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_15
+  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_15
+
+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: 0.5777
+- Bleu: 0.0659
+- Precisions: [0.8158995815899581, 0.7434679334916865, 0.7060439560439561, 0.6644951140065146]
+- Brevity Penalty: 0.0902
+- Length Ratio: 0.2936
+- Translation Length: 478
+- Reference Length: 1628
+- Cer: 0.7557
+- Wer: 0.8239
+
+## 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: 2.349414650597281e-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    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:--------------------------------------------------------------------------------:|:---------------:|:------------:|:------------------:|:----------------:|:------:|:------:|
+| 0.0066        | 1.0   | 253  | 0.5790          | 0.0648 | [0.8305084745762712, 0.7686746987951807, 0.7262569832402235, 0.6843853820598007] | 0.0864          | 0.2899       | 472                | 1628             | 0.7593 | 0.8258 |
+| 0.0143        | 2.0   | 506  | 0.5824          | 0.0663 | [0.8225469728601252, 0.7511848341232228, 0.7041095890410959, 0.6525974025974026] | 0.0908          | 0.2942       | 479                | 1628             | 0.7577 | 0.8265 |
+| 0.009         | 3.0   | 759  | 0.5826          | 0.0640 | [0.8185654008438819, 0.7458033573141487, 0.7055555555555556, 0.6600660066006601] | 0.0876          | 0.2912       | 474                | 1628             | 0.7553 | 0.8248 |
+| 0.0103        | 4.0   | 1012 | 0.5777          | 0.0659 | [0.8158995815899581, 0.7434679334916865, 0.7060439560439561, 0.6644951140065146] | 0.0902          | 0.2936       | 478                | 1628             | 0.7557 | 0.8239 |
+
+
+### 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": 0.5789960622787476, "eval_bleu": 0.06482103941320627, "eval_precisions": [0.8305084745762712, 0.7686746987951807, 0.7262569832402235, 0.6843853820598007], "eval_brevity_penalty": 0.0863667476535313, "eval_length_ratio": 0.28992628992628994, "eval_translation_length": 472, "eval_reference_length": 1628, "eval_cer": 0.7593265153712586, "eval_wer": 0.8257710508514611, "eval_runtime": 75.3465, "eval_samples_per_second": 0.757, "eval_steps_per_second": 0.757, "epoch": 1.0}
 {"eval_loss": 0.5823678374290466, "eval_bleu": 0.0663033580756366, "eval_precisions": [0.8225469728601252, 0.7511848341232228, 0.7041095890410959, 0.6525974025974026], "eval_brevity_penalty": 0.09083165866825564, "eval_length_ratio": 0.2942260442260442, "eval_translation_length": 479, "eval_reference_length": 1628, "eval_cer": 0.7577143653495245, "eval_wer": 0.8265038770690519, "eval_runtime": 75.1287, "eval_samples_per_second": 0.759, "eval_steps_per_second": 0.759, "epoch": 2.0}
 {"eval_loss": 0.5826367139816284, "eval_bleu": 0.06399058729917449, "eval_precisions": [0.8185654008438819, 0.7458033573141487, 0.7055555555555556, 0.6600660066006601], "eval_brevity_penalty": 0.08763286710738645, "eval_length_ratio": 0.29115479115479115, "eval_translation_length": 474, "eval_reference_length": 1628, "eval_cer": 0.755257589739948, "eval_wer": 0.824832117260173, "eval_runtime": 75.5329, "eval_samples_per_second": 0.755, "eval_steps_per_second": 0.755, "epoch": 3.0}
+{"eval_loss": 0.5777499675750732, "eval_bleu": 0.0658726113029137, "eval_precisions": [0.8158995815899581, 0.7434679334916865, 0.7060439560439561, 0.6644951140065146], "eval_brevity_penalty": 0.0901881044262292, "eval_length_ratio": 0.2936117936117936, "eval_translation_length": 478, "eval_reference_length": 1628, "eval_cer": 0.7557476570766476, "eval_wer": 0.8239087562260087, "eval_runtime": 75.9453, "eval_samples_per_second": 0.751, "eval_steps_per_second": 0.751, "epoch": 4.0}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6915f193440adbf77beb99f61319ee32d838ed77f996800c9d351e19901fb860
+oid sha256:2ddfa801fa6c3a3c7ec91e123557e04d053bd74d2de5b7494f1539845902ef6e
 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/Jun26_17-01-38_ip-172-16-186-191.ec2.internal/events.out.tfevents.1719421298.ip-172-16-186-191.ec2.internal.9592.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1452ea881cbca7563ee32e8d231d7666a354ae11b5dcb1b7783cfb9026677fc
-size 12658
+oid sha256:a402e532a00c59f04c9f2f1e962d5ca8d0945f6394709d26d0dae69201bd3709
+size 14295

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>"
+}