Hugging Face's logo

chchen
/
Llama-3.1-8B-Instruct-PsyCourse-fold5

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
chchen commited on
Commit
d1625f0
·
verified ·
1 Parent(s): 7ed0521

Model save

Browse files
Files changed (2) hide show
  1. README.md +193 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-fold5
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-fold5
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: 0.0708
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
+ | 0.9962 | 0.0758 | 50 | 0.7209 |
55
+ | 0.1767 | 0.1517 | 100 | 0.1586 |
56
+ | 0.0837 | 0.2275 | 150 | 0.0798 |
57
+ | 0.0672 | 0.3033 | 200 | 0.0662 |
58
+ | 0.0585 | 0.3791 | 250 | 0.0565 |
59
+ | 0.0501 | 0.4550 | 300 | 0.0505 |
60
+ | 0.0571 | 0.5308 | 350 | 0.0490 |
61
+ | 0.0694 | 0.6066 | 400 | 0.0491 |
62
+ | 0.0582 | 0.6825 | 450 | 0.0486 |
63
+ | 0.0363 | 0.7583 | 500 | 0.0432 |
64
+ | 0.0349 | 0.8341 | 550 | 0.0466 |
65
+ | 0.0473 | 0.9100 | 600 | 0.0458 |
66
+ | 0.0493 | 0.9858 | 650 | 0.0445 |
67
+ | 0.0371 | 1.0616 | 700 | 0.0471 |
68
+ | 0.0413 | 1.1374 | 750 | 0.0468 |
69
+ | 0.0379 | 1.2133 | 800 | 0.0397 |
70
+ | 0.0351 | 1.2891 | 850 | 0.0412 |
71
+ | 0.03 | 1.3649 | 900 | 0.0419 |
72
+ | 0.0321 | 1.4408 | 950 | 0.0431 |
73
+ | 0.0448 | 1.5166 | 1000 | 0.0386 |
74
+ | 0.0301 | 1.5924 | 1050 | 0.0367 |
75
+ | 0.0248 | 1.6682 | 1100 | 0.0376 |
76
+ | 0.0315 | 1.7441 | 1150 | 0.0390 |
77
+ | 0.0357 | 1.8199 | 1200 | 0.0369 |
78
+ | 0.0357 | 1.8957 | 1250 | 0.0344 |
79
+ | 0.0434 | 1.9716 | 1300 | 0.0384 |
80
+ | 0.0275 | 2.0474 | 1350 | 0.0352 |
81
+ | 0.0204 | 2.1232 | 1400 | 0.0347 |
82
+ | 0.022 | 2.1991 | 1450 | 0.0377 |
83
+ | 0.0157 | 2.2749 | 1500 | 0.0375 |
84
+ | 0.0287 | 2.3507 | 1550 | 0.0348 |
85
+ | 0.0279 | 2.4265 | 1600 | 0.0358 |
86
+ | 0.0164 | 2.5024 | 1650 | 0.0384 |
87
+ | 0.03 | 2.5782 | 1700 | 0.0367 |
88
+ | 0.0278 | 2.6540 | 1750 | 0.0399 |
89
+ | 0.0305 | 2.7299 | 1800 | 0.0355 |
90
+ | 0.0329 | 2.8057 | 1850 | 0.0376 |
91
+ | 0.0248 | 2.8815 | 1900 | 0.0360 |
92
+ | 0.0329 | 2.9573 | 1950 | 0.0334 |
93
+ | 0.0129 | 3.0332 | 2000 | 0.0392 |
94
+ | 0.01 | 3.1090 | 2050 | 0.0398 |
95
+ | 0.0156 | 3.1848 | 2100 | 0.0395 |
96
+ | 0.0151 | 3.2607 | 2150 | 0.0446 |
97
+ | 0.0181 | 3.3365 | 2200 | 0.0362 |
98
+ | 0.0114 | 3.4123 | 2250 | 0.0377 |
99
+ | 0.0178 | 3.4882 | 2300 | 0.0382 |
100
+ | 0.0131 | 3.5640 | 2350 | 0.0382 |
101
+ | 0.0207 | 3.6398 | 2400 | 0.0354 |
102
+ | 0.0211 | 3.7156 | 2450 | 0.0391 |
103
+ | 0.0254 | 3.7915 | 2500 | 0.0401 |
104
+ | 0.0171 | 3.8673 | 2550 | 0.0389 |
105
+ | 0.0203 | 3.9431 | 2600 | 0.0386 |
106
+ | 0.0128 | 4.0190 | 2650 | 0.0386 |
107
+ | 0.0072 | 4.0948 | 2700 | 0.0465 |
108
+ | 0.01 | 4.1706 | 2750 | 0.0525 |
109
+ | 0.015 | 4.2464 | 2800 | 0.0420 |
110
+ | 0.0122 | 4.3223 | 2850 | 0.0437 |
111
+ | 0.0147 | 4.3981 | 2900 | 0.0449 |
112
+ | 0.0139 | 4.4739 | 2950 | 0.0425 |
113
+ | 0.011 | 4.5498 | 3000 | 0.0443 |
114
+ | 0.0061 | 4.6256 | 3050 | 0.0445 |
115
+ | 0.0159 | 4.7014 | 3100 | 0.0451 |
116
+ | 0.0111 | 4.7773 | 3150 | 0.0408 |
117
+ | 0.0058 | 4.8531 | 3200 | 0.0434 |
118
+ | 0.0106 | 4.9289 | 3250 | 0.0438 |
119
