Hugging Face's logo

chchen
/
Llama3-OpenBioLLM-8B-PsyCourse-fold8

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
Community
chchen commited on
Commit
f7f35b4
·
verified ·
1 Parent(s): 9a5be29

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-fold8
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-fold8
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: 0.0636
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
+ | 0.5651 | 0.0758 | 50 | 0.3454 |
55
+ | 0.159 | 0.1516 | 100 | 0.0916 |
56
+ | 0.0775 | 0.2275 | 150 | 0.0660 |
57
+ | 0.0565 | 0.3033 | 200 | 0.0587 |
58
+ | 0.0563 | 0.3791 | 250 | 0.0594 |
59
+ | 0.0631 | 0.4549 | 300 | 0.0575 |
60
+ | 0.0677 | 0.5308 | 350 | 0.0503 |
61
+ | 0.0366 | 0.6066 | 400 | 0.0471 |
62
+ | 0.0397 | 0.6824 | 450 | 0.0430 |
63
+ | 0.0383 | 0.7582 | 500 | 0.0479 |
64
+ | 0.0508 | 0.8340 | 550 | 0.0427 |
65
+ | 0.0346 | 0.9099 | 600 | 0.0434 |
66
+ | 0.0513 | 0.9857 | 650 | 0.0444 |
67
+ | 0.0339 | 1.0615 | 700 | 0.0417 |
68
+ | 0.0296 | 1.1373 | 750 | 0.0442 |
69
+ | 0.0288 | 1.2132 | 800 | 0.0397 |
70
+ | 0.0299 | 1.2890 | 850 | 0.0421 |
71
+ | 0.0293 | 1.3648 | 900 | 0.0401 |
72
+ | 0.0278 | 1.4406 | 950 | 0.0393 |
73
+ | 0.0283 | 1.5164 | 1000 | 0.0405 |
74
+ | 0.0493 | 1.5923 | 1050 | 0.0393 |
75
+ | 0.0287 | 1.6681 | 1100 | 0.0392 |
76
+ | 0.0383 | 1.7439 | 1150 | 0.0379 |
77
+ | 0.0312 | 1.8197 | 1200 | 0.0378 |
78
+ | 0.0353 | 1.8956 | 1250 | 0.0379 |
79
+ | 0.0242 | 1.9714 | 1300 | 0.0360 |
80
+ | 0.0176 | 2.0472 | 1350 | 0.0413 |
81
+ | 0.0132 | 2.1230 | 1400 | 0.0386 |
82
+ | 0.0224 | 2.1988 | 1450 | 0.0413 |
83
+ | 0.0198 | 2.2747 | 1500 | 0.0423 |
84
+ | 0.0191 | 2.3505 | 1550 | 0.0429 |
85
+ | 0.017 | 2.4263 | 1600 | 0.0412 |
86
+ | 0.0194 | 2.5021 | 1650 | 0.0465 |
87
+ | 0.0178 | 2.5780 | 1700 | 0.0439 |
88
+ | 0.0238 | 2.6538 | 1750 | 0.0411 |
89
+ | 0.0181 | 2.7296 | 1800 | 0.0414 |
90
+ | 0.0128 | 2.8054 | 1850 | 0.0439 |
91
+ | 0.0287 | 2.8812 | 1900 | 0.0410 |
92
+ | 0.0202 | 2.9571 | 1950 | 0.0418 |
93
+ | 0.011 | 3.0329 | 2000 | 0.0430 |
94
+ | 0.005 | 3.1087 | 2050 | 0.0487 |
95
+ | 0.0045 | 3.1845 | 2100 | 0.0502 |
96
+ | 0.0072 | 3.2604 | 2150 | 0.0496 |
97
+ | 0.0098 | 3.3362 | 2200 | 0.0482 |
98
+ | 0.0089 | 3.4120 | 2250 | 0.0492 |
99
+ | 0.0072 | 3.4878 | 2300 | 0.0486 |
100
+ | 0.0116 | 3.5636 | 2350 | 0.0496 |
101
+ | 0.0094 | 3.6395 | 2400 | 0.0489 |
102
+ | 0.0055 | 3.7153 | 2450 | 0.0501 |
103
+ | 0.0095 | 3.7911 | 2500 | 0.0529 |
104
+ | 0.0113 | 3.8669 | 2550 | 0.0517 |
105
+ | 0.0042 | 3.9428 | 2600 | 0.0518 |
106
+ | 0.0021 | 4.0186 | 2650 | 0.0539 |
107
+ | 0.0027 | 4.0944 | 2700 | 0.0573 |
108
+ | 0.0017 | 4.1702 | 2750 | 0.0590 |
109
+ | 0.0033 | 4.2460 | 2800 | 0.0603 |
110
+ | 0.003 | 4.3219 | 2850 | 0.0618 |
111
+ | 0.0013 | 4.3977 | 2900 | 0.0623 |
112
+ | 0.003 | 4.4735 | 2950 | 0.0625 |
113
+ | 0.0036 | 4.5493 | 3000 | 0.0631 |
114
+ | 0.0017 | 4.6252 | 3050 | 0.0634 |
115
+ | 0.0023 | 4.7010 | 3100 | 0.0635 |
116
+ | 0.0028 | 4.7768 | 3150 | 0.0635 |
117
+ | 0.0028 | 4.8526 | 3200 | 0.0637 |
118
+ | 0.0021 | 4.9284 | 3250 | 0.0636 |
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 sha256:14ec407b9210b2ee2ae88769c0ec6952a847218c2a9b35658f16d948db773f56
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97547215cc004c25ec93cfa68744e9ed1354d5e547734ba986df331908ea9cdc
3
  size 83945296