freyagracia commited on
Commit
2d10af4
1 Parent(s): 4598db6

Training in progress epoch 0

Browse files
Files changed (8) hide show
  1. README.md +54 -0
  2. config.json +84 -0
  3. merges.txt +0 -0
  4. special_tokens_map.json +15 -0
  5. tf_model.h5 +3 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +57 -0
  8. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: w11wo/indonesian-roberta-base-posp-tagger
4
+ tags:
5
+ - generated_from_keras_callback
6
+ model-index:
7
+ - name: freyagracia/indonesian-roberta-base-posp-tagger-finetuned-tweet_pemilu_postagger_2
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
+ # freyagracia/indonesian-roberta-base-posp-tagger-finetuned-tweet_pemilu_postagger_2
15
+
16
+ This model is a fine-tuned version of [w11wo/indonesian-roberta-base-posp-tagger](https://huggingface.co/w11wo/indonesian-roberta-base-posp-tagger) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Train Loss: 12.0302
19
+ - Validation Loss: 11.6101
20
+ - Epoch: 0
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': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': -969, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
40
+ - training_precision: mixed_float16
41
+
42
+ ### Training results
43
+
44
+ | Train Loss | Validation Loss | Epoch |
45
+ |:----------:|:---------------:|:-----:|
46
+ | 12.0302 | 11.6101 | 0 |
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.35.2
52
+ - TensorFlow 2.15.0
53
+ - Datasets 2.16.0
54
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "w11wo/indonesian-roberta-base-posp-tagger",
3
+ "architectures": [
4
+ "RobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "B-PPO",
16
+ "1": "B-KUA",
17
+ "2": "B-ADV",
18
+ "3": "B-PRN",
19
+ "4": "B-VBI",
20
+ "5": "B-PAR",
21
+ "6": "B-VBP",
22
+ "7": "B-NNP",
23
+ "8": "B-UNS",
24
+ "9": "B-VBT",
25
+ "10": "B-VBL",
26
+ "11": "B-NNO",
27
+ "12": "B-ADJ",
28
+ "13": "B-PRR",
29
+ "14": "B-PRK",
30
+ "15": "B-CCN",
31
+ "16": "B-$$$",
32
+ "17": "B-ADK",
33
+ "18": "B-ART",
34
+ "19": "B-CSN",
35
+ "20": "B-NUM",
36
+ "21": "B-SYM",
37
+ "22": "B-INT",
38
+ "23": "B-NEG",
39
+ "24": "B-PRI",
40
+ "25": "B-VBE"
41
+ },
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 3072,
44
+ "label2id": {
45
+ "B-$$$": 16,
46
+ "B-ADJ": 12,
47
+ "B-ADK": 17,
48
+ "B-ADV": 2,
49
+ "B-ART": 18,
50
+ "B-CCN": 15,
51
+ "B-CSN": 19,
52
+ "B-INT": 22,
53
+ "B-KUA": 1,
54
+ "B-NEG": 23,
55
+ "B-NNO": 11,
56
+ "B-NNP": 7,
57
+ "B-NUM": 20,
58
+ "B-PAR": 5,
59
+ "B-PPO": 0,
60
+ "B-PRI": 24,
61
+ "B-PRK": 14,
62
+ "B-PRN": 3,
63
+ "B-PRR": 13,
64
+ "B-SYM": 21,
65
+ "B-UNS": 8,
66
+ "B-VBE": 25,
67
+ "B-VBI": 4,
68
+ "B-VBL": 10,
69
+ "B-VBP": 6,
70
+ "B-VBT": 9
71
+ },
72
+ "layer_norm_eps": 1e-05,
73
+ "max_position_embeddings": 514,
74
+ "model_type": "roberta",
75
+ "num_attention_heads": 12,
76
+ "num_hidden_layers": 12,
77
+ "pad_token_id": 1,
78
+ "position_embedding_type": "absolute",
79
+ "torch_dtype": "float32",
80
+ "transformers_version": "4.35.2",
81
+ "type_vocab_size": 1,
82
+ "use_cache": true,
83
+ "vocab_size": 50265
84
+ }
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:ea1d6b64edb209f63d9d3c493ab17c8d6d4e6f684263fc1768a17bb5a49bb0bf
3
+ size 655071156
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": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
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": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
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": 1000000000000000019884624838656,
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