End of training

README.md

@@ -0,0 +1,53 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+model-index:
+- name: donut-commoncrawl
+  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-commoncrawl
+
+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: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.25.1
+- Pytorch 1.13.0
+- Datasets 2.11.0
+- Tokenizers 0.13.2

added_tokens.json

@@ -0,0 +1,47 @@
+{
+  "</s_Abstract>\n": 57554,
+  "</s_Address>\n": 57550,
+  "</s_Advertisement>\n": 57564,
+  "</s_Author>\n": 57540,
+  "</s_Caption>\n": 57544,
+  "</s_Field-Name>\n": 57560,
+  "</s_Footer>\n": 57548,
+  "</s_Form>\n": 57566,
+  "</s_Header>\n": 57542,
+  "</s_Headline>\n": 57538,
+  "</s_Link>\n": 57562,
+  "</s_List-item>\n": 57534,
+  "</s_List>\n": 57536,
+  "</s_Metadata>\n": 57558,
+  "</s_Misc>\n": 57532,
+  "</s_Picture>\n": 57530,
+  "</s_Subheadline>\n": 57528,
+  "</s_Table>\n": 57546,
+  "</s_Text>\n": 57526,
+  "</s_Title>\n": 57552,
+  "</s_Value>\n": 57556,
+  "<s_Abstract>\n": 57553,
+  "<s_Address>\n": 57549,
+  "<s_Advertisement>\n": 57563,
+  "<s_Author>\n": 57539,
+  "<s_Caption>\n": 57543,
+  "<s_Field-Name>\n": 57559,
+  "<s_Footer>\n": 57547,
+  "<s_Form>\n": 57565,
+  "<s_Header>\n": 57541,
+  "<s_Headline>\n": 57537,
+  "<s_Link>\n": 57561,
+  "<s_List-item>\n": 57533,
+  "<s_List>\n": 57535,
+  "<s_Metadata>\n": 57557,
+  "<s_Misc>\n": 57531,
+  "<s_Picture>\n": 57529,
+  "<s_Subheadline>\n": 57527,
+  "<s_Table>\n": 57545,
+  "<s_Text>\n": 57525,
+  "<s_Title>\n": 57551,
+  "<s_Value>\n": 57555,
+  "<s_iitcdip>": 57523,
+  "<s_synthdog>": 57524,
+  "<sep/>": 57522
+}

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": [
+    1280,
+    1280
+  ]
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5166393786c097835f06dfafc3cd060f5b0f172a827c5aa32715a73c1a3b7d13
+oid sha256:8e12874ad06d04125ca3c64212869817bffd693dc253ffc428895c57e342edf9
 size 809344217

runs/Apr21_18-27-11_Sebastians-MBP/events.out.tfevents.1682094435.Sebastians-MBP

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:736a382470387a087edb68188e95467658498a42f02501ad64c84d2843e6fac9
-size 8546
+oid sha256:9230da15267fce6086c4c8b36eb05ce0858d7b96011123beb62cedac0c72bcec
+size 9202

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 +1,61 @@
+{
+  "additional_special_tokens": [
+    "<s_Text>\n",
+    "</s_Text>\n",
+    "<s_Subheadline>\n",
+    "</s_Subheadline>\n",
+    "<s_Picture>\n",
+    "</s_Picture>\n",
+    "<s_Misc>\n",
+    "</s_Misc>\n",
+    "<s_List-item>\n",
+    "</s_List-item>\n",
+    "<s_List>\n",
+    "</s_List>\n",
+    "<s_Headline>\n",
+    "</s_Headline>\n",
+    "<s_Author>\n",
+    "</s_Author>\n",
+    "<s_Header>\n",
+    "</s_Header>\n",
+    "<s_Caption>\n",
+    "</s_Caption>\n",
+    "<s_Table>\n",
+    "</s_Table>\n",
+    "<s_Footer>\n",
+    "</s_Footer>\n",
+    "<s_Address>\n",
+    "</s_Address>\n",
+    "<s_Title>\n",
+    "</s_Title>\n",
+    "<s_Abstract>\n",
+    "</s_Abstract>\n",
+    "<s_Value>\n",
+    "</s_Value>\n",
+    "<s_Metadata>\n",
+    "</s_Metadata>\n",
+    "<s_Field-Name>\n",
+    "</s_Field-Name>\n",
+    "<s_Link>\n",
+    "</s_Link>\n",
+    "<s_Advertisement>\n",
+    "</s_Advertisement>\n",
+    "<s_Form>\n",
+    "</s_Form>\n",
+    "<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 +1,22 @@
+{
+  "bos_token": "<s>",
+  "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,
+  "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>"
+}