Hugging Face's logo

seoulsky-field
/
KoBART_jeju_dialect

Text2Text Generation
Transformers
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Community
SeoulSKY commited on
Commit
e3e21d4
·
1 Parent(s): 4f2be9f

End of training

Browse files
Files changed (3) hide show
  1. README.md +104 -0
  2. generation_config.json +9 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: gogamza/kobart-base-v2
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: KoBART_base_v2-trial2
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # KoBART_base_v2-trial2
15
+
16
+ This model is a fine-tuned version of [gogamza/kobart-base-v2](https://huggingface.co/gogamza/kobart-base-v2) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.1820
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0005
38
+ - train_batch_size: 64
39
+ - eval_batch_size: 64
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: cosine
43
+ - lr_scheduler_warmup_steps: 20
44
+ - num_epochs: 5
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | 2.3889 | 0.11 | 50 | 0.5425 |
52
+ | 0.5339 | 0.22 | 100 | 0.4328 |
53
+ | 0.4609 | 0.32 | 150 | 0.4180 |
54
+ | 0.4631 | 0.43 | 200 | 0.4167 |
55
+ | 0.4065 | 0.54 | 250 | 0.3775 |
56
+ | 0.3898 | 0.65 | 300 | 0.3539 |
57
+ | 0.3637 | 0.76 | 350 | 0.3389 |
58
+ | 0.3347 | 0.87 | 400 | 0.3275 |
59
+ | 0.3428 | 0.97 | 450 | 0.3087 |
60
+ | 0.2871 | 1.08 | 500 | 0.3189 |
61
+ | 0.2843 | 1.19 | 550 | 0.3016 |
62
+ | 0.2685 | 1.3 | 600 | 0.2954 |
63
+ | 0.2603 | 1.41 | 650 | 0.2860 |
64
+ | 0.2636 | 1.52 | 700 | 0.2804 |
65
+ | 0.2586 | 1.62 | 750 | 0.2821 |
66
+ | 0.2485 | 1.73 | 800 | 0.2674 |
67
+ | 0.2483 | 1.84 | 850 | 0.2662 |
68
+ | 0.2322 | 1.95 | 900 | 0.2525 |
69
+ | 0.2052 | 2.06 | 950 | 0.2634 |
70
+ | 0.1838 | 2.16 | 1000 | 0.2472 |
71
+ | 0.1859 | 2.27 | 1050 | 0.2432 |
72
+ | 0.1887 | 2.38 | 1100 | 0.2392 |
73
+ | 0.1756 | 2.49 | 1150 | 0.2314 |
74
+ | 0.1697 | 2.6 | 1200 | 0.2332 |
75
+ | 0.1741 | 2.71 | 1250 | 0.2257 |
76
+ | 0.1665 | 2.81 | 1300 | 0.2204 |
77
+ | 0.1655 | 2.92 | 1350 | 0.2097 |
78
+ | 0.1539 | 3.03 | 1400 | 0.2141 |
79
+ | 0.126 | 3.14 | 1450 | 0.2129 |
80
+ | 0.1241 | 3.25 | 1500 | 0.2068 |
81
+ | 0.1266 | 3.35 | 1550 | 0.1999 |
82
+ | 0.1161 | 3.46 | 1600 | 0.1996 |
83
+ | 0.1183 | 3.57 | 1650 | 0.1943 |
84
+ | 0.1123 | 3.68 | 1700 | 0.1914 |
85
+ | 0.1096 | 3.79 | 1750 | 0.1881 |
86
+ | 0.1089 | 3.9 | 1800 | 0.1835 |
87
+ | 0.1096 | 4.0 | 1850 | 0.1803 |
88
+ | 0.0857 | 4.11 | 1900 | 0.1873 |
89
+ | 0.0833 | 4.22 | 1950 | 0.1857 |
90
+ | 0.0791 | 4.33 | 2000 | 0.1871 |
91
+ | 0.0825 | 4.44 | 2050 | 0.1852 |
92
+ | 0.0813 | 4.55 | 2100 | 0.1834 |
93
+ | 0.0806 | 4.65 | 2150 | 0.1830 |
94
+ | 0.0805 | 4.76 | 2200 | 0.1822 |
95
+ | 0.0786 | 4.87 | 2250 | 0.1820 |
96
+ | 0.0775 | 4.98 | 2300 | 0.1820 |
97
+
98
+
99
+ ### Framework versions
100
+
101
+ - Transformers 4.36.0
102
+ - Pytorch 2.0.1+cu117
103
+ - Datasets 2.15.0
104
+ - Tokenizers 0.15.0
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "decoder_start_token_id": 1,
5
+ "eos_token_id": 1,
6
+ "forced_eos_token_id": 1,
7
+ "pad_token_id": 3,
8
+ "transformers_version": "4.36.0"
9
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3e676e42e3dab9d03014f299e57f973906ec31879b78b982f81e99cd3afee21
3
  size 495589768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49125719551be6d781b2211f1f270f94168da893ff81eb2b62c90348ae5a912d
3
  size 495589768