Hugging Face's logo

haryoaw
/
scenario-NON-KD-SCR-COPY-CDF-ALL-D2_data-cardiffnlp_tweet_sentiment_multilingual

Text Classification
Transformers
PyTorch
Safetensors
deberta-v2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
haryoaw commited on
Commit
702a9c7
•
1 Parent(s): f59ef6d

Initial Commit

Browse files
Files changed (3) hide show
  1. README.md +52 -52
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -23,10 +23,10 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.4826388888888889
27
  - name: F1
28
  type: f1
29
- value: 0.48296265006448696
30
  ---
31
 
32
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -36,9 +36,9 @@ should probably proofread and complete it, then remove this comment. -->
36
 
37
  This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the tweet_sentiment_multilingual dataset.
38
  It achieves the following results on the evaluation set:
39
- - Loss: 5.8456
40
- - Accuracy: 0.4826
41
- - F1: 0.4830
42
 
43
  ## Model description
44
 
@@ -60,7 +60,7 @@ The following hyperparameters were used during training:
60
  - learning_rate: 5e-05
61
  - train_batch_size: 32
62
  - eval_batch_size: 32
63
- - seed: 111
64
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
65
  - lr_scheduler_type: linear
66
  - num_epochs: 50
@@ -69,52 +69,52 @@ The following hyperparameters were used during training:
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
71
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
72
- | 1.1261 | 1.09 | 500 | 1.1108 | 0.3819 | 0.2985 |
73
- | 1.0135 | 2.17 | 1000 | 1.2743 | 0.4846 | 0.4779 |
74
- | 0.659 | 3.26 | 1500 | 1.4805 | 0.4811 | 0.4796 |
75
- | 0.3617 | 4.35 | 2000 | 2.1233 | 0.4830 | 0.4706 |
76
- | 0.1917 | 5.43 | 2500 | 2.2773 | 0.4931 | 0.4881 |
77
- | 0.1454 | 6.52 | 3000 | 2.6599 | 0.4811 | 0.4815 |
78
- | 0.088 | 7.61 | 3500 | 3.4724 | 0.4799 | 0.4759 |
79
- | 0.0698 | 8.7 | 4000 | 3.0632 | 0.4819 | 0.4811 |
80
- | 0.0575 | 9.78 | 4500 | 3.7450 | 0.4838 | 0.4831 |
81
- | 0.0481 | 10.87 | 5000 | 3.8214 | 0.4799 | 0.4718 |
82
- | 0.0447 | 11.96 | 5500 | 3.9903 | 0.4815 | 0.4811 |
83
- | 0.0266 | 13.04 | 6000 | 3.8879 | 0.4954 | 0.4932 |
84
- | 0.0329 | 14.13 | 6500 | 4.2133 | 0.4807 | 0.4812 |
85
- | 0.0183 | 15.22 | 7000 | 4.8558 | 0.4819 | 0.4678 |
86
- | 0.021 | 16.3 | 7500 | 4.6498 | 0.4884 | 0.4830 |
87
- | 0.0203 | 17.39 | 8000 | 4.7070 | 0.4846 | 0.4777 |
88
- | 0.0173 | 18.48 | 8500 | 4.7503 | 0.4784 | 0.4730 |
89
- | 0.0193 | 19.57 | 9000 | 4.4532 | 0.4873 | 0.4872 |
90
- | 0.0155 | 20.65 | 9500 | 5.2049 | 0.4576 | 0.4333 |
91
- | 0.0168 | 21.74 | 10000 | 4.8907 | 0.4753 | 0.4750 |
92
- | 0.0186 | 22.83 | 10500 | 4.7733 | 0.4853 | 0.4853 |
93
- | 0.0084 | 23.91 | 11000 | 4.7841 | 0.4884 | 0.4889 |
94
- | 0.0093 | 25.0 | 11500 | 4.9761 | 0.4826 | 0.4825 |
95
- | 0.0046 | 26.09 | 12000 | 5.3406 | 0.4819 | 0.4827 |
96
- | 0.0101 | 27.17 | 12500 | 5.1833 | 0.4745 | 0.4740 |
97
- | 0.0056 | 28.26 | 13000 | 5.2410 | 0.4757 | 0.4719 |
98
- | 0.0064 | 29.35 | 13500 | 5.2234 | 0.4850 | 0.4855 |
99
- | 0.0071 | 30.43 | 14000 | 5.2686 | 0.4861 | 0.4724 |
100
- | 0.0056 | 31.52 | 14500 | 5.5030 | 0.4815 | 0.4820 |
101
- | 0.0046 | 32.61 | 15000 | 5.5277 | 0.4811 | 0.4794 |
102
- | 0.005 | 33.7 | 15500 | 5.3082 | 0.4857 | 0.4846 |
103
- | 0.0019 | 34.78 | 16000 | 5.4900 | 0.4815 | 0.4734 |
104
- | 0.0036 | 35.87 | 16500 | 5.4583 | 0.4826 | 0.4820 |
105
- | 0.0029 | 36.96 | 17000 | 5.5468 | 0.4826 | 0.4800 |
106
- | 0.0017 | 38.04 | 17500 | 5.5566 | 0.4788 | 0.4751 |
107
- | 0.0016 | 39.13 | 18000 | 5.8154 | 0.4757 | 0.4764 |
108
- | 0.0032 | 40.22 | 18500 | 5.6983 | 0.4850 | 0.4850 |
109
- | 0.0018 | 41.3 | 19000 | 5.7825 | 0.4826 | 0.4834 |
110
- | 0.004 | 42.39 | 19500 | 5.6200 | 0.4807 | 0.4812 |
111
- | 0.0009 | 43.48 | 20000 | 5.6597 | 0.4799 | 0.4791 |
112
- | 0.0007 | 44.57 | 20500 | 5.7764 | 0.4842 | 0.4845 |
113
- | 0.0009 | 45.65 | 21000 | 5.8673 | 0.4823 | 0.4817 |
114
- | 0.0002 | 46.74 | 21500 | 5.8294 | 0.4884 | 0.4877 |
115
- | 0.0009 | 47.83 | 22000 | 5.8360 | 0.4819 | 0.4822 |
116
- | 0.0001 | 48.91 | 22500 | 5.8439 | 0.4819 | 0.4823 |
117
- | 0.0001 | 50.0 | 23000 | 5.8456 | 0.4826 | 0.4830 |
118
 
