Training in progress, step 500

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": "4.52.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d43cef7a312dbf96c82d53ed0c32bf9959d253235a45d5449ede24b0b2548093
+size 809070744

runs/May30_17-34-37_phi-ThinkPad-T490/events.out.tfevents.1748619277.phi-ThinkPad-T490

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6a71084c9d0dad4618667de1b4bf3092bef33964f4c805fa3b8f6f4083d8a1c
+size 6168

runs/May30_18-19-56_phi-ThinkPad-T490/events.out.tfevents.1748621996.phi-ThinkPad-T490

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea014a8d70f87dd4bb531d116a00fe0e6f53cbd7cd50dd492059b01dd5a9b19
+size 6168

runs/May30_18-20-23_phi-ThinkPad-T490/events.out.tfevents.1748622023.phi-ThinkPad-T490

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3187faf55520732211e8f96b2bb69beb309f0fbf4b73e1885fc4d194e2f59d20
+size 6168

runs/May30_18-22-10_phi-ThinkPad-T490/events.out.tfevents.1748622131.phi-ThinkPad-T490

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f9bc50d5e4f39fcc7abc5ef0db61cac95c3de944a49aa9e7092e381e42647ba
+size 6168

runs/May30_18-22-52_phi-ThinkPad-T490/events.out.tfevents.1748622175.phi-ThinkPad-T490

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77656b339e84c4910cc149fcbba5c1bab7acacf6b8322cd07fd7be6ae4b2dc0b
+size 6168

runs/May30_18-25-10_phi-ThinkPad-T490/events.out.tfevents.1748622311.phi-ThinkPad-T490

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca52a9575337ea27a49430eb76736ffe4202042c741e9bade51b81034e5a332f
+size 7008

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5838ffec63ee86579655914addb1770a1ae8800c0395b6d2a1273e7cac26289d
+size 5496