Training in progress, epoch 1
Browse files- config.json +5 -11
- model.safetensors +2 -2
- tokenizer.json +6 -1
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,15 +1,14 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "bert-
|
3 |
"architectures": [
|
4 |
"BertForTokenClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
8 |
-
"directionality": "bidi",
|
9 |
"gradient_checkpointing": false,
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout_prob": 0.1,
|
12 |
-
"hidden_size":
|
13 |
"id2label": {
|
14 |
"0": "O",
|
15 |
"1": "B-PER",
|
@@ -22,7 +21,7 @@
|
|
22 |
"8": "I-MISC"
|
23 |
},
|
24 |
"initializer_range": 0.02,
|
25 |
-
"intermediate_size":
|
26 |
"label2id": {
|
27 |
"B-LOC": "5",
|
28 |
"B-MISC": "7",
|
@@ -37,14 +36,9 @@
|
|
37 |
"layer_norm_eps": 1e-12,
|
38 |
"max_position_embeddings": 512,
|
39 |
"model_type": "bert",
|
40 |
-
"num_attention_heads":
|
41 |
-
"num_hidden_layers":
|
42 |
"pad_token_id": 0,
|
43 |
-
"pooler_fc_size": 768,
|
44 |
-
"pooler_num_attention_heads": 12,
|
45 |
-
"pooler_num_fc_layers": 3,
|
46 |
-
"pooler_size_per_head": 128,
|
47 |
-
"pooler_type": "first_token_transform",
|
48 |
"position_embedding_type": "absolute",
|
49 |
"torch_dtype": "float32",
|
50 |
"transformers_version": "4.40.0",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
"architectures": [
|
4 |
"BertForTokenClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
|
|
8 |
"gradient_checkpointing": false,
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
"id2label": {
|
13 |
"0": "O",
|
14 |
"1": "B-PER",
|
|
|
21 |
"8": "I-MISC"
|
22 |
},
|
23 |
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 3072,
|
25 |
"label2id": {
|
26 |
"B-LOC": "5",
|
27 |
"B-MISC": "7",
|
|
|
36 |
"layer_norm_eps": 1e-12,
|
37 |
"max_position_embeddings": 512,
|
38 |
"model_type": "bert",
|
39 |
+
"num_attention_heads": 12,
|
40 |
+
"num_hidden_layers": 12,
|
41 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
42 |
"position_embedding_type": "absolute",
|
43 |
"torch_dtype": "float32",
|
44 |
"transformers_version": "4.40.0",
|
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 sha256:4b653498989095bd35f0d68e4ea54ee89d988baafab3e464725d68f1da943d26
|
3 |
+
size 430929740
|
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 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:226cc6d6e9c1fdc4d40cd1243d5f2d9883e1e4337ac264e60c78bbf4a7369a88
|
3 |
size 4984
|