hungphongtrn
commited on
Commit
•
24c7cf7
1
Parent(s):
d262ec2
Training in progress, epoch 0
Browse files- .gitignore +1 -0
- config.json +1 -1
- pytorch_model.bin +3 -0
- runs/May30_07-20-14_labserver/events.out.tfevents.1717054283.labserver.3314871.0 +3 -0
- sentencepiece.bpe.model +3 -0
- tokenizer.json +2 -2
- tokenizer_config.json +8 -43
- training_args.bin +2 -2
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
CHANGED
@@ -99,7 +99,7 @@
|
|
99 |
"pad_token_id": 1,
|
100 |
"position_embedding_type": "absolute",
|
101 |
"torch_dtype": "float32",
|
102 |
-
"transformers_version": "4.
|
103 |
"type_vocab_size": 1,
|
104 |
"use_cache": true,
|
105 |
"vocab_size": 250002
|
|
|
99 |
"pad_token_id": 1,
|
100 |
"position_embedding_type": "absolute",
|
101 |
"torch_dtype": "float32",
|
102 |
+
"transformers_version": "4.32.0.dev0",
|
103 |
"type_vocab_size": 1,
|
104 |
"use_cache": true,
|
105 |
"vocab_size": 250002
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e506be848a1a472e8f34083ca37aaab947c03d38f0b3b964be0d574b9e6b630f
|
3 |
+
size 2235650406
|
runs/May30_07-20-14_labserver/events.out.tfevents.1717054283.labserver.3314871.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d430f9a87c26c73588342ada34a90a9d6d9da00c6544cc0e8d4f4393fecc6d52
|
3 |
+
size 7474
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
tokenizer.json
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 sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
|
3 |
+
size 17082660
|
tokenizer_config.json
CHANGED
@@ -1,51 +1,16 @@
|
|
1 |
{
|
2 |
-
"added_tokens_decoder": {
|
3 |
-
"0": {
|
4 |
-
"content": "<s>",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false,
|
9 |
-
"special": true
|
10 |
-
},
|
11 |
-
"1": {
|
12 |
-
"content": "<pad>",
|
13 |
-
"lstrip": false,
|
14 |
-
"normalized": false,
|
15 |
-
"rstrip": false,
|
16 |
-
"single_word": false,
|
17 |
-
"special": true
|
18 |
-
},
|
19 |
-
"2": {
|
20 |
-
"content": "</s>",
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": false,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
},
|
27 |
-
"3": {
|
28 |
-
"content": "<unk>",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"250001": {
|
36 |
-
"content": "<mask>",
|
37 |
-
"lstrip": true,
|
38 |
-
"normalized": false,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
-
}
|
43 |
-
},
|
44 |
"bos_token": "<s>",
|
45 |
"clean_up_tokenization_spaces": true,
|
46 |
"cls_token": "<s>",
|
47 |
"eos_token": "</s>",
|
48 |
-
"mask_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
"model_max_length": 512,
|
50 |
"pad_token": "<pad>",
|
51 |
"sep_token": "</s>",
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"clean_up_tokenization_spaces": true,
|
4 |
"cls_token": "<s>",
|
5 |
"eos_token": "</s>",
|
6 |
+
"mask_token": {
|
7 |
+
"__type": "AddedToken",
|
8 |
+
"content": "<mask>",
|
9 |
+
"lstrip": true,
|
10 |
+
"normalized": true,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
"model_max_length": 512,
|
15 |
"pad_token": "<pad>",
|
16 |
"sep_token": "</s>",
|
training_args.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 sha256:9119d9e68a951cf6060740e29b6196a11a4d68d9e30b035d567c77fcd5e2174e
|
3 |
+
size 4472
|