apwic commited on
Commit
efbb324
1 Parent(s): 50ffcc1

Training in progress epoch 0

Browse files
Files changed (3) hide show
  1. README.md +9 -11
  2. config.json +79 -79
  3. tf_model.h5 +2 -2
README.md CHANGED
@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.1072
19
- - Validation Loss: 0.1791
20
- - Train Accuracy: 0.9491
21
- - Epoch: 2
22
 
23
  ## Model description
24
 
@@ -37,21 +37,19 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 4698, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
41
  - training_precision: float32
42
 
43
  ### Training results
44
 
45
  | Train Loss | Validation Loss | Train Accuracy | Epoch |
46
  |:----------:|:---------------:|:--------------:|:-----:|
47
- | 0.3745 | 0.1815 | 0.9461 | 0 |
48
- | 0.1501 | 0.1795 | 0.9475 | 1 |
49
- | 0.1072 | 0.1791 | 0.9491 | 2 |
50
 
51
 
52
  ### Framework versions
53
 
54
- - Transformers 4.33.2
55
- - TensorFlow 2.13.0
56
- - Datasets 2.14.5
57
  - Tokenizers 0.13.3
 
15
 
16
  This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.4822
19
+ - Validation Loss: 0.1974
20
+ - Train Accuracy: 0.9415
21
+ - Epoch: 0
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2352, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
41
  - training_precision: float32
42
 
43
  ### Training results
44
 
45
  | Train Loss | Validation Loss | Train Accuracy | Epoch |
46
  |:----------:|:---------------:|:--------------:|:-----:|
47
+ | 0.4822 | 0.1974 | 0.9415 | 0 |
 
 
48
 
49
 
50
  ### Framework versions
51
 
52
+ - Transformers 4.33.0
53
+ - TensorFlow 2.12.0
54
+ - Datasets 2.14.6
55
  - Tokenizers 0.13.3
config.json CHANGED
@@ -11,88 +11,88 @@
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
13
  "id2label": {
14
- "0": "B-CRD",
15
- "1": "B-DAT",
16
- "2": "B-EVT",
17
- "3": "B-FAC",
18
- "4": "B-GPE",
19
- "5": "B-LAN",
20
- "6": "B-LAW",
21
- "7": "B-LOC",
22
- "8": "B-MON",
23
- "9": "B-NOR",
24
- "10": "B-ORD",
25
- "11": "B-ORG",
26
- "12": "B-PER",
27
- "13": "B-PRC",
28
- "14": "B-PRD",
29
- "15": "B-QTY",
30
- "16": "B-REG",
31
- "17": "B-TIM",
32
- "18": "B-WOA",
33
- "19": "I-CRD",
34
- "20": "I-DAT",
35
- "21": "I-EVT",
36
- "22": "I-FAC",
37
- "23": "I-GPE",
38
- "24": "I-LAN",
39
- "25": "I-LAW",
40
- "26": "I-LOC",
41
- "27": "I-MON",
42
- "28": "I-NOR",
43
- "29": "I-ORD",
44
- "30": "I-ORG",
45
- "31": "I-PER",
46
- "32": "I-PRC",
47
- "33": "I-PRD",
48
- "34": "I-QTY",
49
- "35": "I-REG",
50
- "36": "I-TIM",
51
- "37": "I-WOA",
52
- "38": "O"
53
  },
54
  "initializer_range": 0.02,
55
  "intermediate_size": 3072,
56
  "label2id": {
57
- "B-CRD": 0,
58
- "B-DAT": 1,
59
- "B-EVT": 2,
60
- "B-FAC": 3,
61
- "B-GPE": 4,
62
- "B-LAN": 5,
63
- "B-LAW": 6,
64
- "B-LOC": 7,
65
- "B-MON": 8,
66
- "B-NOR": 9,
67
- "B-ORD": 10,
68
- "B-ORG": 11,
69
- "B-PER": 12,
70
- "B-PRC": 13,
71
- "B-PRD": 14,
72
- "B-QTY": 15,
73
- "B-REG": 16,
74
- "B-TIM": 17,
75
- "B-WOA": 18,
76
- "I-CRD": 19,
77
- "I-DAT": 20,
78
- "I-EVT": 21,
79
- "I-FAC": 22,
80
- "I-GPE": 23,
81
- "I-LAN": 24,
82
- "I-LAW": 25,
83
- "I-LOC": 26,
84
- "I-MON": 27,
85
- "I-NOR": 28,
86
- "I-ORD": 29,
87
- "I-ORG": 30,
88
- "I-PER": 31,
89
- "I-PRC": 32,
90
- "I-PRD": 33,
91
- "I-QTY": 34,
92
- "I-REG": 35,
93
- "I-TIM": 36,
94
- "I-WOA": 37,
95
- "O": 38
96
  },
97
  "layer_norm_eps": 1e-12,
98
  "max_position_embeddings": 512,
@@ -102,7 +102,7 @@
102
  "output_past": true,
103
  "pad_token_id": 0,
104
  "position_embedding_type": "absolute",
105
- "transformers_version": "4.33.2",
106
  "type_vocab_size": 2,
107
  "use_cache": true,
108
  "vocab_size": 31923
 
