Cielciel/aift-model
Browse files- .ipynb_checkpoints/config-checkpoint.json +47 -0
- .ipynb_checkpoints/special_tokens_map-checkpoint.json +7 -0
- .ipynb_checkpoints/tokenizer-checkpoint.json +0 -0
- .ipynb_checkpoints/tokenizer_config-checkpoint.json +55 -0
- README.md +12 -12
- model.safetensors +1 -1
- runs/Jan29_07-41-58_aift-review-classification-multiple-label/events.out.tfevents.1706514135.aift-review-classification-multiple-label.3346014.0 +3 -0
- runs/Jan29_07-41-58_aift-review-classification-multiple-label/events.out.tfevents.1706514641.aift-review-classification-multiple-label.3346014.1 +3 -0
- tokenizer.json +6 -1
- training_args.bin +1 -1
.ipynb_checkpoints/config-checkpoint.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "ads",
|
13 |
+
"1": "bugs",
|
14 |
+
"2": "graphic",
|
15 |
+
"3": "gameplay",
|
16 |
+
"4": "others",
|
17 |
+
"5": "request",
|
18 |
+
"6": "neutral",
|
19 |
+
"7": "negative",
|
20 |
+
"8": "positive"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"label2id": {
|
24 |
+
"ads": 0,
|
25 |
+
"bugs": 1,
|
26 |
+
"gameplay": 3,
|
27 |
+
"graphic": 2,
|
28 |
+
"negative": 7,
|
29 |
+
"neutral": 6,
|
30 |
+
"others": 4,
|
31 |
+
"positive": 8,
|
32 |
+
"request": 5
|
33 |
+
},
|
34 |
+
"max_position_embeddings": 512,
|
35 |
+
"model_type": "distilbert",
|
36 |
+
"n_heads": 12,
|
37 |
+
"n_layers": 6,
|
38 |
+
"pad_token_id": 0,
|
39 |
+
"problem_type": "multi_label_classification",
|
40 |
+
"qa_dropout": 0.1,
|
41 |
+
"seq_classif_dropout": 0.2,
|
42 |
+
"sinusoidal_pos_embds": false,
|
43 |
+
"tie_weights_": true,
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.37.1",
|
46 |
+
"vocab_size": 30522
|
47 |
+
}
|
.ipynb_checkpoints/special_tokens_map-checkpoint.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
.ipynb_checkpoints/tokenizer-checkpoint.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
.ipynb_checkpoints/tokenizer_config-checkpoint.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
README.md
CHANGED
@@ -15,8 +15,8 @@ should 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 the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss:
|
19 |
-
- Accuracy Thresh: 0.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -48,16 +48,16 @@ The following hyperparameters were used during training:
|
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy Thresh |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|:---------------:|
|
51 |
-
|
|
52 |
-
|
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
|
62 |
|
63 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 3.1256
|
19 |
+
- Accuracy Thresh: 0.9115
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy Thresh |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|:---------------:|
|
51 |
+
| 2.2235 | 1.0 | 584 | 1.2682 | 0.7171 |
|
52 |
+
| 1.1638 | 2.0 | 1168 | 1.1630 | 0.8122 |
|
53 |
+
| 0.8698 | 3.0 | 1752 | 1.3732 | 0.8635 |
|
54 |
+
| 0.7107 | 4.0 | 2336 | 1.5609 | 0.8770 |
|
55 |
+
| 0.542 | 5.0 | 2920 | 1.9944 | 0.8927 |
|
56 |
+
| 0.3618 | 6.0 | 3504 | 2.2950 | 0.9012 |
|
57 |
+
| 0.2842 | 7.0 | 4088 | 2.5621 | 0.9018 |
|
58 |
+
| 0.2358 | 8.0 | 4672 | 2.8400 | 0.9079 |
|
59 |
+
| 0.2135 | 9.0 | 5256 | 3.1208 | 0.9111 |
|
60 |
+
| 0.1731 | 10.0 | 5840 | 3.1256 | 0.9115 |
|
61 |
|
62 |
|
63 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267854100
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e244b630a1a449882c108a4cf9dc5b400efb23c36f75c7d94672b1f5a620f12
|
3 |
size 267854100
|
runs/Jan29_07-41-58_aift-review-classification-multiple-label/events.out.tfevents.1706514135.aift-review-classification-multiple-label.3346014.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9207268286c7605a78a1ac4827fd8cb27c7f5a1772830c84fc010f4a5e6f54e2
|
3 |
+
size 10309
|
runs/Jan29_07-41-58_aift-review-classification-multiple-label/events.out.tfevents.1706514641.aift-review-classification-multiple-label.3346014.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7eac90f5a1d572388d8c025e38f1a1d02f1957cd4dc159c1dc1ca7c54bac05e
|
3 |
+
size 418
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 512,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4219
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4329ba40331f0e6daf1800e86449eb3954f36410428853becb49723c31dda78a
|
3 |
size 4219
|