Downloads · 30 days
0
falcon-rewrite-581-smallset
sherryzha/falcon-rewrite-581-smallset
falcon-rewrite-581-smallset is a machine learning model from sherryzha. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated Dec 16, 2023
Repo size
5.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin66 MB · 96%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Oct 28, 2023
- Updated
- Dec 16, 2023
- SHA
- a0f191fd
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. -->
falcon-rewrite-581-smallset
This model is a fine-tuned version of tiiuae/falcon-7b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8491
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: 0.0005
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.4549 | 0.04 | 10 | 2.5081 |
| 1.9707 | 0.08 | 20 | 2.3356 |
| 1.6966 | 0.13 | 30 | 2.1397 |
| 1.5642 | 0.17 | 40 | 2.2513 |
| 1.409 | 0.21 | 50 | 2.2261 |
| 3.0587 | 0.25 | 60 | 2.2444 |
| 1.6063 | 0.3 | 70 | 2.1045 |
| 1.7254 | 0.34 | 80 | 2.3067 |
| 1.9013 | 0.38 | 90 | 2.1563 |
| 1.4663 | 0.42 | 100 | 2.0248 |
| 2.0913 | 0.47 | 110 | 2.2581 |
| 2.2229 | 0.51 | 120 | 2.1673 |
| 2.7343 | 0.55 | 130 | 1.9779 |
| 2.0081 | 0.59 | 140 | 2.0840 |
| 0.9549 | 0.64 | 150 | 2.1129 |
| 1.8275 | 0.68 | 160 | 1.9253 |
| 2.2735 | 0.72 | 170 | 2.1204 |
| 2.2702 | 0.76 | 180 | 2.2248 |
| 1.015 | 0.81 | 190 | 2.0940 |
| 0.9042 | 0.85 | 200 | 1.8826 |
| 1.172 | 0.89 | 210 | 2.0679 |
| 1.136 | 0.93 | 220 | 1.8751 |
| 1.0424 | 0.97 | 230 | 1.8596 |
| 0.9668 | 1.02 | 240 | 2.0500 |
| 2.2238 | 1.06 | 250 | 1.9991 |
| 1.5063 | 1.1 | 260 | 1.8657 |
| 1.5397 | 1.14 | 270 | 1.8491 |
| 1.4312 | 1.19 | 280 | 2.1349 |
| 2.1914 | 1.23 | 290 | 2.2101 |
| 1.0044 | 1.27 | 300 | 1.9527 |
| 2.1416 | 1.31 | 310 | 1.9139 |
| 1.7783 | 1.36 | 320 | 1.9060 |
| 0.7976 | 1.4 | 330 | 2.2042 |
| 0.9139 | 1.44 | 340 | 1.9813 |
| 1.7734 | 1.48 | 350 | 2.1706 |
| 0.875 | 1.53 | 360 | 2.1350 |
| 0.9744 | 1.57 | 370 | 1.9577 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
- License
- apache-2.0
- Created
- Oct 28, 2023
- Updated
- Dec 16, 2023