Training in progress, epoch 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": 57525
+  },
+  "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"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:967440b1d99da1f6c00fde73a24c7f48e568a97b0e1a866188b5d6845205d6ad
+size 809070744

runs/Jun09_15-44-56_LAPTOP-ME9G433E/events.out.tfevents.1749451499.LAPTOP-ME9G433E

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e83302bfc370c3e87181e8e26bd7a490e877d846a255a1cb84705c225789309
+size 6146

runs/Jun09_21-38-38_chaeryeong/events.out.tfevents.1749472720.chaeryeong

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef7ae6b252eb7777f12c7ef6ee1482f064aaf25f9b1abf2a93ae5cde17c396cc
+size 7721

runs/Jun10_11-20-05_LAPTOP-ME9G433E/events.out.tfevents.1749522009.LAPTOP-ME9G433E

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59c40dadfad5733dd782445b314f5c8a68103e61782e16c06463cf1fa5bc6e65
+size 6621

runs/Jun10_20-23-09_chaeryeong/events.out.tfevents.1749554591.chaeryeong

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5548fd86f8e78e6f1052d59b35989d0f02bfe6a098c402d106861e7c740028e
+size 53457

runs/Jun11_22-37-58_chaeryeong/events.out.tfevents.1749649080.chaeryeong

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:611bdc572fd0be3b4cae77c635c686eca45c3398a415e842bc3aca6b98a535c5
+size 6143

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a603620bb4ed9810c42585602833955e7bb129e1f909ef2043adc74d93b1f6f
+size 5905