Training in progress, epoch 1

config.json

@@ -1,24 +1,77 @@
 {
-  "_name_or_path": "/content/result/train_cord_finetune/20250713_170309",
-  "align_long_axis": false,
   "architectures": [
-    "DonutModel"
+    "VisionEncoderDecoderModel"
   ],
-  "decoder_layer": 4,
-  "encoder_layer": [
-    2,
-    2,
-    14,
-    2
-  ],
-  "input_size": [
-    1280,
-    960
-  ],
-  "max_length": 768,
-  "max_position_embeddings": 768,
-  "model_type": "donut",
+  "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": 57533
+  },
+  "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": "4.25.1",
-  "window_size": 10
+  "transformers_version": "4.53.2"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3609459862e62998c5d104d4359666e9a2a475fd53702de774caced4be50c68
+size 809103512

runs/Jul24_05-40-50_6919c5791bc4/events.out.tfevents.1753335651.6919c5791bc4.1026.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b31865a7a43536ef0a43f8a1e611bf1ee5648f772b3d00a1f24b50d6500942a0
+size 6231

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f95c2a6a13653a71455d2ad04a9f2d9fdd135e55349361744b70e9f6c0158246
+size 5496