Training in progress, step 500
Browse files- config.json +8 -2
- model.safetensors +2 -2
- runs/Apr26_21-03-56_tdll-3gpu1/events.out.tfevents.1714158237.tdll-3gpu1.1180687.8 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2 -4
- training_args.bin +1 -1
- vocab.txt +0 -0
config.json
CHANGED
@@ -1,10 +1,11 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"BertForQuestionAnswering"
|
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": 768,
|
@@ -16,10 +17,15 @@
|
|
16 |
"num_attention_heads": 12,
|
17 |
"num_hidden_layers": 12,
|
18 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
19 |
"position_embedding_type": "absolute",
|
20 |
"torch_dtype": "float32",
|
21 |
"transformers_version": "4.38.2",
|
22 |
"type_vocab_size": 2,
|
23 |
"use_cache": true,
|
24 |
-
"vocab_size":
|
25 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "../models/bert-base-multilingual-cased",
|
3 |
"architectures": [
|
4 |
"BertForQuestionAnswering"
|
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,
|
|
|
17 |
"num_attention_heads": 12,
|
18 |
"num_hidden_layers": 12,
|
19 |
"pad_token_id": 0,
|
20 |
+
"pooler_fc_size": 768,
|
21 |
+
"pooler_num_attention_heads": 12,
|
22 |
+
"pooler_num_fc_layers": 3,
|
23 |
+
"pooler_size_per_head": 128,
|
24 |
+
"pooler_type": "first_token_transform",
|
25 |
"position_embedding_type": "absolute",
|
26 |
"torch_dtype": "float32",
|
27 |
"transformers_version": "4.38.2",
|
28 |
"type_vocab_size": 2,
|
29 |
"use_cache": true,
|
30 |
+
"vocab_size": 119547
|
31 |
}
|
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:a78b53c36d0375f5795d07648d35ca834116a76cc32a262c477e8fa5ad153456
|
3 |
+
size 709080904
|
runs/Apr26_21-03-56_tdll-3gpu1/events.out.tfevents.1714158237.tdll-3gpu1.1180687.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8450c849ce415c81e30ea45e7050b40ca397fbb2c160d75ba209b4344f4e87db
|
3 |
+
size 5025
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -43,11 +43,9 @@
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
-
"
|
47 |
-
"do_lower_case": true,
|
48 |
"mask_token": "[MASK]",
|
49 |
-
"model_max_length":
|
50 |
-
"never_split": null,
|
51 |
"pad_token": "[PAD]",
|
52 |
"sep_token": "[SEP]",
|
53 |
"strip_accents": null,
|
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": false,
|
|
|
47 |
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
|
|
49 |
"pad_token": "[PAD]",
|
50 |
"sep_token": "[SEP]",
|
51 |
"strip_accents": null,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af80f6e450bdc6e712d27addd780d5d2829c0c1d62f0b8865af41a2e30bc70ab
|
3 |
size 4920
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|