kaisar-barlybay-sse
commited on
Commit
•
eafdf5e
1
Parent(s):
327a5f0
Training in progress epoch 0
Browse files- README.md +6 -13
- config.json +8 -3
- tf_model.h5 +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +2 -4
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- generated_from_keras_callback
|
4 |
model-index:
|
@@ -11,12 +12,12 @@ probably proofread and complete it, then remove this comment. -->
|
|
11 |
|
12 |
# kaisar-barlybay-sse/model
|
13 |
|
14 |
-
This model
|
15 |
It achieves the following results on the evaluation set:
|
16 |
-
- Train Loss: 1.
|
17 |
- Validation Loss: 1.3863
|
18 |
-
- Train Accuracy: 0.
|
19 |
-
- Epoch:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -42,15 +43,7 @@ The following hyperparameters were used during training:
|
|
42 |
|
43 |
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
44 |
|:----------:|:---------------:|:--------------:|:-----:|
|
45 |
-
| 1.
|
46 |
-
| 1.3996 | 1.3852 | 0.3872 | 1 |
|
47 |
-
| 1.3926 | 1.3863 | 0.3513 | 2 |
|
48 |
-
| 1.3906 | 1.3863 | 0.2475 | 3 |
|
49 |
-
| 1.3933 | 1.3863 | 0.2535 | 4 |
|
50 |
-
| 1.3895 | 1.3863 | 0.2375 | 5 |
|
51 |
-
| 1.3947 | 1.3863 | 0.2335 | 6 |
|
52 |
-
| 1.3928 | 1.3863 | 0.2595 | 7 |
|
53 |
-
| 1.3977 | 1.3863 | 0.2655 | 8 |
|
54 |
|
55 |
|
56 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_keras_callback
|
5 |
model-index:
|
|
|
12 |
|
13 |
# kaisar-barlybay-sse/model
|
14 |
|
15 |
+
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 1.3923
|
18 |
- Validation Loss: 1.3863
|
19 |
+
- Train Accuracy: 0.2315
|
20 |
+
- Epoch: 0
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
43 |
|
44 |
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
45 |
|:----------:|:---------------:|:--------------:|:-----:|
|
46 |
+
| 1.3923 | 1.3863 | 0.2315 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
|
48 |
|
49 |
### Framework versions
|
config.json
CHANGED
@@ -1,10 +1,11 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"BertForMultipleChoice"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
|
|
8 |
"hidden_act": "gelu",
|
9 |
"hidden_dropout_prob": 0.1,
|
10 |
"hidden_size": 768,
|
@@ -16,10 +17,14 @@
|
|
16 |
"num_attention_heads": 12,
|
17 |
"num_hidden_layers": 12,
|
18 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
19 |
"position_embedding_type": "absolute",
|
20 |
-
"torch_dtype": "float32",
|
21 |
"transformers_version": "4.28.1",
|
22 |
"type_vocab_size": 2,
|
23 |
"use_cache": true,
|
24 |
-
"vocab_size":
|
25 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "bert-base-multilingual-cased",
|
3 |
"architectures": [
|
4 |
"BertForMultipleChoice"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
|
|
17 |
"num_attention_heads": 12,
|
18 |
"num_hidden_layers": 12,
|
19 |
"pad_token_id": 0,
|
20 |
+
"pooler_fc_size": 768,
|
21 |
+
"pooler_num_attention_heads": 12,
|
22 |
+
"pooler_num_fc_layers": 3,
|
23 |
+
"pooler_size_per_head": 128,
|
24 |
+
"pooler_type": "first_token_transform",
|
25 |
"position_embedding_type": "absolute",
|
|
|
26 |
"transformers_version": "4.28.1",
|
27 |
"type_vocab_size": 2,
|
28 |
"use_cache": true,
|
29 |
+
"vocab_size": 119547
|
30 |
}
|
tf_model.h5
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:ea78ba657adec69cff42953adbd4efa18977297a52d315f2b22d1bfcef98a78d
|
3 |
+
size 711688468
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,11 +1,9 @@
|
|
1 |
{
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
"cls_token": "[CLS]",
|
4 |
-
"
|
5 |
-
"do_lower_case": true,
|
6 |
"mask_token": "[MASK]",
|
7 |
-
"model_max_length":
|
8 |
-
"never_split": null,
|
9 |
"pad_token": "[PAD]",
|
10 |
"sep_token": "[SEP]",
|
11 |
"strip_accents": null,
|
|
|
1 |
{
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": false,
|
|
|
5 |
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
|
|
7 |
"pad_token": "[PAD]",
|
8 |
"sep_token": "[SEP]",
|
9 |
"strip_accents": null,
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|