kasrahabib commited on
Commit
0d806bb
1 Parent(s): a0e7956

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: sentence-transformers/all-MiniLM-L6-v2
4
+ tags:
5
+ - generated_from_keras_callback
6
+ model-index:
7
+ - name: kasrahabib/all-MiniLM-L6-v2-finetuned-on-promise-nf-sub-classes-classifier
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
12
+ probably proofread and complete it, then remove this comment. -->
13
+
14
+ # kasrahabib/all-MiniLM-L6-v2-finetuned-on-promise-nf-sub-classes-classifier
15
+
16
+ This model is a fine-tuned version of [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.2538
19
+ - Epoch: 19
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1840, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
39
+ - training_precision: float32
40
+
41
+ ### Training results
42
+
43
+ | Train Loss | Epoch |
44
+ |:----------:|:-----:|
45
+ | 2.2379 | 0 |
46
+ | 2.0374 | 1 |
47
+ | 1.7129 | 2 |
48
+ | 1.3440 | 3 |
49
+ | 1.0497 | 4 |
50
+ | 0.8493 | 5 |
51
+ | 0.7201 | 6 |
52
+ | 0.6124 | 7 |
53
+ | 0.5268 | 8 |
54
+ | 0.4709 | 9 |
55
+ | 0.4191 | 10 |
56
+ | 0.3842 | 11 |
57
+ | 0.3505 | 12 |
58
+ | 0.3214 | 13 |
59
+ | 0.3017 | 14 |
60
+ | 0.2863 | 15 |
61
+ | 0.2711 | 16 |
62
+ | 0.2612 | 17 |
63
+ | 0.2564 | 18 |
64
+ | 0.2538 | 19 |
65
+
66
+
67
+ ### Framework versions
68
+
69
+ - Transformers 4.42.3
70
+ - TensorFlow 2.15.0
71
+ - Datasets 2.19.1
72
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 384,
12
+ "id2label": {
13
+ "0": "A",
14
+ "1": "FT",
15
+ "2": "L",
16
+ "3": "LF",
17
+ "4": "MN",
18
+ "5": "O",
19
+ "6": "PE",
20
+ "7": "SC",
21
+ "8": "SE",
22
+ "9": "US"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 1536,
26
+ "label2id": {
27
+ "A": 0,
28
+ "FT": 1,
29
+ "L": 2,
30
+ "LF": 3,
31
+ "MN": 4,
32
+ "O": 5,
33
+ "PE": 6,
34
+ "SC": 7,
35
+ "SE": 8,
36
+ "US": 9
37
+ },
38
+ "layer_norm_eps": 1e-12,
39
+ "max_position_embeddings": 512,
40
+ "model_type": "bert",
41
+ "num_attention_heads": 12,
42
+ "num_hidden_layers": 6,
43
+ "pad_token_id": 0,
44
+ "position_embedding_type": "absolute",
45
+ "transformers_version": "4.42.3",
46
+ "type_vocab_size": 2,
47
+ "use_cache": true,
48
+ "vocab_size": 30522
49
+ }
logs/train/events.out.tfevents.1734083426.iste.2400210.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fe583027d5130eef9454f73c725703584154f3e3d2d271de20952592a8b2f23
3
+ size 1835133
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40057b331198209a5153a8e8089bb112d7b9df324a4fbf169c7ace11022dc6b8
3
+ size 91025656
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 128,
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "stride": 0,
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]"
64
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff