Training in progress, epoch 0

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,
+    "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": 512,
+    "max_position_embeddings": 1536,
+    "model_type": "mbart",
+    "num_hidden_layers": 12,
+    "scale_embedding": true,
+    "use_cache": true,
+    "vocab_size": 57572
+  },
+  "decoder_start_token_id": 41040,
+  "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": [
+      2338,
+      1654
+    ],
+    "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": "4.57.3"
+}

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": "4.57.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:962b6c079e4b2897a0f2f70e928fc3a6caf1d29ae7ce1db008e4e3da72e53376
+size 809263256

runs/Dec22_20-13-45_786cc2b00bdd/events.out.tfevents.1766434450.786cc2b00bdd.6704.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f95d635ca4f952e085a27361dbf1500f3992a57347a08b158b51e1f3d4d1278
+size 6343

runs/Dec22_20-21-40_786cc2b00bdd/events.out.tfevents.1766434902.786cc2b00bdd.6704.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d0deb7ed22f63bdbf87419d28db052cadd6b0742c6fcca8d5d5e74d4acd94ce
+size 6898

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ecb1b7fa27a0fa6fcec26d2f13d44eb9f4d51079334901f8369768c4234d3e
+size 6033