End of training
Browse files- README.md +9 -32
- config.json +1 -0
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -14,11 +14,11 @@ probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Train Loss: 0.
|
18 |
-
- Validation Loss:
|
19 |
-
- Train F1: 0.
|
20 |
-
- Train Accuracy: 0.
|
21 |
-
- Epoch:
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -37,39 +37,16 @@ More information needed
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
-
- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps':
|
41 |
- training_precision: float32
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
| Train Loss | Validation Loss | Train F1 | Train Accuracy | Epoch |
|
46 |
|:----------:|:---------------:|:--------:|:--------------:|:-----:|
|
47 |
-
|
|
48 |
-
|
|
49 |
-
|
|
50 |
-
| 0.8341 | 1.5888 | 0.4364 | 0.5533 | 3 |
|
51 |
-
| 0.6159 | 1.7822 | 0.4280 | 0.5392 | 4 |
|
52 |
-
| 0.4387 | 1.9859 | 0.4357 | 0.5301 | 5 |
|
53 |
-
| 0.3102 | 2.2088 | 0.4346 | 0.5257 | 6 |
|
54 |
-
| 0.2183 | 2.3689 | 0.4353 | 0.5386 | 7 |
|
55 |
-
| 0.1620 | 2.5631 | 0.4396 | 0.5379 | 8 |
|
56 |
-
| 0.1254 | 2.6995 | 0.4314 | 0.5342 | 9 |
|
57 |
-
| 0.0959 | 2.8182 | 0.4285 | 0.5333 | 10 |
|
58 |
-
| 0.0788 | 2.8996 | 0.4204 | 0.5334 | 11 |
|
59 |
-
| 0.0677 | 3.0209 | 0.4347 | 0.5318 | 12 |
|
60 |
-
| 0.0562 | 3.1115 | 0.4282 | 0.5222 | 13 |
|
61 |
-
| 0.0493 | 3.1710 | 0.4306 | 0.5268 | 14 |
|
62 |
-
| 0.0435 | 3.1507 | 0.4280 | 0.5322 | 15 |
|
63 |
-
| 0.0391 | 3.3222 | 0.4165 | 0.5110 | 16 |
|
64 |
-
| 0.0321 | 3.3243 | 0.4218 | 0.5309 | 17 |
|
65 |
-
| 0.0298 | 3.3675 | 0.4252 | 0.5307 | 18 |
|
66 |
-
| 0.0255 | 3.4341 | 0.4148 | 0.5217 | 19 |
|
67 |
-
| 0.0230 | 3.4253 | 0.4311 | 0.5250 | 20 |
|
68 |
-
| 0.0195 | 3.5133 | 0.4278 | 0.5233 | 21 |
|
69 |
-
| 0.0166 | 3.5915 | 0.4277 | 0.5301 | 22 |
|
70 |
-
| 0.0165 | 3.5547 | 0.4191 | 0.5340 | 23 |
|
71 |
-
| 0.0142 | 3.6109 | 0.4333 | 0.5362 | 24 |
|
72 |
-
| 0.0126 | 3.6501 | 0.4317 | 0.5275 | 25 |
|
73 |
|
74 |
|
75 |
### Framework versions
|
|
|
14 |
|
15 |
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 0.1805
|
18 |
+
- Validation Loss: 0.1696
|
19 |
+
- Train F1: 0.1393
|
20 |
+
- Train Accuracy: 0.1994
|
21 |
+
- Epoch: 2
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
+
- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 135650, '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}
|
41 |
- training_precision: float32
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
| Train Loss | Validation Loss | Train F1 | Train Accuracy | Epoch |
|
46 |
|:----------:|:---------------:|:--------:|:--------------:|:-----:|
|
47 |
+
| 0.2043 | 0.1756 | 0.0314 | 0.0396 | 0 |
|
48 |
+
| 0.2031 | 0.1816 | 0.1156 | 0.2583 | 1 |
|
49 |
+
| 0.1805 | 0.1696 | 0.1393 | 0.1994 | 2 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
|
51 |
|
52 |
### Framework versions
|
config.json
CHANGED
@@ -74,6 +74,7 @@
|
|
74 |
"n_heads": 12,
|
75 |
"n_layers": 6,
|
76 |
"pad_token_id": 0,
|
|
|
77 |
"qa_dropout": 0.1,
|
78 |
"seq_classif_dropout": 0.2,
|
79 |
"sinusoidal_pos_embds": false,
|
|
|
74 |
"n_heads": 12,
|
75 |
"n_layers": 6,
|
76 |
"pad_token_id": 0,
|
77 |
+
"problem_type": "multi_label_classification",
|
78 |
"qa_dropout": 0.1,
|
79 |
"seq_classif_dropout": 0.2,
|
80 |
"sinusoidal_pos_embds": false,
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 268031680
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd472e2aea5edcf1e1ffadb87858b13d76ec72cb6d0e3783ebfca4190cc0d653
|
3 |
size 268031680
|