Hugging Face's logo

JandC
/
donut-base-full_text_wt_val_1008

Transformers
TensorBoard
Safetensors
vision-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
JandC commited on
Commit
929eaa9
•
1 Parent(s): 3f630fe

End of training

Browse files
Files changed (1) hide show
  1. README.md +51 -11
README.md CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.1215
21
 
22
  ## Model description
23
 
@@ -49,16 +49,56 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
- | 0.3636 | 1.0 | 504 | 0.2522 |
53
- | 0.2144 | 2.0 | 1008 | 0.1862 |
54
- | 0.1898 | 3.0 | 1512 | 0.1540 |
55
- | 0.0952 | 4.0 | 2016 | 0.1459 |
56
- | 0.1096 | 5.0 | 2520 | 0.1319 |
57
- | 0.0742 | 6.0 | 3024 | 0.1265 |
58
- | 0.074 | 7.0 | 3528 | 0.1240 |
59
- | 0.0692 | 8.0 | 4032 | 0.1209 |
60
- | 0.0671 | 9.0 | 4536 | 0.1218 |
61
- | 0.0376 | 10.0 | 5040 | 0.1215 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62
 
63
 
64
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.1060
21
 
22
  ## Model description
23
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
+ | 1.9227 | 0.2 | 100 | 0.6985 |
53
+ | 0.6852 | 0.4 | 200 | 0.4421 |
54
+ | 0.5102 | 0.6 | 300 | 0.3346 |
55
+ | 0.4178 | 0.79 | 400 | 0.2886 |
56
+ | 0.4476 | 0.99 | 500 | 0.2455 |
57
+ | 0.2931 | 1.19 | 600 | 0.2287 |
58
+ | 0.2647 | 1.39 | 700 | 0.2072 |
59
+ | 0.2418 | 1.59 | 800 | 0.1905 |
60
+ | 0.3031 | 1.79 | 900 | 0.1754 |
61
+ | 0.2306 | 1.98 | 1000 | 0.1667 |
62
+ | 0.2031 | 2.18 | 1100 | 0.1619 |
63
+ | 0.1918 | 2.38 | 1200 | 0.1536 |
64
+ | 0.1802 | 2.58 | 1300 | 0.1504 |
65
+ | 0.1646 | 2.78 | 1400 | 0.1436 |
66
+ | 0.1816 | 2.98 | 1500 | 0.1379 |
67
+ | 0.1344 | 3.17 | 1600 | 0.1395 |
68
+ | 0.1752 | 3.37 | 1700 | 0.1336 |
69
+ | 0.1388 | 3.57 | 1800 | 0.1306 |
70
+ | 0.1402 | 3.77 | 1900 | 0.1262 |
71
+ | 0.1123 | 3.97 | 2000 | 0.1277 |
72
+ | 0.144 | 4.17 | 2100 | 0.1248 |
73
+ | 0.1077 | 4.37 | 2200 | 0.1226 |
74
+ | 0.1134 | 4.56 | 2300 | 0.1186 |
75
+ | 0.1192 | 4.76 | 2400 | 0.1179 |
76
+ | 0.1142 | 4.96 | 2500 | 0.1194 |
77
+ | 0.1426 | 5.16 | 2600 | 0.1202 |
78
+ | 0.1022 | 5.36 | 2700 | 0.1165 |
79
+ | 0.0815 | 5.56 | 2800 | 0.1164 |
80
+ | 0.1096 | 5.75 | 2900 | 0.1166 |
81
+ | 0.0866 | 5.95 | 3000 | 0.1121 |
82
+ | 0.1148 | 6.15 | 3100 | 0.1122 |
83
+ | 0.0771 | 6.35 | 3200 | 0.1129 |
84
+ | 0.0996 | 6.55 | 3300 | 0.1096 |
85
+ | 0.0622 | 6.75 | 3400 | 0.1099 |
86
+ | 0.0985 | 6.94 | 3500 | 0.1092 |
87
+ | 0.0684 | 7.14 | 3600 | 0.1097 |
88
+ | 0.0669 | 7.34 | 3700 | 0.1086 |
89
+ | 0.0624 | 7.54 | 3800 | 0.1088 |
90
+ | 0.0763 | 7.74 | 3900 | 0.1069 |
91
+ | 0.0579 | 7.94 | 4000 | 0.1060 |
92
+ | 0.0623 | 8.13 | 4100 | 0.1083 |
93
+ | 0.0599 | 8.33 | 4200 | 0.1058 |
94
+ | 0.0625 | 8.53 | 4300 | 0.1073 |
95
+ | 0.0499 | 8.73 | 4400 | 0.1059 |
96
+ | 0.0628 | 8.93 | 4500 | 0.1059 |
97
+ | 0.0684 | 9.13 | 4600 | 0.1063 |
98
+ | 0.0472 | 9.33 | 4700 | 0.1056 |
99
+ | 0.068 | 9.52 | 4800 | 0.1057 |
100
+ | 0.06 | 9.72 | 4900 | 0.1062 |
101
+ | 0.0636 | 9.92 | 5000 | 0.1060 |
102
 
103
 
104
  ### Framework versions