Hugging Face's logo

chchen
/
Llama-3.1-8B-Instruct-PsyCourse-fold7

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
Community
chchen commited on
Commit
e05cd79
·
verified ·
1 Parent(s): 6ea1ba9

Model save

Browse files
Files changed (2) hide show
  1. README.md +192 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: llama3.1
4
+ base_model: meta-llama/Llama-3.1-8B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: Llama-3.1-8B-Instruct-PsyCourse-fold7
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # Llama-3.1-8B-Instruct-PsyCourse-fold7
17
+
18
+ This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0802
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.0001
40
+ - train_batch_size: 1
41
+ - eval_batch_size: 1
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 16
44
+ - total_train_batch_size: 16
45
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
+ - lr_scheduler_type: cosine
47
+ - lr_scheduler_warmup_ratio: 0.1
48
+ - num_epochs: 10.0
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:------:|:----:|:---------------:|
54
+ | 0.9681 | 0.0764 | 50 | 0.6998 |
55
+ | 0.2016 | 0.1528 | 100 | 0.1420 |
56
+ | 0.0868 | 0.2292 | 150 | 0.0756 |
57
+ | 0.0662 | 0.3056 | 200 | 0.0589 |
58
+ | 0.0623 | 0.3820 | 250 | 0.0552 |
59
+ | 0.0458 | 0.4584 | 300 | 0.0502 |
60
+ | 0.0681 | 0.5348 | 350 | 0.0517 |
61
+ | 0.0451 | 0.6112 | 400 | 0.0472 |
62
+ | 0.0596 | 0.6875 | 450 | 0.0469 |
63
+ | 0.0478 | 0.7639 | 500 | 0.0419 |
64
+ | 0.0329 | 0.8403 | 550 | 0.0406 |
65
+ | 0.0545 | 0.9167 | 600 | 0.0410 |
66
+ | 0.0586 | 0.9931 | 650 | 0.0452 |
67
+ | 0.0407 | 1.0695 | 700 | 0.0391 |
68
+ | 0.029 | 1.1459 | 750 | 0.0369 |
69
+ | 0.0345 | 1.2223 | 800 | 0.0397 |
70
+ | 0.0399 | 1.2987 | 850 | 0.0395 |
71
+ | 0.0419 | 1.3751 | 900 | 0.0393 |
72
+ | 0.0482 | 1.4515 | 950 | 0.0405 |
73
+ | 0.0329 | 1.5279 | 1000 | 0.0361 |
74
+ | 0.0306 | 1.6043 | 1050 | 0.0381 |
75
+ | 0.0308 | 1.6807 | 1100 | 0.0385 |
76
+ | 0.0612 | 1.7571 | 1150 | 0.0365 |
77
+ | 0.0369 | 1.8335 | 1200 | 0.0347 |
78
+ | 0.0394 | 1.9099 | 1250 | 0.0394 |
79
+ | 0.0325 | 1.9862 | 1300 | 0.0373 |
80
+ | 0.0267 | 2.0626 | 1350 | 0.0364 |
81
+ | 0.0236 | 2.1390 | 1400 | 0.0353 |
82
+ | 0.0178 | 2.2154 | 1450 | 0.0401 |
83
+ | 0.0261 | 2.2918 | 1500 | 0.0350 |
84
+ | 0.024 | 2.3682 | 1550 | 0.0350 |
85
+ | 0.0215 | 2.4446 | 1600 | 0.0339 |
86
+ | 0.0316 | 2.5210 | 1650 | 0.0384 |
87
+ | 0.0264 | 2.5974 | 1700 | 0.0362 |
88
+ | 0.027 | 2.6738 | 1750 | 0.0379 |
89
+ | 0.0366 | 2.7502 | 1800 | 0.0333 |
90
+ | 0.0303 | 2.8266 | 1850 | 0.0336 |
91
+ | 0.0264 | 2.9030 | 1900 | 0.0353 |
92
+ | 0.0213 | 2.9794 | 1950 | 0.0371 |
93
+ | 0.0188 | 3.0558 | 2000 | 0.0368 |
94
+ | 0.0199 | 3.1322 | 2050 | 0.0359 |
95
+ | 0.0149 | 3.2086 | 2100 | 0.0406 |
96
+ | 0.0179 | 3.2850 | 2150 | 0.0434 |
97
+ | 0.0209 | 3.3613 | 2200 | 0.0373 |
98
+ | 0.0199 | 3.4377 | 2250 | 0.0443 |
99
+ | 0.0169 | 3.5141 | 2300 | 0.0365 |
100
+ | 0.024 | 3.5905 | 2350 | 0.0377 |
101
+ | 0.0182 | 3.6669 | 2400 | 0.0404 |
102
+ | 0.0138 | 3.7433 | 2450 | 0.0410 |
103
+ | 0.0197 | 3.8197 | 2500 | 0.0382 |
104
+ | 0.0201 | 3.8961 | 2550 | 0.0362 |
105
+ | 0.0129 | 3.9725 | 2600 | 0.0420 |
106
+ | 0.0084 | 4.0489 | 2650 | 0.0419 |
107
+ | 0.01 | 4.1253 | 2700 | 0.0444 |
108
+ | 0.009 | 4.2017 | 2750 | 0.0554 |
109
+ | 0.0075 | 4.2781 | 2800 | 0.0449 |
110
+ | 0.0123 | 4.3545 | 2850 | 0.0445 |
111
+ | 0.0086 | 4.4309 | 2900 | 0.0446 |
112
+ | 0.0128 | 4.5073 | 2950 | 0.0410 |
113
+ | 0.011 | 4.5837 | 3000 | 0.0446 |
114
+ | 0.0079 | 4.6600 | 3050 | 0.0467 |
115
+ | 0.0063 | 4.7364 | 3100 | 0.0447 |
116
+ | 0.0081 | 4.8128 | 3150 | 0.0446 |
117
+ | 0.0092 | 4.8892 | 3200 | 0.0423 |
118
+ | 0.0105 | 4.9656 | 3250 | 0.0434 |
119
+ | 0.0049 | 5.0420 | 3300 | 0.0503 |
120
+ | 0.006 | 5.1184 | 3350 | 0.0521 |
121
+ | 0.0037 | 5.1948 | 3400 | 0.0545 |
122
+ | 0.0032 | 5.2712 | 3450 | 0.0743 |
123
+ | 0.0047 | 5.3476 | 3500 | 0.0558 |
124
+ | 0.0037 | 5.4240 | 3550 | 0.0517 |
125
+ | 0.0054 | 5.5004 | 3600 | 0.0526 |
126
+ | 0.0053 | 5.5768 | 3650 | 0.0507 |
127
+ | 0.0094 | 5.6532 | 3700 | 0.0504 |
128
+ | 0.0067 | 5.7296 | 3750 | 0.0492 |
129
+ | 0.0038 | 5.8060 | 3800 | 0.0524 |
130
+ | 0.0091 | 5.8824 | 3850 | 0.0443 |
131
+ | 0.006 | 5.9587 | 3900 | 0.0490 |
132
+ | 0.0042 | 6.0351 | 3950 | 0.0518 |
133
+ | 0.0023 | 6.1115 | 4000 | 0.0607 |
134
+ | 0.0012 | 6.1879 | 4050 | 0.0625 |
135
+ | 0.0046 | 6.2643 | 4100 | 0.0562 |
136
+ | 0.0017 | 6.3407 | 4150 | 0.0639 |
137
+ | 0.0029 | 6.4171 | 4200 | 0.0585 |
138
+ | 0.0023 | 6.4935 | 4250 | 0.0586 |
139
