Commit
•
680f996
1
Parent(s):
da0d781
Training in progress, epoch 1
Browse files- config.json +17 -20
- pytorch_model.bin +2 -2
- special_tokens_map.json +3 -11
- tokenizer.json +0 -0
- tokenizer_config.json +6 -15
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,26 +1,21 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"attention_probs_dropout_prob": 0,
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"gap_size": 0,
|
13 |
-
"hidden_act": "gelu_new",
|
14 |
-
"hidden_dropout_prob": 0,
|
15 |
-
"hidden_size": 768,
|
16 |
"id2label": {
|
17 |
"0": "LABEL_0",
|
18 |
"1": "LABEL_1",
|
19 |
"2": "LABEL_2"
|
20 |
},
|
21 |
"initializer_range": 0.02,
|
22 |
-
"
|
23 |
-
"intermediate_size": 3072,
|
24 |
"label2id": {
|
25 |
"LABEL_0": 0,
|
26 |
"LABEL_1": 1,
|
@@ -28,17 +23,19 @@
|
|
28 |
},
|
29 |
"layer_norm_eps": 1e-12,
|
30 |
"max_position_embeddings": 512,
|
31 |
-
"model_type": "
|
32 |
-
"
|
33 |
-
"num_attention_heads": 12,
|
34 |
-
"num_hidden_groups": 1,
|
35 |
"num_hidden_layers": 12,
|
36 |
-
"num_memory_blocks": 0,
|
37 |
"pad_token_id": 0,
|
38 |
"position_embedding_type": "absolute",
|
39 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
40 |
"torch_dtype": "float32",
|
41 |
"transformers_version": "4.33.3",
|
42 |
"type_vocab_size": 2,
|
43 |
-
"
|
|
|
44 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "google/electra-base-generator",
|
3 |
"architectures": [
|
4 |
+
"ElectraForSequenceClassification"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"embedding_size": 768,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 256,
|
|
|
|
|
|
|
|
|
12 |
"id2label": {
|
13 |
"0": "LABEL_0",
|
14 |
"1": "LABEL_1",
|
15 |
"2": "LABEL_2"
|
16 |
},
|
17 |
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 1024,
|
|
|
19 |
"label2id": {
|
20 |
"LABEL_0": 0,
|
21 |
"LABEL_1": 1,
|
|
|
23 |
},
|
24 |
"layer_norm_eps": 1e-12,
|
25 |
"max_position_embeddings": 512,
|
26 |
+
"model_type": "electra",
|
27 |
+
"num_attention_heads": 4,
|
|
|
|
|
28 |
"num_hidden_layers": 12,
|
|
|
29 |
"pad_token_id": 0,
|
30 |
"position_embedding_type": "absolute",
|
31 |
"problem_type": "single_label_classification",
|
32 |
+
"summary_activation": "gelu",
|
33 |
+
"summary_last_dropout": 0.1,
|
34 |
+
"summary_type": "first",
|
35 |
+
"summary_use_proj": true,
|
36 |
"torch_dtype": "float32",
|
37 |
"transformers_version": "4.33.3",
|
38 |
"type_vocab_size": 2,
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 30522
|
41 |
}
|
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 sha256:2d0ff5c68c5ae35809114154360fae56b9b723ca5514114564b7a1ccb1cc90f7
|
3 |
+
size 134380982
|
special_tokens_map.json
CHANGED
@@ -1,15 +1,7 @@
|
|
1 |
{
|
2 |
-
"bos_token": "[CLS]",
|
3 |
"cls_token": "[CLS]",
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"content": "[MASK]",
|
7 |
-
"lstrip": true,
|
8 |
-
"normalized": false,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false
|
11 |
-
},
|
12 |
-
"pad_token": "<pad>",
|
13 |
"sep_token": "[SEP]",
|
14 |
-
"unk_token": "
|
15 |
}
|
|
|
1 |
{
|
|
|
2 |
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,22 +1,13 @@
|
|
1 |
{
|
2 |
-
"bos_token": "[CLS]",
|
3 |
"clean_up_tokenization_spaces": true,
|
4 |
"cls_token": "[CLS]",
|
5 |
"do_lower_case": true,
|
6 |
-
"
|
7 |
-
"keep_accents": false,
|
8 |
-
"mask_token": {
|
9 |
-
"__type": "AddedToken",
|
10 |
-
"content": "[MASK]",
|
11 |
-
"lstrip": true,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
"model_max_length": 512,
|
17 |
-
"pad_token": "
|
18 |
-
"remove_space": true,
|
19 |
"sep_token": "[SEP]",
|
20 |
-
"
|
21 |
-
"
|
|
|
|
|
22 |
}
|
|
|
1 |
{
|
|
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
"cls_token": "[CLS]",
|
4 |
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
"model_max_length": 512,
|
7 |
+
"pad_token": "[PAD]",
|
|
|
8 |
"sep_token": "[SEP]",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "ElectraTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4472
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b501de3680c53c40919da5c6b5e3392d85676cd945eff3d117eb6b6c24da08c8
|
3 |
size 4472
|