Model save

README.md

@@ -0,0 +1,58 @@
+---
+library_name: transformers
+license: mit
+base_model: naver-clova-ix/donut-base
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+model-index:
+- name: donut-paper-ktp
+  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-paper-ktp
+
+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:
+- eval_loss: 9.1576
+- eval_runtime: 9.5484
+- eval_samples_per_second: 0.524
+- eval_steps_per_second: 0.105
+- epoch: 1.0
+- step: 20
+
+## 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: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.2

best_f1_checkpoint/config.json

@@ -0,0 +1,77 @@
+{
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": true,
+    "add_final_layer_norm": true,
+    "attention_dropout": 0.0,
+    "classifier_dropout": 0.0,
+    "d_model": 1024,
+    "decoder_attention_heads": 16,
+    "decoder_ffn_dim": 4096,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 4,
+    "dropout": 0.1,
+    "encoder_attention_heads": 16,
+    "encoder_ffn_dim": 4096,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 12,
+    "init_std": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "max_length": 522,
+    "max_position_embeddings": 1536,
+    "model_type": "mbart",
+    "num_hidden_layers": 12,
+    "scale_embedding": true,
+    "torch_dtype": "float32",
+    "use_cache": true,
+    "vocab_size": 57559
+  },
+  "decoder_start_token_id": 0,
+  "encoder": {
+    "attention_probs_dropout_prob": 0.0,
+    "depths": [
+      2,
+      2,
+      14,
+      2
+    ],
+    "drop_path_rate": 0.1,
+    "embed_dim": 128,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 1024,
+    "image_size": [
+      768,
+      1024
+    ],
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-05,
+    "mlp_ratio": 4.0,
+    "model_type": "donut-swin",
+    "num_channels": 3,
+    "num_heads": [
+      4,
+      8,
+      16,
+      32
+    ],
+    "num_layers": 4,
+    "patch_size": 4,
+    "path_norm": true,
+    "qkv_bias": true,
+    "torch_dtype": "float32",
+    "use_absolute_embeddings": false,
+    "window_size": 10
+  },
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 1,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4"
+}

best_f1_checkpoint/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": "4.52.4"
+}

best_f1_checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ba95d33916a792467fb216c9d41b9996ac8111fa75eadc1e8b87c176818c907
+size 809210008

best_f1_checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb7f18c87d5897f22b9849880459e6eb82c45cf99f8b0c82528e3ba71e023bf1
+size 5496

config.json

@@ -0,0 +1,77 @@
+{
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": true,
+    "add_final_layer_norm": true,
+    "attention_dropout": 0.0,
+    "classifier_dropout": 0.0,
+    "d_model": 1024,
+    "decoder_attention_heads": 16,
+    "decoder_ffn_dim": 4096,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 4,
+    "dropout": 0.1,
+    "encoder_attention_heads": 16,
+    "encoder_ffn_dim": 4096,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 12,
+    "init_std": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "max_length": 522,
+    "max_position_embeddings": 1536,
+    "model_type": "mbart",
+    "num_hidden_layers": 12,
+    "scale_embedding": true,
+    "torch_dtype": "float32",
+    "use_cache": true,
+    "vocab_size": 57559
+  },
+  "decoder_start_token_id": 0,
+  "encoder": {
+    "attention_probs_dropout_prob": 0.0,
+    "depths": [
+      2,
+      2,
+      14,
+      2
+    ],
+    "drop_path_rate": 0.1,
+    "embed_dim": 128,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 1024,
+    "image_size": [
+      768,
+      1024
+    ],
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-05,
+    "mlp_ratio": 4.0,
+    "model_type": "donut-swin",
+    "num_channels": 3,
+    "num_heads": [
+      4,
+      8,
+      16,
+      32
+    ],
+    "num_layers": 4,
+    "patch_size": 4,
+    "path_norm": true,
+    "qkv_bias": true,
+    "torch_dtype": "float32",
+    "use_absolute_embeddings": false,
+    "window_size": 10
+  },
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 1,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4"
+}

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": "4.52.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ba95d33916a792467fb216c9d41b9996ac8111fa75eadc1e8b87c176818c907
+size 809210008

runs/Jul01_03-28-00_c3219657bfc3/events.out.tfevents.1751340488.c3219657bfc3.727.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d862e78499b5caa4b4bed4d11f5b3b9473285dde9e1f210b4e7874e3e25e118
+size 6481

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb7f18c87d5897f22b9849880459e6eb82c45cf99f8b0c82528e3ba71e023bf1
+size 5496