Hugging Face's logo

chchen
/
Llama-3.1-8B-Instruct-PsyCourse-fold3

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
Community
chchen commited on
Commit
011f5a4
·
verified ·
1 Parent(s): d68a858

Model save

Browse files
Files changed (2) hide show
  1. README.md +194 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-fold3
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-fold3
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: 0.0904
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
+ | 0.9136 | 0.0753 | 50 | 0.7080 |
55
+ | 0.2044 | 0.1505 | 100 | 0.1460 |
56
+ | 0.1028 | 0.2258 | 150 | 0.0828 |
57
+ | 0.08 | 0.3011 | 200 | 0.0657 |
58
+ | 0.0625 | 0.3763 | 250 | 0.0565 |
59
+ | 0.0631 | 0.4516 | 300 | 0.0624 |
60
+ | 0.0453 | 0.5269 | 350 | 0.0559 |
61
+ | 0.057 | 0.6021 | 400 | 0.0501 |
62
+ | 0.0534 | 0.6774 | 450 | 0.0464 |
63
+ | 0.0377 | 0.7527 | 500 | 0.0456 |
64
+ | 0.0504 | 0.8279 | 550 | 0.0465 |
65
+ | 0.0379 | 0.9032 | 600 | 0.0448 |
66
+ | 0.0403 | 0.9785 | 650 | 0.0455 |
67
+ | 0.0331 | 1.0537 | 700 | 0.0442 |
68
+ | 0.0376 | 1.1290 | 750 | 0.0394 |
69
+ | 0.0425 | 1.2043 | 800 | 0.0431 |
70
+ | 0.0351 | 1.2795 | 850 | 0.0397 |
71
+ | 0.047 | 1.3548 | 900 | 0.0426 |
72
+ | 0.0369 | 1.4300 | 950 | 0.0397 |
73
+ | 0.0327 | 1.5053 | 1000 | 0.0419 |
74
+ | 0.0323 | 1.5806 | 1050 | 0.0428 |
75
+ | 0.0264 | 1.6558 | 1100 | 0.0383 |
76
+ | 0.0445 | 1.7311 | 1150 | 0.0370 |
77
+ | 0.0357 | 1.8064 | 1200 | 0.0378 |
78
+ | 0.0358 | 1.8816 | 1250 | 0.0366 |
79
+ | 0.0336 | 1.9569 | 1300 | 0.0360 |
80
+ | 0.0233 | 2.0322 | 1350 | 0.0408 |
81
+ | 0.0311 | 2.1074 | 1400 | 0.0376 |
82
+ | 0.0243 | 2.1827 | 1450 | 0.0391 |
83
+ | 0.0299 | 2.2580 | 1500 | 0.0432 |
84
+ | 0.0351 | 2.3332 | 1550 | 0.0400 |
85
+ | 0.0189 | 2.4085 | 1600 | 0.0403 |
86
+ | 0.0226 | 2.4838 | 1650 | 0.0422 |
87
+ | 0.0313 | 2.5590 | 1700 | 0.0392 |
88
+ | 0.0456 | 2.6343 | 1750 | 0.0384 |
89
+ | 0.0297 | 2.7096 | 1800 | 0.0397 |
90
+ | 0.0276 | 2.7848 | 1850 | 0.0372 |
91
+ | 0.0309 | 2.8601 | 1900 | 0.0420 |
92
+ | 0.0272 | 2.9354 | 1950 | 0.0379 |
93
+ | 0.0186 | 3.0106 | 2000 | 0.0382 |
94
+ | 0.0154 | 3.0859 | 2050 | 0.0438 |
95
+ | 0.0148 | 3.1612 | 2100 | 0.0421 |
96
+ | 0.0191 | 3.2364 | 2150 | 0.0407 |
97
+ | 0.0223 | 3.3117 | 2200 | 0.0410 |
98
+ | 0.0212 | 3.3870 | 2250 | 0.0409 |
99
+ | 0.0159 | 3.4622 | 2300 | 0.0436 |
100
+ | 0.0109 | 3.5375 | 2350 | 0.0459 |
101
+ | 0.0183 | 3.6128 | 2400 | 0.0437 |
102
+ | 0.0209 | 3.6880 | 2450 | 0.0425 |
103
+ | 0.0187 | 3.7633 | 2500 | 0.0415 |
104
+ | 0.0176 | 3.8386 | 2550 | 0.0412 |
105
+ | 0.0201 | 3.9138 | 2600 | 0.0420 |
106
+ | 0.021 | 3.9891 | 2650 | 0.0418 |
107
+ | 0.0096 | 4.0644 | 2700 | 0.0513 |
108
+ | 0.0075 | 4.1396 | 2750 | 0.0519 |
109
+ | 0.0116 | 4.2149 | 2800 | 0.0540 |
110
+ | 0.0088 | 4.2901 | 2850 | 0.0501 |
111
+ | 0.0166 | 4.3654 | 2900 | 0.0507 |
112
+ | 0.0098 | 4.4407 | 2950 | 0.0504 |
113
+ | 0.0076 | 4.5159 | 3000 | 0.0549 |
114
+ | 0.0175 | 4.5912 | 3050 | 0.0470 |
115
+ | 0.0116 | 4.6665 | 3100 | 0.0573 |
116
+ | 0.0157 | 4.7417 | 3150 | 0.0456 |
117
+ | 0.0079 | 4.8170 | 3200 | 0.0508 |
118
+ | 0.0091 | 4.8923 | 3250 | 0.0512 |
119
+ | 0.009 | 4.9675 | 3300 | 0.0479 |
