Training completed!
Browse files
config.json
CHANGED
@@ -1,17 +1,14 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"_num_labels": 1,
|
4 |
-
"activation_function": "gelu_new",
|
5 |
"architectures": [
|
6 |
-
"
|
7 |
],
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"gradient_checkpointing": false,
|
15 |
"id2label": {
|
16 |
"0": "B-DT",
|
17 |
"1": "I-DT",
|
@@ -28,6 +25,7 @@
|
|
28 |
"12": "O"
|
29 |
},
|
30 |
"initializer_range": 0.02,
|
|
|
31 |
"label2id": {
|
32 |
"B-DT": 0,
|
33 |
"B-LC": 2,
|
@@ -43,33 +41,21 @@
|
|
43 |
"I-TI": 11,
|
44 |
"O": 12
|
45 |
},
|
46 |
-
"
|
47 |
-
"
|
48 |
-
"model_type": "
|
49 |
-
"
|
50 |
-
"
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"
|
54 |
-
"
|
55 |
-
"
|
56 |
-
"
|
57 |
-
"
|
58 |
-
"scale_attn_by_inverse_layer_idx": false,
|
59 |
-
"scale_attn_weights": true,
|
60 |
-
"summary_activation": null,
|
61 |
-
"summary_first_dropout": 0.1,
|
62 |
-
"summary_proj_to_labels": true,
|
63 |
-
"summary_type": "cls_index",
|
64 |
-
"summary_use_proj": true,
|
65 |
-
"task_specific_params": {
|
66 |
-
"text-generation": {
|
67 |
-
"do_sample": true,
|
68 |
-
"max_length": 50
|
69 |
-
}
|
70 |
-
},
|
71 |
"torch_dtype": "float32",
|
72 |
"transformers_version": "4.28.1",
|
|
|
73 |
"use_cache": true,
|
74 |
-
"vocab_size":
|
75 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "bert-base-multilingual-cased",
|
|
|
|
|
3 |
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
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,
|
|
|
12 |
"id2label": {
|
13 |
"0": "B-DT",
|
14 |
"1": "I-DT",
|
|
|
25 |
"12": "O"
|
26 |
},
|
27 |
"initializer_range": 0.02,
|
28 |
+
"intermediate_size": 3072,
|
29 |
"label2id": {
|
30 |
"B-DT": 0,
|
31 |
"B-LC": 2,
|
|
|
41 |
"I-TI": 11,
|
42 |
"O": 12
|
43 |
},
|
44 |
+
"layer_norm_eps": 1e-12,
|
45 |
+
"max_position_embeddings": 512,
|
46 |
+
"model_type": "bert",
|
47 |
+
"num_attention_heads": 12,
|
48 |
+
"num_hidden_layers": 12,
|
49 |
+
"pad_token_id": 0,
|
50 |
+
"pooler_fc_size": 768,
|
51 |
+
"pooler_num_attention_heads": 12,
|
52 |
+
"pooler_num_fc_layers": 3,
|
53 |
+
"pooler_size_per_head": 128,
|
54 |
+
"pooler_type": "first_token_transform",
|
55 |
+
"position_embedding_type": "absolute",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
"torch_dtype": "float32",
|
57 |
"transformers_version": "4.28.1",
|
58 |
+
"type_vocab_size": 2,
|
59 |
"use_cache": true,
|
60 |
+
"vocab_size": 119547
|
61 |
}
|
pytorch_model.bin
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:bef2ad6fab48a6eea4fa57acc0f9686f4fd867be466e34d3f4de01dcbb32fd56
|
3 |
+
size 709163501
|
runs/May07_07-18-19_0df2eebf449c/1683444047.3501084/events.out.tfevents.1683444047.0df2eebf449c.1092.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cc71c5286fe12926477e635ec536098b7aa3f2bf80ed8f30f1fb14a1b243142
|
3 |
+
size 5958
|
runs/May07_07-18-19_0df2eebf449c/events.out.tfevents.1683444047.0df2eebf449c.1092.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ca12304d38faf38cfcce6a41af64bb0e31b970e87bfd818fc0534380355f4e5
|
3 |
+
size 6481
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3643
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb685f0910f127f635e7b8a67a58f3336260d41a2d6f39a78c0183223cc9139a
|
3 |
size 3643
|