Training in progress, epoch 1
Browse files- config.json +38 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-large-cased-whole-word-masking",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
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": 1024,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 4096,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0
|
19 |
+
},
|
20 |
+
"layer_norm_eps": 1e-12,
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"model_type": "bert",
|
23 |
+
"num_attention_heads": 16,
|
24 |
+
"num_hidden_layers": 24,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"pooler_fc_size": 768,
|
27 |
+
"pooler_num_attention_heads": 12,
|
28 |
+
"pooler_num_fc_layers": 3,
|
29 |
+
"pooler_size_per_head": 128,
|
30 |
+
"pooler_type": "first_token_transform",
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
+
"problem_type": "regression",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.45.1",
|
35 |
+
"type_vocab_size": 2,
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 28996
|
38 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9acf55bad9bf87426af48ed7b1f9e4eddd384a25513a098ee11b8d7994d6073d
|
3 |
+
size 1334368164
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5a14ee923a403fb31513d6d6fc1abf54503890b3ebbc8a1117ac07549c9049a
|
3 |
+
size 5240
|