suneeln-duke
commited on
Commit
•
26dad13
1
Parent(s):
bd7e901
End of training
Browse files- README.md +5 -6
- adapter_config.json +1 -1
- adapter_model.safetensors +2 -2
- merges.txt +0 -0
- runs/Apr22_01-14-06_fd43709db3da/events.out.tfevents.1713748448.fd43709db3da.34.0 +3 -0
- special_tokens_map.json +15 -14
- tokenizer.json +0 -0
- tokenizer_config.json +5 -108
- training_args.bin +1 -1
- vocab.json +0 -0
README.md
CHANGED
@@ -1,9 +1,8 @@
|
|
1 |
---
|
2 |
-
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
-
base_model:
|
7 |
model-index:
|
8 |
- name: falcon-clf
|
9 |
results: []
|
@@ -14,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# falcon-clf
|
16 |
|
17 |
-
This model is a fine-tuned version of [
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -51,8 +50,8 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
-
| 1.
|
55 |
-
|
|
56 |
|
57 |
|
58 |
### Framework versions
|
|
|
1 |
---
|
|
|
2 |
library_name: peft
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
+
base_model: Rocketknight1/falcon-rw-1b
|
6 |
model-index:
|
7 |
- name: falcon-clf
|
8 |
results: []
|
|
|
13 |
|
14 |
# falcon-clf
|
15 |
|
16 |
+
This model is a fine-tuned version of [Rocketknight1/falcon-rw-1b](https://huggingface.co/Rocketknight1/falcon-rw-1b) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.9004
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
+
| 1.0238 | 0.99 | 77 | 0.9130 |
|
54 |
+
| 0.9371 | 1.98 | 154 | 0.9004 |
|
55 |
|
56 |
|
57 |
### Framework versions
|
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,
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Rocketknight1/falcon-rw-1b",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
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 sha256:4dfea375b16c353b9f81899316d426004f0551de6cb609e86246f7f359970b5c
|
3 |
+
size 50338848
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Apr22_01-14-06_fd43709db3da/events.out.tfevents.1713748448.fd43709db3da.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53cfc29625858a7cd2becd9e277f5d90def642338e5db8f3f414519cf3648c91
|
3 |
+
size 8064
|
special_tokens_map.json
CHANGED
@@ -1,17 +1,11 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
8 |
-
|
9 |
-
">>QUESTION<<",
|
10 |
-
">>DOMAIN<<",
|
11 |
-
">>PREFIX<<",
|
12 |
-
">>SUFFIX<<",
|
13 |
-
">>MIDDLE<<"
|
14 |
-
],
|
15 |
"eos_token": {
|
16 |
"content": "<|endoftext|>",
|
17 |
"lstrip": false,
|
@@ -19,5 +13,12 @@
|
|
19 |
"rstrip": false,
|
20 |
"single_word": false
|
21 |
},
|
22 |
-
"pad_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
}
|
|
|
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,
|
|
|
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
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -3,95 +3,7 @@
|
|
3 |
"add_eos_token": true,
|
4 |
"add_prefix_space": false,
|
5 |
"added_tokens_decoder": {
|
6 |
-
"
|
7 |
-
"content": ">>TITLE<<",
|
8 |
-
"lstrip": false,
|
9 |
-
"normalized": false,
|
10 |
-
"rstrip": false,
|
11 |
-
"single_word": false,
|
12 |
-
"special": true
|
13 |
-
},
|
14 |
-
"1": {
|
15 |
-
"content": ">>ABSTRACT<<",
|
16 |
-
"lstrip": false,
|
17 |
-
"normalized": false,
|
18 |
-
"rstrip": false,
|
19 |
-
"single_word": false,
|
20 |
-
"special": true
|
21 |
-
},
|
22 |
-
"2": {
|
23 |
-
"content": ">>INTRODUCTION<<",
|
24 |
-
"lstrip": false,
|
