Training in progress, epoch 1

config.json

@@ -40,7 +40,7 @@
     "use_cache": true,
     "vocab_size": 50304
   },
-  "decoder_start_token_id": 50259,
+  "decoder_start_token_id": 50295,
   "dtype": "float32",
   "encoder": {
     "_name_or_path": "microsoft/dit-base",
@@ -58,7 +58,7 @@
     "hidden_act": "gelu",
     "hidden_dropout_prob": 0.0,
     "hidden_size": 768,
-    "image_size": 1024,
+    "image_size": 896,
     "initializer_range": 0.02,
     "intermediate_size": 3072,
     "layer_norm_eps": 1e-12,
@@ -116,7 +116,7 @@
   "max_length": null,
   "model_type": "vision-encoder-decoder",
   "no_repeat_ngram_size": null,
-  "pad_token_id": 50264,
+  "pad_token_id": 50277,
   "tie_word_embeddings": false,
   "transformers_version": "4.57.6"
 }

generation_config.json

@@ -1,10 +1,10 @@
 {
   "_from_model_config": true,
   "bos_token_id": 50256,
-  "decoder_start_token_id": 50259,
+  "decoder_start_token_id": 50295,
   "eos_token_id": 50256,
   "max_length": 768,
   "no_repeat_ngram_size": 3,
-  "pad_token_id": 50264,
+  "pad_token_id": 50277,
   "transformers_version": "4.57.6"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c97780051d0dd30f9daba5e2eb83bdf58513ac463fbe2cded04c8b957cc497
-size 954658376
+oid sha256:de4ff351b17fa4fc1436cd0c75649f31de5b7244824dca2ffb0570afe2286235
+size 963690056

runs/Jan23_22-03-25_e50fb9337ed9/events.out.tfevents.1769205808.e50fb9337ed9.6028.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e636f4c5f52de3153f8d220cc940f9edc0d871530e21c708276c0bf30387f438
+size 10651

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f56ccddf64c1d8a2df0704456da14c43dce7215564f0f39497f0f0f1c54be306
+oid sha256:97fdfed5c09b275d30b93df5c7c6ff2544adc10df8a9f4da3769f1f46cbbfa6a
 size 5905