End of training

README.md

@@ -0,0 +1,74 @@
+---
+license: mit
+base_model: naver-clova-ix/donut-base
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+- wer
+model-index:
+- name: donut_experiment_bayesian_trial_20
+  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_experiment_bayesian_trial_20
+
+This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6042
+- Bleu: 0.0711
+- Precisions: [0.8440748440748441, 0.7924528301886793, 0.7493188010899182, 0.7064516129032258]
+- Brevity Penalty: 0.0921
+- Length Ratio: 0.2955
+- Translation Length: 481
+- Reference Length: 1628
+- Cer: 0.7518
+- Wer: 0.8208
+
+## 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: 1.4151037707088747e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Bleu   | Precisions                                                                       | Brevity Penalty | Length Ratio | Translation Length | Reference Length | Cer    | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:--------------------------------------------------------------------------------:|:---------------:|:------------:|:------------------:|:----------------:|:------:|:------:|
+| 0.0012        | 1.0   | 253  | 0.6392          | 0.0724 | [0.8333333333333334, 0.7762237762237763, 0.7365591397849462, 0.6952380952380952] | 0.0954          | 0.2985       | 486                | 1628             | 0.7482 | 0.8193 |
+| 0.0068        | 2.0   | 506  | 0.6212          | 0.0697 | [0.8413361169102297, 0.7867298578199052, 0.7452054794520548, 0.7012987012987013] | 0.0908          | 0.2942       | 479                | 1628             | 0.7527 | 0.8230 |
+| 0.0087        | 3.0   | 759  | 0.6105          | 0.0687 | [0.83125, 0.7706855791962175, 0.726775956284153, 0.6828478964401294]             | 0.0915          | 0.2948       | 480                | 1628             | 0.7573 | 0.8282 |
+| 0.0056        | 4.0   | 1012 | 0.6042          | 0.0711 | [0.8440748440748441, 0.7924528301886793, 0.7493188010899182, 0.7064516129032258] | 0.0921          | 0.2955       | 481                | 1628             | 0.7518 | 0.8208 |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.1.0
+- Datasets 2.18.0
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "</s_address>": 57532,
+  "</s_company>": 57530,
+  "</s_date>": 57528,
+  "</s_total>": 57526,
+  "<s_address>": 57531,
+  "<s_company>": 57529,
+  "<s_date>": 57527,
+  "<s_iitcdip>": 57523,
+  "<s_synthdog>": 57524,
+  "<s_total>": 57525,
+  "<sep/>": 57522
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.40.0"
+}

metrics.jsonl

@@ -1,3 +1,4 @@
 {"eval_loss": 0.6392162442207336, "eval_bleu": 0.0723659134366324, "eval_precisions": [0.8333333333333334, 0.7762237762237763, 0.7365591397849462, 0.6952380952380952], "eval_brevity_penalty": 0.095388787518951, "eval_length_ratio": 0.2985257985257985, "eval_translation_length": 486, "eval_reference_length": 1628, "eval_cer": 0.7481988417781257, "eval_wer": 0.8193477737643206, "eval_runtime": 70.8766, "eval_samples_per_second": 0.804, "eval_steps_per_second": 0.804, "epoch": 1.0}
 {"eval_loss": 0.6211599111557007, "eval_bleu": 0.06965957248797973, "eval_precisions": [0.8413361169102297, 0.7867298578199052, 0.7452054794520548, 0.7012987012987013], "eval_brevity_penalty": 0.09083165866825564, "eval_length_ratio": 0.2942260442260442, "eval_translation_length": 479, "eval_reference_length": 1628, "eval_cer": 0.7526982086438838, "eval_wer": 0.8229917913198584, "eval_runtime": 70.665, "eval_samples_per_second": 0.807, "eval_steps_per_second": 0.807, "epoch": 2.0}
 {"eval_loss": 0.6105175614356995, "eval_bleu": 0.06869034832144602, "eval_precisions": [0.83125, 0.7706855791962175, 0.726775956284153, 0.6828478964401294], "eval_brevity_penalty": 0.09147709493048638, "eval_length_ratio": 0.29484029484029484, "eval_translation_length": 480, "eval_reference_length": 1628, "eval_cer": 0.7573403902679113, "eval_wer": 0.8282259633904325, "eval_runtime": 70.7388, "eval_samples_per_second": 0.806, "eval_steps_per_second": 0.806, "epoch": 3.0}
+{"eval_loss": 0.6041749715805054, "eval_bleu": 0.07106414809351409, "eval_precisions": [0.8440748440748441, 0.7924528301886793, 0.7493188010899182, 0.7064516129032258], "eval_brevity_penalty": 0.09212440522976928, "eval_length_ratio": 0.29545454545454547, "eval_translation_length": 481, "eval_reference_length": 1628, "eval_cer": 0.7518264371980812, "eval_wer": 0.8208459037250544, "eval_runtime": 70.6045, "eval_samples_per_second": 0.807, "eval_steps_per_second": 0.807, "epoch": 4.0}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c204651a0b252c64f5e57161c3b949b4c4b13d72d7e6793d73dde01b5a715bd
+oid sha256:3a0a740eb41dbfde76ae03188d3cdbb0a2f395f09cbd7b494f9e96c98b857ceb
 size 809103512

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
+  ]
+}

runs/Jul01_17-11-13_ip-172-16-165-117.ec2.internal/events.out.tfevents.1719853874.ip-172-16-165-117.ec2.internal.19172.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:861387f51527935eab009e037d1364daf5a46a396cae2cd23b1f3148d847484f
-size 12657
+oid sha256:1628f7aa04fb949a8f6fa1c14dde2b46928e4a9898223351d1b24bd4e21b1b7b
+size 14294

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 +1,123 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<s_total>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s_total>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s_date>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s_date>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s_company>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s_company>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s_address>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s_address>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "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 +1,156 @@
+{
+  "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
+    },
+    "57525": {
+      "content": "<s_total>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57526": {
+      "content": "</s_total>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57527": {
+      "content": "<s_date>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57528": {
+      "content": "</s_date>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57529": {
+      "content": "<s_company>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57530": {
+      "content": "</s_company>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57531": {
+      "content": "<s_address>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57532": {
+      "content": "</s_address>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s_total>",
+    "</s_total>",
+    "<s_date>",
+    "</s_date>",
+    "<s_company>",
+    "</s_company>",
+    "<s_address>",
+    "</s_address>",
+    "<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>"
+}