Commit
•
24e8600
1
Parent(s):
dd4a42c
Training complete
Browse files- README.md +1 -35
- config.json +0 -1
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -5,24 +5,9 @@ tags:
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- clinc_oos
|
8 |
-
metrics:
|
9 |
-
- accuracy
|
10 |
model-index:
|
11 |
- name: distilbert-base-uncased-distilled-clinc
|
12 |
-
results:
|
13 |
-
- task:
|
14 |
-
name: Text Classification
|
15 |
-
type: text-classification
|
16 |
-
dataset:
|
17 |
-
name: clinc_oos
|
18 |
-
type: clinc_oos
|
19 |
-
config: plus
|
20 |
-
split: validation
|
21 |
-
args: plus
|
22 |
-
metrics:
|
23 |
-
- name: Accuracy
|
24 |
-
type: accuracy
|
25 |
-
value: 0.94
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -31,9 +16,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
31 |
# distilbert-base-uncased-distilled-clinc
|
32 |
|
33 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
|
34 |
-
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 0.1261
|
36 |
-
- Accuracy: 0.94
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -60,22 +42,6 @@ The following hyperparameters were used during training:
|
|
60 |
- lr_scheduler_type: linear
|
61 |
- num_epochs: 10
|
62 |
|
63 |
-
### Training results
|
64 |
-
|
65 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
66 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
67 |
-
| 1.2318 | 1.0 | 318 | 0.7448 | 0.7023 |
|
68 |
-
| 0.5696 | 2.0 | 636 | 0.3308 | 0.8632 |
|
69 |
-
| 0.2888 | 3.0 | 954 | 0.1941 | 0.9187 |
|
70 |
-
| 0.1913 | 4.0 | 1272 | 0.1557 | 0.9284 |
|
71 |
-
| 0.1563 | 5.0 | 1590 | 0.1417 | 0.9365 |
|
72 |
-
| 0.1405 | 6.0 | 1908 | 0.1353 | 0.9387 |
|
73 |
-
| 0.1318 | 7.0 | 2226 | 0.1316 | 0.9403 |
|
74 |
-
| 0.1268 | 8.0 | 2544 | 0.1284 | 0.9426 |
|
75 |
-
| 0.1239 | 9.0 | 2862 | 0.1266 | 0.9394 |
|
76 |
-
| 0.122 | 10.0 | 3180 | 0.1261 | 0.94 |
|
77 |
-
|
78 |
-
|
79 |
### Framework versions
|
80 |
|
81 |
- Transformers 4.34.1
|
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- clinc_oos
|
|
|
|
|
8 |
model-index:
|
9 |
- name: distilbert-base-uncased-distilled-clinc
|
10 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
16 |
# distilbert-base-uncased-distilled-clinc
|
17 |
|
18 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
42 |
- lr_scheduler_type: linear
|
43 |
- num_epochs: 10
|
44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
45 |
### Framework versions
|
46 |
|
47 |
- Transformers 4.34.1
|
config.json
CHANGED
@@ -320,7 +320,6 @@
|
|
320 |
"n_heads": 12,
|
321 |
"n_layers": 6,
|
322 |
"pad_token_id": 0,
|
323 |
-
"problem_type": "single_label_classification",
|
324 |
"qa_dropout": 0.1,
|
325 |
"seq_classif_dropout": 0.2,
|
326 |
"sinusoidal_pos_embds": false,
|
|
|
320 |
"n_heads": 12,
|
321 |
"n_layers": 6,
|
322 |
"pad_token_id": 0,
|
|
|
323 |
"qa_dropout": 0.1,
|
324 |
"seq_classif_dropout": 0.2,
|
325 |
"sinusoidal_pos_embds": false,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 268312874
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab68350c95a2b9a305e007e093c030f624e0a32c23d06ed5a471bca3bac583f4
|
3 |
size 268312874
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12c19648110c21d21f86aa8535565d6c5f099dbf54f5b4d2b3fa019cf385b74a
|
3 |
size 4664
|