Training in progress, step 500

config.json

@@ -14,16 +14,18 @@
     "_attn_implementation_autoset": true,
     "initializer_factor": 1.0,
     "model_type": "blip_text_model",
-    "num_attention_heads": 12
+    "num_attention_heads": 12,
+    "torch_dtype": "float32"
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.48.2",
+  "transformers_version": "4.49.0",
   "vision_config": {
     "_attn_implementation_autoset": true,
     "dropout": 0.0,
     "initializer_factor": 1.0,
     "initializer_range": 0.02,
     "model_type": "blip_vision_model",
-    "num_channels": 3
+    "num_channels": 3,
+    "torch_dtype": "float32"
   }
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c784363f3f545f9216ef90c16e41bfa9e2b57309972ba72cb2cb73999ae55c91
+oid sha256:f3cc0f1824b327dee1bdac2e10ed11216e178f666f9d69d6bfe4a7301f836756
 size 989717056

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07e3c5d72232c38a1f721b3429bbed38747bf930c90b9a8066b9c09657c0bb1e
+oid sha256:5fe2da682ffd1626c3476d31413efcf2d07aa73d5c6581465fe4ccdd3803a707
 size 5304