119
 
120
  ### Framework versions
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.4972993827160494
27
  - name: F1
28
  type: f1
29
+ value: 0.49564146924204383
30
  ---
31
 
32
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
36
 
37
  This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the tweet_sentiment_multilingual dataset.
38
  It achieves the following results on the evaluation set:
39
+ - Loss: 5.7429
40
+ - Accuracy: 0.4973
41
+ - F1: 0.4956
42
 
43
  ## Model description
44
 
 
60
  - learning_rate: 5e-05
61
  - train_batch_size: 32
62
  - eval_batch_size: 32
63
+ - seed: 222
64
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
65
  - lr_scheduler_type: linear
66
  - num_epochs: 50
 
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
71
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
72
+ | 1.1068 | 1.09 | 500 | 1.0681 | 0.4352 | 0.4321 |
73
+ | 0.9081 | 2.17 | 1000 | 1.2631 | 0.5046 | 0.5021 |
74
+ | 0.5532 | 3.26 | 1500 | 1.5304 | 0.5108 | 0.5089 |
75
+ | 0.2998 | 4.35 | 2000 | 2.0584 | 0.4884 | 0.4858 |
76
+ | 0.1717 | 5.43 | 2500 | 2.7362 | 0.5 | 0.4939 |
77
+ | 0.1242 | 6.52 | 3000 | 3.0470 | 0.4969 | 0.4938 |
78
+ | 0.0874 | 7.61 | 3500 | 2.7990 | 0.5046 | 0.5037 |
79
+ | 0.0669 | 8.7 | 4000 | 3.2793 | 0.4942 | 0.4940 |
80
+ | 0.056 | 9.78 | 4500 | 3.2094 | 0.5027 | 0.5028 |
81
+ | 0.0487 | 10.87 | 5000 | 3.5054 | 0.4992 | 0.4972 |
82
+ | 0.0539 | 11.96 | 5500 | 3.2798 | 0.5008 | 0.5003 |
83
+ | 0.0317 | 13.04 | 6000 | 3.4251 | 0.5004 | 0.4994 |
84
+ | 0.0449 | 14.13 | 6500 | 4.0353 | 0.4969 | 0.4923 |
85
+ | 0.0303 | 15.22 | 7000 | 4.3157 | 0.4850 | 0.4733 |
86
+ | 0.0285 | 16.3 | 7500 | 3.8740 | 0.4985 | 0.4987 |
87
+ | 0.0214 | 17.39 | 8000 | 4.5553 | 0.4842 | 0.4828 |
88
+ | 0.0228 | 18.48 | 8500 | 4.7444 | 0.4946 | 0.4903 |
89
+ | 0.0177 | 19.57 | 9000 | 4.5373 | 0.4969 | 0.4939 |
90
+ | 0.0167 | 20.65 | 9500 | 4.4792 | 0.4927 | 0.4859 |
91
+ | 0.0144 | 21.74 | 10000 | 4.6491 | 0.4896 | 0.4897 |
92
+ | 0.0164 | 22.83 | 10500 | 4.8310 | 0.4934 | 0.4926 |
