Training in progress, epoch 0

config.json

@@ -22,16 +22,16 @@
     "init_std": 0.02,
     "is_decoder": true,
     "is_encoder_decoder": false,
-    "max_length": 768,
-    "max_position_embeddings": 768,
+    "max_length": 1024,
+    "max_position_embeddings": 1536,
     "model_type": "mbart",
     "num_hidden_layers": 12,
     "scale_embedding": true,
     "torch_dtype": "float32",
     "use_cache": true,
-    "vocab_size": 57627
+    "vocab_size": 57572
   },
-  "decoder_start_token_id": 57626,
+  "decoder_start_token_id": 57571,
   "encoder": {
     "attention_probs_dropout_prob": 0.0,
     "depths": [
@@ -46,7 +46,7 @@
     "hidden_dropout_prob": 0.0,
     "hidden_size": 1024,
     "image_size": [
-      1280,
+      960,
       960
     ],
     "initializer_range": 0.02,

generation_config.json

@@ -3,7 +3,7 @@
   "bos_token_id": 0,
   "eos_token_id": 2,
   "forced_eos_token_id": 2,
-  "max_length": 768,
+  "max_length": 1024,
   "pad_token_id": 1,
   "transformers_version": "4.51.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab61ebc6e55a44570085d89e955630b0d8bbd985cd5224a1c4156e9f4dc7418c
-size 806342808
+oid sha256:ddc6ed20531fa637ee73b9a60b269795c1671552a73b120c46b93fbc08be3c53
+size 809263256