lmzbonack commited on
Commit
741377c
1 Parent(s): 9bd899c

End of training

Browse files
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: mit
3
- base_model: naver-clova-ix/donut-base
4
  tags:
5
  - generated_from_trainer
6
  model-index:
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # donut-attempt-focused-edgeOne
15
 
16
- This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the None dataset.
17
 
18
  ## Model description
19
 
@@ -38,7 +38,7 @@ The following hyperparameters were used during training:
38
  - seed: 42
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: linear
41
- - num_epochs: 3
42
  - mixed_precision_training: Native AMP
43
 
44
  ### Training results
 
1
  ---
2
  license: mit
3
+ base_model: lmzbonack/donut-attempt-two
4
  tags:
5
  - generated_from_trainer
6
  model-index:
 
13
 
14
  # donut-attempt-focused-edgeOne
15
 
16
+ This model is a fine-tuned version of [lmzbonack/donut-attempt-two](https://huggingface.co/lmzbonack/donut-attempt-two) on the None dataset.
17
 
18
  ## Model description
19
 
 
38
  - seed: 42
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: linear
41
+ - num_epochs: 4
42
  - mixed_precision_training: Native AMP
43
 
44
  ### Training results
generation_config.json CHANGED
@@ -1,8 +1,10 @@
1
  {
2
  "_from_model_config": true,
3
  "bos_token_id": 0,
 
4
  "eos_token_id": 2,
5
  "forced_eos_token_id": 2,
 
6
  "pad_token_id": 1,
7
  "transformers_version": "4.36.0"
8
  }
 
1
  {
2
  "_from_model_config": true,
3
  "bos_token_id": 0,
4
+ "decoder_start_token_id": 0,
5
  "eos_token_id": 2,
6
  "forced_eos_token_id": 2,
7
+ "max_length": 512,
8
  "pad_token_id": 1,
9
  "transformers_version": "4.36.0"
10
  }
preprocessor_config.json CHANGED
@@ -19,8 +19,8 @@
19
  "processor_class": "DonutProcessor",
20
  "resample": 2,
21
  "rescale_factor": 0.00392156862745098,
22
- "size": [
23
- 720,
24
- 960
25
- ]
26
  }
 
19
  "processor_class": "DonutProcessor",
20
  "resample": 2,
21
  "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "height": 960,
24
+ "width": 720
25
+ }
26
  }
special_tokens_map.json CHANGED
@@ -1,23 +1,29 @@
1
  {
2
  "additional_special_tokens": [
3
- {
4
- "content": "</s>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- {
11
- "content": "<s>",
12
- "lstrip": false,
13
- "normalized": false,
14
- "rstrip": false,
15
- "single_word": false
16
- }
17
  ],
18
- "bos_token": "<s>",
19
- "cls_token": "<s>",
20
- "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  "mask_token": {
22
  "content": "<mask>",
23
  "lstrip": true,
@@ -25,7 +31,25 @@
25
  "rstrip": false,
26
  "single_word": false
27
  },
28
- "pad_token": "<pad>",
29
- "sep_token": "</s>",
30
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  }
 
1
  {
2
  "additional_special_tokens": [
3
+ "</s>",
4
+ "<s>"
 
 
 
 
 
 
 
 
 
 
 
 
5
  ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "cls_token": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
  "mask_token": {
28
  "content": "<mask>",
29
  "lstrip": true,
 
31
  "rstrip": false,
32
  "single_word": false
33
  },
34
+ "pad_token": {
35
+ "content": "<pad>",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "sep_token": {
42
+ "content": "</s>",
43
+ "lstrip": false,
44
+ "normalized": false,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "unk_token": {
49
+ "content": "<unk>",
50
+ "lstrip": false,
51
+ "normalized": false,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ }
55
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff