falcon-7b-text-to-base
Browse files- README.md +160 -0
- adapter_config.json +28 -0
- adapter_model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,160 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: tiiuae/falcon-7b
|
7 |
+
model-index:
|
8 |
+
- name: chkpts
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# chkpts
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.1903
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.0003
|
39 |
+
- train_batch_size: 16
|
40 |
+
- eval_batch_size: 16
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- lr_scheduler_warmup_steps: 500
|
45 |
+
- num_epochs: 100
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
52 |
+
| 0.6257 | 1.0 | 489 | 0.5854 |
|
53 |
+
| 0.3832 | 2.0 | 978 | 0.3878 |
|
54 |
+
| 0.3006 | 3.0 | 1467 | 0.3005 |
|
55 |
+
| 0.2695 | 4.0 | 1956 | 0.2657 |
|
56 |
+
| 0.246 | 5.0 | 2445 | 0.2465 |
|
57 |
+
| 0.2243 | 6.0 | 2934 | 0.2336 |
|
58 |
+
| 0.2258 | 7.0 | 3423 | 0.2200 |
|
59 |
+
| 0.2259 | 8.0 | 3912 | 0.2239 |
|
60 |
+
| 0.2189 | 9.0 | 4401 | 0.2181 |
|
61 |
+
| 0.216 | 10.0 | 4890 | 0.2179 |
|
62 |
+
| 0.2158 | 11.0 | 5379 | 0.2148 |
|
63 |
+
| 0.2118 | 12.0 | 5868 | 0.2139 |
|
64 |
+
| 0.2097 | 13.0 | 6357 | 0.2104 |
|
65 |
+
| 0.2053 | 14.0 | 6846 | 0.2075 |
|
66 |
+
| 0.2052 | 15.0 | 7335 | 0.2136 |
|
67 |
+
| 0.2063 | 16.0 | 7824 | 0.2079 |
|
68 |
+
| 0.2132 | 17.0 | 8313 | 0.2047 |
|
69 |
+
| 0.2081 | 18.0 | 8802 | 0.2046 |
|
70 |
+
| 0.2131 | 19.0 | 9291 | 0.2089 |
|
71 |
+
| 0.2046 | 20.0 | 9780 | 0.2067 |
|
72 |
+
| 0.2034 | 21.0 | 10269 | 0.2071 |
|
73 |
+
| 0.1982 | 22.0 | 10758 | 0.2028 |
|
74 |
+
| 0.203 | 23.0 | 11247 | 0.2005 |
|
75 |
+
| 0.2046 | 24.0 | 11736 | 0.2056 |
|
76 |
+
| 0.2049 | 25.0 | 12225 | 0.2033 |
|
77 |
+
| 0.2004 | 26.0 | 12714 | 0.2020 |
|
78 |
+
| 0.1998 | 27.0 | 13203 | 0.2015 |
|
79 |
+
| 0.2027 | 28.0 | 13692 | 0.1996 |
|
80 |
+
| 0.1927 | 29.0 | 14181 | 0.2013 |
|
81 |
+
| 0.1976 | 30.0 | 14670 | 0.2004 |
|
82 |
+
| 0.204 | 31.0 | 15159 | 0.1974 |
|
83 |
+
| 0.1965 | 32.0 | 15648 | 0.1997 |
|
84 |
+
| 0.1977 | 33.0 | 16137 | 0.1974 |
|
85 |
+
| 0.1932 | 34.0 | 16626 | 0.1967 |
|
86 |
+
| 0.1946 | 35.0 | 17115 | 0.1989 |
|
87 |
+
| 0.1989 | 36.0 | 17604 | 0.1976 |
|
88 |
+
| 0.199 | 37.0 | 18093 | 0.1975 |
|
89 |
+
| 0.1938 | 38.0 | 18582 | 0.1987 |
|
90 |
+
| 0.1982 | 39.0 | 19071 | 0.1973 |
|
91 |
+
| 0.2016 | 40.0 | 19560 | 0.1973 |
|
92 |
+
| 0.1971 | 41.0 | 20049 | 0.1985 |
|
93 |
+
| 0.194 | 42.0 | 20538 | 0.1975 |
|
94 |
+
| 0.1968 | 43.0 | 21027 | 0.1973 |
|
95 |
+
| 0.196 | 44.0 | 21516 | 0.1965 |
|
96 |
+
| 0.1939 | 45.0 | 22005 | 0.1965 |
|
97 |
+
| 0.1949 | 46.0 | 22494 | 0.1957 |
|
98 |
+
| 0.2005 | 47.0 | 22983 | 0.1965 |
|
99 |
+
| 0.1961 | 48.0 | 23472 | 0.1948 |
|
100 |
+
| 0.1894 | 49.0 | 23961 | 0.1949 |
|
101 |
+
| 0.1957 | 50.0 | 24450 | 0.1960 |
|
102 |
+
| 0.1986 | 51.0 | 24939 | 0.1969 |
|
103 |
+
