Hugging Face's logo

chchen
/
Llama3-OpenBioLLM-8B-PsyCourse-fold10

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
chchen commited on
Commit
4acd7b8
·
verified ·
1 Parent(s): d419d9d

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-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
+ # Llama3-OpenBioLLM-8B-PsyCourse-fold10
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: 0.0568
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
+ | 0.5221 | 0.0770 | 50 | 0.3092 |
55
+ | 0.0971 | 0.1539 | 100 | 0.0860 |
56
+ | 0.0873 | 0.2309 | 150 | 0.0607 |
57
+ | 0.0616 | 0.3078 | 200 | 0.0565 |
58
+ | 0.071 | 0.3848 | 250 | 0.0542 |
59
+ | 0.0615 | 0.4618 | 300 | 0.0497 |
60
+ | 0.0538 | 0.5387 | 350 | 0.0468 |
61
+ | 0.0532 | 0.6157 | 400 | 0.0462 |
62
+ | 0.0501 | 0.6926 | 450 | 0.0482 |
63
+ | 0.0575 | 0.7696 | 500 | 0.0422 |
64
+ | 0.0418 | 0.8466 | 550 | 0.0440 |
65
+ | 0.048 | 0.9235 | 600 | 0.0398 |
66
+ | 0.0559 | 1.0005 | 650 | 0.0397 |
67
+ | 0.0358 | 1.0774 | 700 | 0.0431 |
68
+ | 0.0277 | 1.1544 | 750 | 0.0392 |
69
+ | 0.029 | 1.2314 | 800 | 0.0376 |
70
+ | 0.0283 | 1.3083 | 850 | 0.0383 |
71
+ | 0.035 | 1.3853 | 900 | 0.0371 |
72
+ | 0.0367 | 1.4622 | 950 | 0.0373 |
73
+ | 0.0272 | 1.5392 | 1000 | 0.0428 |
74
+ | 0.0435 | 1.6162 | 1050 | 0.0367 |
75
+ | 0.0379 | 1.6931 | 1100 | 0.0368 |
76
+ | 0.0296 | 1.7701 | 1150 | 0.0378 |
77
+ | 0.0423 | 1.8470 | 1200 | 0.0377 |
78
+ | 0.0389 | 1.9240 | 1250 | 0.0347 |
79
+ | 0.0349 | 2.0010 | 1300 | 0.0378 |
80
+ | 0.0191 | 2.0779 | 1350 | 0.0376 |
81
+ | 0.0252 | 2.1549 | 1400 | 0.0371 |
82
+ | 0.016 | 2.2318 | 1450 | 0.0381 |
83
+ | 0.0211 | 2.3088 | 1500 | 0.0362 |
84
+ | 0.0223 | 2.3858 | 1550 | 0.0355 |
85
+ | 0.0227 | 2.4627 | 1600 | 0.0385 |
86
+ | 0.0268 | 2.5397 | 1650 | 0.0354 |
87
+ | 0.0267 | 2.6166 | 1700 | 0.0349 |
88
+ | 0.0158 | 2.6936 | 1750 | 0.0352 |
89
+ | 0.0186 | 2.7706 | 1800 | 0.0384 |
90
+ | 0.0155 | 2.8475 | 1850 | 0.0401 |
91
+ | 0.0158 | 2.9245 | 1900 | 0.0365 |
92
+ | 0.0185 | 3.0014 | 1950 | 0.0362 |
93
+ | 0.0103 | 3.0784 | 2000 | 0.0401 |
94
+ | 0.0111 | 3.1554 | 2050 | 0.0402 |
95
+ | 0.0105 | 3.2323 | 2100 | 0.0448 |
96
+ | 0.0077 | 3.3093 | 2150 | 0.0435 |
97
+ | 0.0078 | 3.3862 | 2200 | 0.0476 |
98
+ | 0.0072 | 3.4632 | 2250 | 0.0457 |
99
+ | 0.0118 | 3.5402 | 2300 | 0.0452 |
100
+ | 0.0107 | 3.6171 | 2350 | 0.0448 |
101
+ | 0.01 | 3.6941 | 2400 | 0.0478 |
102
+ | 0.0092 | 3.7710 | 2450 | 0.0471 |
103
+ | 0.0166 | 3.8480 | 2500 | 0.0437 |
104
+ | 0.0048 | 3.9250 | 2550 | 0.0444 |
105
+ | 0.0057 | 4.0019 | 2600 | 0.0454 |
106
+ | 0.0033 | 4.0789 | 2650 | 0.0484 |
107
+ | 0.0032 | 4.1558 | 2700 | 0.0500 |
108
+ | 0.005 | 4.2328 | 2750 | 0.0527 |
109
+ | 0.004 | 4.3098 | 2800 | 0.0546 |
110
+ | 0.0034 | 4.3867 | 2850 | 0.0554 |
111
+ | 0.0023 | 4.4637 | 2900 | 0.0560 |
112
+ | 0.0027 | 4.5406 | 2950 | 0.0564 |
113
+ | 0.0025 | 4.6176 | 3000 | 0.0563 |
114
+ | 0.0054 | 4.6946 | 3050 | 0.0568 |
115
+ | 0.0016 | 4.7715 | 3100 | 0.0569 |
116
+ | 0.0024 | 4.8485 | 3150 | 0.0567 |
117
+ | 0.0018 | 4.9254 | 3200 | 0.0568 |
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 sha256:31846d4c66ead5c2cd4ff85f8a02f697ad2b9ed9caf866f3cfa8f387a478cf11
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1fd319837ad8036f8679b9f176ce9238f297b7f0492580a24a1e3c4072dced4
3
  size 83945296