Training in progress epoch 0
Browse files- README.md +9 -11
- config.json +79 -79
- 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.
|
19 |
-
- Validation Loss: 0.
|
20 |
-
- Train Accuracy: 0.
|
21 |
-
- Epoch:
|
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': {'
|
41 |
- training_precision: float32
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
46 |
|:----------:|:---------------:|:--------------:|:-----:|
|
47 |
-
| 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.
|
55 |
-
- TensorFlow 2.
|
56 |
-
- Datasets 2.14.
|
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": "
|
15 |
-
"1": "B-
|
16 |
-
"2": "
|
17 |
-
"3": "B-
|
18 |
-
"4": "
|
19 |
-
"5": "B-
|
20 |
-
"6": "
|
21 |
-
"7": "B-
|
22 |
-
"8": "
|
23 |
-
"9": "B-
|
24 |
-
"10": "
|
25 |
-
"11": "B-
|
26 |
-
"12": "
|
27 |
-
"13": "B-
|
28 |
-
"14": "
|
29 |
-
"15": "B-
|
30 |
-
"16": "
|
31 |
-
"17": "B-
|
32 |
-
"18": "
|
33 |
-
"19": "
|
34 |
-
"20": "I-
|
35 |
-
"21": "
|
36 |
-
"22": "I-
|
37 |
-
"23": "
|
38 |
-
"24": "I-
|
39 |
-
"25": "
|
40 |
-
"26": "I-
|
41 |
-
"27": "
|
42 |
-
"28": "I-
|
43 |
-
"29": "
|
44 |
-
"30": "I-
|
45 |
-
"31": "
|
46 |
-
"32": "I-
|
47 |
-
"33": "
|
48 |
-
"34": "I-
|
49 |
-
"35": "
|
50 |
-
"36": "I-
|
51 |
-
"37": "
|
52 |
-
"38": "
|
53 |
},
|
54 |
"initializer_range": 0.02,
|
55 |
"intermediate_size": 3072,
|
56 |
"label2id": {
|
57 |
-
"B-CRD":
|
58 |
-
"B-DAT":
|
59 |
-
"B-EVT":
|
60 |
-
"B-FAC":
|
61 |
-
"B-GPE":
|
62 |
-
"B-LAN":
|
63 |
-
"B-LAW":
|
64 |
-
"B-LOC":
|
65 |
-
"B-MON":
|
66 |
-
"B-NOR":
|
67 |
-
"B-ORD":
|
68 |
-
"B-ORG":
|
69 |
-
"B-PER":
|
70 |
-
"B-PRC":
|
71 |
-
"B-PRD":
|
72 |
-
"B-QTY":
|
73 |
-
"B-REG":
|
74 |
-
"B-TIM":
|
75 |
-
"B-WOA":
|
76 |
-
"I-CRD":
|
77 |
-
"I-DAT":
|
78 |
-
"I-EVT":
|
79 |
-
"I-FAC":
|
80 |
-
"I-GPE":
|
81 |
-
"I-LAN":
|
82 |
-
"I-LAW":
|
83 |
-
"I-LOC":
|
84 |
-
"I-MON":
|
85 |
-
"I-NOR":
|
86 |
-
"I-ORD":
|
87 |
-
"I-ORG":
|
88 |
-
"I-PER":
|
89 |
-
"I-PRC":
|
90 |
-
"I-PRD":
|
91 |
-
"I-QTY":
|
92 |
-
"I-REG":
|
93 |
-
"I-TIM":
|
94 |
-
"I-WOA":
|
95 |
-
"O":
|
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.
|
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:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b777dd8f58185bb1b4fd4deb48b78e3b878c34c3855b6c0a129db22dac8857de
|
3 |
+
size 440263780
|