mrm8488 commited on
Commit
6d38f27
1 Parent(s): edcd75b

Initial commit from mrm8488

Browse files
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - hate_speech18
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: deberta-v3-small-hate-speech
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: hate_speech18
17
+ type: hate_speech18
18
+ args: default
19
+ metrics:
20
+ - name: Accuracy
21
+ type: accuracy
22
+ value: 0.916058394160584
23
+ ---
24
+
25
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
+ should probably proofread and complete it, then remove this comment. -->
27
+
28
+ # deberta-v3-small-hate-speech
29
+
30
+ This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the hate_speech18 dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 0.2922
33
+ - Accuracy: 0.9161
34
+
35
+ ## Model description
36
+
37
+ More information needed
38
+
39
+ ## Intended uses & limitations
40
+
41
+ More information needed
42
+
43
+ ## Training and evaluation data
44
+
45
+ More information needed
46
+
47
+ ## Training procedure
48
+
49
+ ### Training hyperparameters
50
+
51
+ The following hyperparameters were used during training:
52
+ - learning_rate: 2e-05
53
+ - train_batch_size: 16
54
+ - eval_batch_size: 16
55
+ - seed: 42
56
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
+ - lr_scheduler_type: linear
58
+ - num_epochs: 5
59
+
60
+ ### Training results
61
+
62
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
63
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
64
+ | 0.4147 | 1.0 | 650 | 0.3910 | 0.8832 |
65
+ | 0.2975 | 2.0 | 1300 | 0.2922 | 0.9161 |
66
+ | 0.2575 | 3.0 | 1950 | 0.3555 | 0.9051 |
67
+ | 0.1553 | 4.0 | 2600 | 0.4263 | 0.9124 |
68
+ | 0.1267 | 5.0 | 3250 | 0.4238 | 0.9161 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.12.5
74
+ - Pytorch 1.10.0+cu111
75
+ - Datasets 1.16.1
76
+ - Tokenizers 0.10.3
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"[MASK]": 128000}
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-small",
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
+ "3": "LABEL_3"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "LABEL_0": 0,
20
+ "LABEL_1": 1,
21
+ "LABEL_2": 2,
22
+ "LABEL_3": 3
23
+ },
24
+ "layer_norm_eps": 1e-07,
25
+ "max_position_embeddings": 512,
26
+ "max_relative_positions": -1,
27
+ "model_type": "deberta-v2",
28
+ "norm_rel_ebd": "layer_norm",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 6,
31
+ "pad_token_id": 0,
32
+ "pooler_dropout": 0,
33
+ "pooler_hidden_act": "gelu",
34
+ "pooler_hidden_size": 768,
35
+ "pos_att_type": [
36
+ "p2c",
37
+ "c2p"
38
+ ],
39
+ "position_biased_input": false,
40
+ "position_buckets": 256,
41
+ "relative_attention": true,
42
+ "share_att_key": true,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.12.5",
45
+ "type_vocab_size": 0,
46
+ "vocab_size": 128100
47
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bba1d425fa321ea03dcefc70da5b922d4bfdce43a60b056f52d8b8ac8deed4a
3
+ size 567639019
runs/Dec01_17-09-18_c9404fbf682f/1638378572.6315808/events.out.tfevents.1638378572.c9404fbf682f.608.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2426294740adf0d06b368cf24915974ae66bde4a118df2fa54ef7cb2b138296
3
+ size 4577
runs/Dec01_17-09-18_c9404fbf682f/events.out.tfevents.1638378572.c9404fbf682f.608.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fd22104c5bbaaa8c62c46bf59980a265b5a17d34ef1c6e101d4e9f78ac895fa
3
+ size 6464
runs/Dec01_17-09-18_c9404fbf682f/events.out.tfevents.1638379118.c9404fbf682f.608.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80b411e4c0d2064e49ce80345b2230bdf7be46dd0f483fabb839355184de4945
3
+ size 363
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": false, "sp_model_kwargs": {}, "vocab_type": "spm", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "microsoft/deberta-v3-small", "tokenizer_class": "DebertaV2Tokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6d1f6c71235107b4e94a472fb0d5f2dfc3ee48ce7c4d109b3799116c2637ce8
3
+ size 2863