kasrahabib commited on
Commit
68e6043
·
verified ·
1 Parent(s): c9dfed2

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: FacebookAI/roberta-base
4
+ tags:
5
+ - generated_from_keras_callback
6
+ model-index:
7
+ - name: kasrahabib/roberta-base-finetuned-iso29148-promise-km-labels-all-cls
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/roberta-base-finetuned-iso29148-promise-km-labels-all-cls
15
+
16
+ This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.0093
19
+ - Validation Loss: 0.1119
20
+ - Epoch: 29
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - 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': 2370, '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}
40
+ - training_precision: float32
41
+
42
+ ### Training results
43
+
44
+ | Train Loss | Validation Loss | Epoch |
45
+ |:----------:|:---------------:|:-----:|
46
+ | 2.2048 | 1.6598 | 0 |
47
+ | 1.1216 | 0.5631 | 1 |
48
+ | 0.3896 | 0.2574 | 2 |
49
+ | 0.1978 | 0.1997 | 3 |
50
+ | 0.1204 | 0.1526 | 4 |
51
+ | 0.0676 | 0.1887 | 5 |
52
+ | 0.0435 | 0.1289 | 6 |
53
+ | 0.0338 | 0.1219 | 7 |
54
+ | 0.0291 | 0.1140 | 8 |
55
+ | 0.0372 | 0.1829 | 9 |
56
+ | 0.0655 | 0.2036 | 10 |
57
+ | 0.0654 | 0.3368 | 11 |
58
+ | 0.1950 | 0.3786 | 12 |
59
+ | 0.0544 | 0.1708 | 13 |
60
+ | 0.0195 | 0.1446 | 14 |
61
+ | 0.0166 | 0.1364 | 15 |
62
+ | 0.0154 | 0.1302 | 16 |
63
+ | 0.0136 | 0.1272 | 17 |
64
+ | 0.0127 | 0.1251 | 18 |
65
+ | 0.0119 | 0.1248 | 19 |
66
+ | 0.0115 | 0.1231 | 20 |
67
+ | 0.0112 | 0.1214 | 21 |
68
+ | 0.0107 | 0.1190 | 22 |
69
+ | 0.0104 | 0.1166 | 23 |
70
+ | 0.0100 | 0.1157 | 24 |
71
+ | 0.0095 | 0.1131 | 25 |
72
+ | 0.0096 | 0.1126 | 26 |
73
+ | 0.0092 | 0.1120 | 27 |
74
+ | 0.0094 | 0.1119 | 28 |
75
+ | 0.0093 | 0.1119 | 29 |
76
+
77
+
78
+ ### Framework versions
79
+
80
+ - Transformers 4.42.3
81
+ - TensorFlow 2.15.0
82
+ - Datasets 2.19.1
83
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "A",
15
+ "1": "F",
16
+ "2": "FT",
17
+ "3": "L",
18
+ "4": "LF",
19
+ "5": "MN",
20
+ "6": "O",
21
+ "7": "PE",
22
+ "8": "SC",
23
+ "9": "SE",
24
+ "10": "US"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 3072,
28
+ "label2id": {
29
+ "A": 0,
30
+ "F": 1,
31
+ "FT": 2,
32
+ "L": 3,
33
+ "LF": 4,
34
+ "MN": 5,
35
+ "O": 6,
36
+ "PE": 7,
37
+ "SC": 8,
38
+ "SE": 9,
39
+ "US": 10
40
+ },
41
+ "layer_norm_eps": 1e-05,
42
+ "max_position_embeddings": 514,
43
+ "model_type": "roberta",
44
+ "num_attention_heads": 12,
45
+ "num_hidden_layers": 12,
46
+ "pad_token_id": 1,
47
+ "position_embedding_type": "absolute",
48
+ "transformers_version": "4.42.3",
49
+ "type_vocab_size": 1,
50
+ "use_cache": true,
51
+ "vocab_size": 50265
52
+ }
logs/train/events.out.tfevents.1724598448.iste.821582.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1181189be59cbac35b0977f90c677509dcef9ce5837d3883efb64f2056218447
3
+ size 3648264
logs/validation/events.out.tfevents.1724598501.iste.821582.1.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fde0356d45ae8958370ff2415b0e74876d8a4897a9f5d1d110f55c3f3aa22aa
3
+ size 4755
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:874003f96d479dbacc29769bef5644254ca570951a552cb78a08d19d0ebc41de
3
+ size 498905920
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
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
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff