Hugging Face's logo

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

Text Classification
Transformers
PyTorch
xlm-roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
haryoaw commited on
Commit
735f322
•
1 Parent(s): cb0b800

Initial Commit

Browse files
Files changed (4) hide show
  1. README.md +125 -0
  2. config.json +39 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: xlm-roberta-base
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - tweet_sentiment_multilingual
8
+ metrics:
9
+ - accuracy
10
+ - f1
11
+ model-index:
12
+ - name: scenario-NON-KD-SCR-COPY-CDF-ALL-D2_data-cardiffnlp_tweet_sentiment_multilingual
13
+ results:
14
+ - task:
15
+ name: Text Classification
16
+ type: text-classification
17
+ dataset:
18
+ name: tweet_sentiment_multilingual
19
+ type: tweet_sentiment_multilingual
20
+ config: all
21
+ split: validation
22
+ args: all
23
+ metrics:
24
+ - name: Accuracy
25
+ type: accuracy
26
+ value: 0.47762345679012347
27
+ - name: F1
28
+ type: f1
29
+ value: 0.47819062529207484
30
+ ---
31
+
32
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
33
+ should probably proofread and complete it, then remove this comment. -->
34
+
35
+ # scenario-NON-KD-SCR-COPY-CDF-ALL-D2_data-cardiffnlp_tweet_sentiment_multilingual
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: 6.0055
40
+ - Accuracy: 0.4776
41
+ - F1: 0.4782
42
+
43
+ ## Model description
44
+
45
+ More information needed
46
+
47
+ ## Intended uses & limitations
48
+
49
+ More information needed
50
+
51
+ ## Training and evaluation data
52
+
53
+ More information needed
54
+
55
+ ## Training procedure
56
+
57
+ ### Training hyperparameters
58
+
59
+ The following hyperparameters were used during training:
60
+ - learning_rate: 5e-05
61
+ - train_batch_size: 32
62
+ - eval_batch_size: 32
63
+ - seed: 11423
64
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
65
+ - lr_scheduler_type: linear
66
+ - num_epochs: 50
67
+
68
+ ### Training results
69
+
70
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
71
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
72
+ | 1.1157 | 1.09 | 500 | 1.0964 | 0.3835 | 0.2965 |
73
+ | 0.9636 | 2.17 | 1000 | 1.1184 | 0.4954 | 0.4470 |
74
+ | 0.5977 | 3.26 | 1500 | 1.4984 | 0.5116 | 0.5070 |
75
+ | 0.342 | 4.35 | 2000 | 1.8178 | 0.5077 | 0.5054 |
76
+ | 0.1946 | 5.43 | 2500 | 2.5918 | 0.5077 | 0.5062 |
77
+ | 0.1442 | 6.52 | 3000 | 2.5451 | 0.4904 | 0.4833 |
78
+ | 0.101 | 7.61 | 3500 | 3.3273 | 0.4942 | 0.4879 |
79
+ | 0.0788 | 8.7 | 4000 | 3.3097 | 0.4811 | 0.4729 |
80
+ | 0.0596 | 9.78 | 4500 | 3.4639 | 0.4954 | 0.4959 |
81
+ | 0.0505 | 10.87 | 5000 | 3.5381 | 0.4884 | 0.4884 |
82
+ | 0.0413 | 11.96 | 5500 | 3.3937 | 0.4958 | 0.4961 |
83
+ | 0.0364 | 13.04 | 6000 | 3.9058 | 0.4850 | 0.4848 |
