Hugging Face's logo

rajevan123
/
STS-Lora-Fine-Tuning-Capstone-bert-testing-23-with-lower-r-mid

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files
xet
Metrics Community
rajevan123 commited on
Commit
d7121b1
·
verified ·
1 Parent(s): 82f226f

End of training

Browse files
Files changed (3) hide show
  1. README.md +101 -0
  2. adapter_model.safetensors +1 -1
  3. runs/Mar24_21-55-36_05ec2ae56015/events.out.tfevents.1711317337.05ec2ae56015.631.6 +2 -2
README.md ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ base_model: dslim/bert-base-NER
9
+ model-index:
10
+ - name: STS-Lora-Fine-Tuning-Capstone-bert-testing-23-with-lower-r-mid
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # STS-Lora-Fine-Tuning-Capstone-bert-testing-23-with-lower-r-mid
18
+
19
+ This model is a fine-tuned version of [dslim/bert-base-NER](https://huggingface.co/dslim/bert-base-NER) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.3610
22
+ - Accuracy: 0.4300
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 3e-05
42
+ - train_batch_size: 32
43
+ - eval_batch_size: 32
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - num_epochs: 40
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | No log | 1.0 | 180 | 1.7491 | 0.2429 |
54
+ | No log | 2.0 | 360 | 1.7395 | 0.2451 |
55
+ | 1.7055 | 3.0 | 540 | 1.7242 | 0.2451 |
56
+ | 1.7055 | 4.0 | 720 | 1.6937 | 0.2980 |
57
+ | 1.7055 | 5.0 | 900 | 1.6446 | 0.3038 |
58
+ | 1.6419 | 6.0 | 1080 | 1.6173 | 0.3176 |
59
+ | 1.6419 | 7.0 | 1260 | 1.5638 | 0.3401 |
60
+ | 1.6419 | 8.0 | 1440 | 1.5355 | 0.3524 |
61
+ | 1.5258 | 9.0 | 1620 | 1.5112 | 0.3590 |
62
+ | 1.5258 | 10.0 | 1800 | 1.4870 | 0.3742 |
63
+ | 1.5258 | 11.0 | 1980 | 1.4729 | 0.3749 |
64
+ | 1.4424 | 12.0 | 2160 | 1.4664 | 0.3938 |
65
+ | 1.4424 | 13.0 | 2340 | 1.4524 | 0.4003 |
66
+ | 1.4002 | 14.0 | 2520 | 1.4390 | 0.4061 |
67
+ | 1.4002 | 15.0 | 2700 | 1.4317 | 0.4090 |
68
+ | 1.4002 | 16.0 | 2880 | 1.4241 | 0.4155 |
69
+ | 1.376 | 17.0 | 3060 | 1.4201 | 0.4148 |
70
+ | 1.376 | 18.0 | 3240 | 1.4069 | 0.4083 |
71
+ | 1.376 | 19.0 | 3420 | 1.4000 | 0.4184 |
72
+ | 1.3533 | 20.0 | 3600 | 1.3978 | 0.4235 |
73
+ | 1.3533 | 21.0 | 3780 | 1.3929 | 0.4329 |
74
+ | 1.3533 | 22.0 | 3960 | 1.3896 | 0.4329 |
75
+ | 1.3336 | 23.0 | 4140 | 1.3856 | 0.4264 |
76
+ | 1.3336 | 24.0 | 4320 | 1.3833 | 0.4322 |
77
+ | 1.3254 | 25.0 | 4500 | 1.3787 | 0.4235 |
78
+ | 1.3254 | 26.0 | 4680 | 1.3744 | 0.4329 |
79
+ | 1.3254 | 27.0 | 4860 | 1.3751 | 0.4300 |
80
+ | 1.3082 | 28.0 | 5040 | 1.3720 | 0.4336 |
81
+ | 1.3082 | 29.0 | 5220 | 1.3687 | 0.4300 |
82
+ | 1.3082 | 30.0 | 5400 | 1.3674 | 0.4293 |
83
+ | 1.3105 | 31.0 | 5580 | 1.3663 | 0.4373 |
84
+ | 1.3105 | 32.0 | 5760 | 1.3643 | 0.4351 |
85
+ | 1.3105 | 33.0 | 5940 | 1.3630 | 0.4271 |
86
+ | 1.295 | 34.0 | 6120 | 1.3628 | 0.4322 |
87
+ | 1.295 | 35.0 | 6300 | 1.3625 | 0.4300 |
88
+ | 1.295 | 36.0 | 6480 | 1.3623 | 0.4307 |
89
+ | 1.2919 | 37.0 | 6660 | 1.3617 | 0.4322 |
90
+ | 1.2919 | 38.0 | 6840 | 1.3613 | 0.4315 |
91
+ | 1.2905 | 39.0 | 7020 | 1.3610 | 0.4300 |
92
+ | 1.2905 | 40.0 | 7200 | 1.3610 | 0.4300 |
93
+
94
+
95
+ ### Framework versions
96
+
97
+ - PEFT 0.10.0
98
+ - Transformers 4.38.2
99
+ - Pytorch 2.2.1+cu121
100
+ - Datasets 2.18.0
101
+ - Tokenizers 0.15.2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddd66ed495a6084efc4235eb2b5c681804a8f94889329bccf50f66ee7e494d1f
3
  size 1354992
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84a54ffc86ec3fbd059642bf9a49912436c6a5d9ee808909c2f0cf14531702bc
3
  size 1354992
runs/Mar24_21-55-36_05ec2ae56015/events.out.tfevents.1711317337.05ec2ae56015.631.6 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec55c5fdea4be6d7f2481bb76ab3f35aa0e86e4a0f584ee5562b79a64005dc92
3
- size 20683
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a5d0c506ce65d4dc8acc8726b0ab00a6f9de4c81eebfecd32e10fe6c70dabed
3
+ size 21360