Downloads · 30 days
4
12% of all-time downloads
mistral_sparse_80_percent_cola_1000
thrunlab/mistral_sparse_80_percent_cola_1000
mistral_sparse_80_percent_cola_1000 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.
should probably proofread and complete it, then remove this comment. --
All-time downloads
34
Public
Parameters
7.2B
48.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors14.7 GB · 100%
At a glance
- Library
- transformers
- Model type
- mistral
- Access
- Public
- Created
- Feb 6, 2024
- Updated
- Feb 6, 2024
- SHA
- 3ab03233
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_1000
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3726
- Accuracy: 0.8441
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: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- total_eval_batch_size: 32
- 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 |
|---|---|---|---|---|
| 0.4653 | 0.22 | 50 | 0.5302 | 0.7405 |
| 0.5191 | 0.44 | 100 | 0.4846 | 0.7638 |
| 0.5233 | 0.66 | 150 | 0.4720 | 0.7701 |
| 0.4905 | 0.88 | 200 | 0.4463 | 0.7802 |
| 0.3672 | 1.1 | 250 | 0.4354 | 0.7927 |
| 0.3929 | 1.32 | 300 | 0.4171 | 0.8028 |
| 0.3643 | 1.54 | 350 | 0.4110 | 0.7997 |
| 0.324 | 1.76 | 400 | 0.3927 | 0.8231 |
| 0.3639 | 1.98 | 450 | 0.4550 | 0.7747 |
| 0.3293 | 2.2 | 500 | 0.4191 | 0.8309 |
| 0.3072 | 2.42 | 550 | 0.4059 | 0.8184 |
| 0.3131 | 2.64 | 600 | 0.3780 | 0.8363 |
| 0.3821 | 2.86 | 650 | 0.3804 | 0.8301 |
| 0.2741 | 3.08 | 700 | 0.3789 | 0.8394 |
| 0.258 | 3.3 | 750 | 0.3984 | 0.8394 |
| 0.2316 | 3.52 | 800 | 0.3998 | 0.8363 |
| 0.1955 | 3.74 | 850 | 0.3799 | 0.8465 |
| 0.2266 | 3.96 | 900 | 0.3750 | 0.8426 |
| 0.1476 | 4.18 | 950 | 0.4402 | 0.8332 |
| 0.1088 | 4.4 | 1000 | 0.4813 | 0.8316 |
| 0.1872 | 4.62 | 1050 | 0.4342 | 0.8410 |
| 0.1248 | 4.84 | 1100 | 0.4700 | 0.8472 |
| 0.108 | 5.05 | 1150 | 0.4632 | 0.8472 |
| 0.1437 | 5.27 | 1200 | 0.6568 | 0.8387 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Library
- transformers
- Type
- mistral
- Created
- Feb 6, 2024
- Updated
- Feb 6, 2024