Hugging Face's logo

chchen
/
Llama3-OpenBioLLM-8B-PsyCourse-fold2

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
chchen commited on
Commit
f281415
·
verified ·
1 Parent(s): deb479f

Model save

Browse files
Files changed (2) hide show
  1. README.md +126 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-fold2
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-fold2
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: 0.0634
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
+ | 0.4179 | 0.0775 | 50 | 0.3434 |
55
+ | 0.0933 | 0.1550 | 100 | 0.0820 |
56
+ | 0.0662 | 0.2326 | 150 | 0.0668 |
57
+ | 0.0584 | 0.3101 | 200 | 0.0589 |
58
+ | 0.0666 | 0.3876 | 250 | 0.0527 |
59
+ | 0.0448 | 0.4651 | 300 | 0.0521 |
60
+ | 0.0474 | 0.5426 | 350 | 0.0490 |
61
+ | 0.0546 | 0.6202 | 400 | 0.0431 |
62
+ | 0.0432 | 0.6977 | 450 | 0.0393 |
63
+ | 0.0526 | 0.7752 | 500 | 0.0401 |
64
+ | 0.0506 | 0.8527 | 550 | 0.0400 |
65
+ | 0.0622 | 0.9302 | 600 | 0.0419 |
66
+ | 0.0363 | 1.0078 | 650 | 0.0380 |
67
+ | 0.032 | 1.0853 | 700 | 0.0377 |
68
+ | 0.0361 | 1.1628 | 750 | 0.0435 |
69
+ | 0.0256 | 1.2403 | 800 | 0.0365 |
70
+ | 0.0361 | 1.3178 | 850 | 0.0357 |
71
+ | 0.0428 | 1.3953 | 900 | 0.0369 |
72
+ | 0.0423 | 1.4729 | 950 | 0.0367 |
73
+ | 0.0298 | 1.5504 | 1000 | 0.0382 |
74
+ | 0.0357 | 1.6279 | 1050 | 0.0366 |
75
+ | 0.0271 | 1.7054 | 1100 | 0.0375 |
76
+ | 0.0325 | 1.7829 | 1150 | 0.0370 |
77
+ | 0.0328 | 1.8605 | 1200 | 0.0346 |
78
+ | 0.0373 | 1.9380 | 1250 | 0.0346 |
79
+ | 0.0219 | 2.0155 | 1300 | 0.0351 |
80
+ | 0.0179 | 2.0930 | 1350 | 0.0380 |
81
+ | 0.018 | 2.1705 | 1400 | 0.0398 |
82
+ | 0.0203 | 2.2481 | 1450 | 0.0382 |
83
+ | 0.0257 | 2.3256 | 1500 | 0.0405 |
84
+ | 0.0165 | 2.4031 | 1550 | 0.0382 |
85
+ | 0.0212 | 2.4806 | 1600 | 0.0375 |
86
+ | 0.0315 | 2.5581 | 1650 | 0.0373 |
87
+ | 0.0155 | 2.6357 | 1700 | 0.0379 |
88
+ | 0.0188 | 2.7132 | 1750 | 0.0379 |
89
+ | 0.0195 | 2.7907 | 1800 | 0.0397 |
90
+ | 0.0213 | 2.8682 | 1850 | 0.0373 |
91
+ | 0.0171 | 2.9457 | 1900 | 0.0374 |
92
+ | 0.0108 | 3.0233 | 1950 | 0.0390 |
93
+ | 0.0125 | 3.1008 | 2000 | 0.0437 |
94
+ | 0.0046 | 3.1783 | 2050 | 0.0459 |
95
+ | 0.0059 | 3.2558 | 2100 | 0.0479 |
96
+ | 0.0088 | 3.3333 | 2150 | 0.0432 |
97
+ | 0.0074 | 3.4109 | 2200 | 0.0455 |
98
+ | 0.0105 | 3.4884 | 2250 | 0.0493 |
99
+ | 0.0116 | 3.5659 | 2300 | 0.0510 |
100
+ | 0.01 | 3.6434 | 2350 | 0.0481 |
101
+ | 0.0126 | 3.7209 | 2400 | 0.0474 |
102
+ | 0.0061 | 3.7984 | 2450 | 0.0477 |
103
+ | 0.0088 | 3.8760 | 2500 | 0.0487 |
104
+ | 0.0074 | 3.9535 | 2550 | 0.0488 |
105
+ | 0.0076 | 4.0310 | 2600 | 0.0499 |
106
+ | 0.0051 | 4.1085 | 2650 | 0.0524 |
107
+ | 0.0038 | 4.1860 | 2700 | 0.0556 |
108
+ | 0.0031 | 4.2636 | 2750 | 0.0584 |
109
+ | 0.0028 | 4.3411 | 2800 | 0.0602 |
110
+ | 0.0037 | 4.4186 | 2850 | 0.0612 |
111
+ | 0.0037 | 4.4961 | 2900 | 0.0620 |
112
+ | 0.0013 | 4.5736 | 2950 | 0.0626 |
113
+ | 0.0013 | 4.6512 | 3000 | 0.0631 |
114
+ | 0.0023 | 4.7287 | 3050 | 0.0634 |
115
+ | 0.0042 | 4.8062 | 3100 | 0.0635 |
116
+ | 0.0053 | 4.8837 | 3150 | 0.0635 |
117
+ | 0.0041 | 4.9612 | 3200 | 0.0634 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - PEFT 0.12.0
123
+ - Transformers 4.46.1
124
+ - Pytorch 2.5.1+cu124
125
+ - Datasets 3.1.0
126
+ - Tokenizers 0.20.3
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21a3cb6b418bef0078d6b052cc840002312caf855607d9d0d2fa20e7a6e37b07
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dfc475a5b056f7a5bbf045106ace3314c40f7430844f44a817ade5d24925646
3
  size 83945296