Hugging Face's logo

genki10
/
ASAP_FineTuningBERT_AugV8_k1_task1_organization_k1_fold3

Text Classification
Transformers
PyTorch
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
genki10 commited on
Commit
5ee9ffb
·
verified ·
1 Parent(s): c678216

Best model for k=1, fold=3

Browse files
Files changed (2) hide show
  1. README.md +37 -48
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.8054
20
- - Qwk: 0.5136
21
- - Mse: 0.8063
22
- - Rmse: 0.8979
23
 
24
  ## Model description
25
 
@@ -48,50 +48,39 @@ The following hyperparameters were used during training:
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse | Rmse |
52
- |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|
53
- | No log | 1.0 | 2 | 8.7877 | 0.0 | 8.7858 | 2.9641 |
54
- | No log | 2.0 | 4 | 8.0798 | 0.0 | 8.0777 | 2.8421 |
55
- | No log | 3.0 | 6 | 6.5572 | 0.0132 | 6.5554 | 2.5604 |
56
- | No log | 4.0 | 8 | 4.7529 | 0.0076 | 4.7518 | 2.1799 |
57
- | No log | 5.0 | 10 | 4.0461 | 0.0 | 4.0449 | 2.0112 |
58
- | No log | 6.0 | 12 | 3.3677 | 0.0 | 3.3667 | 1.8349 |
59
- | No log | 7.0 | 14 | 2.6735 | 0.0120 | 2.6727 | 1.6348 |
60
- | No log | 8.0 | 16 | 2.1030 | 0.1185 | 2.1023 | 1.4499 |
61
- | No log | 9.0 | 18 | 1.6393 | 0.0365 | 1.6386 | 1.2801 |
62
- | No log | 10.0 | 20 | 1.3222 | 0.0202 | 1.3216 | 1.1496 |
63
- | No log | 11.0 | 22 | 1.1494 | 0.0202 | 1.1489 | 1.0719 |
64
- | No log | 12.0 | 24 | 1.0219 | 0.0202 | 1.0216 | 1.0107 |
65
- | No log | 13.0 | 26 | 0.9472 | 0.0668 | 0.9469 | 0.9731 |
66
- | No log | 14.0 | 28 | 1.0645 | 0.1213 | 1.0644 | 1.0317 |
67
- | No log | 15.0 | 30 | 1.0087 | 0.2044 | 1.0087 | 1.0043 |
68
- | No log | 16.0 | 32 | 0.8401 | 0.3634 | 0.8402 | 0.9166 |
69
- | No log | 17.0 | 34 | 0.7652 | 0.4408 | 0.7654 | 0.8748 |
70
- | No log | 18.0 | 36 | 0.7582 | 0.4477 | 0.7586 | 0.8710 |
71
- | No log | 19.0 | 38 | 0.6605 | 0.4754 | 0.6609 | 0.8130 |
72
- | No log | 20.0 | 40 | 0.6212 | 0.4897 | 0.6216 | 0.7884 |
73
- | No log | 21.0 | 42 | 0.5981 | 0.5122 | 0.5985 | 0.7736 |
74
- | No log | 22.0 | 44 | 0.5866 | 0.5205 | 0.5869 | 0.7661 |
75
- | No log | 23.0 | 46 | 0.6460 | 0.4937 | 0.6464 | 0.8040 |
76
- | No log | 24.0 | 48 | 0.6557 | 0.4745 | 0.6561 | 0.8100 |
77
- | No log | 25.0 | 50 | 0.6226 | 0.5604 | 0.6229 | 0.7893 |
78
- | No log | 26.0 | 52 | 0.7104 | 0.5211 | 0.7109 | 0.8431 |
79
- | No log | 27.0 | 54 | 0.6574 | 0.5930 | 0.6580 | 0.8112 |
80
- | No log | 28.0 | 56 | 0.6875 | 0.5776 | 0.6881 | 0.8295 |
81
- | No log | 29.0 | 58 | 0.7127 | 0.5383 | 0.7131 | 0.8444 |
82
- | No log | 30.0 | 60 | 0.7095 | 0.5304 | 0.7098 | 0.8425 |
83
- | No log | 31.0 | 62 | 0.8287 | 0.4918 | 0.8291 | 0.9106 |
84
- | No log | 32.0 | 64 | 0.6883 | 0.5964 | 0.6887 | 0.8299 |
85
- | No log | 33.0 | 66 | 0.7217 | 0.5871 | 0.7223 | 0.8499 |
86
- | No log | 34.0 | 68 | 0.7753 | 0.5367 | 0.7761 | 0.8810 |
87
- | No log | 35.0 | 70 | 0.7526 | 0.5707 | 0.7533 | 0.8679 |
88
- | No log | 36.0 | 72 | 0.7627 | 0.5649 | 0.7633 | 0.8737 |
89
- | No log | 37.0 | 74 | 0.7623 | 0.5184 | 0.7630 | 0.8735 |
90
- | No log | 38.0 | 76 | 0.7574 | 0.5302 | 0.7580 | 0.8706 |
91
- | No log | 39.0 | 78 | 0.7576 | 0.5739 | 0.7579 | 0.8706 |
92
- | No log | 40.0 | 80 | 0.7749 | 0.5730 | 0.7751 | 0.8804 |
93
- | No log | 41.0 | 82 | 0.8074 | 0.5178 | 0.8082 | 0.8990 |
94
- | No log | 42.0 | 84 | 0.8054 | 0.5136 | 0.8063 | 0.8979 |
95
 
