Hugging Face's logo

chchen
/
Llama3-OpenBioLLM-8B-PsyCourse-fold1

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
chchen commited on
Commit
70c7bf7
·
verified ·
1 Parent(s): 4159e8a

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-fold1
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-fold1
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: 0.0575
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
+ | 0.4401 | 0.0770 | 50 | 0.3166 |
55
+ | 0.1222 | 0.1539 | 100 | 0.0882 |
56
+ | 0.0887 | 0.2309 | 150 | 0.0669 |
57
+ | 0.0749 | 0.3078 | 200 | 0.0571 |
58
+ | 0.0607 | 0.3848 | 250 | 0.0536 |
59
+ | 0.0595 | 0.4617 | 300 | 0.0538 |
60
+ | 0.0569 | 0.5387 | 350 | 0.0479 |
61
+ | 0.0692 | 0.6156 | 400 | 0.0517 |
62
+ | 0.0384 | 0.6926 | 450 | 0.0476 |
63
+ | 0.0339 | 0.7695 | 500 | 0.0445 |
64
+ | 0.0515 | 0.8465 | 550 | 0.0412 |
65
+ | 0.0423 | 0.9234 | 600 | 0.0403 |
66
+ | 0.031 | 1.0004 | 650 | 0.0412 |
67
+ | 0.0415 | 1.0773 | 700 | 0.0405 |
68
+ | 0.0308 | 1.1543 | 750 | 0.0384 |
69
+ | 0.0306 | 1.2312 | 800 | 0.0376 |
70
+ | 0.0376 | 1.3082 | 850 | 0.0391 |
71
+ | 0.024 | 1.3851 | 900 | 0.0384 |
72
+ | 0.0406 | 1.4621 | 950 | 0.0392 |
73
+ | 0.0398 | 1.5391 | 1000 | 0.0376 |
74
+ | 0.0325 | 1.6160 | 1050 | 0.0356 |
75
+ | 0.0396 | 1.6930 | 1100 | 0.0394 |
76
+ | 0.0266 | 1.7699 | 1150 | 0.0388 |
77
+ | 0.023 | 1.8469 | 1200 | 0.0392 |
78
+ | 0.0315 | 1.9238 | 1250 | 0.0389 |
79
+ | 0.0238 | 2.0008 | 1300 | 0.0342 |
80
+ | 0.0189 | 2.0777 | 1350 | 0.0361 |
81
+ | 0.0293 | 2.1547 | 1400 | 0.0367 |
82
+ | 0.0128 | 2.2316 | 1450 | 0.0420 |
83
+ | 0.0195 | 2.3086 | 1500 | 0.0385 |
84
+ | 0.0174 | 2.3855 | 1550 | 0.0383 |
85
+ | 0.0143 | 2.4625 | 1600 | 0.0415 |
86
+ | 0.0249 | 2.5394 | 1650 | 0.0404 |
87
+ | 0.0195 | 2.6164 | 1700 | 0.0383 |
88
+ | 0.0266 | 2.6933 | 1750 | 0.0376 |
89
+ | 0.0216 | 2.7703 | 1800 | 0.0365 |
90
+ | 0.0236 | 2.8472 | 1850 | 0.0366 |
91
+ | 0.0198 | 2.9242 | 1900 | 0.0369 |
92
+ | 0.0311 | 3.0012 | 1950 | 0.0370 |
93
+ | 0.0088 | 3.0781 | 2000 | 0.0424 |
94
+ | 0.0126 | 3.1551 | 2050 | 0.0467 |
95
+ | 0.0085 | 3.2320 | 2100 | 0.0463 |
96
+ | 0.0083 | 3.3090 | 2150 | 0.0453 |
97
+ | 0.0164 | 3.3859 | 2200 | 0.0470 |
98
+ | 0.0115 | 3.4629 | 2250 | 0.0465 |
99
+ | 0.0134 | 3.5398 | 2300 | 0.0469 |
100
+ | 0.0052 | 3.6168 | 2350 | 0.0470 |
101
+ | 0.0104 | 3.6937 | 2400 | 0.0448 |
102
+ | 0.0075 | 3.7707 | 2450 | 0.0459 |
103
+ | 0.0068 | 3.8476 | 2500 | 0.0485 |
104
+ | 0.0089 | 3.9246 | 2550 | 0.0494 |
105
+ | 0.0091 | 4.0015 | 2600 | 0.0476 |
106
+ | 0.0021 | 4.0785 | 2650 | 0.0498 |
107
+ | 0.0061 | 4.1554 | 2700 | 0.0529 |
108
+ | 0.0011 | 4.2324 | 2750 | 0.0541 |
109
+ | 0.0025 | 4.3093 | 2800 | 0.0549 |
110
+ | 0.0029 | 4.3863 | 2850 | 0.0560 |
111
+ | 0.0027 | 4.4633 | 2900 | 0.0570 |
112
+ | 0.0017 | 4.5402 | 2950 | 0.0572 |
113
+ | 0.0019 | 4.6172 | 3000 | 0.0574 |
114
+ | 0.005 | 4.6941 | 3050 | 0.0575 |
115
+ | 0.0033 | 4.7711 | 3100 | 0.0573 |
116
+ | 0.005 | 4.8480 | 3150 | 0.0576 |
117
+ | 0.0019 | 4.9250 | 3200 | 0.0575 |
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 sha256:14b86af4dc77f058297c8ed5072595a0c40069798ad2531ce967ddd534eba54f
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c9a9b100c252dea1f5124403223947b0829289a3dde85b2d321312410a88fb6
3
  size 83945296