+ | 0.0123 | 5.0047 | 3300 | 0.0401 |
120
+ | 0.0043 | 5.0806 | 3350 | 0.0508 |
121
+ | 0.0051 | 5.1564 | 3400 | 0.0526 |
122
+ | 0.0043 | 5.2322 | 3450 | 0.0509 |
123
+ | 0.0049 | 5.3081 | 3500 | 0.0480 |
124
+ | 0.0043 | 5.3839 | 3550 | 0.0463 |
125
+ | 0.0052 | 5.4597 | 3600 | 0.0507 |
126
+ | 0.0086 | 5.5355 | 3650 | 0.0571 |
127
+ | 0.0026 | 5.6114 | 3700 | 0.0495 |
128
+ | 0.0032 | 5.6872 | 3750 | 0.0489 |
129
+ | 0.0034 | 5.7630 | 3800 | 0.0507 |
130
+ | 0.0019 | 5.8389 | 3850 | 0.0481 |
131
+ | 0.0024 | 5.9147 | 3900 | 0.0502 |
132
+ | 0.0089 | 5.9905 | 3950 | 0.0476 |
133
+ | 0.0029 | 6.0664 | 4000 | 0.0478 |
134
+ | 0.004 | 6.1422 | 4050 | 0.0524 |
135
+ | 0.0007 | 6.2180 | 4100 | 0.0559 |
136
+ | 0.0038 | 6.2938 | 4150 | 0.0563 |
137
+ | 0.0012 | 6.3697 | 4200 | 0.0545 |
138
+ | 0.0021 | 6.4455 | 4250 | 0.0590 |
139
+ | 0.0027 | 6.5213 | 4300 | 0.0562 |
140
+ | 0.0045 | 6.5972 | 4350 | 0.0500 |
141
+ | 0.0024 | 6.6730 | 4400 | 0.0543 |
142
+ | 0.0025 | 6.7488 | 4450 | 0.0604 |
143
+ | 0.0015 | 6.8246 | 4500 | 0.0572 |
144
+ | 0.0043 | 6.9005 | 4550 | 0.0528 |
145
+ | 0.0064 | 6.9763 | 4600 | 0.0526 |
146
+ | 0.0009 | 7.0521 | 4650 | 0.0575 |
147
+ | 0.0006 | 7.1280 | 4700 | 0.0605 |
148
+ | 0.0007 | 7.2038 | 4750 | 0.0589 |
149
+ | 0.0005 | 7.2796 | 4800 | 0.0606 |
150
+ | 0.0002 | 7.3555 | 4850 | 0.0630 |
151
+ | 0.0003 | 7.4313 | 4900 | 0.0659 |
152
+ | 0.0017 | 7.5071 | 4950 | 0.0695 |
153
+ | 0.0011 | 7.5829 | 5000 | 0.0662 |
154
+ | 0.0017 | 7.6588 | 5050 | 0.0590 |
155
+ | 0.0005 | 7.7346 | 5100 | 0.0615 |
156
+ | 0.0019 | 7.8104 | 5150 | 0.0583 |
157
+ | 0.0009 | 7.8863 | 5200 | 0.0603 |
158
+ | 0.0015 | 7.9621 | 5250 | 0.0600 |
159
+ | 0.0012 | 8.0379 | 5300 | 0.0613 |
160
+ | 0.0003 | 8.1137 | 5350 | 0.0645 |
161
+ | 0.0004 | 8.1896 | 5400 | 0.0653 |
162
+ | 0.0002 | 8.2654 | 5450 | 0.0663 |
163
+ | 0.0006 | 8.3412 | 5500 | 0.0675 |
164
+ | 0.0004 | 8.4171 | 5550 | 0.0670 |
165
+ | 0.0005 | 8.4929 | 5600 | 0.0671 |
166
+ | 0.0018 | 8.5687 | 5650 | 0.0666 |
167
+ | 0.0003 | 8.6445 | 5700 | 0.0645 |
168
+ | 0.0008 | 8.7204 | 5750 | 0.0656 |
169
+ | 0.0009 | 8.7962 | 5800 | 0.0665 |
170
+ | 0.0005 | 8.8720 | 5850 | 0.0677 |
171
+ | 0.0008 | 8.9479 | 5900 | 0.0680 |
172
+ | 0.0007 | 9.0237 | 5950 | 0.0683 |
173
+ | 0.0002 | 9.0995 | 6000 | 0.0691 |
174
+ | 0.0009 | 9.1754 | 6050 | 0.0693 |
175
+ | 0.0007 | 9.2512 | 6100 | 0.0696 |
176
+ | 0.0006 | 9.3270 | 6150 | 0.0702 |
177
+ | 0.0002 | 9.4028 | 6200 | 0.0703 |
178
+ | 0.0001 | 9.4787 | 6250 | 0.0706 |
179
+ | 0.0006 | 9.5545 | 6300 | 0.0706 |
180
+ | 0.0004 | 9.6303 | 6350 | 0.0705 |
181
+ | 0.0008 | 9.7062 | 6400 | 0.0709 |
182
+ | 0.0004 | 9.7820 | 6450 | 0.0709 |
183
+ | 0.0002 | 9.8578 | 6500 | 0.0709 |
184
+ | 0.0001 | 9.9336 | 6550 | 0.0708 |
185
+
186
+
187
+ ### Framework versions
188
+
189
+ - PEFT 0.12.0
190
+ - Transformers 4.46.1
191
+ - Pytorch 2.5.1+cu124
192
+ - Datasets 3.1.0
193
+ - Tokenizers 0.20.3
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7820175e913e2825a3436694fe7d577be2bedbac7b57e72212b8de2e680a35b1
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c88c95b04963e4f18b6ddc7c1720b05142b6273b0f530ccb48b4e79a5e48716
3
  size 83945296