Hugging Face's logo

chchen
/
Llama3-OpenBioLLM-8B-PsyCourse-fold4

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
chchen commited on
Commit
d028943
·
verified ·
1 Parent(s): 9e3b4ef

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-fold4
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-fold4
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: 0.0588
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
+ | 0.4799 | 0.0763 | 50 | 0.2933 |
55
+ | 0.1053 | 0.1527 | 100 | 0.0766 |
56
+ | 0.0594 | 0.2290 | 150 | 0.0722 |
57
+ | 0.0586 | 0.3053 | 200 | 0.0537 |
58
+ | 0.066 | 0.3816 | 250 | 0.0550 |
59
+ | 0.0553 | 0.4580 | 300 | 0.0551 |
60
+ | 0.0468 | 0.5343 | 350 | 0.0476 |
61
+ | 0.0515 | 0.6106 | 400 | 0.0481 |
62
+ | 0.0562 | 0.6870 | 450 | 0.0466 |
63
+ | 0.0347 | 0.7633 | 500 | 0.0401 |
64
+ | 0.0417 | 0.8396 | 550 | 0.0408 |
65
+ | 0.0466 | 0.9159 | 600 | 0.0393 |
66
+ | 0.0346 | 0.9923 | 650 | 0.0404 |
67
+ | 0.035 | 1.0686 | 700 | 0.0389 |
68
+ | 0.0408 | 1.1449 | 750 | 0.0390 |
69
+ | 0.0324 | 1.2213 | 800 | 0.0427 |
70
+ | 0.0331 | 1.2976 | 850 | 0.0382 |
71
+ | 0.0335 | 1.3739 | 900 | 0.0433 |
72
+ | 0.034 | 1.4502 | 950 | 0.0374 |
73
+ | 0.0253 | 1.5266 | 1000 | 0.0399 |
74
+ | 0.0299 | 1.6029 | 1050 | 0.0382 |
75
+ | 0.0534 | 1.6792 | 1100 | 0.0424 |
76
+ | 0.0318 | 1.7556 | 1150 | 0.0402 |
77
+ | 0.0484 | 1.8319 | 1200 | 0.0385 |
78
+ | 0.0263 | 1.9082 | 1250 | 0.0355 |
79
+ | 0.0329 | 1.9845 | 1300 | 0.0349 |
80
+ | 0.0171 | 2.0609 | 1350 | 0.0365 |
81
+ | 0.0204 | 2.1372 | 1400 | 0.0374 |
82
+ | 0.0248 | 2.2135 | 1450 | 0.0413 |
83
+ | 0.0132 | 2.2899 | 1500 | 0.0397 |
84
+ | 0.0152 | 2.3662 | 1550 | 0.0383 |
85
+ | 0.0222 | 2.4425 | 1600 | 0.0387 |
86
+ | 0.0187 | 2.5188 | 1650 | 0.0374 |
87
+ | 0.0177 | 2.5952 | 1700 | 0.0415 |
88
+ | 0.0164 | 2.6715 | 1750 | 0.0380 |
89
+ | 0.0212 | 2.7478 | 1800 | 0.0395 |
90
+ | 0.0248 | 2.8242 | 1850 | 0.0357 |
91
+ | 0.0187 | 2.9005 | 1900 | 0.0384 |
92
+ | 0.0315 | 2.9768 | 1950 | 0.0372 |
93
+ | 0.006 | 3.0531 | 2000 | 0.0423 |
94
+ | 0.0077 | 3.1295 | 2050 | 0.0459 |
95
+ | 0.0073 | 3.2058 | 2100 | 0.0493 |
96
+ | 0.0096 | 3.2821 | 2150 | 0.0523 |
97
+ | 0.0086 | 3.3585 | 2200 | 0.0449 |
98
+ | 0.0057 | 3.4348 | 2250 | 0.0469 |
99
+ | 0.0098 | 3.5111 | 2300 | 0.0460 |
100
+ | 0.0086 | 3.5874 | 2350 | 0.0493 |
101
+ | 0.0073 | 3.6638 | 2400 | 0.0471 |
102
+ | 0.0086 | 3.7401 | 2450 | 0.0468 |
103
+ | 0.0079 | 3.8164 | 2500 | 0.0455 |
104
+ | 0.0042 | 3.8928 | 2550 | 0.0473 |
105
+ | 0.0088 | 3.9691 | 2600 | 0.0474 |
106
+ | 0.004 | 4.0454 | 2650 | 0.0474 |
107
+ | 0.0033 | 4.1217 | 2700 | 0.0500 |
108
+ | 0.0009 | 4.1981 | 2750 | 0.0520 |
109
+ | 0.0021 | 4.2744 | 2800 | 0.0532 |
110
+ | 0.0042 | 4.3507 | 2850 | 0.0546 |
111
+ | 0.0017 | 4.4271 | 2900 | 0.0566 |
112
+ | 0.002 | 4.5034 | 2950 | 0.0577 |
113
+ | 0.0021 | 4.5797 | 3000 | 0.0583 |
114
+ | 0.0017 | 4.6560 | 3050 | 0.0585 |
115
+ | 0.0036 | 4.7324 | 3100 | 0.0587 |
116
+ | 0.0021 | 4.8087 | 3150 | 0.0588 |
117
+ | 0.0028 | 4.8850 | 3200 | 0.0588 |
118
+ | 0.0021 | 4.9614 | 3250 | 0.0588 |
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:f0b2b47d0df35a43696c9315bcc8099a3cbc51f4ce9a16baeb9a15a9372d0834
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e99528d974fd7bae53ed48f552d6d32c12fb0a1d8d106a3d3d25eeeb0b6edc6
3
  size 83945296