Training in progress, step 500
Browse files- config.json +15 -14
- model.safetensors +2 -2
- runs/Nov13_21-58-04_aec2e2be4e16/events.out.tfevents.1699912694.aec2e2be4e16.167.2 +3 -0
- tokenizer.json +1 -6
- tokenizer_config.json +4 -2
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
-
"
|
6 |
],
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
|
|
11 |
"id2label": {
|
12 |
"0": "LABEL_0",
|
13 |
"1": "LABEL_1",
|
@@ -15,23 +15,24 @@
|
|
15 |
"3": "LABEL_3"
|
16 |
},
|
17 |
"initializer_range": 0.02,
|
|
|
18 |
"label2id": {
|
19 |
"LABEL_0": 0,
|
20 |
"LABEL_1": 1,
|
21 |
"LABEL_2": 2,
|
22 |
"LABEL_3": 3
|
23 |
},
|
|
|
24 |
"max_position_embeddings": 512,
|
25 |
-
"model_type": "
|
26 |
-
"
|
27 |
-
"
|
28 |
"pad_token_id": 0,
|
|
|
29 |
"problem_type": "single_label_classification",
|
30 |
-
"qa_dropout": 0.1,
|
31 |
-
"seq_classif_dropout": 0.2,
|
32 |
-
"sinusoidal_pos_embds": false,
|
33 |
-
"tie_weights_": true,
|
34 |
"torch_dtype": "float32",
|
35 |
"transformers_version": "4.35.0",
|
|
|
|
|
36 |
"vocab_size": 30522
|
37 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "google/bert_uncased_L-8_H-256_A-4",
|
|
|
3 |
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 256,
|
11 |
"id2label": {
|
12 |
"0": "LABEL_0",
|
13 |
"1": "LABEL_1",
|
|
|
15 |
"3": "LABEL_3"
|
16 |
},
|
17 |
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 1024,
|
19 |
"label2id": {
|
20 |
"LABEL_0": 0,
|
21 |
"LABEL_1": 1,
|
22 |
"LABEL_2": 2,
|
23 |
"LABEL_3": 3
|
24 |
},
|
25 |
+
"layer_norm_eps": 1e-12,
|
26 |
"max_position_embeddings": 512,
|
27 |
+
"model_type": "bert",
|
28 |
+
"num_attention_heads": 4,
|
29 |
+
"num_hidden_layers": 8,
|
30 |
"pad_token_id": 0,
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
33 |
"torch_dtype": "float32",
|
34 |
"transformers_version": "4.35.0",
|
35 |
+
"type_vocab_size": 2,
|
36 |
+
"use_cache": true,
|
37 |
"vocab_size": 30522
|
38 |
}
|
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 sha256:4da9e7b44f0015cfacc6b0dcd796970958fc6fab8e7b3f278f7be1232f1da798
|
3 |
+
size 57338224
|
runs/Nov13_21-58-04_aec2e2be4e16/events.out.tfevents.1699912694.aec2e2be4e16.167.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1836da2bea58b15c29e90c353d559fe27db96bd33cbf304ee261363052632711
|
3 |
+
size 4552
|
tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
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 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
tokenizer_config.json
CHANGED
@@ -43,13 +43,15 @@
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
|
|
46 |
"do_lower_case": true,
|
47 |
"mask_token": "[MASK]",
|
48 |
-
"model_max_length":
|
|
|
49 |
"pad_token": "[PAD]",
|
50 |
"sep_token": "[SEP]",
|
51 |
"strip_accents": null,
|
52 |
"tokenize_chinese_chars": true,
|
53 |
-
"tokenizer_class": "
|
54 |
"unk_token": "[UNK]"
|
55 |
}
|
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
"do_lower_case": true,
|
48 |
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
"pad_token": "[PAD]",
|
52 |
"sep_token": "[SEP]",
|
53 |
"strip_accents": null,
|
54 |
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
"unk_token": "[UNK]"
|
57 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a6a3897a91d3a7396365897b4f808553dd1cac089d045ff407e13bc56d20986
|
3 |
size 4664
|