Hugging Face's logo

chchen
/
Llama3-OpenBioLLM-8B-PsyCourse-fold9

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
Community
chchen commited on
Commit
0692129
·
verified ·
1 Parent(s): f4ca09f

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-fold9
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-fold9
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: 0.0618
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
+ | 0.5046 | 0.0768 | 50 | 0.3063 |
55
+ | 0.1059 | 0.1535 | 100 | 0.0842 |
56
+ | 0.0783 | 0.2303 | 150 | 0.0695 |
57
+ | 0.0635 | 0.3070 | 200 | 0.0595 |
58
+ | 0.075 | 0.3838 | 250 | 0.0530 |
59
+ | 0.065 | 0.4606 | 300 | 0.0491 |
60
+ | 0.0474 | 0.5373 | 350 | 0.0478 |
61
+ | 0.0461 | 0.6141 | 400 | 0.0493 |
62
+ | 0.0533 | 0.6908 | 450 | 0.0540 |
63
+ | 0.048 | 0.7676 | 500 | 0.0457 |
64
+ | 0.0694 | 0.8444 | 550 | 0.0475 |
65
+ | 0.0396 | 0.9211 | 600 | 0.0416 |
66
+ | 0.0412 | 0.9979 | 650 | 0.0386 |
67
+ | 0.0339 | 1.0746 | 700 | 0.0457 |
68
+ | 0.0357 | 1.1514 | 750 | 0.0434 |
69
+ | 0.0336 | 1.2282 | 800 | 0.0408 |
70
+ | 0.0342 | 1.3049 | 850 | 0.0414 |
71
+ | 0.0307 | 1.3817 | 900 | 0.0407 |
72
+ | 0.0312 | 1.4585 | 950 | 0.0379 |
73
+ | 0.0314 | 1.5352 | 1000 | 0.0392 |
74
+ | 0.0229 | 1.6120 | 1050 | 0.0367 |
75
+ | 0.0337 | 1.6887 | 1100 | 0.0372 |
76
+ | 0.028 | 1.7655 | 1150 | 0.0379 |
77
+ | 0.0191 | 1.8423 | 1200 | 0.0388 |
78
+ | 0.0348 | 1.9190 | 1250 | 0.0411 |
79
+ | 0.0469 | 1.9958 | 1300 | 0.0399 |
80
+ | 0.0193 | 2.0725 | 1350 | 0.0412 |
81
+ | 0.0168 | 2.1493 | 1400 | 0.0416 |
82
+ | 0.019 | 2.2261 | 1450 | 0.0390 |
83
+ | 0.0268 | 2.3028 | 1500 | 0.0390 |
84
+ | 0.0221 | 2.3796 | 1550 | 0.0412 |
85
+ | 0.0264 | 2.4563 | 1600 | 0.0408 |
86
+ | 0.0248 | 2.5331 | 1650 | 0.0390 |
87
+ | 0.018 | 2.6099 | 1700 | 0.0397 |
88
+ | 0.0148 | 2.6866 | 1750 | 0.0406 |
89
+ | 0.0228 | 2.7634 | 1800 | 0.0416 |
90
+ | 0.0216 | 2.8401 | 1850 | 0.0392 |
91
+ | 0.021 | 2.9169 | 1900 | 0.0396 |
92
+ | 0.016 | 2.9937 | 1950 | 0.0393 |
93
+ | 0.0055 | 3.0704 | 2000 | 0.0446 |
94
+ | 0.0128 | 3.1472 | 2050 | 0.0464 |
95
+ | 0.0105 | 3.2239 | 2100 | 0.0466 |
96
+ | 0.009 | 3.3007 | 2150 | 0.0450 |
97
+ | 0.0087 | 3.3775 | 2200 | 0.0487 |
98
+ | 0.0102 | 3.4542 | 2250 | 0.0473 |
99
+ | 0.007 | 3.5310 | 2300 | 0.0486 |
100
+ | 0.0113 | 3.6078 | 2350 | 0.0490 |
101
+ | 0.0066 | 3.6845 | 2400 | 0.0522 |
102
+ | 0.0064 | 3.7613 | 2450 | 0.0510 |
103
+ | 0.0095 | 3.8380 | 2500 | 0.0514 |
104
+ | 0.0089 | 3.9148 | 2550 | 0.0521 |
105
+ | 0.0065 | 3.9916 | 2600 | 0.0524 |
106
+ | 0.0034 | 4.0683 | 2650 | 0.0540 |
107
+ | 0.0032 | 4.1451 | 2700 | 0.0563 |
108
+ | 0.0026 | 4.2218 | 2750 | 0.0564 |
109
+ | 0.0024 | 4.2986 | 2800 | 0.0586 |
110
+ | 0.0021 | 4.3754 | 2850 | 0.0595 |
111
+ | 0.0043 | 4.4521 | 2900 | 0.0604 |
112
+ | 0.0019 | 4.5289 | 2950 | 0.0607 |
113
+ | 0.0011 | 4.6056 | 3000 | 0.0610 |
114
+ | 0.0018 | 4.6824 | 3050 | 0.0617 |
115
+ | 0.0051 | 4.7592 | 3100 | 0.0614 |
116
+ | 0.0032 | 4.8359 | 3150 | 0.0617 |
117
+ | 0.001 | 4.9127 | 3200 | 0.0617 |
118
+ | 0.0029 | 4.9894 | 3250 | 0.0618 |
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 sha256:44d6d3588d4ce494c9586649c0e416cbc8b36b8e02c6cda1a5223c3be87dbe7a
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71787a6fae7c5628103888dd7dea323c80a2052d10d45c470f881cb4c60bdcb8
3
  size 83945296