+ | 0.0021 | 6.5699 | 4300 | 0.0601 |
140
+ | 0.0004 | 6.6463 | 4350 | 0.0675 |
141
+ | 0.0021 | 6.7227 | 4400 | 0.0667 |
142
+ | 0.0024 | 6.7991 | 4450 | 0.0701 |
143
+ | 0.0022 | 6.8755 | 4500 | 0.0674 |
144
+ | 0.0033 | 6.9519 | 4550 | 0.0609 |
145
+ | 0.0009 | 7.0283 | 4600 | 0.0551 |
146
+ | 0.0011 | 7.1047 | 4650 | 0.0607 |
147
+ | 0.0014 | 7.1811 | 4700 | 0.0657 |
148
+ | 0.0003 | 7.2574 | 4750 | 0.0645 |
149
+ | 0.0013 | 7.3338 | 4800 | 0.0692 |
150
+ | 0.0004 | 7.4102 | 4850 | 0.0737 |
151
+ | 0.0004 | 7.4866 | 4900 | 0.0669 |
152
+ | 0.0028 | 7.5630 | 4950 | 0.0651 |
153
+ | 0.0008 | 7.6394 | 5000 | 0.0633 |
154
+ | 0.0014 | 7.7158 | 5050 | 0.0643 |
155
+ | 0.0012 | 7.7922 | 5100 | 0.0659 |
156
+ | 0.0006 | 7.8686 | 5150 | 0.0663 |
157
+ | 0.0005 | 7.9450 | 5200 | 0.0700 |
158
+ | 0.0007 | 8.0214 | 5250 | 0.0659 |
159
+ | 0.0009 | 8.0978 | 5300 | 0.0691 |
160
+ | 0.0002 | 8.1742 | 5350 | 0.0709 |
161
+ | 0.0004 | 8.2506 | 5400 | 0.0735 |
162
+ | 0.0006 | 8.3270 | 5450 | 0.0750 |
163
+ | 0.0007 | 8.4034 | 5500 | 0.0772 |
164
+ | 0.0001 | 8.4798 | 5550 | 0.0785 |
165
+ | 0.0007 | 8.5561 | 5600 | 0.0807 |
166
+ | 0.0013 | 8.6325 | 5650 | 0.0787 |
167
+ | 0.0005 | 8.7089 | 5700 | 0.0770 |
168
+ | 0.0012 | 8.7853 | 5750 | 0.0768 |
169
+ | 0.0004 | 8.8617 | 5800 | 0.0756 |
170
+ | 0.0032 | 8.9381 | 5850 | 0.0763 |
171
+ | 0.0008 | 9.0145 | 5900 | 0.0764 |
172
+ | 0.0002 | 9.0909 | 5950 | 0.0777 |
173
+ | 0.0002 | 9.1673 | 6000 | 0.0781 |
174
+ | 0.0003 | 9.2437 | 6050 | 0.0786 |
175
+ | 0.0007 | 9.3201 | 6100 | 0.0790 |
176
+ | 0.0002 | 9.3965 | 6150 | 0.0798 |
177
+ | 0.0003 | 9.4729 | 6200 | 0.0796 |
178
+ | 0.0008 | 9.5493 | 6250 | 0.0798 |
179
+ | 0.0002 | 9.6257 | 6300 | 0.0800 |
180
+ | 0.0012 | 9.7021 | 6350 | 0.0801 |
181
+ | 0.0008 | 9.7785 | 6400 | 0.0801 |
182
+ | 0.0001 | 9.8549 | 6450 | 0.0801 |
183
+ | 0.0005 | 9.9312 | 6500 | 0.0802 |
184
+
185
+
186
+ ### Framework versions
187
+
188
+ - PEFT 0.12.0
189
+ - Transformers 4.46.1
190
+ - Pytorch 2.5.1+cu124
191
+ - Datasets 3.1.0
192
+ - Tokenizers 0.20.3
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91921bcbfca36239cfe8429eee3c74afc86cd7e8448d53e9185dc0109d20b6be
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d05314fb13d8ba215549e3c19b55fbd5ec9bccc8ecbf99e90e796db21559efb
3
  size 83945296