kasrahabib
commited on
Upload folder using huggingface_hub
Browse files- README.md +83 -0
- config.json +50 -0
- logs/train/events.out.tfevents.1724597231.iste.784101.0.v2 +3 -0
- logs/validation/events.out.tfevents.1724597282.iste.784101.1.v2 +3 -0
- merges.txt +0 -0
- special_tokens_map.json +15 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- vocab.json +0 -0
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-nf-subclasses-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-nf-subclasses-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: 0.0124
|
19 |
+
- Validation Loss: 0.1623
|
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': 1770, '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 |
+
| 2.1848 | 1.7407 | 0 |
|
47 |
+
| 1.2611 | 0.8464 | 1 |
|
48 |
+
| 0.5377 | 0.4928 | 2 |
|
49 |
+
| 0.2843 | 0.2790 | 3 |
|
50 |
+
| 0.1531 | 0.3657 | 4 |
|
51 |
+
| 0.1186 | 0.1997 | 5 |
|
52 |
+
| 0.0646 | 0.1742 | 6 |
|
53 |
+
| 0.0498 | 0.1731 | 7 |
|
54 |
+
| 0.0417 | 0.1709 | 8 |
|
55 |
+
| 0.0351 | 0.1689 | 9 |
|
56 |
+
| 0.0309 | 0.1659 | 10 |
|
57 |
+
| 0.0270 | 0.1674 | 11 |
|
58 |
+
| 0.0255 | 0.1687 | 12 |
|
59 |
+
| 0.0229 | 0.1665 | 13 |
|
60 |
+
| 0.0210 | 0.1673 | 14 |
|
61 |
+
| 0.0193 | 0.1677 | 15 |
|
62 |
+
| 0.0185 | 0.1664 | 16 |
|
63 |
+
| 0.0168 | 0.1658 | 17 |
|
64 |
+
| 0.0162 | 0.1649 | 18 |
|
65 |
+
| 0.0156 | 0.1670 | 19 |
|
66 |
+
| 0.0150 | 0.1678 | 20 |
|
67 |
+
| 0.0144 | 0.1656 | 21 |
|
68 |
+
| 0.0141 | 0.1653 | 22 |
|
69 |
+
| 0.0138 | 0.1662 | 23 |
|
70 |
+
| 0.0132 | 0.1668 | 24 |
|
71 |
+
| 0.0127 | 0.1629 | 25 |
|
72 |
+
| 0.0125 | 0.1614 | 26 |
|
73 |
+
| 0.0123 | 0.1619 | 27 |
|
74 |
+
| 0.0122 | 0.1624 | 28 |
|
75 |
+
| 0.0124 | 0.1623 | 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 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "FT",
|
16 |
+
"2": "L",
|
17 |
+
"3": "LF",
|
18 |
+
"4": "MN",
|
19 |
+
"5": "O",
|
20 |
+
"6": "PE",
|
21 |
+
"7": "SC",
|
22 |
+
"8": "SE",
|
23 |
+
"9": "US"
|
24 |
+
},
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"intermediate_size": 3072,
|
27 |
+
"label2id": {
|
28 |
+
"A": 0,
|
29 |
+
"FT": 1,
|
30 |
+
"L": 2,
|
31 |
+
"LF": 3,
|
32 |
+
"MN": 4,
|
33 |
+
"O": 5,
|
34 |
+
"PE": 6,
|
35 |
+
"SC": 7,
|
36 |
+
"SE": 8,
|
37 |
+
"US": 9
|
38 |
+
},
|
39 |
+
"layer_norm_eps": 1e-05,
|
40 |
+
"max_position_embeddings": 514,
|
41 |
+
"model_type": "roberta",
|
42 |
+
"num_attention_heads": 12,
|
43 |
+
"num_hidden_layers": 12,
|
44 |
+
"pad_token_id": 1,
|
45 |
+
"position_embedding_type": "absolute",
|
46 |
+
"transformers_version": "4.42.3",
|
47 |
+
"type_vocab_size": 1,
|
48 |
+
"use_cache": true,
|
49 |
+
"vocab_size": 50265
|
50 |
+
}
|
logs/train/events.out.tfevents.1724597231.iste.784101.0.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23abb1fc999d0ee82fcf2a7f7f396eb2f86095377638a21b9e8a892b8358c6ee
|
3 |
+
size 3648264
|
logs/validation/events.out.tfevents.1724597282.iste.784101.1.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ee6456447fa1f6fec5a33a529052cd2f83da41e911f1f7a1188881f92d84185
|
3 |
+
size 4754
|
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 sha256:691d66c2ad3376d925ec3ffb879c285db1333a8a1ed0bf4faf8fa0db7f037142
|
3 |
+
size 498902848
|
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
|
|