Hugging Face's logo

chchen
/
Llama-3.1-8B-Instruct-PsyCourse-fold4

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
chchen commited on
Commit
786ce61
·
verified ·
1 Parent(s): 74c1f7e

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-fold4
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-fold4
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: 0.1026
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
+ | 0.916 | 0.0763 | 50 | 0.6882 |
55
+ | 0.2175 | 0.1527 | 100 | 0.1345 |
56
+ | 0.0687 | 0.2290 | 150 | 0.0777 |
57
+ | 0.0541 | 0.3053 | 200 | 0.0599 |
58
+ | 0.0681 | 0.3816 | 250 | 0.0532 |
59
+ | 0.0534 | 0.4580 | 300 | 0.0525 |
60
+ | 0.0503 | 0.5343 | 350 | 0.0565 |
61
+ | 0.0505 | 0.6106 | 400 | 0.0519 |
62
+ | 0.0641 | 0.6870 | 450 | 0.0547 |
63
+ | 0.038 | 0.7633 | 500 | 0.0414 |
64
+ | 0.0491 | 0.8396 | 550 | 0.0440 |
65
+ | 0.048 | 0.9159 | 600 | 0.0416 |
66
+ | 0.0394 | 0.9923 | 650 | 0.0428 |
67
+ | 0.04 | 1.0686 | 700 | 0.0399 |
68
+ | 0.041 | 1.1449 | 750 | 0.0392 |
69
+ | 0.0349 | 1.2213 | 800 | 0.0456 |
70
+ | 0.0351 | 1.2976 | 850 | 0.0409 |
71
+ | 0.0372 | 1.3739 | 900 | 0.0435 |
72
+ | 0.0349 | 1.4502 | 950 | 0.0378 |
73
+ | 0.0289 | 1.5266 | 1000 | 0.0392 |
74
+ | 0.0329 | 1.6029 | 1050 | 0.0396 |
75
+ | 0.0547 | 1.6792 | 1100 | 0.0405 |
76
+ | 0.0385 | 1.7556 | 1150 | 0.0407 |
77
+ | 0.054 | 1.8319 | 1200 | 0.0386 |
78
+ | 0.0311 | 1.9082 | 1250 | 0.0370 |
79
+ | 0.0381 | 1.9845 | 1300 | 0.0356 |
80
+ | 0.0222 | 2.0609 | 1350 | 0.0367 |
81
+ | 0.0259 | 2.1372 | 1400 | 0.0379 |
82
+ | 0.0332 | 2.2135 | 1450 | 0.0382 |
83
+ | 0.0186 | 2.2899 | 1500 | 0.0399 |
84
+ | 0.0181 | 2.3662 | 1550 | 0.0415 |
85
+ | 0.0253 | 2.4425 | 1600 | 0.0371 |
86
+ | 0.0267 | 2.5188 | 1650 | 0.0368 |
87
+ | 0.0275 | 2.5952 | 1700 | 0.0381 |
88
+ | 0.0242 | 2.6715 | 1750 | 0.0376 |
89
+ | 0.0277 | 2.7478 | 1800 | 0.0382 |
90
+ | 0.0315 | 2.8242 | 1850 | 0.0364 |
91
+ | 0.0276 | 2.9005 | 1900 | 0.0370 |
92
+ | 0.0333 | 2.9768 | 1950 | 0.0362 |
93
+ | 0.013 | 3.0531 | 2000 | 0.0408 |
94
+ | 0.0146 | 3.1295 | 2050 | 0.0397 |
95
+ | 0.0168 | 3.2058 | 2100 | 0.0419 |
96
+ | 0.0202 | 3.2821 | 2150 | 0.0451 |
97
+ | 0.0197 | 3.3585 | 2200 | 0.0398 |
98
+ | 0.0167 | 3.4348 | 2250 | 0.0421 |
99
+ | 0.0224 | 3.5111 | 2300 | 0.0413 |
100
+ | 0.0173 | 3.5874 | 2350 | 0.0457 |
101
+ | 0.0143 | 3.6638 | 2400 | 0.0442 |
102
+ | 0.0179 | 3.7401 | 2450 | 0.0422 |
103
+ | 0.0178 | 3.8164 | 2500 | 0.0436 |
104
+ | 0.0136 | 3.8928 | 2550 | 0.0450 |
105
+ | 0.0193 | 3.9691 | 2600 | 0.0397 |
106
+ | 0.009 | 4.0454 | 2650 | 0.0460 |
107
+ | 0.0107 | 4.1217 | 2700 | 0.0470 |
108
+ | 0.0038 | 4.1981 | 2750 | 0.0484 |
109
+ | 0.0078 | 4.2744 | 2800 | 0.0531 |
110
+ | 0.0105 | 4.3507 | 2850 | 0.0516 |
111
+ | 0.0067 | 4.4271 | 2900 | 0.0596 |
112
+ | 0.0082 | 4.5034 | 2950 | 0.0517 |
113
+ | 0.0121 | 4.5797 | 3000 | 0.0526 |
114
+ | 0.0044 | 4.6560 | 3050 | 0.0487 |
115
+ | 0.0107 | 4.7324 | 3100 | 0.0495 |
116
+ | 0.0146 | 4.8087 | 3150 | 0.0517 |
117
+ | 0.0098 | 4.8850 | 3200 | 0.0537 |
118