96
 
97
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.7391
20
+ - Qwk: 0.5287
21
+ - Mse: 0.7399
22
+ - Rmse: 0.8602
23
 
24
  ## Model description
25
 
 
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse | Rmse |
52
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:------:|
53
+ | No log | 1.0 | 2 | 10.3196 | 0.0014 | 10.3178 | 3.2121 |
54
+ | No log | 2.0 | 4 | 7.2215 | 0.0 | 7.2202 | 2.6870 |
55
+ | No log | 3.0 | 6 | 5.3307 | 0.0161 | 5.3295 | 2.3086 |
56
+ | No log | 4.0 | 8 | 4.0710 | 0.0 | 4.0699 | 2.0174 |
57
+ | No log | 5.0 | 10 | 3.3146 | 0.0 | 3.3134 | 1.8203 |
58
+ | No log | 6.0 | 12 | 2.5785 | -0.0111 | 2.5776 | 1.6055 |
59
+ | No log | 7.0 | 14 | 2.0507 | 0.0266 | 2.0499 | 1.4318 |
60
+ | No log | 8.0 | 16 | 1.6022 | 0.0202 | 1.6015 | 1.2655 |
61
+ | No log | 9.0 | 18 | 1.2505 | 0.0266 | 1.2500 | 1.1180 |
62
+ | No log | 10.0 | 20 | 1.3209 | 0.0202 | 1.3204 | 1.1491 |
63
+ | No log | 11.0 | 22 | 1.0664 | 0.0717 | 1.0661 | 1.0325 |
64
+ | No log | 12.0 | 24 | 1.0138 | 0.3620 | 1.0139 | 1.0069 |
65
+ | No log | 13.0 | 26 | 0.8288 | 0.5269 | 0.8291 | 0.9105 |
66
+ | No log | 14.0 | 28 | 0.8755 | 0.2203 | 0.8753 | 0.9356 |
67
+ | No log | 15.0 | 30 | 1.0460 | 0.2004 | 1.0458 | 1.0227 |
68
+ | No log | 16.0 | 32 | 0.9638 | 0.3144 | 0.9639 | 0.9818 |
69
+ | No log | 17.0 | 34 | 0.8350 | 0.5351 | 0.8354 | 0.9140 |
70
+ | No log | 18.0 | 36 | 0.8384 | 0.5377 | 0.8388 | 0.9159 |
71
+ | No log | 19.0 | 38 | 0.8951 | 0.4324 | 0.8954 | 0.9462 |
72
+ | No log | 20.0 | 40 | 0.8969 | 0.4082 | 0.8973 | 0.9472 |
73
+ | No log | 21.0 | 42 | 0.8200 | 0.5473 | 0.8205 | 0.9058 |
74
+ | No log | 22.0 | 44 | 0.7806 | 0.5406 | 0.7811 | 0.8838 |
75
+ | No log | 23.0 | 46 | 0.7539 | 0.4906 | 0.7545 | 0.8686 |
76
+ | No log | 24.0 | 48 | 0.7043 | 0.5153 | 0.7048 | 0.8395 |
77
+ | No log | 25.0 | 50 | 0.6591 | 0.5214 | 0.6596 | 0.8122 |
78
+ | No log | 26.0 | 52 | 0.6587 | 0.5178 | 0.6593 | 0.8120 |
79
+ | No log | 27.0 | 54 | 0.6943 | 0.5135 | 0.6951 | 0.8337 |
80
+ | No log | 28.0 | 56 | 0.6894 | 0.5219 | 0.6902 | 0.8308 |
81
+ | No log | 29.0 | 58 | 0.7109 | 0.5223 | 0.7118 | 0.8437 |
82
+ | No log | 30.0 | 60 | 0.8405 | 0.4449 | 0.8412 | 0.9172 |
83
+ | No log | 31.0 | 62 | 0.7391 | 0.5287 | 0.7399 | 0.8602 |
 
 
 
 
 
 
 
 
 
 
 
84
 
85
 
86
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bccbdd284084a86b2dcab504d06fe7fafb59f80da6bd8243c79f465c7a2ac93a
3
  size 438000878
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58b58dedb4ac06b7106c800041ec2cc086fe0451bd1564d7870fb8c4e9ee4a43
3
  size 438000878