Training in progress, step 100
Browse files- config.json +4 -4
- runs/Jun20_20-05-31_n136-100-194/events.out.tfevents.1718885507.n136-100-194.378377.0 +3 -0
- special_tokens_map.json +2 -6
- tokenizer.json +0 -18
- tokenizer_config.json +5 -24
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,16 +1,16 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/mnt/bn/xuruijie-llm/checkpoints/
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
6 |
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 1,
|
8 |
-
"eos_token_id":
|
9 |
"hidden_act": "silu",
|
10 |
"hidden_size": 4096,
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 14336,
|
13 |
-
"max_position_embeddings":
|
14 |
"model_type": "mistral",
|
15 |
"num_attention_heads": 32,
|
16 |
"num_hidden_layers": 32,
|
@@ -22,5 +22,5 @@
|
|
22 |
"torch_dtype": "bfloat16",
|
23 |
"transformers_version": "4.39.3",
|
24 |
"use_cache": false,
|
25 |
-
"vocab_size":
|
26 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/mnt/bn/xuruijie-llm/checkpoints/chatml/round1-5-beta1",
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
6 |
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
"hidden_act": "silu",
|
10 |
"hidden_size": 4096,
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
"model_type": "mistral",
|
15 |
"num_attention_heads": 32,
|
16 |
"num_hidden_layers": 32,
|
|
|
22 |
"torch_dtype": "bfloat16",
|
23 |
"transformers_version": "4.39.3",
|
24 |
"use_cache": false,
|
25 |
+
"vocab_size": 32000
|
26 |
}
|
runs/Jun20_20-05-31_n136-100-194/events.out.tfevents.1718885507.n136-100-194.378377.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4763fa132a753b81b8a2677127b61d69a9bc3e7d0492ae8e128456c5dc591acf
|
3 |
+
size 12339
|
special_tokens_map.json
CHANGED
@@ -1,8 +1,4 @@
|
|
1 |
{
|
2 |
-
"additional_special_tokens": [
|
3 |
-
"<|end_of_turn|>",
|
4 |
-
"<|pad_0|>"
|
5 |
-
],
|
6 |
"bos_token": {
|
7 |
"content": "<s>",
|
8 |
"lstrip": false,
|
@@ -11,14 +7,14 @@
|
|
11 |
"single_word": false
|
12 |
},
|
13 |
"eos_token": {
|
14 |
-
"content": "
|
15 |
"lstrip": false,
|
16 |
"normalized": false,
|
17 |
"rstrip": false,
|
18 |
"single_word": false
|
19 |
},
|
20 |
"pad_token": {
|
21 |
-
"content": "
|
22 |
"lstrip": false,
|
23 |
"normalized": false,
|
24 |
"rstrip": false,
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
"content": "<s>",
|
4 |
"lstrip": false,
|
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
"pad_token": {
|
17 |
+
"content": "</s>",
|
18 |
"lstrip": false,
|
19 |
"normalized": false,
|
20 |
"rstrip": false,
|
tokenizer.json
CHANGED
@@ -29,24 +29,6 @@
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
32 |
-
},
|
33 |
-
{
|
34 |
-
"id": 32000,
|
35 |
-
"content": "<|end_of_turn|>",
|
36 |
-
"single_word": false,
|
37 |
-
"lstrip": false,
|
38 |
-
"rstrip": false,
|
39 |
-
"normalized": false,
|
40 |
-
"special": true
|
41 |
-
},
|
42 |
-
{
|
43 |
-
"id": 32001,
|
44 |
-
"content": "<|pad_0|>",
|
45 |
-
"single_word": false,
|
46 |
-
"lstrip": false,
|
47 |
-
"rstrip": false,
|
48 |
-
"normalized": false,
|
49 |
-
"special": true
|
50 |
}
|
51 |
],
|
52 |
"normalizer": {
|
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
}
|
33 |
],
|
34 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -25,38 +25,19 @@
|
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
28 |
-
},
|
29 |
-
"32000": {
|
30 |
-
"content": "<|end_of_turn|>",
|
31 |
-
"lstrip": false,
|
32 |
-
"normalized": false,
|
33 |
-
"rstrip": false,
|
34 |
-
"single_word": false,
|
35 |
-
"special": true
|
36 |
-
},
|
37 |
-
"32001": {
|
38 |
-
"content": "<|pad_0|>",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": false,
|
41 |
-
"rstrip": false,
|
42 |
-
"single_word": false,
|
43 |
-
"special": true
|
44 |
}
|
45 |
},
|
46 |
-
"additional_special_tokens": [
|
47 |
-
"<|end_of_turn|>",
|
48 |
-
"<|pad_0|>"
|
49 |
-
],
|
50 |
"bos_token": "<s>",
|
51 |
-
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '\n\
|
52 |
"clean_up_tokenization_spaces": false,
|
53 |
-
"eos_token": "
|
54 |
"legacy": true,
|
55 |
"model_max_length": 2048,
|
56 |
-
"pad_token": "
|
57 |
"sp_model_kwargs": {},
|
58 |
"spaces_between_special_tokens": false,
|
59 |
"tokenizer_class": "LlamaTokenizer",
|
60 |
"unk_token": "<unk>",
|
61 |
-
"use_default_system_prompt":
|
62 |
}
|
|
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
}
|
29 |
},
|
30 |
+
"additional_special_tokens": [],
|
|
|
|
|
|
|
31 |
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
"legacy": true,
|
36 |
"model_max_length": 2048,
|
37 |
+
"pad_token": "</s>",
|
38 |
"sp_model_kwargs": {},
|
39 |
"spaces_between_special_tokens": false,
|
40 |
"tokenizer_class": "LlamaTokenizer",
|
41 |
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6264
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe7da40db16a51dcbfcb44ab0f7561191eeb18f6e0129fb058cc3472c12226f7
|
3 |
size 6264
|