Hugging Face's logo

chchen
/
Llama3-OpenBioLLM-8B-PsyCourse-fold6

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
Community
chchen commited on
Commit
58c4880
·
verified ·
1 Parent(s): 111a77a

Model save

Browse files
Files changed (2) hide show
  1. README.md +128 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-fold6
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-fold6
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: 0.0628
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
+ | 0.4971 | 0.0751 | 50 | 0.3237 |
55
+ | 0.1179 | 0.1502 | 100 | 0.0942 |
56
+ | 0.0891 | 0.2254 | 150 | 0.0797 |
57
+ | 0.0539 | 0.3005 | 200 | 0.0598 |
58
+ | 0.065 | 0.3756 | 250 | 0.0575 |
59
+ | 0.052 | 0.4507 | 300 | 0.0530 |
60
+ | 0.0535 | 0.5258 | 350 | 0.0545 |
61
+ | 0.0512 | 0.6009 | 400 | 0.0466 |
62
+ | 0.0597 | 0.6761 | 450 | 0.0495 |
63
+ | 0.0509 | 0.7512 | 500 | 0.0469 |
64
+ | 0.0624 | 0.8263 | 550 | 0.0431 |
65
+ | 0.035 | 0.9014 | 600 | 0.0458 |
66
+ | 0.0546 | 0.9765 | 650 | 0.0444 |
67
+ | 0.0404 | 1.0516 | 700 | 0.0443 |
68
+ | 0.0342 | 1.1268 | 750 | 0.0434 |
69
+ | 0.0298 | 1.2019 | 800 | 0.0428 |
70
+ | 0.0348 | 1.2770 | 850 | 0.0407 |
71
+ | 0.0291 | 1.3521 | 900 | 0.0397 |
72
+ | 0.0373 | 1.4272 | 950 | 0.0397 |
73
+ | 0.0289 | 1.5023 | 1000 | 0.0406 |
74
+ | 0.0339 | 1.5775 | 1050 | 0.0450 |
75
+ | 0.0244 | 1.6526 | 1100 | 0.0412 |
76
+ | 0.0288 | 1.7277 | 1150 | 0.0402 |
77
+ | 0.036 | 1.8028 | 1200 | 0.0395 |
78
+ | 0.0334 | 1.8779 | 1250 | 0.0392 |
79
+ | 0.0568 | 1.9531 | 1300 | 0.0428 |
80
+ | 0.0206 | 2.0282 | 1350 | 0.0409 |
81
+ | 0.0226 | 2.1033 | 1400 | 0.0408 |
82
+ | 0.0257 | 2.1784 | 1450 | 0.0407 |
83
+ | 0.0138 | 2.2535 | 1500 | 0.0414 |
84
+ | 0.0167 | 2.3286 | 1550 | 0.0409 |
85
+ | 0.0217 | 2.4038 | 1600 | 0.0388 |
86
+ | 0.0195 | 2.4789 | 1650 | 0.0427 |
87
+ | 0.0223 | 2.5540 | 1700 | 0.0437 |
88
+ | 0.0195 | 2.6291 | 1750 | 0.0428 |
89
+ | 0.0218 | 2.7042 | 1800 | 0.0409 |
90
+ | 0.0189 | 2.7793 | 1850 | 0.0401 |
91
+ | 0.0195 | 2.8545 | 1900 | 0.0381 |
92
+ | 0.0188 | 2.9296 | 1950 | 0.0399 |
93
+ | 0.0105 | 3.0047 | 2000 | 0.0412 |
94
+ | 0.0073 | 3.0798 | 2050 | 0.0443 |
95
+ | 0.0082 | 3.1549 | 2100 | 0.0466 |
96
+ | 0.0107 | 3.2300 | 2150 | 0.0490 |
97
+ | 0.0143 | 3.3052 | 2200 | 0.0447 |
98
+ | 0.005 | 3.3803 | 2250 | 0.0471 |
99
+ | 0.0079 | 3.4554 | 2300 | 0.0481 |
100
+ | 0.0085 | 3.5305 | 2350 | 0.0501 |
101
+ | 0.0073 | 3.6056 | 2400 | 0.0468 |
102
+ | 0.0034 | 3.6808 | 2450 | 0.0481 |
103
+ | 0.0053 | 3.7559 | 2500 | 0.0496 |
104
+ | 0.0052 | 3.8310 | 2550 | 0.0498 |
105
+ | 0.0117 | 3.9061 | 2600 | 0.0501 |
106
+ | 0.0082 | 3.9812 | 2650 | 0.0500 |
107
+ | 0.0054 | 4.0563 | 2700 | 0.0516 |
108
+ | 0.0019 | 4.1315 | 2750 | 0.0546 |
109
+ | 0.0048 | 4.2066 | 2800 | 0.0565 |
110
+ | 0.0026 | 4.2817 | 2850 | 0.0583 |
111
+ | 0.001 | 4.3568 | 2900 | 0.0608 |
112
+ | 0.0022 | 4.4319 | 2950 | 0.0609 |
113
+ | 0.0036 | 4.5070 | 3000 | 0.0615 |
114
+ | 0.0006 | 4.5822 | 3050 | 0.0621 |
115
+ | 0.0019 | 4.6573 | 3100 | 0.0624 |
116
+ | 0.0027 | 4.7324 | 3150 | 0.0628 |
117
+ | 0.0022 | 4.8075 | 3200 | 0.0629 |
118
+ | 0.002 | 4.8826 | 3250 | 0.0630 |
119
+ | 0.0063 | 4.9577 | 3300 | 0.0628 |
120
+
121
+
122
+ ### Framework versions
123
+
124
+ - PEFT 0.12.0
125
+ - Transformers 4.46.1
126
+ - Pytorch 2.5.1+cu124
127
+ - Datasets 3.1.0
128
+ - Tokenizers 0.20.3
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a46e148559311e20431915a0d7b218d7adebc1c15bcf89385a180f2fedb4203b
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8247f240b2e296615eac011d06703e7cb53b7ee797377d8c351e646614df0786
3
  size 83945296