End of training

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+model-index:
+- name: donut-base-finetuned-Latvian-receipts-v2
+  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-base-finetuned-Latvian-receipts-v2
+
+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
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.26.1
+- Pytorch 1.13.1+cu116
+- Datasets 2.10.1
+- Tokenizers 0.13.2

added_tokens.json

@@ -0,0 +1,20 @@
+{
+  "</s_PVN_maksataja_numurs>": 57539,
+  "</s_datums>": 57537,
+  "</s_laiks>": 57535,
+  "</s_nosaukums>": 57533,
+  "</s_receipt_nr>": 57531,
+  "</s_summa>": 57529,
+  "<s_PVN_maksataja_numurs>": 57538,
+  "<s_datums>": 57536,
+  "<s_iitcdip>": 57523,
+  "<s_laiks>": 57534,
+  "<s_nosaukums>": 57532,
+  "<s_receipt_nr>": 57530,
+  "<s_summa>": 57528,
+  "<s_synthdog>": 57524,
+  "<sep/>": 57522,
+  "ķ": 57525,
+  "ļ": 57526,
+  "ņ": 57527
+}

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": "4.26.1"
+}

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
+  ]
+}

runs/Mar13_15-46-22_3a6c3faecf36/events.out.tfevents.1678722429.3a6c3faecf36.318.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc6a333184d79558fb3ac1b67c5a52db7af78d7bac9ea470b6d90e56006495f
-size 9354
+oid sha256:3b85dbc2e5a403edd6aee47ee2e85f8359251cc299e4bc84daae1655549f3dee
+size 9708

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_summa>",
+    "</s_summa>",
+    "<s_receipt_nr>",
+    "</s_receipt_nr>",
+    "<s_nosaukums>",
+    "</s_nosaukums>",
+    "<s_laiks>",
+    "</s_laiks>",
+    "<s_datums>",
+    "</s_datums>",
+    "<s_PVN_maksataja_numurs>",
+    "</s_PVN_maksataja_numurs>",
+    "<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>"
+}