Update README.md
Browse files
README.md
CHANGED
@@ -19,40 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
19 |
|
20 |
This model is a fine-tuned version of [LDCC/LDCC-SOLAR-10.7B](https://huggingface.co/LDCC/LDCC-SOLAR-10.7B) on the generator dataset.
|
21 |
|
22 |
-
|
23 |
-
|
24 |
-
More information needed
|
25 |
-
|
26 |
-
## Intended uses & limitations
|
27 |
-
|
28 |
-
More information needed
|
29 |
-
|
30 |
-
## Training and evaluation data
|
31 |
-
|
32 |
-
More information needed
|
33 |
-
|
34 |
-
## Training procedure
|
35 |
-
|
36 |
-
### Training hyperparameters
|
37 |
-
|
38 |
-
The following hyperparameters were used during training:
|
39 |
-
- learning_rate: 1e-06
|
40 |
-
- train_batch_size: 1
|
41 |
-
- eval_batch_size: 8
|
42 |
-
- seed: 42
|
43 |
-
- distributed_type: multi-GPU
|
44 |
-
- num_devices: 7
|
45 |
-
- gradient_accumulation_steps: 16
|
46 |
-
- total_train_batch_size: 112
|
47 |
-
- total_eval_batch_size: 56
|
48 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
-
- lr_scheduler_type: cosine
|
50 |
-
- lr_scheduler_warmup_ratio: 0.03
|
51 |
-
- num_epochs: 2
|
52 |
-
|
53 |
-
### Training results
|
54 |
-
|
55 |
-
|
56 |
|
57 |
### Framework versions
|
58 |
|
|
|
19 |
|
20 |
This model is a fine-tuned version of [LDCC/LDCC-SOLAR-10.7B](https://huggingface.co/LDCC/LDCC-SOLAR-10.7B) on the generator dataset.
|
21 |
|
22 |
+
* dataset: leaderboard dataset 1.3 + open-Hermes dataset(ko-mt)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
|
24 |
### Framework versions
|
25 |
|