Training in progress, epoch 1
Browse files- config.json +2 -24
- model.safetensors +2 -2
- tokenizer.json +13 -4
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"_name_or_path": "bert-base-cased",
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
@@ -9,30 +9,8 @@
|
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
12 |
-
"id2label": {
|
13 |
-
"0": "O",
|
14 |
-
"1": "B-PER",
|
15 |
-
"2": "I-PER",
|
16 |
-
"3": "B-ORG",
|
17 |
-
"4": "I-ORG",
|
18 |
-
"5": "B-LOC",
|
19 |
-
"6": "I-LOC",
|
20 |
-
"7": "B-MISC",
|
21 |
-
"8": "I-MISC"
|
22 |
-
},
|
23 |
"initializer_range": 0.02,
|
24 |
"intermediate_size": 3072,
|
25 |
-
"label2id": {
|
26 |
-
"B-LOC": 5,
|
27 |
-
"B-MISC": 7,
|
28 |
-
"B-ORG": 3,
|
29 |
-
"B-PER": 1,
|
30 |
-
"I-LOC": 6,
|
31 |
-
"I-MISC": 8,
|
32 |
-
"I-ORG": 4,
|
33 |
-
"I-PER": 2,
|
34 |
-
"O": 0
|
35 |
-
},
|
36 |
"layer_norm_eps": 1e-12,
|
37 |
"max_position_embeddings": 512,
|
38 |
"model_type": "bert",
|
@@ -41,7 +19,7 @@
|
|
41 |
"pad_token_id": 0,
|
42 |
"position_embedding_type": "absolute",
|
43 |
"torch_dtype": "float32",
|
44 |
-
"transformers_version": "4.
|
45 |
"type_vocab_size": 2,
|
46 |
"use_cache": true,
|
47 |
"vocab_size": 28996
|
|
|
1 |
{
|
2 |
"_name_or_path": "bert-base-cased",
|
3 |
"architectures": [
|
4 |
+
"BertForQuestionAnswering"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
|
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 3072,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
"layer_norm_eps": 1e-12,
|
15 |
"max_position_embeddings": 512,
|
16 |
"model_type": "bert",
|
|
|
19 |
"pad_token_id": 0,
|
20 |
"position_embedding_type": "absolute",
|
21 |
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.42.4",
|
23 |
"type_vocab_size": 2,
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 28996
|
model.safetensors
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 sha256:0748f91da14d46c8944c27c8f7c24c261b341e50335b05b4ccb167e735352a45
|
3 |
+
size 430908208
|
tokenizer.json
CHANGED
@@ -2,11 +2,20 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
-
"strategy": "
|
7 |
-
"stride":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
},
|
9 |
-
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
12 |
"id": 0,
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 384,
|
6 |
+
"strategy": "OnlySecond",
|
7 |
+
"stride": 128
|
8 |
+
},
|
9 |
+
"padding": {
|
10 |
+
"strategy": {
|
11 |
+
"Fixed": 384
|
12 |
+
},
|
13 |
+
"direction": "Right",
|
14 |
+
"pad_to_multiple_of": null,
|
15 |
+
"pad_id": 0,
|
16 |
+
"pad_type_id": 0,
|
17 |
+
"pad_token": "[PAD]"
|
18 |
},
|
|
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9a9fbbf9d04c792eb33beb1ad9cc404cb8d7565669e2fd15d83a3ba94be3287
|
3 |
size 5176
|