young lee
commited on
Commit
•
15f3f74
1
Parent(s):
4b5df21
Training complete
Browse files
README.md
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: Helsinki-NLP/opus-mt-tc-big-en-ko
|
3 |
+
datasets:
|
4 |
+
- kde4
|
5 |
+
library_name: peft
|
6 |
+
license: cc-by-4.0
|
7 |
+
metrics:
|
8 |
+
- bleu
|
9 |
+
tags:
|
10 |
+
- tanslation
|
11 |
+
- generated_from_trainer
|
12 |
+
model-index:
|
13 |
+
- name: finetuned-kde4-en-to-ko-lora
|
14 |
+
results: []
|
15 |
+
---
|
16 |
+
|
17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
18 |
+
should probably proofread and complete it, then remove this comment. -->
|
19 |
+
|
20 |
+
# finetuned-kde4-en-to-ko-lora
|
21 |
+
|
22 |
+
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-tc-big-en-ko](https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-en-ko) on the kde4 dataset.
|
23 |
+
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 3.9452
|
25 |
+
- Bleu: 1.4159
|
26 |
+
|
27 |
+
## Model description
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Intended uses & limitations
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training and evaluation data
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training procedure
|
40 |
+
|
41 |
+
### Training hyperparameters
|
42 |
+
|
43 |
+
The following hyperparameters were used during training:
|
44 |
+
- learning_rate: 2e-05
|
45 |
+
- train_batch_size: 32
|
46 |
+
- eval_batch_size: 64
|
47 |
+
- seed: 42
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 3
|
51 |
+
- mixed_precision_training: Native AMP
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
|
56 |
+
|
57 |
+
### Framework versions
|
58 |
+
|
59 |
+
- PEFT 0.12.0
|
60 |
+
- Transformers 4.42.4
|
61 |
+
- Pytorch 2.4.0+cu121
|
62 |
+
- Datasets 2.21.0
|
63 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9457568
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4009f7c3676ac678bb2d1dd90674c4cd5eb409bbeeea7165d88b0cbf6e0ca89
|
3 |
size 9457568
|
runs/Aug29_05-54-37_d2e653be60fc/events.out.tfevents.1724911801.d2e653be60fc.5517.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f68159c8ba4ac86a5cc873137f7cfbd63e8c86b51e3d6a752439dddb6e1e195a
|
3 |
+
size 8632
|
runs/Aug29_05-54-37_d2e653be60fc/events.out.tfevents.1724913582.d2e653be60fc.5517.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65ecfcff9ce5e2a51fd371ef03ece54868b696e616f479f380704c07028d6b27
|
3 |
+
size 407
|