Training in progress, step 500
Browse files- config.json +3 -2
- model.safetensors +2 -2
- runs/Jun05_01-53-01_2764dce19e75/events.out.tfevents.1717552382.2764dce19e75.34.4 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
- vocab.txt +0 -0
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "distilbert/distilbert-base-
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForQuestionAnswering"
|
@@ -13,6 +13,7 @@
|
|
13 |
"model_type": "distilbert",
|
14 |
"n_heads": 12,
|
15 |
"n_layers": 6,
|
|
|
16 |
"pad_token_id": 0,
|
17 |
"qa_dropout": 0.1,
|
18 |
"seq_classif_dropout": 0.2,
|
@@ -20,5 +21,5 @@
|
|
20 |
"tie_weights_": true,
|
21 |
"torch_dtype": "float32",
|
22 |
"transformers_version": "4.41.1",
|
23 |
-
"vocab_size":
|
24 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "distilbert/distilbert-base-cased",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForQuestionAnswering"
|
|
|
13 |
"model_type": "distilbert",
|
14 |
"n_heads": 12,
|
15 |
"n_layers": 6,
|
16 |
+
"output_past": true,
|
17 |
"pad_token_id": 0,
|
18 |
"qa_dropout": 0.1,
|
19 |
"seq_classif_dropout": 0.2,
|
|
|
21 |
"tie_weights_": true,
|
22 |
"torch_dtype": "float32",
|
23 |
"transformers_version": "4.41.1",
|
24 |
+
"vocab_size": 28996
|
25 |
}
|
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:d8cfbe295c10bb916ab7d850b7904c8ab96b4b6e8cb7189f2e21356cf1b13f5a
|
3 |
+
size 260782152
|
runs/Jun05_01-53-01_2764dce19e75/events.out.tfevents.1717552382.2764dce19e75.34.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65aaff48fc7007be8c220ac4c89d198ffb291f7f388a83d413acdcf674ec6d60
|
3 |
+
size 5222
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -43,7 +43,7 @@
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
-
"do_lower_case":
|
47 |
"mask_token": "[MASK]",
|
48 |
"model_max_length": 512,
|
49 |
"pad_token": "[PAD]",
|
|
|
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]",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d0c6a6d6ed1481bbb83e65d85fa08e0948e4377736810adeb056b72d7edf889
|
3 |
size 5112
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|