Training in progress, step 500
Browse files- config.json +1 -1
- model.safetensors +3 -0
- runs/Jul24_16-01-15_4d00249eedb1/events.out.tfevents.1721836896.4d00249eedb1.4767.0 +3 -0
- special_tokens_map.json +42 -6
- tokenizer.json +1 -0
- tokenizer_config.json +49 -0
- training_args.bin +2 -2
config.json
CHANGED
@@ -21,7 +21,7 @@
|
|
21 |
"position_embedding_type": "absolute",
|
22 |
"problem_type": "single_label_classification",
|
23 |
"torch_dtype": "float32",
|
24 |
-
"transformers_version": "4.
|
25 |
"type_vocab_size": 1,
|
26 |
"use_cache": true,
|
27 |
"vocab_size": 50265
|
|
|
21 |
"position_embedding_type": "absolute",
|
22 |
"problem_type": "single_label_classification",
|
23 |
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.42.4",
|
25 |
"type_vocab_size": 1,
|
26 |
"use_cache": true,
|
27 |
"vocab_size": 50265
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6812557d00c7cfe2b63a645b39d9298a487a53870a2597e2116c97e045f9dcd
|
3 |
+
size 498612824
|
runs/Jul24_16-01-15_4d00249eedb1/events.out.tfevents.1721836896.4d00249eedb1.4767.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bb911558b07e7332d7fbcdf63ebe60c2d4f1f2e67f2ccaa5d110f4dcf504edd
|
3 |
+
size 5145
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,25 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"mask_token": {
|
6 |
"content": "<mask>",
|
7 |
"lstrip": true,
|
@@ -9,7 +27,25 @@
|
|
9 |
"rstrip": false,
|
10 |
"single_word": false
|
11 |
},
|
12 |
-
"pad_token":
|
13 |
-
|
14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
"mask_token": {
|
24 |
"content": "<mask>",
|
25 |
"lstrip": true,
|
|
|
27 |
"rstrip": false,
|
28 |
"single_word": false
|
29 |
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
}
|
tokenizer.json
CHANGED
@@ -88,6 +88,7 @@
|
|
88 |
"end_of_word_suffix": "",
|
89 |
"fuse_unk": false,
|
90 |
"byte_fallback": false,
|
|
|
91 |
"vocab": {
|
92 |
"<s>": 0,
|
93 |
"<pad>": 1,
|
|
|
88 |
"end_of_word_suffix": "",
|
89 |
"fuse_unk": false,
|
90 |
"byte_fallback": false,
|
91 |
+
"ignore_merges": false,
|
92 |
"vocab": {
|
93 |
"<s>": 0,
|
94 |
"<pad>": 1,
|
tokenizer_config.json
CHANGED
@@ -1,15 +1,64 @@
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"bos_token": "<s>",
|
4 |
"clean_up_tokenization_spaces": true,
|
5 |
"cls_token": "<s>",
|
6 |
"eos_token": "</s>",
|
7 |
"errors": "replace",
|
8 |
"mask_token": "<mask>",
|
|
|
9 |
"model_max_length": 512,
|
|
|
10 |
"pad_token": "<pad>",
|
|
|
|
|
11 |
"sep_token": "</s>",
|
|
|
12 |
"tokenizer_class": "RobertaTokenizer",
|
13 |
"trim_offsets": true,
|
|
|
|
|
14 |
"unk_token": "<unk>"
|
15 |
}
|
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
"bos_token": "<s>",
|
46 |
"clean_up_tokenization_spaces": true,
|
47 |
"cls_token": "<s>",
|
48 |
"eos_token": "</s>",
|
49 |
"errors": "replace",
|
50 |
"mask_token": "<mask>",
|
51 |
+
"max_length": 64,
|
52 |
"model_max_length": 512,
|
53 |
+
"pad_to_multiple_of": null,
|
54 |
"pad_token": "<pad>",
|
55 |
+
"pad_token_type_id": 0,
|
56 |
+
"padding_side": "right",
|
57 |
"sep_token": "</s>",
|
58 |
+
"stride": 0,
|
59 |
"tokenizer_class": "RobertaTokenizer",
|
60 |
"trim_offsets": true,
|
61 |
+
"truncation_side": "right",
|
62 |
+
"truncation_strategy": "longest_first",
|
63 |
"unk_token": "<unk>"
|
64 |
}
|
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:fd1726bb09e60beeca7c1bfce0dacaa7112450868c2cc315185acca614e1a4d6
|
3 |
+
size 5176
|