Hugging Face's logo

chchen
/
Llama3-OpenBioLLM-8B-PsyCourse-fold5

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
chchen commited on
Commit
01adbdc
·
verified ·
1 Parent(s): afbf3e4

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-fold5
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-fold5
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: 0.0529
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
+ | 0.5262 | 0.0758 | 50 | 0.3222 |
55
+ | 0.0888 | 0.1517 | 100 | 0.0871 |
56
+ | 0.0821 | 0.2275 | 150 | 0.0828 |
57
+ | 0.0718 | 0.3033 | 200 | 0.0627 |
58
+ | 0.0622 | 0.3791 | 250 | 0.0543 |
59
+ | 0.0509 | 0.4550 | 300 | 0.0504 |
60
+ | 0.0576 | 0.5308 | 350 | 0.0506 |
61
+ | 0.066 | 0.6066 | 400 | 0.0472 |
62
+ | 0.0593 | 0.6825 | 450 | 0.0450 |
63
+ | 0.0316 | 0.7583 | 500 | 0.0445 |
64
+ | 0.0318 | 0.8341 | 550 | 0.0472 |
65
+ | 0.0436 | 0.9100 | 600 | 0.0449 |
66
+ | 0.0454 | 0.9858 | 650 | 0.0416 |
67
+ | 0.0339 | 1.0616 | 700 | 0.0424 |
68
+ | 0.0369 | 1.1374 | 750 | 0.0448 |
69
+ | 0.034 | 1.2133 | 800 | 0.0374 |
70
+ | 0.0332 | 1.2891 | 850 | 0.0419 |
71
+ | 0.029 | 1.3649 | 900 | 0.0428 |
72
+ | 0.031 | 1.4408 | 950 | 0.0432 |
73
+ | 0.0353 | 1.5166 | 1000 | 0.0388 |
74
+ | 0.0278 | 1.5924 | 1050 | 0.0380 |
75
+ | 0.0261 | 1.6682 | 1100 | 0.0366 |
76
+ | 0.0294 | 1.7441 | 1150 | 0.0390 |
77
+ | 0.0337 | 1.8199 | 1200 | 0.0366 |
78
+ | 0.0359 | 1.8957 | 1250 | 0.0350 |
79
+ | 0.0358 | 1.9716 | 1300 | 0.0363 |
80
+ | 0.0233 | 2.0474 | 1350 | 0.0363 |
81
+ | 0.0157 | 2.1232 | 1400 | 0.0363 |
82
+ | 0.0227 | 2.1991 | 1450 | 0.0357 |
83
+ | 0.018 | 2.2749 | 1500 | 0.0389 |
84
+ | 0.0237 | 2.3507 | 1550 | 0.0354 |
85
+ | 0.025 | 2.4265 | 1600 | 0.0365 |
86
+ | 0.015 | 2.5024 | 1650 | 0.0392 |
87
+ | 0.0265 | 2.5782 | 1700 | 0.0360 |
88
+ | 0.0181 | 2.6540 | 1750 | 0.0368 |
89
+ | 0.0228 | 2.7299 | 1800 | 0.0380 |
90
+ | 0.0224 | 2.8057 | 1850 | 0.0366 |
91
+ | 0.0162 | 2.8815 | 1900 | 0.0356 |
92
+ | 0.0284 | 2.9573 | 1950 | 0.0349 |
93
+ | 0.0069 | 3.0332 | 2000 | 0.0351 |
94
+ | 0.0065 | 3.1090 | 2050 | 0.0394 |
95
+ | 0.0069 | 3.1848 | 2100 | 0.0438 |
96
+ | 0.006 | 3.2607 | 2150 | 0.0446 |
97
+ | 0.0088 | 3.3365 | 2200 | 0.0436 |
98
+ | 0.0056 | 3.4123 | 2250 | 0.0424 |
99
+ | 0.0086 | 3.4882 | 2300 | 0.0445 |
100
+ | 0.0058 | 3.5640 | 2350 | 0.0438 |
101
+ | 0.0092 | 3.6398 | 2400 | 0.0426 |
102
+ | 0.0082 | 3.7156 | 2450 | 0.0433 |
103
+ | 0.01 | 3.7915 | 2500 | 0.0422 |
104
+ | 0.0082 | 3.8673 | 2550 | 0.0426 |
105
+ | 0.012 | 3.9431 | 2600 | 0.0433 |
106
+ | 0.0054 | 4.0190 | 2650 | 0.0437 |
107
+ | 0.0037 | 4.0948 | 2700 | 0.0452 |
108
+ | 0.0049 | 4.1706 | 2750 | 0.0474 |
109
+ | 0.0024 | 4.2464 | 2800 | 0.0492 |
110
+ | 0.0023 | 4.3223 | 2850 | 0.0507 |
111
+ | 0.0048 | 4.3981 | 2900 | 0.0512 |
112
+ | 0.0073 | 4.4739 | 2950 | 0.0514 |
113
+ | 0.0014 | 4.5498 | 3000 | 0.0518 |
114
+ | 0.0021 | 4.6256 | 3050 | 0.0521 |
115
+ | 0.0043 | 4.7014 | 3100 | 0.0525 |
116
+ | 0.005 | 4.7773 | 3150 | 0.0528 |
117
+ | 0.0021 | 4.8531 | 3200 | 0.0531 |
118
+ | 0.0032 | 4.9289 | 3250 | 0.0529 |
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:bca98eac139bc90afd54c38c6d316d3528c10a6f6b9ed549e01e2fbe5ed4bd14
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87673953311e436802cd790ee71b1c03ccb3c337d6c68642553c82469a10028f
3
  size 83945296