gemma7b-summarize-gemini1_5flash-128k
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: 2.4815
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 |
|---|---|---|---|
| 1.067 | 1.0 | 208 | 2.5660 |
| 0.9432 | 2.0 | 416 | 2.4475 |
| 0.9222 | 3.0 | 624 | 2.4423 |
| 0.8069 | 4.0 | 832 | 2.4327 |
| 0.7635 | 5.0 | 1040 | 2.4233 |
| 0.7364 | 6.0 | 1248 | 2.4451 |
| 0.7168 | 7.0 | 1456 | 2.4510 |
| 0.7064 | 8.0 | 1664 | 2.4729 |
| 0.6934 | 9.0 | 1872 | 2.4781 |
| 0.7018 | 10.0 | 2080 | 2.4815 |
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
- 0
Model tree for llama-duo/gemma7b-summarize-gemini1_5flash-128k
Base model
google/gemma-7b