End of training

README.md

@@ -0,0 +1,117 @@
+---
+license: mit
+base_model: naver-clova-ix/donut-base
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+model-index:
+- name: donut-base-eco_v3
+  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-eco_v3
+
+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.
+It achieves the following results on the evaluation set:
+- Loss: 1.1236
+
+## 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: 4
+- 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
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 5.7637        | 0.05  | 10   | 4.3966          |
+| 4.7131        | 0.1   | 20   | 3.4323          |
+| 3.6024        | 0.15  | 30   | 2.7923          |
+| 2.8768        | 0.2   | 40   | 2.4152          |
+| 3.0689        | 0.25  | 50   | 2.2683          |
+| 2.4879        | 0.3   | 60   | 2.0826          |
+| 2.3029        | 0.35  | 70   | 1.9588          |
+| 2.2746        | 0.4   | 80   | 1.8516          |
+| 2.7149        | 0.45  | 90   | 1.7636          |
+| 2.1114        | 0.51  | 100  | 1.7028          |
+| 2.2623        | 0.56  | 110  | 1.6586          |
+| 1.826         | 0.61  | 120  | 1.5988          |
+| 2.0984        | 0.66  | 130  | 1.5454          |
+| 1.4917        | 0.71  | 140  | 1.5161          |
+| 1.4414        | 0.76  | 150  | 1.4859          |
+| 1.9446        | 0.81  | 160  | 1.4424          |
+| 1.923         | 0.86  | 170  | 1.4239          |
+| 1.5272        | 0.91  | 180  | 1.4003          |
+| 1.8752        | 0.96  | 190  | 1.3695          |
+| 1.1883        | 1.01  | 200  | 1.3520          |
+| 1.432         | 1.06  | 210  | 1.3340          |
+| 1.6104        | 1.11  | 220  | 1.3292          |
+| 1.3261        | 1.16  | 230  | 1.3174          |
+| 1.3727        | 1.21  | 240  | 1.3024          |
+| 1.6194        | 1.26  | 250  | 1.2777          |
+| 1.6811        | 1.31  | 260  | 1.2793          |
+| 1.3327        | 1.36  | 270  | 1.2636          |
+| 1.2379        | 1.41  | 280  | 1.2492          |
+| 1.8061        | 1.46  | 290  | 1.2423          |
+| 1.6403        | 1.52  | 300  | 1.2333          |
+| 1.5277        | 1.57  | 310  | 1.2245          |
+| 1.8438        | 1.62  | 320  | 1.2114          |
+| 1.6035        | 1.67  | 330  | 1.2127          |
+| 1.4338        | 1.72  | 340  | 1.2061          |
+| 1.4517        | 1.77  | 350  | 1.1997          |
+| 1.7217        | 1.82  | 360  | 1.1891          |
+| 1.1229        | 1.87  | 370  | 1.1836          |
+| 1.2508        | 1.92  | 380  | 1.1767          |
+| 1.0494        | 1.97  | 390  | 1.1726          |
+| 1.3746        | 2.02  | 400  | 1.1710          |
+| 0.8878        | 2.07  | 410  | 1.1708          |
+| 1.4181        | 2.12  | 420  | 1.1642          |
+| 1.1233        | 2.17  | 430  | 1.1627          |
+| 1.4889        | 2.22  | 440  | 1.1654          |
+| 1.4098        | 2.27  | 450  | 1.1592          |
+| 1.4169        | 2.32  | 460  | 1.1526          |
+| 1.3255        | 2.37  | 470  | 1.1470          |
+| 1.4087        | 2.42  | 480  | 1.1449          |
+| 0.9108        | 2.47  | 490  | 1.1455          |
+| 1.4604        | 2.53  | 500  | 1.1425          |
+| 1.47          | 2.58  | 510  | 1.1334          |
+| 1.4215        | 2.63  | 520  | 1.1313          |
+| 1.2907        | 2.68  | 530  | 1.1285          |
+| 1.2292        | 2.73  | 540  | 1.1273          |
+| 1.3936        | 2.78  | 550  | 1.1261          |
+| 1.1875        | 2.83  | 560  | 1.1250          |
+| 1.4496        | 2.88  | 570  | 1.1245          |
+| 1.3273        | 2.93  | 580  | 1.1239          |
+| 1.4324        | 2.98  | 590  | 1.1236          |
+
+
+### Framework versions
+
+- Transformers 4.39.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<s_iitcdip>": 57523,
+  "<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": "4.39.2"
+}

preprocessor_config.json

@@ -0,0 +1,44 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_thumbnail",
+    "do_align_long_axis",
+    "do_pad",
+    "random_padding",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "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
+  ]
+}

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 +1,67 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,84 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57521": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57522": {
+      "content": "<sep/>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57523": {
+      "content": "<s_iitcdip>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57524": {
+      "content": "<s_synthdog>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "DonutProcessor",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}