Downloads · 30 days
5
26% of all-time downloads
Mistral-7B_task-2_60-samples_config-2_auto
GaetanMichelet/Mistral-7B_task-2_60-samples_config-2_auto
Mistral-7B_task-2_60-samples_config-2_auto is a machine learning model from GaetanMichelet. 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 apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
19
Public
Repo size
2.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors168 MB · 98%
At a glance
- Library
- peft
- License
- apache-2.0
- Model type
- mistral
- Access
- Public
- Created
- Aug 24, 2024
- Updated
- Aug 24, 2024
- SHA
- 6aa190ba
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. -->
Mistral-7B_task-2_60-samples_config-2_auto
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the GaetanMichelet/chat-60_ft_task-2_auto dataset. It achieves the following results on the evaluation set:
- Loss: 0.4866
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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 16
- total_train_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: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7431 | 0.6957 | 2 | 0.7449 |
| 0.7384 | 1.7391 | 5 | 0.6326 |
| 0.5622 | 2.7826 | 8 | 0.5593 |
| 0.5178 | 3.8261 | 11 | 0.5219 |
| 0.4354 | 4.8696 | 14 | 0.4904 |
| 0.3931 | 5.9130 | 17 | 0.4866 |
| 0.3085 | 6.9565 | 20 | 0.4901 |
| 0.2647 | 8.0 | 23 | 0.5032 |
| 0.2271 | 8.6957 | 25 | 0.5300 |
| 0.1316 | 9.7391 | 28 | 0.6066 |
| 0.11 | 10.7826 | 31 | 0.6682 |
| 0.0479 | 11.8261 | 34 | 0.7445 |
| 0.0271 | 12.8696 | 37 | 0.8261 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Library
- peft
- Type
- mistral
- License
- apache-2.0
- Created
- Aug 24, 2024
- Updated
- Aug 24, 2024