5Elza5 commited on
Commit
64bf693
1 Parent(s): 81f3ff7

Upload 10 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_Letter.Date>": 57527,
3
+ "</s_Letter.Number>": 57525,
4
+ "<s_Letter.Date>": 57528,
5
+ "<s_Letter.Number>": 57526,
6
+ "<s_dataset_letter_date_number>": 57529,
7
+ "<s_iitcdip>": 57523,
8
+ "<s_synthdog>": 57524,
9
+ "<sep/>": 57522
10
+ }
artifacts.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e909c7a969b2ff7c16e032b8bc75004eedd5c0b4484e568318e4053c4a806db
3
+ size 2080175518
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/drive/MyDrive/20230814_081015_colab_colab_69acc",
3
+ "align_long_axis": false,
4
+ "architectures": [
5
+ "DonutModel"
6
+ ],
7
+ "decoder_layer": 4,
8
+ "encoder_layer": [
9
+ 2,
10
+ 2,
11
+ 14,
12
+ 2
13
+ ],
14
+ "input_size": [
15
+ 1280,
16
+ 960
17
+ ],
18
+ "max_length": 768,
19
+ "max_position_embeddings": 768,
20
+ "model_type": "donut",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.31.0",
23
+ "window_size": 10
24
+ }
config.yaml ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ resume_from_checkpoint_path: None
2
+ result_path: '/content/drive/MyDrive/donut_results'
3
+ pretrained_model_name_or_path: '/content/drive/MyDrive/20230814_081015_colab_colab_69acc'
4
+ dataset_name_or_paths:
5
+ - '/content/drive/MyDrive/dataset_letter_date_number'
6
+ sort_json_key: False
7
+ train_batch_sizes:
8
+ - 1
9
+ val_batch_sizes:
10
+ - 1
11
+ input_size:
12
+ - 1280
13
+ - 960
14
+ max_length: 768
15
+ align_long_axis: False
16
+ num_nodes: 1
17
+ seed: 2022
18
+ lr: 3e-05
19
+ warmup_steps: 300
20
+ num_training_samples_per_epoch: 800
21
+ max_epochs: 20
22
+ max_steps: -1
23
+ num_workers: 8
24
+ val_check_interval: 1.0
25
+ check_val_every_n_epoch: 5
26
+ gradient_clip_val: 1.0
27
+ verbose: True
28
+ exp_name: 'train_cord'
29
+ exp_version: '20230816_034305'
events.out.tfevents.1692157542.3720eacfb3e8.2795.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa32391a32ab230eacd506ab93752a9fab2a2ba18a077a37342720337bbc9c73
3
+ size 49587
hparams.yaml ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39b5254dbbd3db916122da779ef26aa2731297814999499b13d58c578ad9398b
3
+ size 1093988869
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
3
+ size 1296245
special_tokens_map.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s_dataset_letter_date_number>"
4
+ ],
5
+ "bos_token": "<s>",
6
+ "cls_token": "<s>",
7
+ "eos_token": "</s>",
8
+ "mask_token": {
9
+ "content": "<mask>",
10
+ "lstrip": true,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "unk_token": "<unk>"
18
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "from_slow": true,
7
+ "mask_token": {
8
+ "__type": "AddedToken",
9
+ "content": "<mask>",
10
+ "lstrip": true,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "model_max_length": 1000000000000000019884624838656,
16
+ "pad_token": "<pad>",
17
+ "processor_class": "DonutProcessor",
18
+ "sep_token": "</s>",
19
+ "sp_model_kwargs": {},
20
+ "tokenizer_class": "XLMRobertaTokenizer",
21
+ "unk_token": "<unk>"
22
+ }