Training in progress, epoch 1
Browse files- adapter_config.json +3 -3
- adapter_model.safetensors +2 -2
- runs/Dec28_23-20-59_eff23ba4fb13/events.out.tfevents.1703805660.eff23ba4fb13.862.0 +3 -0
- runs/Dec28_23-22-38_eff23ba4fb13/events.out.tfevents.1703805759.eff23ba4fb13.1926.0 +3 -0
- special_tokens_map.json +3 -9
- tokenizer.json +0 -0
- tokenizer_config.json +6 -47
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path": "
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
@@ -19,8 +19,8 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
-
"
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM"
|
26 |
}
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM"
|
26 |
}
|
adapter_model.safetensors
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:d854c9e1b3291bba66d9ab82013d4c8bd7d494c58099c70dd630f9a1cf0b63ba
|
3 |
+
size 13648432
|
runs/Dec28_23-20-59_eff23ba4fb13/events.out.tfevents.1703805660.eff23ba4fb13.862.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ba05aee0567d11fe05248908ada92f94d6fd77013121601f29551bcf54da433
|
3 |
+
size 4184
|
runs/Dec28_23-22-38_eff23ba4fb13/events.out.tfevents.1703805759.eff23ba4fb13.1926.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:967794c94ca4250181db5457aafc425834ae8baeaf80717c143248b23489b81e
|
3 |
+
size 4184
|
special_tokens_map.json
CHANGED
@@ -1,21 +1,15 @@
|
|
1 |
{
|
2 |
-
"additional_special_tokens": [
|
3 |
-
"β<PRE>",
|
4 |
-
"β<MID>",
|
5 |
-
"β<SUF>",
|
6 |
-
"β<EOT>"
|
7 |
-
],
|
8 |
"bos_token": {
|
9 |
"content": "<s>",
|
10 |
"lstrip": false,
|
11 |
-
"normalized":
|
12 |
"rstrip": false,
|
13 |
"single_word": false
|
14 |
},
|
15 |
"eos_token": {
|
16 |
"content": "</s>",
|
17 |
"lstrip": false,
|
18 |
-
"normalized":
|
19 |
"rstrip": false,
|
20 |
"single_word": false
|
21 |
},
|
@@ -23,7 +17,7 @@
|
|
23 |
"unk_token": {
|
24 |
"content": "<unk>",
|
25 |
"lstrip": false,
|
26 |
-
"normalized":
|
27 |
"rstrip": false,
|
28 |
"single_word": false
|
29 |
}
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
"content": "<s>",
|
4 |
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
"rstrip": 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 |
},
|
|
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
"rstrip": false,
|
22 |
"single_word": false
|
23 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -3,7 +3,7 @@
|
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
5 |
"lstrip": false,
|
6 |
-
"normalized":
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
@@ -11,7 +11,7 @@
|
|
11 |
"1": {
|
12 |
"content": "<s>",
|
13 |
"lstrip": false,
|
14 |
-
"normalized":
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
@@ -19,63 +19,22 @@
|
|
19 |
"2": {
|
20 |
"content": "</s>",
|
21 |
"lstrip": false,
|
22 |
-
"normalized": true,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
},
|
27 |
-
"32007": {
|
28 |
-
"content": "β<PRE>",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"32008": {
|
36 |
-
"content": "β<SUF>",
|
37 |
-
"lstrip": false,
|
38 |
-
"normalized": false,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
-
},
|
43 |
-
"32009": {
|
44 |
-
"content": "β<MID>",
|
45 |
-
"lstrip": false,
|
46 |
-
"normalized": false,
|
47 |
-
"rstrip": false,
|
48 |
-
"single_word": false,
|
49 |
-
"special": true
|
50 |
-
},
|
51 |
-
"32010": {
|
52 |
-
"content": "β<EOT>",
|
53 |
-
"lstrip": false,
|
54 |
"normalized": false,
|
55 |
"rstrip": false,
|
56 |
"single_word": false,
|
57 |
"special": true
|
58 |
}
|
59 |
},
|
60 |
-
"additional_special_tokens": [
|
61 |
-
"β<PRE>",
|
62 |
-
"β<MID>",
|
63 |
-
"β<SUF>",
|
64 |
-
"β<EOT>"
|
65 |
-
],
|
66 |
"bos_token": "<s>",
|
67 |
"clean_up_tokenization_spaces": false,
|
68 |
"eos_token": "</s>",
|
69 |
-
"
|
70 |
-
"fill_token": "<FILL_ME>",
|
71 |
-
"legacy": null,
|
72 |
-
"middle_token": "β<MID>",
|
73 |
"model_max_length": 1000000000000000019884624838656,
|
74 |
"pad_token": "</s>",
|
75 |
-
"prefix_token": "β<PRE>",
|
76 |
"sp_model_kwargs": {},
|
77 |
-
"
|
78 |
-
"tokenizer_class": "
|
79 |
"unk_token": "<unk>",
|
80 |
"use_default_system_prompt": false
|
81 |
}
|
|
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
5 |
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
|
|
11 |
"1": {
|
12 |
"content": "<s>",
|
13 |
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
|
|
19 |
"2": {
|
20 |
"content": "</s>",
|
21 |
"lstrip": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
}
|
27 |
},
|
28 |
+
"additional_special_tokens": [],
|
|
|
|
|
|
|
|
|
|
|
29 |
"bos_token": "<s>",
|
30 |
"clean_up_tokenization_spaces": false,
|
31 |
"eos_token": "</s>",
|
32 |
+
"legacy": true,
|
|
|
|
|
|
|
33 |
"model_max_length": 1000000000000000019884624838656,
|
34 |
"pad_token": "</s>",
|
|
|
35 |
"sp_model_kwargs": {},
|
36 |
+
"spaces_between_special_tokens": false,
|
37 |
+
"tokenizer_class": "LlamaTokenizer",
|
38 |
"unk_token": "<unk>",
|
39 |
"use_default_system_prompt": false
|
40 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4600
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2692b9de974cc3dd7b66338af3604228d4e996b6af8cd57dec2a7f19b044a29
|
3 |
size 4600
|