Training in progress, step 13600

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "OFA-Sys/chinese-clip-vit-base-patch16",
   "architectures": [
     "ChineseCLIPDualTextModel"
   ],
@@ -9,26 +8,55 @@
   "model_type": "chinese_clip",
   "projection_dim": 512,
   "text_config": {
+    "_attn_implementation_autoset": true,
     "architectures": [
       "ChineseCLIPTextModel"
     ],
+    "attention_probs_dropout_prob": 0.1,
     "bos_token_id": 0,
     "directionality": "bidi",
     "eos_token_id": 2,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-12,
+    "max_position_embeddings": 512,
     "model_type": "chinese_clip_text_model",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
     "output_past": true,
     "pooler_fc_size": 768,
     "pooler_num_attention_heads": 12,
     "pooler_num_fc_layers": 3,
     "pooler_size_per_head": 128,
     "pooler_type": "first_token_transform",
+    "position_embedding_type": "absolute",
+    "torch_dtype": "float32",
+    "type_vocab_size": 2,
+    "use_cache": true,
     "vocab_size": 21128
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.45.0",
+  "transformers_version": "4.50.0",
   "vision_config": {
+    "attention_dropout": 0.0,
     "dropout": 0.0,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-05,
     "model_type": "chinese_clip_vision_model",
-    "patch_size": 16
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "projection_dim": 512,
+    "torch_dtype": "float32"
   }
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b82630c8b787df58b407d612433aaf91ed9a2132fda3564c3a9d62367008d21
+oid sha256:8290529a13185094079b8790cfe81ab7b8423a8a83e1eb750610ec9a6a94f765
 size 816611916

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b0180fe093698eb55e17573a57b410ec9e92d7ba108a1a4c3d585a948d09421
-size 5240
+oid sha256:e84f3d31103c491a87c4ddfd45c281d6b93b4b3769b8841dbe516755a9947f4a
+size 5368