Training in progress, step 500

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "2ndSetAI/clip-from-unclip",
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 512,
+  "text_config": {
+    "_name_or_path": "/root/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2-1-unclip/snapshots/e99f66a92bdcd1b0fb0d4b6a9b81b3b37d8bea44/text_encoder",
+    "architectures": [
+      "CLIPTextModel"
+    ],
+    "bos_token_id": 0,
+    "dropout": 0.0,
+    "eos_token_id": 2,
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "model_type": "clip_text_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 23,
+    "torch_dtype": "float16"
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "vision_config": {
+    "_name_or_path": "/root/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2-1-unclip/snapshots/e99f66a92bdcd1b0fb0d4b6a9b81b3b37d8bea44/image_encoder",
+    "architectures": [
+      "CLIPVisionModelWithProjection"
+    ],
+    "dropout": 0.0,
+    "hidden_act": "gelu",
+    "hidden_size": 1280,
+    "intermediate_size": 5120,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 32,
+    "patch_size": 14,
+    "projection_dim": 1024,
+    "torch_dtype": "float16"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d8d9c1a44ef0a404d94c5b0e8d46d5ece20407ff125397e82039cc591ceb233
+size 3889443916

runs/Aug26_00-17-15_e61355052b78/events.out.tfevents.1724631561.e61355052b78.6644.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b19f8c1081fb83be4878c5540cdb17fc5b73f1717a43ddd29cdf52375a37ced0
+size 5718

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f8d9f13d228f27f19a5bb144db2fd405acdb04d1847c2bf5b4d8cb7d894d1ec
+size 5112