Downloads · 30 days
7
19% of all-time downloads
mistral7binstruct_summarize
HeRksTAn/mistral7binstruct_summarize
mistral7binstruct_summarize is a machine learning model from HeRksTAn. 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
37
Public
Repo size
150 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json1.8 MB · 99%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Feb 28, 2024
- Updated
- Mar 4, 2024
- SHA
- 96f6c1bd
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. -->
mistral7binstruct_summarize
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.6323
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: 2
- total_train_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.03
- training_steps: 150
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.5172 | 0.02 | 5 | 2.3926 |
| 2.2822 | 0.04 | 10 | 2.1537 |
| 2.1109 | 0.06 | 15 | 2.0087 |
| 1.8571 | 0.08 | 20 | 1.9020 |
| 1.8964 | 0.11 | 25 | 1.8310 |
| 1.7335 | 0.13 | 30 | 1.7901 |
| 1.7744 | 0.15 | 35 | 1.7607 |
| 1.8654 | 0.17 | 40 | 1.7396 |
| 1.7379 | 0.19 | 45 | 1.7235 |
| 1.7442 | 0.21 | 50 | 1.7113 |
| 1.6483 | 0.23 | 55 | 1.7011 |
| 1.7006 | 0.25 | 60 | 1.6919 |
| 1.6783 | 0.28 | 65 | 1.6833 |
| 1.6468 | 0.3 | 70 | 1.6754 |
| 1.6116 | 0.32 | 75 | 1.6678 |
| 1.5899 | 0.34 | 80 | 1.6605 |
| 1.7426 | 0.36 | 85 | 1.6538 |
| 1.7244 | 0.38 | 90 | 1.6491 |
| 1.6652 | 0.4 | 95 | 1.6457 |
| 1.7859 | 0.42 | 100 | 1.6422 |
| 1.5836 | 0.44 | 105 | 1.6395 |
| 1.6265 | 0.47 | 110 | 1.6374 |
| 1.5187 | 0.49 | 115 | 1.6358 |
| 1.5989 | 0.51 | 120 | 1.6345 |
| 1.684 | 0.53 | 125 | 1.6336 |
| 1.6257 | 0.55 | 130 | 1.6329 |
| 1.7211 | 0.57 | 135 | 1.6325 |
| 1.6235 | 0.59 | 140 | 1.6324 |
| 1.5885 | 0.61 | 145 | 1.6323 |
| 1.5885 | 0.64 | 150 | 1.6323 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Library
- peft
- License
- apache-2.0
- Created
- Feb 28, 2024
- Updated
- Mar 4, 2024