Hugging Face's logo

haryoaw
/
scenario-KD-SCR-CDF-ALL-D2_data-cardiffnlp_tweet_sentiment_multilingual_all44

Transformers
PyTorch
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Community
haryoaw commited on
Commit
86945b2
•
1 Parent(s): d2fd4ca

Initial Commit

Browse files
Files changed (4) hide show
  1. README.md +109 -0
  2. config.json +45 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/mdeberta-v3-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-KD-SCR-CDF-ALL-D2_data-cardiffnlp_tweet_sentiment_multilingual_all44
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # scenario-KD-SCR-CDF-ALL-D2_data-cardiffnlp_tweet_sentiment_multilingual_all44
20
+
21
+ This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the tweet_sentiment_multilingual dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: nan
24
+ - Accuracy: 0.3333
25
+ - F1: 0.1667
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 5e-05
45
+ - train_batch_size: 32
46
+ - eval_batch_size: 32
47
+ - seed: 44
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: linear
50
+ - num_epochs: 50
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
55
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
56
+ | 4.5807 | 1.09 | 500 | nan | 0.3333 | 0.1667 |
57
+ | 0.0 | 2.17 | 1000 | nan | 0.3333 | 0.1667 |
58
+ | 0.0 | 3.26 | 1500 | nan | 0.3333 | 0.1667 |
59
+ | 0.0 | 4.35 | 2000 | nan | 0.3333 | 0.1667 |
60
+ | 0.0 | 5.43 | 2500 | nan | 0.3333 | 0.1667 |
61
+ | 0.0 | 6.52 | 3000 | nan | 0.3333 | 0.1667 |
62
+ | 0.0 | 7.61 | 3500 | nan | 0.3333 | 0.1667 |
63
+ | 0.0 | 8.7 | 4000 | nan | 0.3333 | 0.1667 |
64
+ | 0.0 | 9.78 | 4500 | nan | 0.3333 | 0.1667 |
65
+ | 0.0 | 10.87 | 5000 | nan | 0.3333 | 0.1667 |
66
+ | 0.0 | 11.96 | 5500 | nan | 0.3333 | 0.1667 |
67
+ | 0.0 | 13.04 | 6000 | nan | 0.3333 | 0.1667 |
68
+ | 0.0 | 14.13 | 6500 | nan | 0.3333 | 0.1667 |
69
+ | 0.0 | 15.22 | 7000 | nan | 0.3333 | 0.1667 |
70
+ | 0.0 | 16.3 | 7500 | nan | 0.3333 | 0.1667 |
71
+ | 0.0 | 17.39 | 8000 | nan | 0.3333 | 0.1667 |
72
+ | 0.0 | 18.48 | 8500 | nan | 0.3333 | 0.1667 |
73
+ | 0.0 | 19.57 | 9000 | nan | 0.3333 | 0.1667 |
74
+ | 0.0 | 20.65 | 9500 | nan | 0.3333 | 0.1667 |
75
+ | 0.0 | 21.74 | 10000 | nan | 0.3333 | 0.1667 |
76
+ | 0.0 | 22.83 | 10500 | nan | 0.3333 | 0.1667 |
77
+ | 0.0 | 23.91 | 11000 | nan | 0.3333 | 0.1667 |
78
+ | 0.0 | 25.0 | 11500 | nan | 0.3333 | 0.1667 |
79
+ | 0.0 | 26.09 | 12000 | nan | 0.3333 | 0.1667 |
80
+ | 0.0 | 27.17 | 12500 | nan | 0.3333 | 0.1667 |
81
+ | 0.0 | 28.26 | 13000 | nan | 0.3333 | 0.1667 |
82
+ | 0.0 | 29.35 | 13500 | nan | 0.3333 | 0.1667 |
83
+ | 0.0 | 30.43 | 14000 | nan | 0.3333 | 0.1667 |
84
+ | 0.0 | 31.52 | 14500 | nan | 0.3333 | 0.1667 |
85
+ | 0.0 | 32.61 | 15000 | nan | 0.3333 | 0.1667 |
86
+ | 0.0 | 33.7 | 15500 | nan | 0.3333 | 0.1667 |
87
+ | 0.0 | 34.78 | 16000 | nan | 0.3333 | 0.1667 |
88
+ | 0.0 | 35.87 | 16500 | nan | 0.3333 | 0.1667 |
89
+ | 0.0 | 36.96 | 17000 | nan | 0.3333 | 0.1667 |
90
+ | 0.0 | 38.04 | 17500 | nan | 0.3333 | 0.1667 |
91
+ | 0.0 | 39.13 | 18000 | nan | 0.3333 | 0.1667 |
92
+ | 0.0 | 40.22 | 18500 | nan | 0.3333 | 0.1667 |
93
+ | 0.0 | 41.3 | 19000 | nan | 0.3333 | 0.1667 |
94
+ | 0.0 | 42.39 | 19500 | nan | 0.3333 | 0.1667 |
95
+ | 0.0 | 43.48 | 20000 | nan | 0.3333 | 0.1667 |
96
+ | 0.0 | 44.57 | 20500 | nan | 0.3333 | 0.1667 |
97
+ | 0.0 | 45.65 | 21000 | nan | 0.3333 | 0.1667 |
98
+ | 0.0 | 46.74 | 21500 | nan | 0.3333 | 0.1667 |
99
+ | 0.0 | 47.83 | 22000 | nan | 0.3333 | 0.1667 |
100
+ | 0.0 | 48.91 | 22500 | nan | 0.3333 | 0.1667 |
101
+ | 0.0 | 50.0 | 23000 | nan | 0.3333 | 0.1667 |
102
+
103
+
104
+ ### Framework versions
105
+
106
+ - Transformers 4.33.3
107
+ - Pytorch 2.1.1+cu121
108
+ - Datasets 2.14.5
109
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/mdeberta-v3-base",
3
+ "architectures": [
4
+ "DebertaForSequenceClassificationKD"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0,
19
+ "LABEL_1": 1,
20
+ "LABEL_2": 2
21
+ },
22
+ "layer_norm_eps": 1e-07,
23
+ "max_position_embeddings": 512,
24
+ "max_relative_positions": -1,
25
+ "model_type": "deberta-v2",
26
+ "norm_rel_ebd": "layer_norm",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 6,
29
+ "pad_token_id": 0,
30
+ "pooler_dropout": 0,
31
+ "pooler_hidden_act": "gelu",
32
+ "pooler_hidden_size": 768,
33
+ "pos_att_type": [
34
+ "p2c",
35
+ "c2p"
36
+ ],
37
+ "position_biased_input": false,
38
+ "position_buckets": 256,
39
+ "relative_attention": true,
40
+ "share_att_key": true,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.33.3",
43
+ "type_vocab_size": 0,
44
+ "vocab_size": 251000
45
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a386029b865791d97a4715ebe9e09c0f4eb82b22eda843e7bdbf3d178ad3913a
3
+ size 975051818
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dbcf71a215765ced3e301ea4a210363faa52656a689d1678d836579de4e7dee
3
+ size 4664