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
13
  "id2label": {
14
+ "0": "O",
15
+ "1": "B-CRD",
16
+ "2": "I-CRD",
17
+ "3": "B-DAT",
18
+ "4": "I-DAT",
19
+ "5": "B-EVT",
20
+ "6": "I-EVT",
21
+ "7": "B-FAC",
22
+ "8": "I-FAC",
23
+ "9": "B-GPE",
24
+ "10": "I-GPE",
25
+ "11": "B-LAW",
26
+ "12": "I-LAW",
27
+ "13": "B-LOC",
28
+ "14": "I-LOC",
29
+ "15": "B-MON",
30
+ "16": "I-MON",
31
+ "17": "B-NOR",
32
+ "18": "I-NOR",
33
+ "19": "B-ORD",
34
+ "20": "I-ORD",
35
+ "21": "B-ORG",
36
+ "22": "I-ORG",
37
+ "23": "B-PER",
38
+ "24": "I-PER",
39
+ "25": "B-PRC",
40
+ "26": "I-PRC",
41
+ "27": "B-PRD",
42
+ "28": "I-PRD",
43
+ "29": "B-QTY",
44
+ "30": "I-QTY",
45
+ "31": "B-REG",
46
+ "32": "I-REG",
47
+ "33": "B-TIM",
48
+ "34": "I-TIM",
49
+ "35": "B-WOA",
50
+ "36": "I-WOA",
51
+ "37": "B-LAN",
52
+ "38": "I-LAN"
53
  },
54
  "initializer_range": 0.02,
55
  "intermediate_size": 3072,
56
  "label2id": {
57
+ "B-CRD": 1,
58
+ "B-DAT": 3,
59
+ "B-EVT": 5,
60
+ "B-FAC": 7,
61
+ "B-GPE": 9,
62
+ "B-LAN": 37,
63
+ "B-LAW": 11,
64
+ "B-LOC": 13,
65
+ "B-MON": 15,
66
+ "B-NOR": 17,
67
+ "B-ORD": 19,
68
+ "B-ORG": 21,
69
+ "B-PER": 23,
70
+ "B-PRC": 25,
71
+ "B-PRD": 27,
72
+ "B-QTY": 29,
73
+ "B-REG": 31,
74
+ "B-TIM": 33,
75
+ "B-WOA": 35,
76
+ "I-CRD": 2,
77
+ "I-DAT": 4,
78
+ "I-EVT": 6,
79
+ "I-FAC": 8,
80
+ "I-GPE": 10,
81
+ "I-LAN": 38,
82
+ "I-LAW": 12,
83
+ "I-LOC": 14,
84
+ "I-MON": 16,
85
+ "I-NOR": 18,
86
+ "I-ORD": 20,
87
+ "I-ORG": 22,
88
+ "I-PER": 24,
89
+ "I-PRC": 26,
90
+ "I-PRD": 28,
91
+ "I-QTY": 30,
92
+ "I-REG": 32,
93
+ "I-TIM": 34,
94
+ "I-WOA": 36,
95
+ "O": 0
96
  },
97
  "layer_norm_eps": 1e-12,
98
  "max_position_embeddings": 512,
 
102
  "output_past": true,
103
  "pad_token_id": 0,
104
  "position_embedding_type": "absolute",
105
+ "transformers_version": "4.33.0",
106
  "type_vocab_size": 2,
107
  "use_cache": true,
108
  "vocab_size": 31923
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:397d8bb102bfbe9f6e75cf680d4f30a479b446cb88fa21970d2eb170e83b1dbf
3
- size 440276068
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b777dd8f58185bb1b4fd4deb48b78e3b878c34c3855b6c0a129db22dac8857de
3
+ size 440263780