Training done

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "google/pix2struct-base",
+  "architectures": [
+    "Pix2StructForConditionalGeneration"
+  ],
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "is_encoder_decoder": true,
+  "is_vqa": false,
+  "model_type": "pix2struct",
+  "pad_token_id": 0,
+  "text_config": {
+    "_attn_implementation_autoset": true,
+    "dropout_rate": 0.2,
+    "encoder_hidden_size": 768,
+    "initializer_range": 0.02,
+    "is_encoder_decoder": true,
+    "model_type": "pix2struct_text_model",
+    "vocab_size": 50388
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "vision_config": {
+    "_attn_implementation_autoset": true,
+    "attention_dropout": 0.2,
+    "dropout_rate": 0.2,
+    "hidden_dropout_prob": 0.2,
+    "initializer_range": 0.02,
+    "layer_norm_bias": false,
+    "model_type": "pix2struct_vision_model",
+    "num_channels": 3,
+    "patch_size": 16,
+    "projection_dim": 768
+  }
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6100dbf5e06878e09587e4e55473c48b802529c954e5bc3b075e976627c654a
+size 1130062712