120
+ | 0.0042 | 5.0428 | 3350 | 0.0596 |
121
+ | 0.0059 | 5.1181 | 3400 | 0.0585 |
122
+ | 0.0041 | 5.1933 | 3450 | 0.0657 |
123
+ | 0.0027 | 5.2686 | 3500 | 0.0646 |
124
+ | 0.0021 | 5.3439 | 3550 | 0.0598 |
125
+ | 0.0011 | 5.4191 | 3600 | 0.0593 |
126
+ | 0.0028 | 5.4944 | 3650 | 0.0583 |
127
+ | 0.0069 | 5.5697 | 3700 | 0.0527 |
128
+ | 0.0044 | 5.6449 | 3750 | 0.0575 |
129
+ | 0.005 | 5.7202 | 3800 | 0.0603 |
130
+ | 0.0034 | 5.7955 | 3850 | 0.0663 |
131
+ | 0.007 | 5.8707 | 3900 | 0.0544 |
132
+ | 0.0059 | 5.9460 | 3950 | 0.0533 |
133
+ | 0.0021 | 6.0213 | 4000 | 0.0597 |
134
+ | 0.0017 | 6.0965 | 4050 | 0.0612 |
135
+ | 0.0065 | 6.1718 | 4100 | 0.0606 |
136
+ | 0.001 | 6.2471 | 4150 | 0.0655 |
137
+ | 0.0035 | 6.3223 | 4200 | 0.0675 |
138
+ | 0.0058 | 6.3976 | 4250 | 0.0619 |
139
+ | 0.0025 | 6.4729 | 4300 | 0.0636 |
140
+ | 0.002 | 6.5481 | 4350 | 0.0681 |
141
+ | 0.0008 | 6.6234 | 4400 | 0.0721 |
142
+ | 0.0025 | 6.6987 | 4450 | 0.0603 |
143
+ | 0.0021 | 6.7739 | 4500 | 0.0615 |
144
+ | 0.0032 | 6.8492 | 4550 | 0.0608 |
145
+ | 0.0046 | 6.9245 | 4600 | 0.0656 |
146
+ | 0.0021 | 6.9997 | 4650 | 0.0695 |
147
+ | 0.0008 | 7.0750 | 4700 | 0.0669 |
148
+ | 0.0001 | 7.1502 | 4750 | 0.0729 |
149
+ | 0.0016 | 7.2255 | 4800 | 0.0755 |
150
+ | 0.0011 | 7.3008 | 4850 | 0.0772 |
151
+ | 0.0037 | 7.3760 | 4900 | 0.0756 |
152
+ | 0.0002 | 7.4513 | 4950 | 0.0770 |
153
+ | 0.0013 | 7.5266 | 5000 | 0.0709 |
154
+ | 0.0016 | 7.6018 | 5050 | 0.0706 |
155
+ | 0.0003 | 7.6771 | 5100 | 0.0718 |
156
+ | 0.0024 | 7.7524 | 5150 | 0.0724 |
157
+ | 0.0024 | 7.8276 | 5200 | 0.0750 |
158
+ | 0.0003 | 7.9029 | 5250 | 0.0753 |
159
+ | 0.0008 | 7.9782 | 5300 | 0.0762 |
160
+ | 0.0002 | 8.0534 | 5350 | 0.0798 |
161
+ | 0.0014 | 8.1287 | 5400 | 0.0810 |
162
+ | 0.0001 | 8.2040 | 5450 | 0.0807 |
163
+ | 0.0022 | 8.2792 | 5500 | 0.0826 |
164
+ | 0.0011 | 8.3545 | 5550 | 0.0840 |
165
+ | 0.0001 | 8.4298 | 5600 | 0.0858 |
166
+ | 0.0012 | 8.5050 | 5650 | 0.0878 |
167
+ | 0.0006 | 8.5803 | 5700 | 0.0870 |
168
+ | 0.0005 | 8.6556 | 5750 | 0.0883 |
169
+ | 0.0016 | 8.7308 | 5800 | 0.0883 |
170
+ | 0.0004 | 8.8061 | 5850 | 0.0892 |
171
+ | 0.0003 | 8.8814 | 5900 | 0.0878 |
172
+ | 0.0009 | 8.9566 | 5950 | 0.0877 |
173
+ | 0.0007 | 9.0319 | 6000 | 0.0878 |
174
+ | 0.0001 | 9.1072 | 6050 | 0.0888 |
175
+ | 0.0013 | 9.1824 | 6100 | 0.0888 |
176
+ | 0.0006 | 9.2577 | 6150 | 0.0888 |
177
+ | 0.0006 | 9.3330 | 6200 | 0.0891 |
178
+ | 0.0003 | 9.4082 | 6250 | 0.0894 |
179
+ | 0.0 | 9.4835 | 6300 | 0.0897 |
180
+ | 0.0001 | 9.5588 | 6350 | 0.0902 |
181
+ | 0.0004 | 9.6340 | 6400 | 0.0901 |
182
+ | 0.0008 | 9.7093 | 6450 | 0.0900 |
183
+ | 0.0002 | 9.7846 | 6500 | 0.0901 |
184
+ | 0.0003 | 9.8598 | 6550 | 0.0902 |
185
+ | 0.0001 | 9.9351 | 6600 | 0.0904 |
186
+
187
+
188
+ ### Framework versions
189
+
190
+ - PEFT 0.12.0
191
+ - Transformers 4.46.1
192
+ - Pytorch 2.5.1+cu124
193
+ - Datasets 3.1.0
194
+ - Tokenizers 0.20.3
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8b57fc49c6cb585961d88f993a0dd6c0d6f700f00eedf4ad36b6707a692bb2f
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3858e3f7e72ff77fc7ed02b660fa746aaea0646e9de9b9b7770635af08569315
3
  size 83945296