Upload 10 files

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<s_iitcdip>": 57523,
+  "<s_ro_base>": 57525,
+  "<s_synthdog>": 57524,
+  "<sep/>": 57522
+}

artifacts.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d29fafec9a14085a3750d836b8d4c279fee4e4ad5ce2b25a48a29343ddb9bf04
+size 1606756251

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": [
+    960,
+    1280
+  ],
+  "max_length": 512,
+  "max_position_embeddings": 512,
+  "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: 
+  - 'dataset/ro_base'
+sort_json_key: False
+train_batch_sizes: 
+  - 2
+val_batch_sizes: 
+  - 1
+input_size: 
+  - 960
+  - 1280
+max_length: 512
+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: 'base'
+exp_version: 'base'

events.out.tfevents.1676488911.server.5455.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b078ffd3c90e0741bfdef313907bca1a727fb59c12573bf8819dca46d11951d2
+size 139438

hparams.yaml

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

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e1f860fbb1bad24131432b0fc6c438405b068a4d295804e050ae65a719043d7
+size 857286595

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_ro_base>"
+  ],
+  "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>"
+}