Downloads · 30 days
3
5% of all-time downloads
Ministral-8B-Instruct-2410-JEP
raulgdp/Ministral-8B-Instruct-2410-JEP
Ministral-8B-Instruct-2410-JEP is a machine learning model from raulgdp. 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 other.
should probably proofread and complete it, then remove this comment. --
All-time downloads
55
Public
Repo size
2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors30.7 MB · 64%
At a glance
- Library
- peft
- License
- other
- Access
- Public
- Created
- Apr 19, 2025
- Updated
- Apr 19, 2025
- SHA
- 5358af24
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. -->
Ministral-8B-Instruct-2410-JEP
This model is a fine-tuned version of mistralai/Ministral-8B-Instruct-2410 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1977
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3744 | 0.1535 | 100 | 1.3521 |
| 1.287 | 0.3070 | 200 | 1.2976 |
| 1.2346 | 0.4605 | 300 | 1.2699 |
| 1.2384 | 0.6140 | 400 | 1.2527 |
| 1.2937 | 0.7675 | 500 | 1.2421 |
| 1.2046 | 0.9210 | 600 | 1.2340 |
| 1.1915 | 1.0737 | 700 | 1.2277 |
| 1.2159 | 1.2272 | 800 | 1.2253 |
| 1.1631 | 1.3807 | 900 | 1.2206 |
| 1.1935 | 1.5342 | 1000 | 1.2162 |
| 1.1701 | 1.6876 | 1100 | 1.2129 |
| 1.1925 | 1.8411 | 1200 | 1.2067 |
| 1.2215 | 1.9946 | 1300 | 1.2037 |
| 1.1858 | 2.1474 | 1400 | 1.2032 |
| 1.1737 | 2.3008 | 1500 | 1.2008 |
| 1.1751 | 2.4543 | 1600 | 1.1988 |
| 1.1514 | 2.6078 | 1700 | 1.1957 |
| 1.1327 | 2.7613 | 1800 | 1.1930 |
| 1.1266 | 2.9148 | 1900 | 1.1906 |
| 1.0929 | 3.0675 | 2000 | 1.1909 |
| 1.1054 | 3.2210 | 2100 | 1.1913 |
| 1.1097 | 3.3745 | 2200 | 1.1896 |
| 1.2006 | 3.5280 | 2300 | 1.1869 |
| 1.1605 | 3.6815 | 2400 | 1.1839 |
| 1.1155 | 3.8350 | 2500 | 1.1844 |
| 1.1481 | 3.9885 | 2600 | 1.1836 |
| 1.1011 | 4.1412 | 2700 | 1.1878 |
| 1.0627 | 4.2947 | 2800 | 1.1897 |
| 1.1387 | 4.4482 | 2900 | 1.1863 |
| 1.0656 | 4.6017 | 3000 | 1.1826 |
| 1.0951 | 4.7552 | 3100 | 1.1837 |
| 1.0806 | 4.9087 | 3200 | 1.1795 |
| 1.0508 | 5.0614 | 3300 | 1.1830 |
| 1.1051 | 5.2149 | 3400 | 1.1876 |
| 1.0061 | 5.3684 | 3500 | 1.1894 |
| 1.1471 | 5.5219 | 3600 | 1.1811 |
| 1.1143 | 5.6754 | 3700 | 1.1833 |
| 1.1146 | 5.8289 | 3800 | 1.1823 |
| 1.0648 | 5.9823 | 3900 | 1.1837 |
| 1.062 | 6.1351 | 4000 | 1.1903 |
| 1.065 | 6.2886 | 4100 | 1.1877 |
| 1.0379 | 6.4421 | 4200 | 1.1875 |
| 1.0188 | 6.5955 | 4300 | 1.1873 |
| 1.0332 | 6.7490 | 4400 | 1.1850 |
| 1.026 | 6.9025 | 4500 | 1.1854 |
| 1.0365 | 7.0553 | 4600 | 1.1897 |
| 1.0359 | 7.2087 | 4700 | 1.1928 |
| 1.0483 | 7.3622 | 4800 | 1.1921 |
| 0.9988 | 7.5157 | 4900 | 1.1914 |
| 1.0348 | 7.6692 | 5000 | 1.1893 |
| 0.9884 | 7.8227 | 5100 | 1.1879 |
| 1.0903 | 7.9762 | 5200 | 1.1890 |
| 0.9946 | 8.1289 | 5300 | 1.1942 |
| 1.0328 | 8.2824 | 5400 | 1.1941 |
| 1.0031 | 8.4359 | 5500 | 1.1949 |
| 0.9096 | 8.5894 | 5600 | 1.1946 |
| 1.018 | 8.7429 | 5700 | 1.1939 |
| 1.0533 | 8.8964 | 5800 | 1.1920 |
| 0.9476 | 9.0491 | 5900 | 1.1967 |
| 0.9817 | 9.2026 | 6000 | 1.1989 |
| 0.9774 | 9.3561 | 6100 | 1.1987 |
| 1.0092 | 9.5096 | 6200 | 1.1974 |
| 1.0067 | 9.6631 | 6300 | 1.1977 |
| 1.0243 | 9.8166 | 6400 | 1.1983 |
| 0.9359 | 9.9701 | 6500 | 1.1977 |
Framework versions
- PEFT 0.15.2
- Transformers 4.51.3
- Pytorch 2.6.0+cu126
- Datasets 3.5.0
- Tokenizers 0.21.1
- Library
- peft
- License
- other
- Created
- Apr 19, 2025
- Updated
- Apr 19, 2025