Hugging Face's logo

bustamiyusoef
/
Mix_JawiNougat_01

Image-Text-to-Text
Transformers
Safetensors
vision-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Community
bustamiyusoef commited on
Commit
e4e1028
·
verified ·
1 Parent(s): df821f9

bustamiyusoef/Mix_JawiNougat_Ori

Browse files
Files changed (5) hide show
  1. README.md +36 -36
  2. config.json +1 -1
  3. generation_config.json +1 -1
  4. model.safetensors +1 -1
  5. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [facebook/nougat-base](https://huggingface.co/facebook/nougat-base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.3731
20
 
21
  ## Model description
22
 
@@ -47,43 +47,43 @@ The following hyperparameters were used during training:
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss |
51
- |:-------------:|:------:|:----:|:---------------:|
52
- | 2.0544 | 0.996 | 83 | 1.9791 |
53
- | 1.8446 | 1.992 | 166 | 1.7828 |
54
- | 1.6758 | 3.0 | 250 | 1.6437 |
55
- | 1.583 | 3.996 | 333 | 1.5812 |
56
- | 1.5336 | 4.992 | 416 | 1.5246 |
57
- | 1.4567 | 6.0 | 500 | 1.4858 |
58
- | 1.3788 | 6.996 | 583 | 1.4464 |
59
- | 1.2748 | 7.992 | 666 | 1.3263 |
60
- | 1.0082 | 9.0 | 750 | 1.0481 |
61
- | 0.8389 | 9.996 | 833 | 0.8384 |
62
- | 0.6963 | 10.992 | 916 | 0.7219 |
63
- | 0.6003 | 12.0 | 1000 | 0.5988 |
64
- | 0.5013 | 12.996 | 1083 | 0.5561 |
65
- | 0.4806 | 13.992 | 1166 | 0.4835 |
66
- | 0.3913 | 15.0 | 1250 | 0.4571 |
67
- | 0.3294 | 15.996 | 1333 | 0.4435 |
68
- | 0.343 | 16.992 | 1416 | 0.4156 |
69
- | 0.3246 | 18.0 | 1500 | 0.4017 |
70
- | 0.3139 | 18.996 | 1583 | 0.3957 |
71
- | 0.2746 | 19.992 | 1666 | 0.4048 |
72
- | 0.3028 | 21.0 | 1750 | 0.3881 |
73
- | 0.3127 | 21.996 | 1833 | 0.3851 |
74
- | 0.2879 | 22.992 | 1916 | 0.3835 |
75
- | 0.2806 | 24.0 | 2000 | 0.3748 |
76
- | 0.2827 | 24.996 | 2083 | 0.3732 |
77
- | 0.2683 | 25.992 | 2166 | 0.3739 |
78
- | 0.2662 | 27.0 | 2250 | 0.3754 |
79
- | 0.255 | 27.996 | 2333 | 0.3728 |
80
- | 0.2888 | 28.992 | 2416 | 0.3727 |
81
- | 0.2972 | 29.88 | 2490 | 0.3731 |
82
 
83
 
84
  ### Framework versions
85
 
86
- - Transformers 4.46.2
87
- - Pytorch 2.5.0+cu121
88
- - Datasets 3.1.0
89
  - Tokenizers 0.20.3
 
16
 
17
  This model is a fine-tuned version of [facebook/nougat-base](https://huggingface.co/facebook/nougat-base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.4360
20
 
21
  ## Model description
22
 
 
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-------:|:----:|:---------------:|
52
+ | 2.0261 | 0.9901 | 83 | 1.9705 |
53
+ | 1.8445 | 1.9920 | 167 | 1.7617 |
54
+ | 1.6923 | 2.9940 | 251 | 1.6539 |
55
+ | 1.597 | 3.9960 | 335 | 1.5871 |
56
+ | 1.5287 | 4.9980 | 419 | 1.5196 |
57
+ | 1.46 | 6.0 | 503 | 1.4804 |
58
+ | 1.3647 | 6.9901 | 586 | 1.4360 |
59
+ | 1.289 | 7.9920 | 670 | 1.3772 |
60
+ | 1.1741 | 8.9940 | 754 | 1.2350 |
61
+ | 0.9947 | 9.9960 | 838 | 1.0415 |
62
+ | 0.7889 | 10.9980 | 922 | 0.9238 |
63
+ | 0.6771 | 12.0 | 1006 | 0.7884 |
64
+ | 0.6256 | 12.9901 | 1089 | 0.6646 |
65
+ | 0.5402 | 13.9920 | 1173 | 0.6095 |
66
+ | 0.5252 | 14.9940 | 1257 | 0.5702 |
67
+ | 0.441 | 15.9960 | 1341 | 0.5282 |
68
+ | 0.4077 | 16.9980 | 1425 | 0.5030 |
69
+ | 0.3841 | 18.0 | 1509 | 0.4855 |
70
+ | 0.3762 | 18.9901 | 1592 | 0.4703 |
71
+ | 0.3611 | 19.9920 | 1676 | 0.4587 |
72
+ | 0.3486 | 20.9940 | 1760 | 0.4486 |
73
+ | 0.3679 | 21.9960 | 1844 | 0.4416 |
74
+ | 0.3356 | 22.9980 | 1928 | 0.4400 |
75
+ | 0.3343 | 24.0 | 2012 | 0.4387 |
76
+ | 0.3229 | 24.9901 | 2095 | 0.4410 |
77
+ | 0.2928 | 25.9920 | 2179 | 0.4377 |
78
+ | 0.3042 | 26.9940 | 2263 | 0.4393 |
79
+ | 0.3439 | 27.9960 | 2347 | 0.4353 |
80
+ | 0.3286 | 28.9980 | 2431 | 0.4365 |
81
+ | 0.353 | 29.7018 | 2490 | 0.4360 |
82
 
83
 
84
  ### Framework versions
85
 
86
+ - Transformers 4.46.3
87
+ - Pytorch 2.5.1+cu121
88
+ - Datasets 3.2.0
89
  - Tokenizers 0.20.3
config.json CHANGED
@@ -189,5 +189,5 @@
189
  "pad_token_id": 1,
190
  "tie_word_embeddings": false,
191
  "torch_dtype": "bfloat16",
192
- "transformers_version": "4.46.2"
193
  }
 
189
  "pad_token_id": 1,
190
  "tie_word_embeddings": false,
191
  "torch_dtype": "bfloat16",
192
+ "transformers_version": "4.46.3"
193
  }
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": "4.46.2"
8
  }
 
4
  "eos_token_id": 2,
5
  "forced_eos_token_id": 2,
6
  "pad_token_id": 1,
7
+ "transformers_version": "4.46.3"
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37c3b11f5c82bf18750b843c0a94d193e081aa4a41ae6e50d464dda43902441c
3
  size 697843112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea1b39d1f6a30cf036ff1ba390d822980a85cbdb7e3a9277e168e20eec212615
3
  size 697843112
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52f056df3120d628541863e3916ce438643e08eb83742a82425a9a09946c0c14
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fea43bac055128cae802e1d383a4685c77ebbeb1fff0a1767bc62e86691b6913
3
  size 5496