| 0.1895 | 52.0 | 25428 | 0.1947 |
|
104 |
+
| 0.1906 | 53.0 | 25917 | 0.1945 |
|
105 |
+
| 0.1986 | 54.0 | 26406 | 0.1939 |
|
106 |
+
| 0.192 | 55.0 | 26895 | 0.1926 |
|
107 |
+
| 0.1857 | 56.0 | 27384 | 0.1942 |
|
108 |
+
| 0.1885 | 57.0 | 27873 | 0.1946 |
|
109 |
+
| 0.1923 | 58.0 | 28362 | 0.1947 |
|
110 |
+
| 0.1898 | 59.0 | 28851 | 0.1938 |
|
111 |
+
| 0.2003 | 60.0 | 29340 | 0.1940 |
|
112 |
+
| 0.1934 | 61.0 | 29829 | 0.1931 |
|
113 |
+
| 0.1946 | 62.0 | 30318 | 0.1928 |
|
114 |
+
| 0.205 | 63.0 | 30807 | 0.1928 |
|
115 |
+
| 0.1951 | 64.0 | 31296 | 0.1940 |
|
116 |
+
| 0.1926 | 65.0 | 31785 | 0.1932 |
|
117 |
+
| 0.1986 | 66.0 | 32274 | 0.1930 |
|
118 |
+
| 0.1918 | 67.0 | 32763 | 0.1921 |
|
119 |
+
| 0.1893 | 68.0 | 33252 | 0.1922 |
|
120 |
+
| 0.1879 | 69.0 | 33741 | 0.1928 |
|
121 |
+
| 0.2012 | 70.0 | 34230 | 0.1915 |
|
122 |
+
| 0.1934 | 71.0 | 34719 | 0.1922 |
|
123 |
+
| 0.1915 | 72.0 | 35208 | 0.1929 |
|
124 |
+
| 0.1967 | 73.0 | 35697 | 0.1920 |
|
125 |
+
| 0.19 | 74.0 | 36186 | 0.1924 |
|
126 |
+
| 0.2008 | 75.0 | 36675 | 0.1917 |
|
127 |
+
| 0.1953 | 76.0 | 37164 | 0.1912 |
|
128 |
+
| 0.1948 | 77.0 | 37653 | 0.1926 |
|
129 |
+
| 0.1898 | 78.0 | 38142 | 0.1919 |
|
130 |
+
| 0.1909 | 79.0 | 38631 | 0.1913 |
|
131 |
+
| 0.1895 | 80.0 | 39120 | 0.1917 |
|
132 |
+
| 0.1963 | 81.0 | 39609 | 0.1911 |
|
133 |
+
| 0.1946 | 82.0 | 40098 | 0.1912 |
|
134 |
+
| 0.1915 | 83.0 | 40587 | 0.1916 |
|
135 |
+
| 0.1858 | 84.0 | 41076 | 0.1914 |
|
136 |
+
| 0.1957 | 85.0 | 41565 | 0.1917 |
|
137 |
+
| 0.194 | 86.0 | 42054 | 0.1907 |
|
138 |
+
| 0.1832 | 87.0 | 42543 | 0.1913 |
|
139 |
+
| 0.1865 | 88.0 | 43032 | 0.1912 |
|
140 |
+
| 0.1886 | 89.0 | 43521 | 0.1913 |
|
141 |
+
| 0.1846 | 90.0 | 44010 | 0.1906 |
|
142 |
+
| 0.1896 | 91.0 | 44499 | 0.1905 |
|
143 |
+
| 0.1847 | 92.0 | 44988 | 0.1905 |
|
144 |
+
| 0.1843 | 93.0 | 45477 | 0.1907 |
|
145 |
+
| 0.1847 | 94.0 | 45966 | 0.1909 |
|
146 |
+
| 0.1925 | 95.0 | 46455 | 0.1905 |
|
147 |
+
| 0.1888 | 96.0 | 46944 | 0.1900 |
|
148 |
+
| 0.1808 | 97.0 | 47433 | 0.1904 |
|
149 |
+
| 0.1872 | 98.0 | 47922 | 0.1903 |
|
150 |
+
| 0.1849 | 99.0 | 48411 | 0.1902 |
|
151 |
+
| 0.1923 | 100.0 | 48900 | 0.1903 |
|
152 |
+
|
153 |
+
|
154 |
+
### Framework versions
|
155 |
+
|
156 |
+
- PEFT 0.10.0
|
157 |
+
- Transformers 4.40.0.dev0
|
158 |
+
- Pytorch 2.2.2+cu121
|
159 |
+
- Datasets 2.18.0
|
160 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "tiiuae/falcon-7b",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"query_key_value"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_dora": false,
|
27 |
+
"use_rslora": false
|
28 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebc1c395e1d29237592fbbffafe0e437c1fdbf2fe6b71314a01ee93ebb0e0315
|
3 |
+
size 18883912
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0de3b39016ec2b707a0aa16e78f1699cd94a59ee0747ccb5ae0e6fc21310c1da
|
3 |
+
size 5048
|