Hugging Face's logo

idah4
/
qa_kor_math

Text2Text Generation
Transformers
TensorBoard
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
idah4 commited on
Commit
6efe871
•
1 Parent(s): 058319a

Model save

Browse files
Files changed (3) hide show
  1. README.md +37 -17
  2. model.safetensors +1 -1
  3. runs/Apr15_13-30-07_fa02c93dd5cc/events.out.tfevents.1713187810.fa02c93dd5cc.2726.6 +2 -2
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [gogamza/kobart-base-v2](https://huggingface.co/gogamza/kobart-base-v2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.2586
19
 
20
  ## Model description
21
 
@@ -41,27 +41,47 @@ The following hyperparameters were used during training:
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - lr_scheduler_warmup_steps: 400
44
- - num_epochs: 10
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | No log | 0.63 | 100 | 2.9907 |
51
- | No log | 1.26 | 200 | 0.9196 |
52
- | No log | 1.89 | 300 | 0.5858 |
53
- | No log | 2.52 | 400 | 0.4351 |
54
- | 2.4889 | 3.14 | 500 | 0.3693 |
55
- | 2.4889 | 3.77 | 600 | 0.3356 |
56
- | 2.4889 | 4.4 | 700 | 0.3182 |
57
- | 2.4889 | 5.03 | 800 | 0.3017 |
58
- | 2.4889 | 5.66 | 900 | 0.2949 |
59
- | 0.3483 | 6.29 | 1000 | 0.2798 |
60
- | 0.3483 | 6.92 | 1100 | 0.2748 |
61
- | 0.3483 | 7.55 | 1200 | 0.2695 |
62
- | 0.3483 | 8.18 | 1300 | 0.2649 |
63
- | 0.3483 | 8.81 | 1400 | 0.2610 |
64
- | 0.2753 | 9.43 | 1500 | 0.2586 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65
 
66
 
67
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [gogamza/kobart-base-v2](https://huggingface.co/gogamza/kobart-base-v2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.3294
19
 
20
  ## Model description
21
 
 
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - lr_scheduler_warmup_steps: 400
44
+ - num_epochs: 20
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | No log | 0.56 | 100 | 3.5725 |
51
+ | No log | 1.13 | 200 | 1.2367 |
52
+ | No log | 1.69 | 300 | 0.7100 |
53
+ | No log | 2.26 | 400 | 0.5420 |
54
+ | 2.4974 | 2.82 | 500 | 0.5891 |
55
+ | 2.4974 | 3.39 | 600 | 0.5370 |
56
+ | 2.4974 | 3.95 | 700 | 0.4738 |
57
+ | 2.4974 | 4.52 | 800 | 0.4985 |
58
+ | 2.4974 | 5.08 | 900 | 0.4540 |
59
+ | 0.3445 | 5.65 | 1000 | 0.4439 |
60
+ | 0.3445 | 6.21 | 1100 | 0.4261 |
61
+ | 0.3445 | 6.78 | 1200 | 0.4007 |
62
+ | 0.3445 | 7.34 | 1300 | 0.3739 |
63
+ | 0.3445 | 7.91 | 1400 | 0.3937 |
64
+ | 0.26 | 8.47 | 1500 | 0.3550 |
65
+ | 0.26 | 9.04 | 1600 | 0.3623 |
66
+ | 0.26 | 9.6 | 1700 | 0.3944 |
67
+ | 0.26 | 10.17 | 1800 | 0.3669 |
68
+ | 0.26 | 10.73 | 1900 | 0.3628 |
69
+ | 0.217 | 11.3 | 2000 | 0.3703 |
70
+ | 0.217 | 11.86 | 2100 | 0.3580 |
71
+ | 0.217 | 12.43 | 2200 | 0.3318 |
72
+ | 0.217 | 12.99 | 2300 | 0.3199 |
73
+ | 0.217 | 13.56 | 2400 | 0.3537 |
74
+ | 0.1916 | 14.12 | 2500 | 0.3198 |
75
+ | 0.1916 | 14.69 | 2600 | 0.3317 |
76
+ | 0.1916 | 15.25 | 2700 | 0.3333 |
77
+ | 0.1916 | 15.82 | 2800 | 0.3280 |
78
+ | 0.1916 | 16.38 | 2900 | 0.3269 |
79
+ | 0.1737 | 16.95 | 3000 | 0.3315 |
80
+ | 0.1737 | 17.51 | 3100 | 0.3346 |
81
+ | 0.1737 | 18.08 | 3200 | 0.3290 |
82
+ | 0.1737 | 18.64 | 3300 | 0.3317 |
83
+ | 0.1737 | 19.21 | 3400 | 0.3282 |
84
+ | 0.1637 | 19.77 | 3500 | 0.3294 |
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d17d1ab501d8f33543e3251760d978d88e56077a5af0abfff0280a55a91e29b
3
  size 495589768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e8872e2596a198d4adcbb30c64c91950fe8568ccfc70e58467fb6eb231ea285
3
  size 495589768
runs/Apr15_13-30-07_fa02c93dd5cc/events.out.tfevents.1713187810.fa02c93dd5cc.2726.6 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4daf38542b1f330a0bf7410f04f705ba7ccce3f2fd6705bef7377b44bd086e5
3
- size 15400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:799d747e3c9d48550c51e5c5cbf60aabf94454b4b65b5134fa0b4f4db99d45b8
3
+ size 16778