|
--- |
|
license: apache-2.0 |
|
base_model: tiiuae/falcon-7b |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: falcon-rewrite-581-smallset |
|
results: [] |
|
--- |
|
|
|
<!-- 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](https://huggingface.co/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 |
|
|
