Hugging Face's logo

Bigheadjoshy
/
layoutlmv3_document_classification

Text Classification
Transformers
Safetensors
layoutlmv3
Generated from Trainer
Model card Files Community
Bigheadjoshy commited on
Commit
faf9844
·
verified ·
1 Parent(s): 79b0159

End of training

Browse files
Files changed (4) hide show
  1. README.md +32 -27
  2. config.json +6 -2
  3. model.safetensors +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.8183
23
- - Accuracy: 0.8340
24
- - F1: 0.8221
25
 
26
  ## Model description
27
 
@@ -40,40 +40,45 @@ More information needed
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - learning_rate: 1e-05
44
- - train_batch_size: 16
45
- - eval_batch_size: 16
46
  - seed: 42
47
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
- - lr_scheduler_warmup_steps: 500
50
- - num_epochs: 7
 
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
55
- |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
56
- | 0.6545 | 0.4274 | 100 | 0.9149 | 0.8233 | 0.8041 |
57
- | 0.6313 | 0.8547 | 200 | 0.9024 | 0.8276 | 0.8085 |
58
- | 0.5714 | 1.2821 | 300 | 0.9112 | 0.8223 | 0.8067 |
59
- | 0.5408 | 1.7094 | 400 | 0.8816 | 0.8298 | 0.8093 |
60
- | 0.482 | 2.1368 | 500 | 0.9015 | 0.8244 | 0.8081 |
61
- | 0.4546 | 2.5641 | 600 | 0.8779 | 0.8287 | 0.8180 |
62
- | 0.4718 | 2.9915 | 700 | 0.8879 | 0.8212 | 0.8056 |
63
- | 0.4302 | 3.4188 | 800 | 0.8562 | 0.8276 | 0.8155 |
64
- | 0.5039 | 3.8462 | 900 | 0.8382 | 0.8330 | 0.8226 |
65
- | 0.4644 | 4.2735 | 1000 | 0.8455 | 0.8308 | 0.8200 |
66
- | 0.4411 | 4.7009 | 1100 | 0.8461 | 0.8308 | 0.8228 |
67
- | 0.4007 | 5.1282 | 1200 | 0.8304 | 0.8308 | 0.8200 |
68
- | 0.4023 | 5.5556 | 1300 | 0.8370 | 0.8330 | 0.8242 |
69
- | 0.3756 | 5.9829 | 1400 | 0.8193 | 0.8405 | 0.8286 |
70
- | 0.3592 | 6.4103 | 1500 | 0.8185 | 0.8394 | 0.8282 |
71
- | 0.3429 | 6.8376 | 1600 | 0.8183 | 0.8340 | 0.8221 |
 
 
 
 
72
 
73
 
74
  ### Framework versions
75
 
76
  - Transformers 4.47.1
77
- - Pytorch 2.5.1+cu121
78
  - Datasets 3.2.0
79
  - Tokenizers 0.21.0
 
19
 
20
  This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.6852
23
+ - Accuracy: 0.8480
24
+ - F1: 0.8373
25
 
26
  ## Model description
27
 
 
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
+ - learning_rate: 3e-05
44
+ - train_batch_size: 24
45
+ - eval_batch_size: 24
46
  - seed: 42
47
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_ratio: 0.06
50
+ - num_epochs: 10
51
+ - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
56
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
57
+ | 4.1758 | 0.5 | 100 | 3.6479 | 0.1754 | 0.0743 |
58
+ | 3.1634 | 1.0 | 200 | 2.5074 | 0.4645 | 0.3598 |
59
+ | 2.2494 | 1.5 | 300 | 1.9309 | 0.5856 | 0.4950 |
60
+ | 1.8063 | 2.0 | 400 | 1.5119 | 0.6817 | 0.6152 |
61
+ | 1.458 | 2.5 | 500 | 1.2952 | 0.7126 | 0.6529 |
62
+ | 1.2453 | 3.0 | 600 | 1.1118 | 0.7728 | 0.7327 |
63
+ | 1.046 | 3.5 | 700 | 1.0126 | 0.7987 | 0.7681 |
64
+ | 0.966 | 4.0 | 800 | 0.9096 | 0.8154 | 0.7929 |
65
+ | 0.7941 | 4.5 | 900 | 0.8714 | 0.8179 | 0.7972 |
66
+ | 0.7796 | 5.0 | 1000 | 0.8019 | 0.8329 | 0.8126 |
67
+ | 0.6561 | 5.5 | 1100 | 0.7623 | 0.8421 | 0.8235 |
68
+ | 0.6419 | 6.0 | 1200 | 0.7399 | 0.8421 | 0.8262 |
69
+ | 0.5715 | 6.5 | 1300 | 0.7127 | 0.8480 | 0.8321 |
70
+ | 0.4991 | 7.0 | 1400 | 0.7502 | 0.8396 | 0.8257 |
71
+ | 0.4697 | 7.5 | 1500 | 0.7124 | 0.8429 | 0.8305 |
72
+ | 0.4618 | 8.0 | 1600 | 0.6976 | 0.8463 | 0.8330 |
73
+ | 0.4117 | 8.5 | 1700 | 0.6892 | 0.8546 | 0.8429 |
74
+ | 0.4274 | 9.0 | 1800 | 0.6915 | 0.8496 | 0.8390 |
75
+ | 0.383 | 9.5 | 1900 | 0.6830 | 0.8471 | 0.8349 |
76
+ | 0.3604 | 10.0 | 2000 | 0.6852 | 0.8480 | 0.8373 |
77
 
78
 
79
  ### Framework versions
80
 
81
  - Transformers 4.47.1
82
+ - Pytorch 2.5.1+cu124
83
  - Datasets 3.2.0
84
  - Tokenizers 0.21.0
config.json CHANGED
@@ -103,7 +103,9 @@
103
  "86": "LABEL_86",
104
  "87": "LABEL_87",
105
  "88": "LABEL_88",
106
- "89": "LABEL_89"
 
 
107
  },
108
  "initializer_range": 0.02,
109
  "input_size": 224,
@@ -198,7 +200,9 @@
198
  "LABEL_87": 87,
199
  "LABEL_88": 88,
200
  "LABEL_89": 89,
201
- "LABEL_9": 9
 
 
202
  },
203
  "layer_norm_eps": 1e-05,
204
  "max_2d_position_embeddings": 1024,
 
103
  "86": "LABEL_86",
104
  "87": "LABEL_87",
105
  "88": "LABEL_88",
106
+ "89": "LABEL_89",
107
+ "90": "LABEL_90",
108
+ "91": "LABEL_91"
109
  },
110
  "initializer_range": 0.02,
111
  "input_size": 224,
 
200
  "LABEL_87": 87,
201
  "LABEL_88": 88,
202
  "LABEL_89": 89,
203
+ "LABEL_9": 9,
204
+ "LABEL_90": 90,
205
+ "LABEL_91": 91
206
  },
207
  "layer_norm_eps": 1e-05,
208
  "max_2d_position_embeddings": 1024,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19b413cd672035c2b7d6b201b4b77bbf15bcd8afc439e600a5fcbb9d9e87c71e
3
- size 503973440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e75d7ab0bf7fc49091fa690d58386688f7d15790e1ebcc726a0597406c6a9d3
3
+ size 503979592
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84cf2b868a64f2e07969c87c926b36a66eee346affe39502dbb857a58784315e
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76f4fd1c90339fcbd74254e3d2c0112c4481691964b86166db203d717189a314
3
  size 5304