Upload 9 files

added_tokens.json

@@ -0,0 +1,14 @@
+{
+  "</s_address>": 57529,
+  "</s_company>": 57525,
+  "</s_date>": 57527,
+  "</s_total>": 57531,
+  "<s_address>": 57530,
+  "<s_company>": 57526,
+  "<s_date>": 57528,
+  "<s_iitcdip>": 57523,
+  "<s_srorie-donut>": 57533,
+  "<s_synthdog>": 57524,
+  "<s_total>": 57532,
+  "<sep/>": 57522
+}

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "naver-clova-ix/donut-base",
+  "align_long_axis": false,
+  "architectures": [
+    "DonutModel"
+  ],
+  "decoder_layer": 4,
+  "encoder_layer": [
+    2,
+    2,
+    14,
+    2
+  ],
+  "input_size": [
+    1280,
+    960
+  ],
+  "max_length": 768,
+  "max_position_embeddings": 768,
+  "model_type": "donut",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "window_size": 10
+}

config.yaml

@@ -0,0 +1,29 @@
+resume_from_checkpoint_path: None
+result_path: './result'
+pretrained_model_name_or_path: 'naver-clova-ix/donut-base'
+dataset_name_or_paths: 
+  - '/kaggle/working/donut/srorie-donut'
+sort_json_key: False
+train_batch_sizes: 
+  - 2
+val_batch_sizes: 
+  - 1
+input_size: 
+  - 1280
+  - 960
+max_length: 768
+align_long_axis: False
+num_nodes: 1
+seed: 2022
+lr: 3e-05
+warmup_steps: 300
+num_training_samples_per_epoch: 800
+max_epochs: 30
+max_steps: -1
+num_workers: 8
+val_check_interval: 1.0
+check_val_every_n_epoch: 3
+gradient_clip_val: 1.0
+verbose: True
+exp_name: 'train_srorie'
+exp_version: '20240719_094501'

last.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67c88cefa33c0ab38850d72594e0f84bcebfeca6005b4df4c3f8c473eed10021
+size 1608870370

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:706ad751648b4f0a684241dcee363757f399079f5c4380be7bde4d6c52229e56
+size 858362622

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
+size 1296245

special_tokens_map.json

@@ -0,0 +1,18 @@
+{
+  "additional_special_tokens": [
+    "<s_srorie-donut>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "from_slow": true,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "naver-clova-ix/donut-base",
+  "pad_token": "<pad>",
+  "processor_class": "DonutProcessor",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}