+ | 0.0088 | 4.9614 | 3250 | 0.0484 |
119
+ | 0.0041 | 5.0377 | 3300 | 0.0548 |
120
+ | 0.0049 | 5.1140 | 3350 | 0.0611 |
121
+ | 0.0048 | 5.1903 | 3400 | 0.0641 |
122
+ | 0.0025 | 5.2667 | 3450 | 0.0638 |
123
+ | 0.0054 | 5.3430 | 3500 | 0.0624 |
124
+ | 0.0069 | 5.4193 | 3550 | 0.0626 |
125
+ | 0.0031 | 5.4957 | 3600 | 0.0694 |
126
+ | 0.0109 | 5.5720 | 3650 | 0.0659 |
127
+ | 0.0015 | 5.6483 | 3700 | 0.0763 |
128
+ | 0.0034 | 5.7246 | 3750 | 0.0662 |
129
+ | 0.0094 | 5.8010 | 3800 | 0.0618 |
130
+ | 0.0027 | 5.8773 | 3850 | 0.0643 |
131
+ | 0.0038 | 5.9536 | 3900 | 0.0737 |
132
+ | 0.001 | 6.0300 | 3950 | 0.0605 |
133
+ | 0.0022 | 6.1063 | 4000 | 0.0703 |
134
+ | 0.0015 | 6.1826 | 4050 | 0.0744 |
135
+ | 0.003 | 6.2589 | 4100 | 0.0747 |
136
+ | 0.0022 | 6.3353 | 4150 | 0.0690 |
137
+ | 0.0055 | 6.4116 | 4200 | 0.0651 |
138
+ | 0.0039 | 6.4879 | 4250 | 0.0651 |
139
+ | 0.0038 | 6.5643 | 4300 | 0.0638 |
140
+ | 0.0009 | 6.6406 | 4350 | 0.0696 |
141
+ | 0.0032 | 6.7169 | 4400 | 0.0711 |
142
+ | 0.001 | 6.7932 | 4450 | 0.0718 |
143
+ | 0.0024 | 6.8696 | 4500 | 0.0740 |
144
+ | 0.0014 | 6.9459 | 4550 | 0.0733 |
145
+ | 0.0017 | 7.0222 | 4600 | 0.0682 |
146
+ | 0.0009 | 7.0986 | 4650 | 0.0757 |
147
+ | 0.0016 | 7.1749 | 4700 | 0.0777 |
148
+ | 0.0004 | 7.2512 | 4750 | 0.0799 |
149
+ | 0.0019 | 7.3275 | 4800 | 0.0839 |
150
+ | 0.0003 | 7.4039 | 4850 | 0.0895 |
151
+ | 0.0001 | 7.4802 | 4900 | 0.0925 |
152
+ | 0.0004 | 7.5565 | 4950 | 0.0872 |
153
+ | 0.0005 | 7.6329 | 5000 | 0.0858 |
154
+ | 0.0007 | 7.7092 | 5050 | 0.0887 |
155
+ | 0.0002 | 7.7855 | 5100 | 0.0849 |
156
+ | 0.0007 | 7.8618 | 5150 | 0.0830 |
157
+ | 0.0016 | 7.9382 | 5200 | 0.0849 |
158
+ | 0.0003 | 8.0145 | 5250 | 0.0859 |
159
+ | 0.0001 | 8.0908 | 5300 | 0.0888 |
160
+ | 0.0007 | 8.1672 | 5350 | 0.0886 |
161
+ | 0.0003 | 8.2435 | 5400 | 0.0913 |
162
+ | 0.0001 | 8.3198 | 5450 | 0.0924 |
163
+ | 0.0008 | 8.3961 | 5500 | 0.0937 |
164
+ | 0.0001 | 8.4725 | 5550 | 0.0948 |
165
+ | 0.0001 | 8.5488 | 5600 | 0.0949 |
166
+ | 0.0005 | 8.6251 | 5650 | 0.0965 |
167
+ | 0.0009 | 8.7015 | 5700 | 0.0980 |
168
+ | 0.001 | 8.7778 | 5750 | 0.0979 |
169
+ | 0.0002 | 8.8541 | 5800 | 0.0976 |
170
+ | 0.0004 | 8.9304 | 5850 | 0.0987 |
171
+ | 0.0008 | 9.0068 | 5900 | 0.0994 |
172
+ | 0.0001 | 9.0831 | 5950 | 0.1002 |
173
+ | 0.0001 | 9.1594 | 6000 | 0.1007 |
174
+ | 0.0001 | 9.2358 | 6050 | 0.1010 |
175
+ | 0.0001 | 9.3121 | 6100 | 0.1017 |
176
+ | 0.0003 | 9.3884 | 6150 | 0.1019 |
177
+ | 0.0001 | 9.4647 | 6200 | 0.1018 |
178
+ | 0.0006 | 9.5411 | 6250 | 0.1023 |
179
+ | 0.0001 | 9.6174 | 6300 | 0.1022 |
180
+ | 0.0006 | 9.6937 | 6350 | 0.1026 |
181
+ | 0.0001 | 9.7701 | 6400 | 0.1025 |
182
+ | 0.0 | 9.8464 | 6450 | 0.1024 |
183
+ | 0.0 | 9.9227 | 6500 | 0.1023 |
184
+ | 0.0002 | 9.9990 | 6550 | 0.1026 |
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 sha256:49bbfc433316fbbc671778c597ac15c220af94bcece3f0d9628a049dc080474b
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd77ef110e521eddf68c1128bd93f757a9936bb2a817e2eb6c1e7f269ab54ae5
3
  size 83945296