Hugging Face's logo

chchen
/
Llama-3.1-8B-Instruct-PsyCourse-fold10

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
Community
chchen commited on
Commit
10b867a
·
verified ·
1 Parent(s): ae6425b

Model save

Browse files
Files changed (2) hide show
  1. README.md +191 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-fold10
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-fold10
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: 0.0890
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
+ | 0.9905 | 0.0770 | 50 | 0.6974 |
55
+ | 0.177 | 0.1539 | 100 | 0.1452 |
56
+ | 0.0969 | 0.2309 | 150 | 0.0721 |
57
+ | 0.066 | 0.3078 | 200 | 0.0581 |
58
+ | 0.0733 | 0.3848 | 250 | 0.0600 |
59
+ | 0.0617 | 0.4618 | 300 | 0.0514 |
60
+ | 0.0509 | 0.5387 | 350 | 0.0460 |
61
+ | 0.0501 | 0.6157 | 400 | 0.0434 |
62
+ | 0.0517 | 0.6926 | 450 | 0.0504 |
63
+ | 0.0623 | 0.7696 | 500 | 0.0477 |
64
+ | 0.0485 | 0.8466 | 550 | 0.0467 |
65
+ | 0.0535 | 0.9235 | 600 | 0.0413 |
66
+ | 0.0576 | 1.0005 | 650 | 0.0397 |
67
+ | 0.0376 | 1.0774 | 700 | 0.0444 |
68
+ | 0.0331 | 1.1544 | 750 | 0.0397 |
69
+ | 0.0306 | 1.2314 | 800 | 0.0376 |
70
+ | 0.0328 | 1.3083 | 850 | 0.0379 |
71
+ | 0.044 | 1.3853 | 900 | 0.0380 |
72
+ | 0.0392 | 1.4622 | 950 | 0.0367 |
73
+ | 0.0314 | 1.5392 | 1000 | 0.0414 |
74
+ | 0.0412 | 1.6162 | 1050 | 0.0359 |
75
+ | 0.0384 | 1.6931 | 1100 | 0.0383 |
76
+ | 0.0308 | 1.7701 | 1150 | 0.0370 |
77
+ | 0.0437 | 1.8470 | 1200 | 0.0385 |
78
+ | 0.037 | 1.9240 | 1250 | 0.0373 |
79
+ | 0.0375 | 2.0010 | 1300 | 0.0385 |
80
+ | 0.0241 | 2.0779 | 1350 | 0.0360 |
81
+ | 0.0304 | 2.1549 | 1400 | 0.0360 |
82
+ | 0.0248 | 2.2318 | 1450 | 0.0354 |
83
+ | 0.0283 | 2.3088 | 1500 | 0.0362 |
84
+ | 0.0281 | 2.3858 | 1550 | 0.0370 |
85
+ | 0.0331 | 2.4627 | 1600 | 0.0389 |
86
+ | 0.0338 | 2.5397 | 1650 | 0.0359 |
87
+ | 0.033 | 2.6166 | 1700 | 0.0346 |
88
+ | 0.0226 | 2.6936 | 1750 | 0.0357 |
89
+ | 0.0281 | 2.7706 | 1800 | 0.0385 |
90
+ | 0.0181 | 2.8475 | 1850 | 0.0421 |
91
+ | 0.0234 | 2.9245 | 1900 | 0.0365 |
92
+ | 0.0285 | 3.0014 | 1950 | 0.0375 |
93
+ | 0.019 | 3.0784 | 2000 | 0.0424 |
94
+ | 0.0201 | 3.1554 | 2050 | 0.0406 |
95
+ | 0.0229 | 3.2323 | 2100 | 0.0383 |
96
+ | 0.0182 | 3.3093 | 2150 | 0.0395 |
97
+ | 0.0189 | 3.3862 | 2200 | 0.0400 |
98
+ | 0.0148 | 3.4632 | 2250 | 0.0441 |
99
+ | 0.0184 | 3.5402 | 2300 | 0.0418 |
100
+ | 0.0186 | 3.6171 | 2350 | 0.0375 |
101
+ | 0.0178 | 3.6941 | 2400 | 0.0459 |
102
+ | 0.0165 | 3.7710 | 2450 | 0.0413 |
103
+ | 0.0272 | 3.8480 | 2500 | 0.0401 |
104
+ | 0.0154 | 3.9250 | 2550 | 0.0454 |
105
+ | 0.0197 | 4.0019 | 2600 | 0.0391 |
106
+ | 0.0104 | 4.0789 | 2650 | 0.0452 |
107
+ | 0.0096 | 4.1558 | 2700 | 0.0471 |
108
+ | 0.0114 | 4.2328 | 2750 | 0.0492 |
109
+ | 0.0093 | 4.3098 | 2800 | 0.0504 |
110
+ | 0.0113 | 4.3867 | 2850 | 0.0572 |
111
+ | 0.0118 | 4.4637 | 2900 | 0.0476 |
112
+ | 0.0116 | 4.5406 | 2950 | 0.0523 |
113
+ | 0.0196 | 4.6176 | 3000 | 0.0424 |
114
+ | 0.0199 | 4.6946 | 3050 | 0.0511 |
115
+ | 0.0106 | 4.7715 | 3100 | 0.0506 |
116
+ | 0.0091 | 4.8485 | 3150 | 0.0457 |
117
+ | 0.009 | 4.9254 | 3200 | 0.0525 |
118
