Downloads · 30 days
28
35% of all-time downloads
gemma7b-summarize-gpt4o-30k
llama-duo/gemma7b-summarize-gpt4o-30k
gemma7b-summarize-gpt4o-30k is a machine learning model from llama-duo. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as gemma.
should probably proofread and complete it, then remove this comment. --
All-time downloads
79
Public
Repo size
1.1 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors50.1 MB · 74%
At a glance
- Library
- peft
- License
- gemma
- Model type
- gemma
- Access
- Public
- Created
- May 19, 2024
- Updated
- May 21, 2024
- SHA
- e55b5ff6
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
gemma7b-summarize-gpt4o-30k
This model is a fine-tuned version of google/gemma-7b on the llama-duo/synth_summarize_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 3.2430
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 |
|---|---|---|---|
| 1.1572 | 1.0 | 111 | 2.3072 |
| 0.9296 | 2.0 | 222 | 2.1789 |
| 0.8273 | 3.0 | 333 | 2.1709 |
| 0.7586 | 4.0 | 444 | 2.2164 |
| 0.6613 | 5.0 | 555 | 2.3182 |
| 0.577 | 6.0 | 666 | 2.4774 |
| 0.4958 | 7.0 | 777 | 2.7036 |
| 0.4205 | 8.0 | 888 | 2.9689 |
| 0.382 | 9.0 | 999 | 3.2252 |
| 0.372 | 10.0 | 1110 | 3.2430 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Library
- peft
- Type
- gemma
- License
- gemma
- Created
- May 19, 2024
- Updated
- May 21, 2024