Training in progress, step 200

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "laion/clap-htsat-unfused",
+  "architectures": [
+    "ClapModel"
+  ],
+  "audio_config": {
+    "fusion_num_hidden_layers": 2,
+    "model_type": "clap_audio_model",
+    "projection_hidden_size": 768
+  },
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 14.285714285714285,
+  "model_type": "clap",
+  "num_hidden_layers": 16,
+  "projection_dim": 512,
+  "projection_hidden_act": "relu",
+  "text_config": {
+    "classifier_dropout": null,
+    "fusion_hidden_size": 768,
+    "fusion_num_hidden_layers": 2,
+    "initializer_range": 0.02,
+    "model_type": "clap_text_model",
+    "projection_hidden_size": 768
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee0e77451967f9207b020756ec0856be43d303570e343c88f0dc2bc51ddbe10d
+size 614431440

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af22e948da03cf2ae1e4879b1404fe263ba7868a7edba74127847c530174828
+size 5176