84
+ | 0.0273 | 14.13 | 6500 | 4.3025 | 0.4892 | 0.4887 |
85
+ | 0.0282 | 15.22 | 7000 | 3.9833 | 0.4877 | 0.4885 |
86
+ | 0.0253 | 16.3 | 7500 | 4.4515 | 0.4811 | 0.4802 |
87
+ | 0.0188 | 17.39 | 8000 | 4.7345 | 0.4873 | 0.4843 |
88
+ | 0.0191 | 18.48 | 8500 | 4.5842 | 0.4880 | 0.4880 |
89
+ | 0.0187 | 19.57 | 9000 | 4.6871 | 0.4838 | 0.4821 |
90
+ | 0.0189 | 20.65 | 9500 | 4.7307 | 0.4931 | 0.4857 |
91
+ | 0.0157 | 21.74 | 10000 | 4.8938 | 0.4796 | 0.4722 |
92
+ | 0.0133 | 22.83 | 10500 | 4.6099 | 0.4765 | 0.4681 |
93
+ | 0.0107 | 23.91 | 11000 | 5.0670 | 0.4815 | 0.4787 |
94
+ | 0.0076 | 25.0 | 11500 | 4.9710 | 0.4799 | 0.4780 |
95
+ | 0.0078 | 26.09 | 12000 | 5.0339 | 0.4830 | 0.4841 |
96
+ | 0.0101 | 27.17 | 12500 | 5.0560 | 0.4904 | 0.4907 |
97
+ | 0.0086 | 28.26 | 13000 | 5.0095 | 0.4850 | 0.4843 |
98
+ | 0.0074 | 29.35 | 13500 | 5.1031 | 0.4846 | 0.4831 |
99
+ | 0.0032 | 30.43 | 14000 | 5.4537 | 0.4830 | 0.4840 |
100
+ | 0.0054 | 31.52 | 14500 | 5.4554 | 0.4838 | 0.4847 |
101
+ | 0.0046 | 32.61 | 15000 | 5.5972 | 0.4780 | 0.4774 |
102
+ | 0.0059 | 33.7 | 15500 | 5.3884 | 0.4853 | 0.4863 |
103
+ | 0.0029 | 34.78 | 16000 | 5.3174 | 0.4738 | 0.4736 |
104
+ | 0.0033 | 35.87 | 16500 | 5.5911 | 0.4753 | 0.4742 |
105
+ | 0.0041 | 36.96 | 17000 | 5.2149 | 0.4769 | 0.4747 |
106
+ | 0.0034 | 38.04 | 17500 | 5.5052 | 0.4857 | 0.4853 |
107
+ | 0.0014 | 39.13 | 18000 | 5.5164 | 0.4807 | 0.4812 |
108
+ | 0.0015 | 40.22 | 18500 | 5.6182 | 0.4803 | 0.4791 |
109
+ | 0.0002 | 41.3 | 19000 | 5.7053 | 0.4799 | 0.4780 |
110
+ | 0.0001 | 42.39 | 19500 | 5.7820 | 0.4826 | 0.4808 |
111
+ | 0.0001 | 43.48 | 20000 | 5.8324 | 0.4850 | 0.4844 |
112
+ | 0.0005 | 44.57 | 20500 | 5.9002 | 0.4823 | 0.4798 |
113
+ | 0.0004 | 45.65 | 21000 | 5.9340 | 0.4811 | 0.4810 |
114
+ | 0.0011 | 46.74 | 21500 | 5.9656 | 0.4780 | 0.4785 |
115
+ | 0.0002 | 47.83 | 22000 | 5.9859 | 0.4792 | 0.4798 |
116
+ | 0.0001 | 48.91 | 22500 | 5.9994 | 0.4788 | 0.4793 |
117
+ | 0.0001 | 50.0 | 23000 | 6.0055 | 0.4776 | 0.4782 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.33.3
123
+ - Pytorch 2.1.1+cu121
124
+ - Datasets 2.14.5
125
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2
24
+ },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "xlm-roberta",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 6,
30
+ "output_past": true,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.33.3",
36
+ "type_vocab_size": 1,
37
+ "use_cache": true,
38
+ "vocab_size": 250002
39
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e91f02dfd4398d161da56b9fb755f2cbc63059141f0437e372d72c8bb75e68f
3
+ size 942111086
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3d13abb88cac290134c27c63becb8875194b37a7bad9f344b72523ff88e2fe5
3
+ size 4664