Downloads · 30 days
9
32% of all-time downloads
mistral7b_instruct_generation
mitultiwari/mistral7b_instruct_generation
mistral7b_instruct_generation is a machine learning model from mitultiwari. 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
28
Public
Repo size
24.5 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json1.8 MB · 98%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Jan 29, 2024
- Updated
- Jan 29, 2024
- SHA
- aa639172
Base models
Datasets
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. -->
mistral7b_instruct_generation
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.7938
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7581 | 0.0 | 20 | 1.8261 |
| 1.8319 | 0.01 | 40 | 1.7927 |
| 1.7686 | 0.01 | 60 | 1.7898 |
| 1.846 | 0.01 | 80 | 1.7932 |
| 1.8539 | 0.01 | 100 | 1.7876 |
| 1.8364 | 0.02 | 120 | 1.7909 |
| 1.8257 | 0.02 | 140 | 1.7919 |
| 1.8652 | 0.02 | 160 | 1.8286 |
| 1.8587 | 0.03 | 180 | 1.8063 |
| 1.8607 | 0.03 | 200 | 1.7983 |
| 1.7993 | 0.03 | 220 | 1.7921 |
| 1.9047 | 0.03 | 240 | 1.7946 |
| 1.8314 | 0.04 | 260 | 1.7951 |
| 1.8249 | 0.04 | 280 | 1.7943 |
| 1.7954 | 0.04 | 300 | 1.7982 |
| 1.7981 | 0.04 | 320 | 1.7943 |
| 1.8316 | 0.05 | 340 | 1.7925 |
| 1.9764 | 0.05 | 360 | 1.8037 |
| 1.9152 | 0.05 | 380 | 1.7945 |
| 1.9301 | 0.06 | 400 | 1.8024 |
| 1.7994 | 0.06 | 420 | 1.7896 |
| 1.8697 | 0.06 | 440 | 1.7986 |
| 1.8057 | 0.06 | 460 | 1.7983 |
| 1.8194 | 0.07 | 480 | 1.7940 |
| 1.9606 | 0.07 | 500 | 1.7938 |
Framework versions
- PEFT 0.7.1
- Transformers 4.37.1
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
- Library
- peft
- License
- apache-2.0
- Created
- Jan 29, 2024
- Updated
- Jan 29, 2024