Training in progress, epoch 0

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "vishnu027/sm_type01051223",
+  "_name_or_path": "naver-clova-ix/donut-base",
   "architectures": [
     "VisionEncoderDecoderModel"
   ],
@@ -85,9 +85,9 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 57542
+    "vocab_size": 57546
   },
-  "decoder_start_token_id": 57541,
+  "decoder_start_token_id": 57545,
   "encoder": {
     "_name_or_path": "",
     "add_cross_attention": false,
@@ -124,8 +124,8 @@
       "1": "LABEL_1"
     },
     "image_size": [
-      1200,
-      800
+      800,
+      1200
     ],
     "initializer_range": 0.02,
     "is_decoder": false,

generation_config.json

@@ -1,7 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 0,
-  "decoder_start_token_id": 57541,
+  "decoder_start_token_id": 57545,
   "eos_token_id": 2,
   "forced_eos_token_id": 2,
   "max_length": 768,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a2608b085256fbb9889812a2e05bd3a6e4b1129b15b8b5de5509b0c4d1c3a16
-size 809140376
+oid sha256:ceaa20f5d8e57ac7728e25fc82c44e4ddd52a0094069a5bc535e5a48959b32d6
+size 809156760