ChiJuiChen
commited on
Commit
•
92022ff
1
Parent(s):
f2891ad
End of training
Browse files- README.md +3 -2
- config.json +1 -1
- generation_config.json +6 -0
- merges.txt +1 -1
- model.safetensors +3 -0
- runs/Apr27_17-54-44_LAPTOP-Q93LLSSJ/events.out.tfevents.1714211686.LAPTOP-Q93LLSSJ.6208.0 +3 -0
- special_tokens_map.json +24 -1
- tokenizer.json +2 -0
- tokenizer_config.json +20 -1
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
model-index:
|
@@ -49,7 +50,7 @@ The following hyperparameters were used during training:
|
|
49 |
|
50 |
### Framework versions
|
51 |
|
52 |
-
- Transformers 4.
|
53 |
- Pytorch 2.0.0+cu118
|
54 |
- Datasets 2.18.0
|
55 |
-
- Tokenizers 0.
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: distilgpt2
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
|
|
50 |
|
51 |
### Framework versions
|
52 |
|
53 |
+
- Transformers 4.40.1
|
54 |
- Pytorch 2.0.0+cu118
|
55 |
- Datasets 2.18.0
|
56 |
+
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -40,7 +40,7 @@
|
|
40 |
}
|
41 |
},
|
42 |
"torch_dtype": "float32",
|
43 |
-
"transformers_version": "4.
|
44 |
"use_cache": true,
|
45 |
"vocab_size": 50000
|
46 |
}
|
|
|
40 |
}
|
41 |
},
|
42 |
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.40.1",
|
44 |
"use_cache": true,
|
45 |
"vocab_size": 50000
|
46 |
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"transformers_version": "4.40.1"
|
6 |
+
}
|
merges.txt
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
-
#version: 0.2
|
2 |
Ġ Ġ
|
3 |
ĠĠ ĠĠ
|
4 |
ĠĠ Ġ
|
|
|
1 |
+
#version: 0.2
|
2 |
Ġ Ġ
|
3 |
ĠĠ ĠĠ
|
4 |
ĠĠ Ġ
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c52d47c9dd47bd9536500c4eb0210866a23ae9125dffba548f9431d5cecf470c
|
3 |
+
size 326868424
|
runs/Apr27_17-54-44_LAPTOP-Q93LLSSJ/events.out.tfevents.1714211686.LAPTOP-Q93LLSSJ.6208.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:def6ad777c63955cc62dc05dda9fdf29ef5665bac75bfb87a770f8891f94c63f
|
3 |
+
size 5295
|
special_tokens_map.json
CHANGED
@@ -1 +1,24 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|endoftext|>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
CHANGED
@@ -44,6 +44,8 @@
|
|
44 |
"continuing_subword_prefix": "",
|
45 |
"end_of_word_suffix": "",
|
46 |
"fuse_unk": false,
|
|
|
|
|
47 |
"vocab": {
|
48 |
"<|endoftext|>": 0,
|
49 |
"!": 1,
|
|
|
44 |
"continuing_subword_prefix": "",
|
45 |
"end_of_word_suffix": "",
|
46 |
"fuse_unk": false,
|
47 |
+
"byte_fallback": false,
|
48 |
+
"ignore_merges": false,
|
49 |
"vocab": {
|
50 |
"<|endoftext|>": 0,
|
51 |
"!": 1,
|
tokenizer_config.json
CHANGED
@@ -1 +1,20 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
}
|
12 |
+
},
|
13 |
+
"bos_token": "<|endoftext|>",
|
14 |
+
"clean_up_tokenization_spaces": true,
|
15 |
+
"eos_token": "<|endoftext|>",
|
16 |
+
"model_max_length": 1024,
|
17 |
+
"pad_token": "<|endoftext|>",
|
18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
19 |
+
"unk_token": "<|endoftext|>"
|
20 |
+
}
|
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 sha256:37ef3fefc80b60dfe5b7e8c2439a50e4078cf3a4bdd5de4a626aee2f97a7ac93
|
3 |
+
size 4539
|