Commit
•
0eaf274
1
Parent(s):
2baa8e0
End of training
Browse files- README.md +99 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: kacper-cierzniewski/daigram_detr_r50_albumentations
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- bpmn-shapes
|
8 |
+
model-index:
|
9 |
+
- name: daigram_detr_r50_albumentations_finetuning
|
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 |
+
# daigram_detr_r50_albumentations_finetuning
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [kacper-cierzniewski/daigram_detr_r50_albumentations](https://huggingface.co/kacper-cierzniewski/daigram_detr_r50_albumentations) on the bpmn-shapes dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.9817
|
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: 1e-05
|
40 |
+
- train_batch_size: 48
|
41 |
+
- eval_batch_size: 48
|
42 |
+
- seed: 42
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 500
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| 0.9457 | 12.5 | 50 | 1.0238 |
|
53 |
+
| 0.9717 | 25.0 | 100 | 1.0411 |
|
54 |
+
| 0.9823 | 37.5 | 150 | 1.0269 |
|
55 |
+
| 0.9524 | 50.0 | 200 | 1.0518 |
|
56 |
+
| 0.9886 | 62.5 | 250 | 1.0548 |
|
57 |
+
| 0.9638 | 75.0 | 300 | 1.0454 |
|
58 |
+
| 0.948 | 87.5 | 350 | 1.0240 |
|
59 |
+
| 0.9312 | 100.0 | 400 | 1.0281 |
|
60 |
+
| 0.9183 | 112.5 | 450 | 1.0112 |
|
61 |
+
| 0.9219 | 125.0 | 500 | 1.0110 |
|
62 |
+
| 0.9285 | 137.5 | 550 | 1.0325 |
|
63 |
+
| 0.9177 | 150.0 | 600 | 1.0009 |
|
64 |
+
| 0.9323 | 162.5 | 650 | 1.0124 |
|
65 |
+
| 0.9333 | 175.0 | 700 | 1.0154 |
|
66 |
+
| 0.9386 | 187.5 | 750 | 1.0188 |
|
67 |
+
| 0.9586 | 200.0 | 800 | 0.9978 |
|
68 |
+
| 0.894 | 212.5 | 850 | 1.0087 |
|
69 |
+
| 0.8999 | 225.0 | 900 | 1.0055 |
|
70 |
+
| 0.9324 | 237.5 | 950 | 1.0185 |
|
71 |
+
| 0.9313 | 250.0 | 1000 | 0.9840 |
|
72 |
+
| 0.9177 | 262.5 | 1050 | 0.9785 |
|
73 |
+
| 0.8918 | 275.0 | 1100 | 0.9874 |
|
74 |
+
| 0.9145 | 287.5 | 1150 | 0.9802 |
|
75 |
+
| 0.89 | 300.0 | 1200 | 0.9879 |
|
76 |
+
| 0.8818 | 312.5 | 1250 | 0.9857 |
|
77 |
+
| 0.9256 | 325.0 | 1300 | 0.9951 |
|
78 |
+
| 0.9028 | 337.5 | 1350 | 1.0001 |
|
79 |
+
| 0.9252 | 350.0 | 1400 | 1.0033 |
|
80 |
+
| 0.9017 | 362.5 | 1450 | 0.9916 |
|
81 |
+
| 0.8783 | 375.0 | 1500 | 0.9858 |
|
82 |
+
| 0.911 | 387.5 | 1550 | 0.9758 |
|
83 |
+
| 0.8797 | 400.0 | 1600 | 0.9810 |
|
84 |
+
| 0.8995 | 412.5 | 1650 | 0.9840 |
|
85 |
+
| 0.8781 | 425.0 | 1700 | 0.9843 |
|
86 |
+
| 0.8897 | 437.5 | 1750 | 0.9745 |
|
87 |
+
| 0.905 | 450.0 | 1800 | 0.9825 |
|
88 |
+
| 0.8961 | 462.5 | 1850 | 0.9781 |
|
89 |
+
| 0.8865 | 475.0 | 1900 | 0.9781 |
|
90 |
+
| 0.8824 | 487.5 | 1950 | 0.9794 |
|
91 |
+
| 0.8836 | 500.0 | 2000 | 0.9817 |
|
92 |
+
|
93 |
+
|
94 |
+
### Framework versions
|
95 |
+
|
96 |
+
- Transformers 4.35.2
|
97 |
+
- Pytorch 2.1.0+cu121
|
98 |
+
- Datasets 2.16.1
|
99 |
+
- Tokenizers 0.15.0
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 166500992
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e20a90a613f61dfb76515ffe778ed469e91145225face4596a9fdcda00cdf0c9
|
3 |
size 166500992
|