Downloads · 30 days
9
30% of all-time downloads
mistral_sparse_80_percent_cola_raw
thrunlab/mistral_sparse_80_percent_cola_raw
mistral_sparse_80_percent_cola_raw is a machine learning model from thrunlab. 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 transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
30
Public
Parameters
7.2B
17 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors14.7 GB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- mistral
- Access
- Public
- Created
- Feb 5, 2024
- Updated
- Feb 5, 2024
- SHA
- 46b29c9e
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_sparse_80_percent_cola_raw
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3881
- Accuracy: 0.8309
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 0
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4842 | 0.22 | 25 | 0.5429 | 0.7319 |
| 0.5152 | 0.44 | 50 | 0.5166 | 0.7451 |
| 0.4976 | 0.66 | 75 | 0.5337 | 0.7311 |
| 0.4889 | 0.88 | 100 | 0.4847 | 0.7631 |
| 0.4781 | 1.1 | 125 | 0.4716 | 0.7747 |
| 0.4421 | 1.32 | 150 | 0.4569 | 0.7786 |
| 0.4289 | 1.54 | 175 | 0.4589 | 0.7849 |
| 0.4495 | 1.75 | 200 | 0.4373 | 0.7911 |
| 0.417 | 1.97 | 225 | 0.4308 | 0.7903 |
| 0.3719 | 2.19 | 250 | 0.4528 | 0.7950 |
| 0.3746 | 2.41 | 275 | 0.4242 | 0.8114 |
| 0.3942 | 2.63 | 300 | 0.4137 | 0.8176 |
| 0.3603 | 2.85 | 325 | 0.4021 | 0.8215 |
| 0.3509 | 3.07 | 350 | 0.4043 | 0.8184 |
| 0.2865 | 3.29 | 375 | 0.4222 | 0.8277 |
| 0.352 | 3.51 | 400 | 0.4311 | 0.8145 |
| 0.2957 | 3.73 | 425 | 0.3978 | 0.8332 |
| 0.3338 | 3.95 | 450 | 0.3887 | 0.8231 |
| 0.2342 | 4.17 | 475 | 0.4616 | 0.8348 |
| 0.2424 | 4.39 | 500 | 0.4019 | 0.8301 |
| 0.2543 | 4.61 | 525 | 0.4011 | 0.8355 |
| 0.2055 | 4.82 | 550 | 0.4132 | 0.8316 |
| 0.1853 | 5.04 | 575 | 0.3987 | 0.8402 |
| 0.2035 | 5.26 | 600 | 0.4507 | 0.8324 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Created
- Feb 5, 2024
- Updated
- Feb 5, 2024