Model save

README.md

@@ -0,0 +1,64 @@
+---
+library_name: transformers
+license: mit
+base_model: hf-tuner/donut-efficient-test2
+tags:
+- generated_from_trainer
+model-index:
+- name: donut-classification-turbo
+  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-classification-turbo
+
+This model is a fine-tuned version of [hf-tuner/donut-efficient-test2](https://huggingface.co/hf-tuner/donut-efficient-test2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0499
+
+## 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_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.1319        | 0.5   | 2000  | 0.1200          |
+| 0.1365        | 1.0   | 4000  | 0.0845          |
+| 0.1203        | 1.5   | 6000  | 0.0751          |
+| 0.1128        | 2.0   | 8000  | 0.0677          |
+| 0.0734        | 2.5   | 10000 | 0.0541          |
+| 0.0707        | 3.0   | 12000 | 0.0499          |
+
+
+### Framework versions
+
+- Transformers 4.56.1
+- Pytorch 2.8.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,77 @@
+{
+  "architectures": [
+    "DonutModel"
+  ],
+  "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,
+    "dtype": "float32",
+    "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": 8,
+    "max_position_embeddings": 8,
+    "model_type": "mbart",
+    "num_hidden_layers": 12,
+    "scale_embedding": true,
+    "use_cache": true,
+    "vocab_size": 57542
+  },
+  "decoder_start_token_id": 57541,
+  "dtype": "float32",
+  "encoder": {
+    "attention_probs_dropout_prob": 0.0,
+    "depths": [
+      2,
+      2,
+      14,
+      2
+    ],
+    "drop_path_rate": 0.1,
+    "dtype": "float32",
+    "embed_dim": 128,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 1024,
+    "image_size": [
+      1280,
+      960
+    ],
+    "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,
+    "use_absolute_embeddings": false,
+    "window_size": 10
+  },
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 1,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.1"
+}

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": "4.56.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f86291b4e46679f72c7accad916ee474c5f7ce8659eff316198d758a6ea61f
+size 802881688

runs/Oct14_02-42-34_2fe5d31d5bed/events.out.tfevents.1760409766.2fe5d31d5bed.1264.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21297eeecfd40c0d96c7b89d55fb7f02790ea2c49db6a6018ec19cbda28606ce
+size 27321

runs/Oct14_02-44-39_2fe5d31d5bed/events.out.tfevents.1760409885.2fe5d31d5bed.1264.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ee63751b61d2605501749bb0afee3f3e85a4451172e8f9fbc0e69136966bf48
+size 27321

runs/Oct14_02-46-48_2fe5d31d5bed/events.out.tfevents.1760410012.2fe5d31d5bed.1264.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e595e184d57369f0b2f0d6caaddb32b57c4182a259182ff11ffcfcd33e4718f9
+size 27321

runs/Oct14_03-10-38_2fe5d31d5bed/events.out.tfevents.1760411453.2fe5d31d5bed.9200.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:023c3f0151edac2fd39c0f493cefc796253cbeac6735c2381a35e9934585c62e
+size 13277

runs/Oct14_03-37-17_2fe5d31d5bed/events.out.tfevents.1760413049.2fe5d31d5bed.16145.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25057706c073418b52954a620f913de5129af7d6ffc13de9ed454f3db98c0a79
+size 33554

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9e625e4fc34939ba3f668eabdd34d7d8f7f74b5656395fc2096e6d9f8ea414e
+size 5905