hajili commited on
Commit
71ce966
1 Parent(s): 6080e77

hajili/mdeberta-v3-base-azsci-topics

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/mdeberta-v3-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
+ model-index:
12
+ - name: mdeberta-v3-base-azsci-topics
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
+ # mdeberta-v3-base-azsci-topics
20
+
21
+ This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.5213
24
+ - Precision: 0.8633
25
+ - Recall: 0.8759
26
+ - F1: 0.8685
27
+ - Accuracy: 0.8759
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: 16
48
+ - eval_batch_size: 64
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 5
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | No log | 1.0 | 288 | 0.9919 | 0.6713 | 0.7465 | 0.6959 | 0.7465 |
59
+ | 1.4813 | 2.0 | 576 | 0.7035 | 0.7994 | 0.8238 | 0.8022 | 0.8238 |
60
+ | 1.4813 | 3.0 | 864 | 0.5605 | 0.8540 | 0.8568 | 0.8462 | 0.8568 |
61
+ | 0.5512 | 4.0 | 1152 | 0.5296 | 0.8615 | 0.8689 | 0.8623 | 0.8689 |
62
+ | 0.5512 | 5.0 | 1440 | 0.5213 | 0.8633 | 0.8759 | 0.8685 | 0.8759 |
63
+
64
+
65
+ ### Framework versions
66
+
67
+ - Transformers 4.38.2
68
+ - Pytorch 2.1.0+cu121
69
+ - Datasets 2.18.0
70
+ - Tokenizers 0.15.2
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 250101
3
+ }
config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6",
18
+ "7": "LABEL_7",
19
+ "8": "LABEL_8",
20
+ "9": "LABEL_9",
21
+ "10": "LABEL_10",
22
+ "11": "LABEL_11",
23
+ "12": "LABEL_12",
24
+ "13": "LABEL_13",
25
+ "14": "LABEL_14",
26
+ "15": "LABEL_15",
27
+ "16": "LABEL_16",
28
+ "17": "LABEL_17",
29
+ "18": "LABEL_18",
30
+ "19": "LABEL_19",
31
+ "20": "LABEL_20",
32
+ "21": "LABEL_21",
33
+ "22": "LABEL_22"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_10": 10,
41
+ "LABEL_11": 11,
42
+ "LABEL_12": 12,
43
+ "LABEL_13": 13,
44
+ "LABEL_14": 14,
45
+ "LABEL_15": 15,
46
+ "LABEL_16": 16,
47
+ "LABEL_17": 17,
48
+ "LABEL_18": 18,
49
+ "LABEL_19": 19,
50
+ "LABEL_2": 2,
51
+ "LABEL_20": 20,
52
+ "LABEL_21": 21,
53
+ "LABEL_22": 22,
54
+ "LABEL_3": 3,
55
+ "LABEL_4": 4,
56
+ "LABEL_5": 5,
57
+ "LABEL_6": 6,
58
+ "LABEL_7": 7,
59
+ "LABEL_8": 8,
60
+ "LABEL_9": 9
61
+ },
62
+ "layer_norm_eps": 1e-07,
63
+ "max_position_embeddings": 512,
64
+ "max_relative_positions": -1,
65
+ "model_type": "deberta-v2",
66
+ "norm_rel_ebd": "layer_norm",
67
+ "num_attention_heads": 12,
68
+ "num_hidden_layers": 12,
69
+ "pad_token_id": 0,
70
+ "pooler_dropout": 0,
71
+ "pooler_hidden_act": "gelu",
72
+ "pooler_hidden_size": 768,
73
+ "pos_att_type": [
74
+ "p2c",
75
+ "c2p"
76
+ ],
77
+ "position_biased_input": false,
78
+ "position_buckets": 256,
79
+ "relative_attention": true,
80
+ "share_att_key": true,
81
+ "torch_dtype": "float32",
82
+ "transformers_version": "4.38.2",
83
+ "type_vocab_size": 0,
84
+ "vocab_size": 251000
85
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c754ef5e27e21fcbbf351fe4bbb9d8026f5d44d9a3bacec988f3c44227d1d6b9
3
+ size 1115332804
runs/Mar03_10-27-00_ec070931aaa2/events.out.tfevents.1709461629.ec070931aaa2.89967.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c72e015b8b11831e296f0ff289f349cc3410169771fe37f548e1cfb6352af1d7
3
+ size 8849
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 sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
3
+ size 4305025
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aca3ce69a0a35aeb144a52c4f1d41c4246b8785f8f398315cc8fb6b24057810
3
+ size 16331396
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250101": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3126a8ed206b0fb10667f32a8af0def084f0f0ba898c628d4077485706871b8f
3
+ size 4920