Training in progress, step 10

config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "BlipForConditionalGeneration"
+  ],
+  "image_text_hidden_size": 256,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "label_smoothing": 0.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "blip",
+  "projection_dim": 512,
+  "text_config": {
+    "_attn_implementation_autoset": true,
+    "attention_probs_dropout_prob": 0.0,
+    "encoder_hidden_size": 1024,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 768,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "label_smoothing": 0.0,
+    "layer_norm_eps": 1e-12,
+    "max_position_embeddings": 512,
+    "model_type": "blip_text_model",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "projection_dim": 768,
+    "torch_dtype": "float32",
+    "use_cache": true,
+    "vocab_size": 30524
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "vision_config": {
+    "_attn_implementation_autoset": true,
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
+    "image_size": 384,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "layer_norm_eps": 1e-05,
+    "model_type": "blip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "patch_size": 16,
+    "projection_dim": 512,
+    "torch_dtype": "float32"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88e3087804f0708fca3957ca887bbdba30ccfabd2d207a36acd64099ca3e0364
+size 1879010480

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:993059de6346ca6455cc5739f8b476309c27c7363bf918b60b11e542dfafda2e
+size 5368