Upload TFDistilBertForTokenClassification
Browse files- README.md +7 -9
- config.json +16 -16
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-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 |
-
- Epoch:
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -36,18 +36,16 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 4e-05, 'decay_steps':
|
40 |
- training_precision: float32
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
-
| 0.
|
47 |
-
| 0.
|
48 |
-
| 0.
|
49 |
-
| 0.1261 | 0.3577 | 3 |
|
50 |
-
| 0.0896 | 0.3813 | 4 |
|
51 |
|
52 |
|
53 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 0.1913
|
19 |
+
- Validation Loss: 0.3219
|
20 |
+
- Epoch: 2
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 4e-05, 'decay_steps': 2205, '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': 0.07}
|
40 |
- training_precision: float32
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
+
| 0.5249 | 0.3549 | 0 |
|
47 |
+
| 0.2824 | 0.3316 | 1 |
|
48 |
+
| 0.1913 | 0.3219 | 2 |
|
|
|
|
|
49 |
|
50 |
|
51 |
### Framework versions
|
config.json
CHANGED
@@ -10,25 +10,25 @@
|
|
10 |
"hidden_dim": 3072,
|
11 |
"id2label": {
|
12 |
"0": "O",
|
13 |
-
"1": "B-
|
14 |
-
"2": "I-
|
15 |
-
"3": "B-
|
16 |
-
"4": "I-
|
17 |
-
"5": "B-
|
18 |
-
"6": "I-
|
19 |
-
"7": "B-
|
20 |
-
"8": "I-
|
21 |
},
|
22 |
"initializer_range": 0.02,
|
23 |
"label2id": {
|
24 |
-
"B-allergy_name":
|
25 |
-
"B-cancer":
|
26 |
-
"B-chronic_disease":
|
27 |
-
"B-treatment":
|
28 |
-
"I-allergy_name":
|
29 |
-
"I-cancer":
|
30 |
-
"I-chronic_disease":
|
31 |
-
"I-treatment":
|
32 |
"O": 0
|
33 |
},
|
34 |
"max_position_embeddings": 512,
|
|
|
10 |
"hidden_dim": 3072,
|
11 |
"id2label": {
|
12 |
"0": "O",
|
13 |
+
"1": "B-allergy_name",
|
14 |
+
"2": "I-allergy_name",
|
15 |
+
"3": "B-cancer",
|
16 |
+
"4": "I-cancer",
|
17 |
+
"5": "B-chronic_disease",
|
18 |
+
"6": "I-chronic_disease",
|
19 |
+
"7": "B-treatment",
|
20 |
+
"8": "I-treatment"
|
21 |
},
|
22 |
"initializer_range": 0.02,
|
23 |
"label2id": {
|
24 |
+
"B-allergy_name": 1,
|
25 |
+
"B-cancer": 3,
|
26 |
+
"B-chronic_disease": 5,
|
27 |
+
"B-treatment": 7,
|
28 |
+
"I-allergy_name": 2,
|
29 |
+
"I-cancer": 4,
|
30 |
+
"I-chronic_disease": 6,
|
31 |
+
"I-treatment": 8,
|
32 |
"O": 0
|
33 |
},
|
34 |
"max_position_embeddings": 512,
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 265606416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93346d02c5635935e1fb66b6b7c7256eb0cdd95fb1a0ab30bf404aa7cdc105bf
|
3 |
size 265606416
|