EverDarling commited on
Commit
5de54fc
·
verified ·
1 Parent(s): 65223f1

Training complete

Browse files
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/deberta-v3-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
+ model-index:
12
+ - name: deberta-v3-base
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
+ # deberta-v3-base
20
+
21
+ This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the None dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.0349
24
+ - Precision: 0.0
25
+ - Recall: 0.0
26
+ - F1: 0.0
27
+ - Accuracy: 0.9994
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 2e-05
47
+ - train_batch_size: 1
48
+ - eval_batch_size: 8
49
+ - seed: 42
50
+ - gradient_accumulation_steps: 4
51
+ - total_train_batch_size: 4
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: linear
54
+ - num_epochs: 3
55
+ - mixed_precision_training: Native AMP
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
60
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
61
+ | No log | 0.96 | 6 | 0.7401 | 0.0 | 0.0 | 0.0 | 0.9908 |
62
+ | No log | 1.92 | 12 | 0.1427 | 0.0 | 0.0 | 0.0 | 0.9993 |
63
+ | No log | 2.88 | 18 | 0.0349 | 0.0 | 0.0 | 0.0 | 0.9994 |
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - Transformers 4.38.1
69
+ - Pytorch 2.1.2
70
+ - Datasets 2.1.0
71
+ - Tokenizers 0.15.2
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForTokenClassification"
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": "B-EMAIL",
12
+ "1": "B-ID_NUM",
13
+ "2": "B-NAME_STUDENT",
14
+ "3": "B-PHONE_NUM",
15
+ "4": "B-STREET_ADDRESS",
16
+ "5": "B-URL_PERSONAL",
17
+ "6": "B-USERNAME",
18
+ "7": "I-ID_NUM",
19
+ "8": "I-NAME_STUDENT",
20
+ "9": "I-PHONE_NUM",
21
+ "10": "I-STREET_ADDRESS",
22
+ "11": "I-URL_PERSONAL",
23
+ "12": "I-EMAIL",
24
+ "13": "I-USERNAME",
25
+ "14": "O"
26
+ },
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 3072,
29
+ "label2id": {
30
+ "B-EMAIL": 0,
31
+ "B-ID_NUM": 1,
32
+ "B-NAME_STUDENT": 2,
33
+ "B-PHONE_NUM": 3,
34
+ "B-STREET_ADDRESS": 4,
35
+ "B-URL_PERSONAL": 5,
36
+ "B-USERNAME": 6,
37
+ "I-EMAIL": 12,
38
+ "I-ID_NUM": 7,
39
+ "I-NAME_STUDENT": 8,
40
+ "I-PHONE_NUM": 9,
41
+ "I-STREET_ADDRESS": 10,
42
+ "I-URL_PERSONAL": 11,
43
+ "I-USERNAME": 13,
44
+ "O": 14
45
+ },
46
+ "layer_norm_eps": 1e-07,
47
+ "max_position_embeddings": 512,
48
+ "max_relative_positions": -1,
49
+ "model_type": "deberta-v2",
50
+ "norm_rel_ebd": "layer_norm",
51
+ "num_attention_heads": 12,
52
+ "num_hidden_layers": 12,
53
+ "pad_token_id": 0,
54
+ "pooler_dropout": 0,
55
+ "pooler_hidden_act": "gelu",
56
+ "pooler_hidden_size": 768,
57
+ "pos_att_type": [
58
+ "p2c",
59
+ "c2p"
60
+ ],
61
+ "position_biased_input": false,
62
+ "position_buckets": 256,
63
+ "relative_attention": true,
64
+ "share_att_key": true,
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.38.1",
67
+ "type_vocab_size": 0,
68
+ "vocab_size": 128100
69
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73111fbdf3f8dccc3dcda4c39a8dcf602488b45fcdfb43c0633b16e3dea1e349
3
+ size 735396724
runs/Mar18_11-24-21_3bf33da4a243/events.out.tfevents.1710761231.3bf33da4a243.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82faba1a19836672c653de578f53aec7cd62f8a954592ce453c3e25f6ae8d7d8
3
+ size 7228
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[CLS]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[SEP]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[UNK]",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128000": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "[CLS]",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "[CLS]",
48
+ "do_lower_case": false,
49
+ "eos_token": "[SEP]",
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9a04601c3ab835e99e1e6fd6b2a4aab114d2f8ccba7d2153438fe9b5afedf60
3
+ size 4920