25 |
-
"normalized": false,
|
26 |
-
"rstrip": false,
|
27 |
-
"single_word": false,
|
28 |
-
"special": true
|
29 |
-
},
|
30 |
-
"3": {
|
31 |
-
"content": ">>SUMMARY<<",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false,
|
36 |
-
"special": true
|
37 |
-
},
|
38 |
-
"4": {
|
39 |
-
"content": ">>COMMENT<<",
|
40 |
-
"lstrip": false,
|
41 |
-
"normalized": false,
|
42 |
-
"rstrip": false,
|
43 |
-
"single_word": false,
|
44 |
-
"special": true
|
45 |
-
},
|
46 |
-
"5": {
|
47 |
-
"content": ">>ANSWER<<",
|
48 |
-
"lstrip": false,
|
49 |
-
"normalized": false,
|
50 |
-
"rstrip": false,
|
51 |
-
"single_word": false,
|
52 |
-
"special": true
|
53 |
-
},
|
54 |
-
"6": {
|
55 |
-
"content": ">>QUESTION<<",
|
56 |
-
"lstrip": false,
|
57 |
-
"normalized": false,
|
58 |
-
"rstrip": false,
|
59 |
-
"single_word": false,
|
60 |
-
"special": true
|
61 |
-
},
|
62 |
-
"7": {
|
63 |
-
"content": ">>DOMAIN<<",
|
64 |
-
"lstrip": false,
|
65 |
-
"normalized": false,
|
66 |
-
"rstrip": false,
|
67 |
-
"single_word": false,
|
68 |
-
"special": true
|
69 |
-
},
|
70 |
-
"8": {
|
71 |
-
"content": ">>PREFIX<<",
|
72 |
-
"lstrip": false,
|
73 |
-
"normalized": false,
|
74 |
-
"rstrip": false,
|
75 |
-
"single_word": false,
|
76 |
-
"special": true
|
77 |
-
},
|
78 |
-
"9": {
|
79 |
-
"content": ">>SUFFIX<<",
|
80 |
-
"lstrip": false,
|
81 |
-
"normalized": false,
|
82 |
-
"rstrip": false,
|
83 |
-
"single_word": false,
|
84 |
-
"special": true
|
85 |
-
},
|
86 |
-
"10": {
|
87 |
-
"content": ">>MIDDLE<<",
|
88 |
-
"lstrip": false,
|
89 |
-
"normalized": false,
|
90 |
-
"rstrip": false,
|
91 |
-
"single_word": false,
|
92 |
-
"special": true
|
93 |
-
},
|
94 |
-
"11": {
|
95 |
"content": "<|endoftext|>",
|
96 |
"lstrip": false,
|
97 |
"normalized": false,
|
@@ -100,27 +12,12 @@
|
|
100 |
"special": true
|
101 |
}
|
102 |
},
|
103 |
-
"
|
104 |
-
">>TITLE<<",
|
105 |
-
">>ABSTRACT<<",
|
106 |
-
">>INTRODUCTION<<",
|
107 |
-
">>SUMMARY<<",
|
108 |
-
">>COMMENT<<",
|
109 |
-
">>ANSWER<<",
|
110 |
-
">>QUESTION<<",
|
111 |
-
">>DOMAIN<<",
|
112 |
-
">>PREFIX<<",
|
113 |
-
">>SUFFIX<<",
|
114 |
-
">>MIDDLE<<"
|
115 |
-
],
|
116 |
"clean_up_tokenization_spaces": true,
|
117 |
"eos_token": "<|endoftext|>",
|
118 |
-
"
|
119 |
-
"input_ids",
|
120 |
-
"attention_mask"
|
121 |
-
],
|
122 |
-
"model_max_length": 2048,
|
123 |
"pad_token": "<|endoftext|>",
|
124 |
"padding_side": "left",
|
125 |
-
"tokenizer_class": "
|
|
|
126 |
}
|
|
|
3 |
"add_eos_token": true,
|
4 |
"add_prefix_space": false,
|
5 |
"added_tokens_decoder": {
|
6 |
+
"50256": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
"content": "<|endoftext|>",
|
8 |
"lstrip": false,
|
9 |
"normalized": false,
|
|
|
12 |
"special": true
|
13 |
}
|
14 |
},
|
15 |
+
"bos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
"clean_up_tokenization_spaces": true,
|
17 |
"eos_token": "<|endoftext|>",
|
18 |
+
"model_max_length": 1024,
|
|
|
|
|
|
|
|
|
19 |
"pad_token": "<|endoftext|>",
|
20 |
"padding_side": "left",
|
21 |
+
"tokenizer_class": "GPT2Tokenizer",
|
22 |
+
"unk_token": "<|endoftext|>"
|
23 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4219
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74baa111c4e16b3ab8750343e9601dfa67e8da839eb2c7f010692af6219f2585
|
3 |
size 4219
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|