sreejith8100 commited on
Commit
fc975aa
1 Parent(s): d858566

End of training

Browse files
Files changed (3) hide show
  1. README.md +48 -2
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
README.md CHANGED
@@ -16,6 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
  # donut-base-vishnu
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
 
20
  ## Model description
21
 
@@ -40,15 +42,59 @@ The following hyperparameters were used during training:
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 12
 
44
 
45
  ### Training results
46
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
 
48
 
49
  ### Framework versions
50
 
51
- - Transformers 4.34.1
52
  - Pytorch 2.1.0+cu118
53
  - Datasets 2.14.6
54
  - Tokenizers 0.14.1
 
16
  # donut-base-vishnu
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: 0.3250
21
 
22
  ## Model description
23
 
 
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - num_epochs: 50
46
+ - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 2.9387 | 1.0 | 127 | 2.0237 |
53
+ | 0.8381 | 2.0 | 254 | 1.3332 |
54
+ | 1.4923 | 3.0 | 381 | 1.1110 |
55
+ | 0.9061 | 4.0 | 508 | 0.9530 |
56
+ | 0.4627 | 5.0 | 635 | 0.9156 |
57
+ | 0.4305 | 6.0 | 762 | 0.7884 |
58
+ | 0.4383 | 7.0 | 889 | 0.6936 |
59
+ | 0.1852 | 8.0 | 1016 | 0.6715 |
60
+ | 0.2348 | 9.0 | 1143 | 0.6209 |
61
+ | 0.3975 | 10.0 | 1270 | 0.5614 |
62
+ | 0.1548 | 11.0 | 1397 | 0.5152 |
63
+ | 0.0377 | 12.0 | 1524 | 0.5135 |
64
+ | 0.043 | 13.0 | 1651 | 0.4759 |
65
+ | 0.0698 | 14.0 | 1778 | 0.4697 |
66
+ | 0.0292 | 15.0 | 1905 | 0.4243 |
67
+ | 0.0516 | 16.0 | 2032 | 0.4594 |
68
+ | 0.2062 | 17.0 | 2159 | 0.4332 |
69
+ | 0.0307 | 18.0 | 2286 | 0.4030 |
70
+ | 0.0775 | 19.0 | 2413 | 0.4069 |
71
+ | 0.0157 | 20.0 | 2540 | 0.4111 |
72
+ | 0.0137 | 21.0 | 2667 | 0.4072 |
73
+ | 0.0148 | 22.0 | 2794 | 0.3938 |
74
+ | 0.0454 | 23.0 | 2921 | 0.3789 |
75
+ | 0.0023 | 24.0 | 3048 | 0.3864 |
76
+ | 0.0033 | 25.0 | 3175 | 0.3750 |
77
+ | 0.0292 | 26.0 | 3302 | 0.3847 |
78
+ | 0.0087 | 27.0 | 3429 | 0.3592 |
79
+ | 0.0032 | 28.0 | 3556 | 0.3665 |
80
+ | 0.0048 | 29.0 | 3683 | 0.3372 |
81
+ | 0.0035 | 30.0 | 3810 | 0.3349 |
82
+ | 0.0197 | 31.0 | 3937 | 0.3591 |
83
+ | 0.0006 | 32.0 | 4064 | 0.3504 |
84
+ | 0.0016 | 33.0 | 4191 | 0.3450 |
85
+ | 0.0006 | 34.0 | 4318 | 0.3505 |
86
+ | 0.0046 | 35.0 | 4445 | 0.3332 |
87
+ | 0.0045 | 36.0 | 4572 | 0.3206 |
88
+ | 0.0006 | 37.0 | 4699 | 0.3361 |
89
+ | 0.0039 | 38.0 | 4826 | 0.3348 |
90
+ | 0.0059 | 39.0 | 4953 | 0.3328 |
91
+ | 0.0039 | 40.0 | 5080 | 0.3406 |
92
+ | 0.0014 | 41.0 | 5207 | 0.3250 |
93
 
94
 
95
  ### Framework versions
96
 
97
+ - Transformers 4.35.0
98
  - Pytorch 2.1.0+cu118
99
  - Datasets 2.14.6
100
  - Tokenizers 0.14.1
generation_config.json CHANGED
@@ -4,5 +4,5 @@
4
  "eos_token_id": 2,
5
  "forced_eos_token_id": 2,
6
  "pad_token_id": 1,
7
- "transformers_version": "4.34.1"
8
  }
 
4
  "eos_token_id": 2,
5
  "forced_eos_token_id": 2,
6
  "pad_token_id": 1,
7
+ "transformers_version": "4.35.0"
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d194b7d01283f4068fcc6ec9a736c4f6e14af597e4b76f9dc79897e848df924
3
  size 809234584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a46fbb808ae084d7b959bd360f0b068ce768fbbdef06282fbf1f08b41afbf361
3
  size 809234584