Training in progress, epoch 0

config.json

@@ -87,9 +87,9 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 57525
+    "vocab_size": 57615
   },
-  "decoder_start_token_id": 0,
+  "decoder_start_token_id": 3,
   "encoder": {
     "_name_or_path": "",
     "add_cross_attention": false,
@@ -126,7 +126,7 @@
       "1": "LABEL_1"
     },
     "image_size": [
-      792,
+      729,
       612
     ],
     "initializer_range": 0.02,

generation_config.json

@@ -1,8 +1,10 @@
 {
   "_from_model_config": true,
   "bos_token_id": 0,
+  "decoder_start_token_id": 3,
   "eos_token_id": 2,
   "forced_eos_token_id": 2,
+  "max_length": 512,
   "pad_token_id": 1,
   "transformers_version": "4.28.0"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfc44bd18150429f3fe9a57986880c953baad429ff760340439987f41329037e
-size 809172185
+oid sha256:7e515cae4889692a5ae477f66bce00032567b992d25958c0a70aeda9315d51b6
+size 809547545