Hugging Face's logo

genki10
/
ASAP_FineTuningBERT_AugV5_k1_task1_organization_fold1

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
genki10 commited on
Commit
77d6b57
·
verified ·
1 Parent(s): 341b45c

Training in progress, step 100

Browse files
Files changed (4) hide show
  1. README.md +64 -24
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. training_args.bin +2 -2
README.md CHANGED
@@ -5,21 +5,21 @@ base_model: bert-base-uncased
5
  tags:
6
  - generated_from_trainer
7
  model-index:
8
- - name: ASAP_FineTuningBERT_AugV5_k1_task1_organization_fold1
9
  results: []
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
  should probably proofread and complete it, then remove this comment. -->
14
 
15
- # ASAP_FineTuningBERT_AugV5_k1_task1_organization_fold1
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: 2.6993
20
- - Qwk: 0.0
21
- - Mse: 2.6988
22
- - Rmse: 1.6428
23
 
24
  ## Model description
25
 
@@ -39,32 +39,72 @@ More information needed
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 2e-05
42
- - train_batch_size: 64
43
- - eval_batch_size: 64
44
  - seed: 42
45
- - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
  - num_epochs: 100
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse | Rmse |
52
- |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|
53
- | No log | 2.0 | 2 | 8.3789 | 0.0005 | 8.3770 | 2.8943 |
54
- | No log | 4.0 | 4 | 7.4118 | 0.0 | 7.4100 | 2.7221 |
55
- | No log | 6.0 | 6 | 6.6888 | 0.0 | 6.6871 | 2.5859 |
56
- | No log | 8.0 | 8 | 6.1510 | 0.0 | 6.1495 | 2.4798 |
57
- | 9.6925 | 10.0 | 10 | 5.7285 | 0.0611 | 5.7271 | 2.3931 |
58
- | 9.6925 | 12.0 | 12 | 5.1815 | 0.0 | 5.1803 | 2.2760 |
59
- | 9.6925 | 14.0 | 14 | 4.4482 | 0.0 | 4.4472 | 2.1088 |
60
- | 9.6925 | 16.0 | 16 | 3.7486 | 0.0 | 3.7477 | 1.9359 |
61
- | 9.6925 | 18.0 | 18 | 3.1214 | 0.0 | 3.1208 | 1.7666 |
62
- | 5.6728 | 20.0 | 20 | 2.6993 | 0.0 | 2.6988 | 1.6428 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
 
64
 
65
  ### Framework versions
66
 
67
- - Transformers 4.48.0
68
- - Pytorch 2.5.1+cu121
69
  - Datasets 3.2.0
70
- - Tokenizers 0.21.0
 
5
  tags:
6
  - generated_from_trainer
7
  model-index:
8
+ - name: ASAP_FineTuningBERT_AugV5_k1_task1_organization_fold0
9
  results: []
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
  should probably proofread and complete it, then remove this comment. -->
14
 
15
+ # ASAP_FineTuningBERT_AugV5_k1_task1_organization_fold0
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: 0.6580
20
+ - Qwk: 0.5710
21
+ - Mse: 0.6580
22
+ - Rmse: 0.8112
23
 
