Training in progress, step 213

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Salesforce/blip-image-captioning-base",
+  "architectures": [
+    "BlipForConditionalGeneration"
+  ],
+  "decoder_start_token_id": 101,
+  "image_text_hidden_size": 256,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "logit_scale_init_value": 2.6592,
+  "max_length": 50,
+  "model_type": "blip",
+  "pad_token_id": 0,
+  "projection_dim": 512,
+  "text_config": {
+    "initializer_factor": 1.0,
+    "model_type": "blip_text_model",
+    "num_attention_heads": 12
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "vision_config": {
+    "dropout": 0.0,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "model_type": "blip_vision_model",
+    "num_channels": 3
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f3cc048a345783f1764efd5a6a54173494d3e745559d81e4029137230c0bdbd
+size 989717056

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef428d2491921efffd5cfc9ebe86644b8416b7df0e4e27e164024e3cc975a3d
+size 4664