Output from training [5 Feb 24 11.50am]

added_tokens.json

@@ -0,0 +1,52 @@
+{
+  "</s_bill_of_lading_no>": 57527,
+  "</s_carrier>": 57569,
+  "</s_consignee>": 57531,
+  "</s_container_no>": 57549,
+  "</s_date>": 57559,
+  "</s_document_type>": 57525,
+  "</s_ex_rate>": 57565,
+  "</s_freight_paym>": 57563,
+  "</s_goods_descriptn>": 57553,
+  "</s_gross_weight>": 57555,
+  "</s_measurement>": 57557,
+  "</s_no_pkg_ctr>": 57551,
+  "</s_notify_party>": 57533,
+  "</s_original_bol>": 57567,
+  "</s_place_delivery>": 57547,
+  "</s_place_issued>": 57561,
+  "</s_place_receipt>": 57545,
+  "</s_port_discharge>": 57543,
+  "</s_port_loading>": 57541,
+  "</s_shipper>": 57529,
+  "</s_shipping_agent>": 57535,
+  "</s_vessel>": 57537,
+  "</s_voy_no>": 57539,
+  "<s_bill_of_lading_no>": 57528,
+  "<s_carrier>": 57570,
+  "<s_consignee>": 57532,
+  "<s_container_no>": 57550,
+  "<s_dataset>": 57571,
+  "<s_date>": 57560,
+  "<s_document_type>": 57526,
+  "<s_ex_rate>": 57566,
+  "<s_freight_paym>": 57564,
+  "<s_goods_descriptn>": 57554,
+  "<s_gross_weight>": 57556,
+  "<s_iitcdip>": 57523,
+  "<s_measurement>": 57558,
+  "<s_no_pkg_ctr>": 57552,
+  "<s_notify_party>": 57534,
+  "<s_original_bol>": 57568,
+  "<s_place_delivery>": 57548,
+  "<s_place_issued>": 57562,
+  "<s_place_receipt>": 57546,
+  "<s_port_discharge>": 57544,
+  "<s_port_loading>": 57542,
+  "<s_shipper>": 57530,
+  "<s_shipping_agent>": 57536,
+  "<s_synthdog>": 57524,
+  "<s_vessel>": 57538,
+  "<s_voy_no>": 57540,
+  "<sep/>": 57522
+}

artifacts.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6024511b43ebaa1b97f57fe0300156c54e409ac60c4c4e7efd963b1b51f0de80
+size 1609232720

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: 
+  - '/content/gdrive/MyDrive/240205_DonutFinetune_BOL/dataset'
+sort_json_key: False
+train_batch_sizes: 
+  - 1
+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: 0
+num_training_samples_per_epoch: 17
+max_epochs: 50
+max_steps: -1
+num_workers: 2
+val_check_interval: 1.0
+check_val_every_n_epoch: 2
+gradient_clip_val: 1.0
+verbose: True
+exp_name: 'train_alliedbol_upd'
+exp_version: '20240205_032742'

events.out.tfevents.1707103717.9c38969d081c.453.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca7dc4188a1060e34ad9520db54960bac82613539ee54ab6abd6c13f32691e6
+size 7117

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_dataset>"
+  ],
+  "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>"
+}