24
  ## Model description
25
 
 
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 2e-05
42
+ - train_batch_size: 128
43
+ - eval_batch_size: 128
44
  - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - num_epochs: 100
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse | Rmse |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:------:|
53
+ | No log | 2.0 | 2 | 14.3675 | 0.0 | 14.3675 | 3.7904 |
54
+ | No log | 4.0 | 4 | 12.2657 | 0.0001 | 12.2657 | 3.5022 |
55
+ | No log | 6.0 | 6 | 9.9287 | 0.0075 | 9.9287 | 3.1510 |
56
+ | No log | 8.0 | 8 | 6.5850 | 0.0092 | 6.5850 | 2.5661 |
57
+ | 12.2366 | 10.0 | 10 | 5.4001 | 0.0058 | 5.4001 | 2.3238 |
58
+ | 12.2366 | 12.0 | 12 | 4.9546 | 0.0150 | 4.9546 | 2.2259 |
59
+ | 12.2366 | 14.0 | 14 | 3.6432 | 0.0077 | 3.6432 | 1.9087 |
60
+ | 12.2366 | 16.0 | 16 | 3.1559 | 0.0090 | 3.1559 | 1.7765 |
61
+ | 12.2366 | 18.0 | 18 | 2.1463 | 0.1246 | 2.1463 | 1.4650 |
62
+ | 4.8314 | 20.0 | 20 | 1.5956 | 0.0644 | 1.5956 | 1.2632 |
63
+ | 4.8314 | 22.0 | 22 | 1.3239 | 0.0520 | 1.3239 | 1.1506 |
64
+ | 4.8314 | 24.0 | 24 | 1.0140 | 0.0520 | 1.0140 | 1.0070 |
65
+ | 4.8314 | 26.0 | 26 | 0.8329 | 0.2300 | 0.8329 | 0.9126 |
66
+ | 4.8314 | 28.0 | 28 | 0.7248 | 0.3921 | 0.7248 | 0.8513 |
67
+ | 2.3166 | 30.0 | 30 | 0.6718 | 0.3949 | 0.6718 | 0.8196 |
68
+ | 2.3166 | 32.0 | 32 | 0.6289 | 0.3068 | 0.6289 | 0.7931 |
69
+ | 2.3166 | 34.0 | 34 | 0.6426 | 0.2838 | 0.6426 | 0.8016 |
70
+ | 2.3166 | 36.0 | 36 | 0.5991 | 0.3369 | 0.5991 | 0.7740 |
71
+ | 2.3166 | 38.0 | 38 | 0.4894 | 0.4522 | 0.4894 | 0.6996 |
72
+ | 1.1272 | 40.0 | 40 | 0.4630 | 0.5015 | 0.4630 | 0.6804 |
73
+ | 1.1272 | 42.0 | 42 | 0.5050 | 0.5564 | 0.5050 | 0.7106 |
74
+ | 1.1272 | 44.0 | 44 | 0.5615 | 0.5275 | 0.5615 | 0.7493 |
75
+ | 1.1272 | 46.0 | 46 | 0.6567 | 0.5092 | 0.6567 | 0.8103 |
76
+ | 1.1272 | 48.0 | 48 | 0.6235 | 0.5537 | 0.6235 | 0.7896 |
77
+ | 0.5121 | 50.0 | 50 | 0.5088 | 0.6184 | 0.5088 | 0.7133 |
78
+ | 0.5121 | 52.0 | 52 | 0.6130 | 0.5643 | 0.6130 | 0.7829 |
79
+ | 0.5121 | 54.0 | 54 | 0.6681 | 0.5319 | 0.6681 | 0.8174 |
80
+ | 0.5121 | 56.0 | 56 | 0.6829 | 0.5234 | 0.6829 | 0.8263 |
81
+ | 0.5121 | 58.0 | 58 | 0.6326 | 0.5640 | 0.6326 | 0.7953 |
82
+ | 0.2162 | 60.0 | 60 | 0.6202 | 0.5799 | 0.6202 | 0.7875 |
83
+ | 0.2162 | 62.0 | 62 | 0.7463 | 0.5338 | 0.7463 | 0.8639 |
84
+ | 0.2162 | 64.0 | 64 | 0.5717 | 0.6001 | 0.5717 | 0.7561 |
85
+ | 0.2162 | 66.0 | 66 | 0.5592 | 0.6122 | 0.5592 | 0.7478 |
86
+ | 0.2162 | 68.0 | 68 | 0.6357 | 0.5792 | 0.6357 | 0.7973 |
87
+ | 0.1097 | 70.0 | 70 | 0.8207 | 0.5011 | 0.8207 | 0.9059 |
88
+ | 0.1097 | 72.0 | 72 | 0.7455 | 0.5342 | 0.7455 | 0.8634 |
89
+ | 0.1097 | 74.0 | 74 | 0.5724 | 0.6094 | 0.5724 | 0.7566 |
90
+ | 0.1097 | 76.0 | 76 | 0.5791 | 0.6223 | 0.5791 | 0.7610 |
91
+ | 0.1097 | 78.0 | 78 | 0.6575 | 0.5670 | 0.6575 | 0.8109 |
92
+ | 0.0725 | 80.0 | 80 | 0.6171 | 0.5747 | 0.6171 | 0.7856 |
93
+ | 0.0725 | 82.0 | 82 | 0.5949 | 0.6070 | 0.5949 | 0.7713 |
94
+ | 0.0725 | 84.0 | 84 | 0.6999 | 0.5545 | 0.6999 | 0.8366 |
95
+ | 0.0725 | 86.0 | 86 | 0.7311 | 0.5221 | 0.7311 | 0.8551 |
96
+ | 0.0725 | 88.0 | 88 | 0.6533 | 0.5682 | 0.6533 | 0.8083 |
97
+ | 0.0571 | 90.0 | 90 | 0.6079 | 0.5915 | 0.6079 | 0.7797 |
98
+ | 0.0571 | 92.0 | 92 | 0.6229 | 0.6009 | 0.6229 | 0.7892 |
99
+ | 0.0571 | 94.0 | 94 | 0.6542 | 0.5774 | 0.6542 | 0.8088 |
100
+ | 0.0571 | 96.0 | 96 | 0.6677 | 0.5640 | 0.6677 | 0.8171 |
101
+ | 0.0571 | 98.0 | 98 | 0.6665 | 0.5684 | 0.6665 | 0.8164 |
102
+ | 0.0489 | 100.0 | 100 | 0.6580 | 0.5710 | 0.6580 | 0.8112 |
103
 
104
 
105
  ### Framework versions
106
 
107
+ - Transformers 4.44.2
108
+ - Pytorch 2.4.1+cu121
109
  - Datasets 3.2.0
110
+ - Tokenizers 0.19.1
config.json CHANGED
@@ -26,7 +26,7 @@
26
  "position_embedding_type": "absolute",
27
  "problem_type": "regression",
28
  "torch_dtype": "float32",
29
- "transformers_version": "4.48.0",
30
  "type_vocab_size": 2,
31
  "use_cache": true,
32
  "vocab_size": 30522
 
26
  "position_embedding_type": "absolute",
27
  "problem_type": "regression",
28
  "torch_dtype": "float32",
29
+ "transformers_version": "4.44.2",
30
  "type_vocab_size": 2,
31
  "use_cache": true,
32
  "vocab_size": 30522
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6b60cb49964f66ca8a439abb4e68432bad9ba9d3e7c1d2ba99d426a630761b4
3
  size 437955572
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d48a848f20fcf030333a8ce090225740e63ea136d4432bcf07413f6d18a39c6
3
  size 437955572
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:266fc29ad32f2ce0ea4d01b9f3b84d04767f43534b6abd78d9a12b3ab7de8203
3
- size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba57c107b20821dce96936483c382fb86a6123ad18baedaf600899b2f98a253e
3
+ size 5176