+ | 0.0114 | 5.0024 | 3250 | 0.0509 |
119
+ | 0.0094 | 5.0794 | 3300 | 0.0544 |
120
+ | 0.0068 | 5.1563 | 3350 | 0.0576 |
121
+ | 0.008 | 5.2333 | 3400 | 0.0621 |
122
+ | 0.0043 | 5.3102 | 3450 | 0.0562 |
123
+ | 0.0052 | 5.3872 | 3500 | 0.0636 |
124
+ | 0.0106 | 5.4642 | 3550 | 0.0624 |
125
+ | 0.0071 | 5.5411 | 3600 | 0.0550 |
126
+ | 0.0071 | 5.6181 | 3650 | 0.0575 |
127
+ | 0.0037 | 5.6950 | 3700 | 0.0676 |
128
+ | 0.0048 | 5.7720 | 3750 | 0.0585 |
129
+ | 0.0095 | 5.8490 | 3800 | 0.0627 |
130
+ | 0.0044 | 5.9259 | 3850 | 0.0622 |
131
+ | 0.0059 | 6.0029 | 3900 | 0.0537 |
132
+ | 0.0027 | 6.0798 | 3950 | 0.0611 |
133
+ | 0.0014 | 6.1568 | 4000 | 0.0681 |
134
+ | 0.0027 | 6.2338 | 4050 | 0.0721 |
135
+ | 0.0015 | 6.3107 | 4100 | 0.0669 |
136
+ | 0.0052 | 6.3877 | 4150 | 0.0680 |
137
+ | 0.0043 | 6.4646 | 4200 | 0.0635 |
138
+ | 0.0038 | 6.5416 | 4250 | 0.0666 |
139
+ | 0.0044 | 6.6186 | 4300 | 0.0672 |
140
+ | 0.0012 | 6.6955 | 4350 | 0.0659 |
141
+ | 0.0017 | 6.7725 | 4400 | 0.0688 |
142
+ | 0.0072 | 6.8494 | 4450 | 0.0691 |
143
+ | 0.0036 | 6.9264 | 4500 | 0.0659 |
144
+ | 0.0006 | 7.0034 | 4550 | 0.0667 |
145
+ | 0.0012 | 7.0803 | 4600 | 0.0716 |
146
+ | 0.0018 | 7.1573 | 4650 | 0.0735 |
147
+ | 0.002 | 7.2342 | 4700 | 0.0761 |
148
+ | 0.0006 | 7.3112 | 4750 | 0.0762 |
149
+ | 0.0002 | 7.3882 | 4800 | 0.0765 |
150
+ | 0.0003 | 7.4651 | 4850 | 0.0802 |
151
+ | 0.0002 | 7.5421 | 4900 | 0.0789 |
152
+ | 0.0025 | 7.6190 | 4950 | 0.0805 |
153
+ | 0.0003 | 7.6960 | 5000 | 0.0750 |
154
+ | 0.0006 | 7.7730 | 5050 | 0.0741 |
155
+ | 0.0011 | 7.8499 | 5100 | 0.0746 |
156
+ | 0.0002 | 7.9269 | 5150 | 0.0748 |
157
+ | 0.0016 | 8.0038 | 5200 | 0.0746 |
158
+ | 0.0011 | 8.0808 | 5250 | 0.0755 |
159
+ | 0.0002 | 8.1578 | 5300 | 0.0791 |
160
+ | 0.0001 | 8.2347 | 5350 | 0.0823 |
161
+ | 0.0 | 8.3117 | 5400 | 0.0834 |
162
+ | 0.0001 | 8.3886 | 5450 | 0.0856 |
163
+ | 0.0002 | 8.4656 | 5500 | 0.0842 |
164
+ | 0.0002 | 8.5426 | 5550 | 0.0853 |
165
+ | 0.0014 | 8.6195 | 5600 | 0.0852 |
166
+ | 0.0009 | 8.6965 | 5650 | 0.0854 |
167
+ | 0.0006 | 8.7734 | 5700 | 0.0849 |
168
+ | 0.0003 | 8.8504 | 5750 | 0.0848 |
169
+ | 0.0007 | 8.9274 | 5800 | 0.0857 |
170
+ | 0.0 | 9.0043 | 5850 | 0.0865 |
171
+ | 0.0 | 9.0813 | 5900 | 0.0873 |
172
+ | 0.0006 | 9.1582 | 5950 | 0.0876 |
173
+ | 0.0003 | 9.2352 | 6000 | 0.0879 |
174
+ | 0.0002 | 9.3122 | 6050 | 0.0882 |
175
+ | 0.0004 | 9.3891 | 6100 | 0.0885 |
176
+ | 0.0003 | 9.4661 | 6150 | 0.0884 |
177
+ | 0.0005 | 9.5430 | 6200 | 0.0887 |
178
+ | 0.0003 | 9.6200 | 6250 | 0.0887 |
179
+ | 0.0001 | 9.6970 | 6300 | 0.0890 |
180
+ | 0.0004 | 9.7739 | 6350 | 0.0889 |
181
+ | 0.001 | 9.8509 | 6400 | 0.0889 |
182
+ | 0.0 | 9.9278 | 6450 | 0.0890 |
183
+
184
+
185
+ ### Framework versions
186
+
187
+ - PEFT 0.12.0
188
+ - Transformers 4.46.1
189
+ - Pytorch 2.5.1+cu124
190
+ - Datasets 3.1.0
191
+ - Tokenizers 0.20.3
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a5e73523a9f9cb7f47fd3b1c3a582508f399db10dcc47009d58699a7c2baf3c
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0e75a3b4af4aee932d7aea10d600df5aa3fbffe0db645c82d4bfe0510ab39c0
3
  size 83945296