End of training

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+license: mit
+base_model: naver-clova-ix/donut-base
+tags:
+- generated_from_trainer
+model-index:
+- name: donut_checkpoints
+  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_checkpoints
+
+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: 0.7296
+
+## 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: 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: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 4.0573        | 1.0   | 250  | 1.4718          |
+| 0.6312        | 2.0   | 500  | 0.7169          |
+| 0.2924        | 3.0   | 750  | 0.6494          |
+| 0.1544        | 4.0   | 1000 | 0.6331          |
+| 0.0682        | 5.0   | 1250 | 0.7624          |
+| 0.0562        | 6.0   | 1500 | 0.7330          |
+| 0.027         | 7.0   | 1750 | 0.7246          |
+| 0.0076        | 8.0   | 2000 | 0.6950          |
+| 0.0069        | 9.0   | 2250 | 0.7208          |
+| 0.008         | 10.0  | 2500 | 0.7296          |
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.6.0+cu124
+- Datasets 2.14.4
+- Tokenizers 0.21.1

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": 512,
+    "max_position_embeddings": 1536,
+    "model_type": "mbart",
+    "num_hidden_layers": 12,
+    "scale_embedding": true,
+    "torch_dtype": "float32",
+    "use_cache": true,
+    "vocab_size": 57529
+  },
+  "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": [
+      960,
+      720
+    ],
+    "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:b3285cff1052f2c808a3d33bee80336021296a8809a11701871a9879bd80908e
+size 809087128

runs/Jun21_17-28-39_46460c7ba23f/events.out.tfevents.1750527003.46460c7ba23f.453.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84a6eadd26a7bba61a839b48cd0f46a835e4e535a44b9635cf9161126477f960
+size 14586

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c25ddc2f2e6febed9f12b84fa0efa1b31f66d0bdb51ebbe84f400fdbcb808448
+size 5496