Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</s_adr1>": 57537,
+  "</s_adr2>": 57535,
+  "</s_bnm>": 57533,
+  "</s_bval>": 57541,
+  "</s_cbx>": 57539,
+  "</s_enm>": 57531,
+  "</s_ent>": 57525,
+  "</s_sdt>": 57529,
+  "</s_ssn>": 57527,
+  "<s_adr1>": 57538,
+  "<s_adr2>": 57536,
+  "<s_bnm>": 57534,
+  "<s_bval>": 57542,
+  "<s_cbx>": 57540,
+  "<s_enm>": 57532,
+  "<s_ent>": 57526,
+  "<s_iitcdip>": 57523,
+  "<s_sdt>": 57530,
+  "<s_ssn>": 57528,
+  "<s_synthdog>": 57524,
+  "<s_w9_cord>": 57543,
+  "<sep/>": 57522
+}

artifacts.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa393432df37edbc874d61352aca8bc593cb6a42902d48604d8d019b67fe00c4
+size 1603760464

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": 128,
+  "max_position_embeddings": 128,
+  "model_type": "donut",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "window_size": 10
+}

config.yaml

@@ -0,0 +1,34 @@
+resume_from_checkpoint_path: None
+result_path: './result'
+pretrained_model_name_or_path: 'naver-clova-ix/donut-base'
+dataset_name_or_paths: 
+  - 'jfargus/w9_cord_ltd_fields_phila_domain_v5'
+sort_json_key: True
+train_batch_sizes: 
+  - 4
+val_batch_sizes: 
+  - 1
+input_size: 
+  - 1280
+  - 960
+max_length: 128
+align_long_axis: False
+num_nodes: 1
+seed: 2022
+lr: 3e-05
+num_training_samples_per_epoch: 2500
+warmup_steps: 300
+max_epochs: 4
+max_steps: -1
+num_workers: 4
+val_check_interval: 1.0
+check_val_every_n_epoch: 1
+gradient_clip_val: 1.0
+verbose: True
+limit_val_batches: 0.75
+task_name: 'w9_cord'
+augment: True
+augment_prob: 0.75
+pexels_key: 'GpOfCma7X0faYw2FldfWGymfzdCyPJ9AePbfQbLDp757QPU4IUPzGJc2'
+exp_name: 'train_w9_cord_stage_1'
+exp_version: '20250617_132202'

events.out.tfevents.1750166642.218ebeccb76c.2610.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2944b8ab36cac7ac29037244abc1a4e57369833972e120e6cc882902bdf6d29
+size 10848

hparams.yaml

@@ -0,0 +1 @@
+{}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5bf830a5c26af44d11799d90ecaafb9fa175cb907dcc949afd9a1e580ab2458
+size 855782142

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_w9_cord>"
+  ],
+  "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 +1,22 @@
+{
+  "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
+  },
+  "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>"
+}