Training in progress, step 500
Browse files- config.json +10 -17
- model.safetensors +2 -2
- runs/Jul29_08-35-52_527e583798d6/events.out.tfevents.1722242219.527e583798d6.14614.0 +3 -0
- special_tokens_map.json +3 -11
- tokenizer.json +0 -0
- tokenizer_config.json +12 -14
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,25 +1,20 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"_num_labels": 2,
|
4 |
"architectures": [
|
5 |
-
"
|
6 |
],
|
7 |
-
"attention_probs_dropout_prob": 0,
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"eos_token_id": 3,
|
13 |
-
"gap_size": 0,
|
14 |
-
"hidden_act": "gelu_new",
|
15 |
-
"hidden_dropout_prob": 0,
|
16 |
"hidden_size": 768,
|
17 |
"id2label": {
|
18 |
"0": "neg",
|
19 |
"1": "pos"
|
20 |
},
|
21 |
"initializer_range": 0.02,
|
22 |
-
"inner_group_num": 1,
|
23 |
"intermediate_size": 3072,
|
24 |
"label2id": {
|
25 |
"neg": 0,
|
@@ -27,17 +22,15 @@
|
|
27 |
},
|
28 |
"layer_norm_eps": 1e-12,
|
29 |
"max_position_embeddings": 512,
|
30 |
-
"model_type": "
|
31 |
-
"net_structure_type": 0,
|
32 |
"num_attention_heads": 12,
|
33 |
-
"num_hidden_groups": 1,
|
34 |
"num_hidden_layers": 12,
|
35 |
-
"num_memory_blocks": 0,
|
36 |
"pad_token_id": 0,
|
37 |
"position_embedding_type": "absolute",
|
38 |
"problem_type": "single_label_classification",
|
39 |
"torch_dtype": "float32",
|
40 |
"transformers_version": "4.40.2",
|
41 |
"type_vocab_size": 2,
|
42 |
-
"
|
|
|
43 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
3 |
"_num_labels": 2,
|
4 |
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
|
|
|
|
|
|
|
|
12 |
"hidden_size": 768,
|
13 |
"id2label": {
|
14 |
"0": "neg",
|
15 |
"1": "pos"
|
16 |
},
|
17 |
"initializer_range": 0.02,
|
|
|
18 |
"intermediate_size": 3072,
|
19 |
"label2id": {
|
20 |
"neg": 0,
|
|
|
22 |
},
|
23 |
"layer_norm_eps": 1e-12,
|
24 |
"max_position_embeddings": 512,
|
25 |
+
"model_type": "bert",
|
|
|
26 |
"num_attention_heads": 12,
|
|
|
27 |
"num_hidden_layers": 12,
|
|
|
28 |
"pad_token_id": 0,
|
29 |
"position_embedding_type": "absolute",
|
30 |
"problem_type": "single_label_classification",
|
31 |
"torch_dtype": "float32",
|
32 |
"transformers_version": "4.40.2",
|
33 |
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 30522
|
36 |
}
|
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:b7f80461ebbffec0fcf915f3e37fa6449711f6f231506d3badb57fd73bde6b71
|
3 |
+
size 437958648
|
runs/Jul29_08-35-52_527e583798d6/events.out.tfevents.1722242219.527e583798d6.14614.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d167f47c8a9ce97438ba5e80d81cbb95e9b4b30e44264f49d70701350737d74d
|
3 |
+
size 5377
|
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 +1,22 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
-
"content": "
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
-
"content": "
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
"content": "[CLS]",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
@@ -24,7 +24,7 @@
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
"content": "[SEP]",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
@@ -32,26 +32,24 @@
|
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
"content": "[MASK]",
|
37 |
-
"lstrip":
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
44 |
-
"bos_token": "[CLS]",
|
45 |
"clean_up_tokenization_spaces": true,
|
46 |
"cls_token": "[CLS]",
|
47 |
"do_lower_case": true,
|
48 |
-
"eos_token": "[SEP]",
|
49 |
-
"keep_accents": false,
|
50 |
"mask_token": "[MASK]",
|
51 |
"model_max_length": 512,
|
52 |
-
"pad_token": "
|
53 |
-
"remove_space": true,
|
54 |
"sep_token": "[SEP]",
|
55 |
-
"
|
56 |
-
"
|
|
|
|
|
57 |
}
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"101": {
|
20 |
"content": "[CLS]",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"102": {
|
28 |
"content": "[SEP]",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
|
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
+
"103": {
|
36 |
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_lower_case": true,
|
|
|
|
|
47 |
"mask_token": "[MASK]",
|
48 |
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
|
|
50 |
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4792
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5bde9f5778612c472853aa3e6f5daeba8e41d17e713092a03781758e9167046
|
3 |
size 4792
|