End of training

README.md

@@ -1,3 +1,54 @@
 ---
-license: artistic-2.0
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+model-index:
+- name: donut_pdf_ocr
+  results: []
 ---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# donut_pdf_ocr
+
+This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 30
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.28.1
+- Pytorch 2.0.0+cu118
+- Datasets 2.11.0
+- Tokenizers 0.13.3

added_tokens.json

@@ -0,0 +1,17 @@
+{
+  "</s_admit_date>": 57536,
+  "</s_discharge_date>": 57534,
+  "</s_discharge_diagnosis>": 57532,
+  "</s_gender>": 57530,
+  "</s_patient_id>": 57528,
+  "</s_patient_name>": 57526,
+  "<s_admit_date>": 57535,
+  "<s_discharge_date>": 57533,
+  "<s_discharge_diagnosis>": 57531,
+  "<s_gender>": 57529,
+  "<s_iitcdip>": 57523,
+  "<s_patient_id>": 57527,
+  "<s_patient_name>": 57525,
+  "<s_synthdog>": 57524,
+  "<sep/>": 57522
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.28.1"
+}

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_align_long_axis": false,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_thumbnail": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "DonutImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "DonutProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": [
+    720,
+    960
+  ]
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45f7bcb20d921aa3dc94d97623c8b26affc19ac92befac82942957d0d9df4498
+oid sha256:345edecf4051d700cc8370ae9fc46d83a97a68b11bd91a1f115eca638385a1f0
 size 809228057

runs/Apr17_14-15-34_7bfb0267266a/events.out.tfevents.1681740951.7bfb0267266a.318.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97e713214a50c14f52e56354a62b47a10a7e6382d04ac8f1c70e7a71fe4b73b8
-size 8873
+oid sha256:5433869bb15b8210a7e3e594e2c55a2093c52d8f737379a2618ed812d96c8d9d
+size 9227

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 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<s_patient_name>",
+    "</s_patient_name>",
+    "<s_patient_id>",
+    "</s_patient_id>",
+    "<s_gender>",
+    "</s_gender>",
+    "<s_discharge_diagnosis>",
+    "</s_discharge_diagnosis>",
+    "<s_discharge_date>",
+    "</s_discharge_date>",
+    "<s_admit_date>",
+    "</s_admit_date>",
+    "<s>",
+    "</s>"
+  ],
+  "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 +1,21 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "DonutProcessor",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}