sumo43 commited on
Commit
0d2acfc
1 Parent(s): 8fc0da7

Upload 7 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|end_of_turn|>": 32000,
3
+ "<|pad_0|>": 32001
4
+ }
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.02496550857218381,
4
+ "train_runtime": 20594.9178,
5
+ "train_samples": 45045,
6
+ "train_samples_per_second": 6.562,
7
+ "train_steps_per_second": 0.103
8
+ }
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/workspace/SPIN/outputs",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
@@ -19,8 +19,8 @@
19
  "rope_theta": 10000.0,
20
  "sliding_window": 4096,
21
  "tie_word_embeddings": false,
22
- "torch_dtype": "float16",
23
- "transformers_version": "4.38.0",
24
  "use_cache": true,
25
  "vocab_size": 32002
26
  }
 
1
  {
2
+ "_name_or_path": "openchat/openchat-3.5-0106",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
 
19
  "rope_theta": 10000.0,
20
  "sliding_window": 4096,
21
  "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.35.0",
24
  "use_cache": true,
25
  "vocab_size": 32002
26
  }
special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|end_of_turn|>",
4
+ "<|pad_0|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|end_of_turn|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": "<|end_of_turn|>",
21
+ "unk_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
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
+ "32000": {
28
+ "content": "<|end_of_turn|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "<|pad_0|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [
45
+ "<|end_of_turn|>",
46
+ "<|pad_0|>"
47
+ ],
48
+ "bos_token": "<s>",
49
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
50
+ "clean_up_tokenization_spaces": false,
51
+ "eos_token": "<|end_of_turn|>",
52
+ "legacy": true,
53
+ "model_max_length": 2048,
54
+ "pad_token": "<|end_of_turn|>",
55
+ "sp_model_kwargs": {},
56
+ "spaces_between_special_tokens": false,
57
+ "tokenizer_class": "LlamaTokenizer",
58
+ "unk_token": "<unk>",
59
+ "use_default_system_prompt": true
60
+ }