Hugging Face's logo

haryoaw
/
scenario-NON-KD-SCR-COPY-CDF-CL-D2_data-cl-cardiff_cl_only44

Text Classification
Transformers
PyTorch
Safetensors
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Community
haryoaw commited on
Commit
039d34e
•
1 Parent(s): 9ed1afb

Initial Commit

Browse files
Files changed (4) hide show
  1. README.md +88 -0
  2. config.json +45 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/mdeberta-v3-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - f1
9
+ model-index:
10
+ - name: scenario-NON-KD-SCR-COPY-CDF-CL-D2_data-cl-cardiff_cl_only44
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # scenario-NON-KD-SCR-COPY-CDF-CL-D2_data-cl-cardiff_cl_only44
18
+
19
+ This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 6.4226
22
+ - Accuracy: 0.3519
23
+ - F1: 0.3509
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 5e-05
43
+ - train_batch_size: 32
44
+ - eval_batch_size: 32
45
+ - seed: 44
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 30
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
54
+ | No log | 1.09 | 250 | 1.5386 | 0.3758 | 0.3686 |
55
+ | 0.9197 | 2.17 | 500 | 2.0548 | 0.3688 | 0.3621 |
56
+ | 0.9197 | 3.26 | 750 | 2.5900 | 0.3503 | 0.3328 |
57
+ | 0.3157 | 4.35 | 1000 | 3.0692 | 0.3642 | 0.3590 |
58
+ | 0.3157 | 5.43 | 1250 | 3.3934 | 0.3588 | 0.3541 |
59
+ | 0.1137 | 6.52 | 1500 | 3.7443 | 0.3665 | 0.3645 |
60
+ | 0.1137 | 7.61 | 1750 | 4.0421 | 0.3619 | 0.3533 |
61
+ | 0.06 | 8.7 | 2000 | 4.1722 | 0.3634 | 0.3627 |
62
+ | 0.06 | 9.78 | 2250 | 4.3554 | 0.3673 | 0.3646 |
63
+ | 0.0376 | 10.87 | 2500 | 4.4540 | 0.3727 | 0.3719 |
64
+ | 0.0376 | 11.96 | 2750 | 4.8442 | 0.3603 | 0.3524 |
65
+ | 0.0242 | 13.04 | 3000 | 4.9101 | 0.3549 | 0.3545 |
66
+ | 0.0242 | 14.13 | 3250 | 5.1904 | 0.3549 | 0.3547 |
67
+ | 0.0163 | 15.22 | 3500 | 4.9427 | 0.3634 | 0.3633 |
68
+ | 0.0163 | 16.3 | 3750 | 5.6506 | 0.3588 | 0.3576 |
69
+ | 0.0069 | 17.39 | 4000 | 5.7963 | 0.3627 | 0.3575 |
70
+ | 0.0069 | 18.48 | 4250 | 5.6658 | 0.3634 | 0.3635 |
71
+ | 0.0045 | 19.57 | 4500 | 5.9666 | 0.3611 | 0.3601 |
72
+ | 0.0045 | 20.65 | 4750 | 6.1602 | 0.3526 | 0.3500 |
73
+ | 0.003 | 21.74 | 5000 | 6.0325 | 0.3627 | 0.3581 |
74
+ | 0.003 | 22.83 | 5250 | 6.2296 | 0.3580 | 0.3547 |
75
+ | 0.0023 | 23.91 | 5500 | 6.3871 | 0.3603 | 0.3536 |
76
+ | 0.0023 | 25.0 | 5750 | 6.3503 | 0.3580 | 0.3569 |
77
+ | 0.0021 | 26.09 | 6000 | 6.3992 | 0.3580 | 0.3559 |
78
+ | 0.0021 | 27.17 | 6250 | 6.5017 | 0.3627 | 0.3597 |
79
+ | 0.0008 | 28.26 | 6500 | 6.4331 | 0.3534 | 0.3521 |
80
+ | 0.0008 | 29.35 | 6750 | 6.4226 | 0.3519 | 0.3509 |
81
+
82
+
83
+ ### Framework versions
84
+
85
+ - Transformers 4.33.3
86
+ - Pytorch 2.1.1+cu121
87
+ - Datasets 2.14.5
88
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/mdeberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
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 sha256:6ed24c788a2515db2c9c2698c7808ea542dbc14f16a88071379c7023aeb70341
3
+ size 945174322
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40cfe5d71c93fd32f7ec6cb2b7b261e86f707338b51736eb0cad57230ca92407
3
+ size 4600