93
+ | 0.0116 | 23.91 | 11000 | 4.6267 | 0.4996 | 0.4965 |
94
+ | 0.0102 | 25.0 | 11500 | 5.0420 | 0.4904 | 0.4808 |
95
+ | 0.0053 | 26.09 | 12000 | 5.2202 | 0.4915 | 0.4824 |
96
+ | 0.01 | 27.17 | 12500 | 4.8786 | 0.4900 | 0.4868 |
97
+ | 0.0076 | 28.26 | 13000 | 4.8830 | 0.4919 | 0.4906 |
98
+ | 0.0064 | 29.35 | 13500 | 5.2319 | 0.4934 | 0.4890 |
99
+ | 0.0055 | 30.43 | 14000 | 5.4810 | 0.4973 | 0.4953 |
100
+ | 0.0057 | 31.52 | 14500 | 5.4109 | 0.5035 | 0.5019 |
101
+ | 0.0032 | 32.61 | 15000 | 5.3979 | 0.5054 | 0.5041 |
102
+ | 0.0092 | 33.7 | 15500 | 5.3848 | 0.4942 | 0.4940 |
103
+ | 0.0053 | 34.78 | 16000 | 5.2937 | 0.5066 | 0.5046 |
104
+ | 0.0029 | 35.87 | 16500 | 5.5430 | 0.5012 | 0.4971 |
105
+ | 0.0011 | 36.96 | 17000 | 5.6338 | 0.4919 | 0.4905 |
106
+ | 0.0027 | 38.04 | 17500 | 5.6234 | 0.4958 | 0.4960 |
107
+ | 0.0042 | 39.13 | 18000 | 5.5802 | 0.4988 | 0.4991 |
108
+ | 0.0012 | 40.22 | 18500 | 5.6464 | 0.4988 | 0.4993 |
109
+ | 0.0037 | 41.3 | 19000 | 5.6227 | 0.4965 | 0.4945 |
110
+ | 0.0007 | 42.39 | 19500 | 5.6263 | 0.4958 | 0.4939 |
111
+ | 0.0003 | 43.48 | 20000 | 5.6946 | 0.4934 | 0.4937 |
112
+ | 0.0016 | 44.57 | 20500 | 5.6654 | 0.4973 | 0.4977 |
113
+ | 0.0018 | 45.65 | 21000 | 5.6725 | 0.4965 | 0.4952 |
114
+ | 0.0012 | 46.74 | 21500 | 5.6500 | 0.4873 | 0.4869 |
115
+ | 0.0008 | 47.83 | 22000 | 5.6626 | 0.4992 | 0.4985 |
116
+ | 0.0006 | 48.91 | 22500 | 5.7378 | 0.4985 | 0.4968 |
117
+ | 0.0004 | 50.0 | 23000 | 5.7429 | 0.4973 | 0.4956 |
118
 
119
 
120
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:451c8b87a3d59f322c955dea7cb3a84d542c469a3fe8617bdc576fd353984c54
3
  size 942111086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:307f60615c3fec1907c8e173c4dcf69b6300fa4d284bad1ed6302a50c7ddb627
3
  size 942111086
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee88ae0b891a366c8d36caad974179bdad0f2cbefc839a2af112f624684baf33
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:246cd7359a48928978a78cbf2369a367f6d8d40b3f0066894c6f3f39a12ad6f4
3
  size 4664