Hugging Face's logo

chchen
/
Llama3-OpenBioLLM-8B-PsyCourse-fold3

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
Community
chchen commited on
Commit
1babdea
·
verified ·
1 Parent(s): 73411c7

Model save

Browse files
Files changed (2) hide show
  1. README.md +128 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-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
+ # Llama3-OpenBioLLM-8B-PsyCourse-fold3
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: 0.0526
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
+ | 0.4566 | 0.0753 | 50 | 0.3151 |
55
+ | 0.1039 | 0.1505 | 100 | 0.0934 |
56
+ | 0.0879 | 0.2258 | 150 | 0.0729 |
57
+ | 0.0684 | 0.3011 | 200 | 0.0644 |
58
+ | 0.0696 | 0.3763 | 250 | 0.0604 |
59
+ | 0.064 | 0.4516 | 300 | 0.0538 |
60
+ | 0.048 | 0.5269 | 350 | 0.0553 |
61
+ | 0.0568 | 0.6021 | 400 | 0.0504 |
62
+ | 0.0548 | 0.6774 | 450 | 0.0462 |
63
+ | 0.0387 | 0.7527 | 500 | 0.0457 |
64
+ | 0.0454 | 0.8279 | 550 | 0.0439 |
65
+ | 0.0343 | 0.9032 | 600 | 0.0421 |
66
+ | 0.0363 | 0.9785 | 650 | 0.0402 |
67
+ | 0.0272 | 1.0537 | 700 | 0.0415 |
68
+ | 0.0324 | 1.1290 | 750 | 0.0384 |
69
+ | 0.0394 | 1.2043 | 800 | 0.0429 |
70
+ | 0.0297 | 1.2795 | 850 | 0.0411 |
71
+ | 0.0423 | 1.3548 | 900 | 0.0396 |
72
+ | 0.0324 | 1.4300 | 950 | 0.0372 |
73
+ | 0.0311 | 1.5053 | 1000 | 0.0395 |
74
+ | 0.0309 | 1.5806 | 1050 | 0.0407 |
75
+ | 0.0233 | 1.6558 | 1100 | 0.0377 |
76
+ | 0.0455 | 1.7311 | 1150 | 0.0354 |
77
+ | 0.0329 | 1.8064 | 1200 | 0.0364 |
78
+ | 0.0352 | 1.8816 | 1250 | 0.0351 |
79
+ | 0.029 | 1.9569 | 1300 | 0.0350 |
80
+ | 0.0187 | 2.0322 | 1350 | 0.0363 |
81
+ | 0.025 | 2.1074 | 1400 | 0.0380 |
82
+ | 0.0209 | 2.1827 | 1450 | 0.0377 |
83
+ | 0.0224 | 2.2580 | 1500 | 0.0407 |
84
+ | 0.0261 | 2.3332 | 1550 | 0.0393 |
85
+ | 0.0156 | 2.4085 | 1600 | 0.0387 |
86
+ | 0.0173 | 2.4838 | 1650 | 0.0388 |
87
+ | 0.0228 | 2.5590 | 1700 | 0.0367 |
88
+ | 0.0328 | 2.6343 | 1750 | 0.0371 |
89
+ | 0.0264 | 2.7096 | 1800 | 0.0393 |
90
+ | 0.0235 | 2.7848 | 1850 | 0.0364 |
91
+ | 0.0204 | 2.8601 | 1900 | 0.0386 |
92
+ | 0.0207 | 2.9354 | 1950 | 0.0372 |
93
+ | 0.01 | 3.0106 | 2000 | 0.0390 |
94
+ | 0.0103 | 3.0859 | 2050 | 0.0431 |
95
+ | 0.0096 | 3.1612 | 2100 | 0.0418 |
96
+ | 0.012 | 3.2364 | 2150 | 0.0431 |
97
+ | 0.0098 | 3.3117 | 2200 | 0.0443 |
98
+ | 0.0104 | 3.3870 | 2250 | 0.0466 |
99
+ | 0.0061 | 3.4622 | 2300 | 0.0481 |
100
+ | 0.0051 | 3.5375 | 2350 | 0.0463 |
101
+ | 0.0085 | 3.6128 | 2400 | 0.0458 |
102
+ | 0.0093 | 3.6880 | 2450 | 0.0467 |
103
+ | 0.0103 | 3.7633 | 2500 | 0.0477 |
104
+ | 0.0066 | 3.8386 | 2550 | 0.0487 |
105
+ | 0.0101 | 3.9138 | 2600 | 0.0477 |
106
+ | 0.0104 | 3.9891 | 2650 | 0.0455 |
107
+ | 0.0073 | 4.0644 | 2700 | 0.0460 |
108
+ | 0.003 | 4.1396 | 2750 | 0.0478 |
109
+ | 0.0025 | 4.2149 | 2800 | 0.0498 |
110
+ | 0.0051 | 4.2901 | 2850 | 0.0506 |
111
+ | 0.0078 | 4.3654 | 2900 | 0.0516 |
112
+ | 0.0019 | 4.4407 | 2950 | 0.0518 |
113
+ | 0.0029 | 4.5159 | 3000 | 0.0521 |
114
+ | 0.0048 | 4.5912 | 3050 | 0.0521 |
115
+ | 0.0033 | 4.6665 | 3100 | 0.0525 |
116
+ | 0.002 | 4.7417 | 3150 | 0.0525 |
117
+ | 0.0017 | 4.8170 | 3200 | 0.0528 |
118
+ | 0.003 | 4.8923 | 3250 | 0.0529 |
119
+ | 0.0021 | 4.9675 | 3300 | 0.0526 |
120
+
121
+
122
+ ### Framework versions
123
+
124
+ - PEFT 0.12.0
125
+ - Transformers 4.46.1
126
+ - Pytorch 2.5.1+cu124
127
+ - Datasets 3.1.0
128
+ - Tokenizers 0.20.3
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ce81b10cf33734ae3283e8099f58d4d7260f97c50198bb80989d2ccfb96b8af
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cd46b029b903e5b3e1fddaa3f26469b8f9fb5f6513e340033bc9f9c432ec4c7
3
  size 83945296