Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,38 @@
|
|
1 |
---
|
2 |
license: cc-by-nc-4.0
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: cc-by-nc-4.0
|
3 |
---
|
4 |
+
## DAVinCI-42dot_LLM-PLM-1.3B-v1.2
|
5 |
+
|
6 |
+
This model is a fine-tuned version of [42dot/42dot_LLM-PLM-1.3B](https://huggingface.co/42dot/42dot_LLM-PLM-1.3B) on a custom dataset.
|
7 |
+
|
8 |
+
### Model description
|
9 |
+
More information needed
|
10 |
+
|
11 |
+
### Intended uses & limitations
|
12 |
+
More information needed
|
13 |
+
|
14 |
+
### Training and evaluation data
|
15 |
+
More information needed
|
16 |
+
|
17 |
+
### Training procedure
|
18 |
+
|
19 |
+
### Training hyperparameters
|
20 |
+
The following hyperparameters were used during training:
|
21 |
+
* learning_rate: 2e-05
|
22 |
+
* train_batch_size: 24
|
23 |
+
* eval_batch_size: 8
|
24 |
+
* seed: 42
|
25 |
+
* gradient_accumulation_steps: 4
|
26 |
+
* total_train_batch_size: 96
|
27 |
+
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
28 |
+
* lr_scheduler_type: linear
|
29 |
+
* num_epochs: 1.0
|
30 |
+
* mixed_precision_training: Native AMP
|
31 |
+
|
32 |
+
### Training results
|
33 |
+
|
34 |
+
### Framework versions
|
35 |
+
* Transformers 4.36.2
|
36 |
+
* Pytorch 2.1.2+cu121
|
37 |
+
* Datasets 2.0.0
|
38 |
+
* Tokenizers 0.15.0
|