cicids2018-distilbert
Browse files- README.md +1 -19
- config.json +4 -5
- model.safetensors +1 -1
- training_args.bin +2 -2
README.md
CHANGED
@@ -3,8 +3,6 @@ license: apache-2.0
|
|
3 |
base_model: distilbert-base-uncased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
-
metrics:
|
7 |
-
- accuracy
|
8 |
model-index:
|
9 |
- name: cicids2018-distilbert
|
10 |
results: []
|
@@ -16,9 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
# cicids2018-distilbert
|
17 |
|
18 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
19 |
-
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.6071
|
21 |
-
- Accuracy: 0.75
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -43,20 +38,7 @@ The following hyperparameters were used during training:
|
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
-
- num_epochs:
|
47 |
-
|
48 |
-
### Training results
|
49 |
-
|
50 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
-
| No log | 1.0 | 1 | 0.6822 | 0.5 |
|
53 |
-
| No log | 2.0 | 2 | 0.6674 | 0.5 |
|
54 |
-
| No log | 3.0 | 3 | 0.6530 | 0.75 |
|
55 |
-
| No log | 4.0 | 4 | 0.6379 | 0.75 |
|
56 |
-
| No log | 5.0 | 5 | 0.6242 | 0.75 |
|
57 |
-
| No log | 6.0 | 6 | 0.6133 | 0.75 |
|
58 |
-
| No log | 7.0 | 7 | 0.6071 | 0.75 |
|
59 |
-
|
60 |
|
61 |
### Framework versions
|
62 |
|
|
|
3 |
base_model: distilbert-base-uncased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: cicids2018-distilbert
|
8 |
results: []
|
|
|
14 |
# cicids2018-distilbert
|
15 |
|
16 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
38 |
- seed: 42
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
|
43 |
### Framework versions
|
44 |
|
config.json
CHANGED
@@ -9,20 +9,19 @@
|
|
9 |
"dropout": 0.1,
|
10 |
"hidden_dim": 3072,
|
11 |
"id2label": {
|
12 |
-
"0": "
|
13 |
-
"1": "
|
14 |
},
|
15 |
"initializer_range": 0.02,
|
16 |
"label2id": {
|
17 |
-
"
|
18 |
-
"
|
19 |
},
|
20 |
"max_position_embeddings": 512,
|
21 |
"model_type": "distilbert",
|
22 |
"n_heads": 12,
|
23 |
"n_layers": 6,
|
24 |
"pad_token_id": 0,
|
25 |
-
"problem_type": "single_label_classification",
|
26 |
"qa_dropout": 0.1,
|
27 |
"seq_classif_dropout": 0.2,
|
28 |
"sinusoidal_pos_embds": false,
|
|
|
9 |
"dropout": 0.1,
|
10 |
"hidden_dim": 3072,
|
11 |
"id2label": {
|
12 |
+
"0": "BENIGN",
|
13 |
+
"1": "MALICIOUS"
|
14 |
},
|
15 |
"initializer_range": 0.02,
|
16 |
"label2id": {
|
17 |
+
"BENIGN": 0,
|
18 |
+
"MALICIOUS": 1
|
19 |
},
|
20 |
"max_position_embeddings": 512,
|
21 |
"model_type": "distilbert",
|
22 |
"n_heads": 12,
|
23 |
"n_layers": 6,
|
24 |
"pad_token_id": 0,
|
|
|
25 |
"qa_dropout": 0.1,
|
26 |
"seq_classif_dropout": 0.2,
|
27 |
"sinusoidal_pos_embds": false,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267832560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99fc238fcc06104edb812c139b21fb88c157d81314c5b73a8ca91cf2e3f9b46a
|
3 |
size 267832560
|
training_args.bin
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 sha256:4126c5b5b90ade449eebd6f20307161fd202a64b00f7297a6c4fa2cb976a6379
|
3 |
+
size 4536
|