loha_fine_tuned_cb
Browse files- README.md +17 -5
- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- special_tokens_map.json +5 -35
- tokenizer.json +6 -1
- tokenizer_config.json +0 -4
- training_args.bin +1 -1
README.md
CHANGED
@@ -6,6 +6,7 @@ tags:
|
|
6 |
base_model: google-bert/bert-base-uncased
|
7 |
metrics:
|
8 |
- accuracy
|
|
|
9 |
model-index:
|
10 |
- name: loha_fine_tuned_cb
|
11 |
results: []
|
@@ -18,8 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 3.
|
22 |
-
- Accuracy: 0.
|
|
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -38,9 +40,9 @@ More information needed
|
|
38 |
### Training hyperparameters
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
-
- learning_rate:
|
42 |
-
- train_batch_size:
|
43 |
-
- eval_batch_size:
|
44 |
- seed: 42
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
@@ -48,6 +50,16 @@ The following hyperparameters were used during training:
|
|
48 |
|
49 |
### Training results
|
50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
|
52 |
|
53 |
### Framework versions
|
|
|
6 |
base_model: google-bert/bert-base-uncased
|
7 |
metrics:
|
8 |
- accuracy
|
9 |
+
- f1
|
10 |
model-index:
|
11 |
- name: loha_fine_tuned_cb
|
12 |
results: []
|
|
|
19 |
|
20 |
This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
|
21 |
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 3.6524
|
23 |
+
- Accuracy: 0.3636
|
24 |
+
- F1: 0.2923
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
40 |
### Training hyperparameters
|
41 |
|
42 |
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 0.003
|
44 |
+
- train_batch_size: 8
|
45 |
+
- eval_batch_size: 8
|
46 |
- seed: 42
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: linear
|
|
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
54 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
|
55 |
+
| 0.7795 | 3.5714 | 50 | 2.0073 | 0.3182 | 0.1536 |
|
56 |
+
| 0.7479 | 7.1429 | 100 | 1.3794 | 0.3182 | 0.1536 |
|
57 |
+
| 0.3979 | 10.7143 | 150 | 3.8538 | 0.3182 | 0.1536 |
|
58 |
+
| 0.1064 | 14.2857 | 200 | 3.6640 | 0.3182 | 0.2636 |
|
59 |
+
| 0.0423 | 17.8571 | 250 | 1.8668 | 0.4091 | 0.4067 |
|
60 |
+
| 0.0025 | 21.4286 | 300 | 3.6246 | 0.4091 | 0.3208 |
|
61 |
+
| 0.002 | 25.0 | 350 | 3.9578 | 0.4091 | 0.3208 |
|
62 |
+
| 0.0023 | 28.5714 | 400 | 3.6524 | 0.3636 | 0.2923 |
|
63 |
|
64 |
|
65 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -18,8 +18,8 @@
|
|
18 |
"rank_pattern": {},
|
19 |
"revision": null,
|
20 |
"target_modules": [
|
21 |
-
"
|
22 |
-
"
|
23 |
],
|
24 |
"task_type": "SEQ_CLS",
|
25 |
"use_effective_conv2d": false
|
|
|
18 |
"rank_pattern": {},
|
19 |
"revision": null,
|
20 |
"target_modules": [
|
21 |
+
"query",
|
22 |
+
"value"
|
23 |
],
|
24 |
"task_type": "SEQ_CLS",
|
25 |
"use_effective_conv2d": false
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4741180
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abcb03c2c6fe58660c0c99a87a81929b7c22ac51fce8c8844047bcb60cf5ad35
|
3 |
size 4741180
|
special_tokens_map.json
CHANGED
@@ -1,37 +1,7 @@
|
|
1 |
{
|
2 |
-
"cls_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"mask_token": {
|
10 |
-
"content": "[MASK]",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "[PAD]",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"sep_token": {
|
24 |
-
"content": "[SEP]",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
},
|
30 |
-
"unk_token": {
|
31 |
-
"content": "[UNK]",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false
|
36 |
-
}
|
37 |
}
|
|
|
1 |
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
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 |
{
|
tokenizer_config.json
CHANGED
@@ -45,15 +45,11 @@
|
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_lower_case": true,
|
47 |
"mask_token": "[MASK]",
|
48 |
-
"max_length": 512,
|
49 |
"model_max_length": 512,
|
50 |
"pad_token": "[PAD]",
|
51 |
"sep_token": "[SEP]",
|
52 |
-
"stride": 0,
|
53 |
"strip_accents": null,
|
54 |
"tokenize_chinese_chars": true,
|
55 |
"tokenizer_class": "BertTokenizer",
|
56 |
-
"truncation_side": "right",
|
57 |
-
"truncation_strategy": "longest_first",
|
58 |
"unk_token": "[UNK]"
|
59 |
}
|
|
|
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": "BertTokenizer",
|
|
|
|
|
54 |
"unk_token": "[UNK]"
|
55 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03ad40f941eedbb45a97a90438434470dcc420fd1dda47e7b9e23571e1432d7a
|
3 |
size 4984
|