5flash-16k
Base model
google/gemma-7b