End of training
Browse files- added_tokens.json +2 -1
- special_tokens_map.json +7 -1
- tokenizer.json +15 -1
- tokenizer_config.json +9 -1
- training_args.bin +1 -1
added_tokens.json
CHANGED
@@ -36,5 +36,6 @@
|
|
36 |
" ": 50260,
|
37 |
" ": 50259,
|
38 |
" ": 50258,
|
39 |
-
" ": 50257
|
|
|
40 |
}
|
|
|
36 |
" ": 50260,
|
37 |
" ": 50259,
|
38 |
" ": 50258,
|
39 |
+
" ": 50257,
|
40 |
+
"[PAD]": 50295
|
41 |
}
|
special_tokens_map.json
CHANGED
@@ -13,7 +13,13 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
"unk_token": {
|
18 |
"content": "<|endoftext|>",
|
19 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
"unk_token": {
|
24 |
"content": "<|endoftext|>",
|
25 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
@@ -353,6 +358,15 @@
|
|
353 |
"rstrip": false,
|
354 |
"normalized": true,
|
355 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
356 |
}
|
357 |
],
|
358 |
"normalizer": null,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 2048,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
358 |
"rstrip": false,
|
359 |
"normalized": true,
|
360 |
"special": false
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"id": 50295,
|
364 |
+
"content": "[PAD]",
|
365 |
+
"single_word": false,
|
366 |
+
"lstrip": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"normalized": false,
|
369 |
+
"special": true
|
370 |
}
|
371 |
],
|
372 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
@@ -312,13 +312,21 @@
|
|
312 |
"rstrip": false,
|
313 |
"single_word": false,
|
314 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
315 |
}
|
316 |
},
|
317 |
"bos_token": "<|endoftext|>",
|
318 |
"clean_up_tokenization_spaces": true,
|
319 |
"eos_token": "<|endoftext|>",
|
320 |
"model_max_length": 2048,
|
321 |
-
"pad_token": "
|
322 |
"tokenizer_class": "CodeGenTokenizer",
|
323 |
"unk_token": "<|endoftext|>"
|
324 |
}
|
|
|
312 |
"rstrip": false,
|
313 |
"single_word": false,
|
314 |
"special": false
|
315 |
+
},
|
316 |
+
"50295": {
|
317 |
+
"content": "[PAD]",
|
318 |
+
"lstrip": false,
|
319 |
+
"normalized": false,
|
320 |
+
"rstrip": false,
|
321 |
+
"single_word": false,
|
322 |
+
"special": true
|
323 |
}
|
324 |
},
|
325 |
"bos_token": "<|endoftext|>",
|
326 |
"clean_up_tokenization_spaces": true,
|
327 |
"eos_token": "<|endoftext|>",
|
328 |
"model_max_length": 2048,
|
329 |
+
"pad_token": "[PAD]",
|
330 |
"tokenizer_class": "CodeGenTokenizer",
|
331 |
"unk_token": "<|endoftext|>"
|
332 |
}
|
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:b8f46aa7fec5ae27567cc08e775d9617ef6c10bf09eb8547c7c398b4a36f9e19
|
3 |
size 4664
|