Hugging Face's logo

chchen
/
Llama3-OpenBioLLM-8B-PsyCourse-fold7

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
chchen commited on
Commit
7538012
·
verified ·
1 Parent(s): 5f5bbd2

Model save

Browse files
Files changed (2) hide show
  1. README.md +127 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: llama3
4
+ base_model: aaditya/Llama3-OpenBioLLM-8B
5
+ tags:
6
+ - llama-factory
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: Llama3-OpenBioLLM-8B-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
+ # Llama3-OpenBioLLM-8B-PsyCourse-fold7
17
+
18
+ This model is a fine-tuned version of [aaditya/Llama3-OpenBioLLM-8B](https://huggingface.co/aaditya/Llama3-OpenBioLLM-8B) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0511
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: 5.0
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:------:|:----:|:---------------:|
54
+ | 0.5143 | 0.0764 | 50 | 0.3069 |
55
+ | 0.1115 | 0.1528 | 100 | 0.0800 |
56
+ | 0.0781 | 0.2292 | 150 | 0.0636 |
57
+ | 0.0677 | 0.3056 | 200 | 0.0595 |
58
+ | 0.0609 | 0.3820 | 250 | 0.0500 |
59
+ | 0.0442 | 0.4584 | 300 | 0.0519 |
60
+ | 0.0605 | 0.5348 | 350 | 0.0530 |
61
+ | 0.0415 | 0.6112 | 400 | 0.0427 |
62
+ | 0.0616 | 0.6875 | 450 | 0.0430 |
63
+ | 0.0412 | 0.7639 | 500 | 0.0389 |
64
+ | 0.0306 | 0.8403 | 550 | 0.0385 |
65
+ | 0.0579 | 0.9167 | 600 | 0.0378 |
66
+ | 0.0625 | 0.9931 | 650 | 0.0424 |
67
+ | 0.0363 | 1.0695 | 700 | 0.0368 |
68
+ | 0.024 | 1.1459 | 750 | 0.0377 |
69
+ | 0.0331 | 1.2223 | 800 | 0.0374 |
70
+ | 0.0368 | 1.2987 | 850 | 0.0383 |
71
+ | 0.039 | 1.3751 | 900 | 0.0359 |
72
+ | 0.0428 | 1.4515 | 950 | 0.0387 |
73
+ | 0.0285 | 1.5279 | 1000 | 0.0350 |
74
+ | 0.0292 | 1.6043 | 1050 | 0.0368 |
75
+ | 0.0317 | 1.6807 | 1100 | 0.0365 |
76
+ | 0.0506 | 1.7571 | 1150 | 0.0349 |
77
+ | 0.0329 | 1.8335 | 1200 | 0.0353 |
78
+ | 0.0352 | 1.9099 | 1250 | 0.0377 |
79
+ | 0.0289 | 1.9862 | 1300 | 0.0365 |
80
+ | 0.0202 | 2.0626 | 1350 | 0.0356 |
81
+ | 0.0174 | 2.1390 | 1400 | 0.0357 |
82
+ | 0.0134 | 2.2154 | 1450 | 0.0395 |
83
+ | 0.02 | 2.2918 | 1500 | 0.0361 |
84
+ | 0.0189 | 2.3682 | 1550 | 0.0374 |
85
+ | 0.0162 | 2.4446 | 1600 | 0.0348 |
86
+ | 0.0252 | 2.5210 | 1650 | 0.0371 |
87
+ | 0.0175 | 2.5974 | 1700 | 0.0366 |
88
+ | 0.0222 | 2.6738 | 1750 | 0.0346 |
89
+ | 0.0274 | 2.7502 | 1800 | 0.0347 |
90
+ | 0.0215 | 2.8266 | 1850 | 0.0362 |
91
+ | 0.0201 | 2.9030 | 1900 | 0.0378 |
92
+ | 0.016 | 2.9794 | 1950 | 0.0343 |
93
+ | 0.009 | 3.0558 | 2000 | 0.0372 |
94
+ | 0.0106 | 3.1322 | 2050 | 0.0389 |
95
+ | 0.0061 | 3.2086 | 2100 | 0.0432 |
96
+ | 0.0075 | 3.2850 | 2150 | 0.0434 |
97
+ | 0.0089 | 3.3613 | 2200 | 0.0434 |
98
+ | 0.0102 | 3.4377 | 2250 | 0.0462 |
99
+ | 0.0083 | 3.5141 | 2300 | 0.0465 |
100
+ | 0.0131 | 3.5905 | 2350 | 0.0443 |
101
+ | 0.0054 | 3.6669 | 2400 | 0.0424 |
102
+ | 0.0038 | 3.7433 | 2450 | 0.0428 |
103
+ | 0.0074 | 3.8197 | 2500 | 0.0429 |
104
+ | 0.0056 | 3.8961 | 2550 | 0.0426 |
105
+ | 0.007 | 3.9725 | 2600 | 0.0428 |
106
+ | 0.0034 | 4.0489 | 2650 | 0.0434 |
107
+ | 0.0051 | 4.1253 | 2700 | 0.0460 |
108
+ | 0.0043 | 4.2017 | 2750 | 0.0464 |
109
+ | 0.0023 | 4.2781 | 2800 | 0.0472 |
110
+ | 0.0035 | 4.3545 | 2850 | 0.0477 |
111
+ | 0.0021 | 4.4309 | 2900 | 0.0488 |
112
+ | 0.0021 | 4.5073 | 2950 | 0.0497 |
113
+ | 0.0024 | 4.5837 | 3000 | 0.0501 |
114
+ | 0.0013 | 4.6600 | 3050 | 0.0505 |
115
+ | 0.0031 | 4.7364 | 3100 | 0.0511 |
116
+ | 0.0031 | 4.8128 | 3150 | 0.0511 |
117
+ | 0.0023 | 4.8892 | 3200 | 0.0512 |
118
+ | 0.0023 | 4.9656 | 3250 | 0.0511 |
119
+
120
+
121
+ ### Framework versions
122
+
123
+ - PEFT 0.12.0
124
+ - Transformers 4.46.1
125
+ - Pytorch 2.5.1+cu124
126
+ - Datasets 3.1.0
127
+ - Tokenizers 0.20.3
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eaff196ebe39a8c0c511cc55fb0f4c1de98bc73f1158f44590a42368fd250ad3
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87072625d114f3c3d678f665e63e8afea9ae72a43ebaef26988567b78e4ddca7
3
  size 83945296