Training in progress, step 200

config.json

@@ -1,44 +1,64 @@
 {
-  "_name_or_path": "/root/.cache/huggingface/hub/OpenAI_Clip_Roco_ALL_V1",
   "architectures": [
-    "CLIPModel"
+    "CustomVisionTextModel"
   ],
-  "initializer_factor": 1.0,
   "logit_scale_init_value": 2.6592,
-  "model_type": "clip",
-  "projection_dim": 512,
+  "model_type": "vision-text-dual-encoder",
+  "projection_dim": 1024,
   "text_config": {
-    "_name_or_path": "/kaggle/working/TextModel",
+    "_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
     "architectures": [
-      "RobertaModel"
+      "LlamaForCausalLM"
     ],
-    "attention_probs_dropout_prob": 0.1,
-    "bos_token_id": 0,
-    "classifier_dropout": null,
-    "eos_token_id": 2,
-    "hidden_act": "gelu",
-    "hidden_dropout_prob": 0.1,
-    "hidden_size": 768,
-    "intermediate_size": 3072,
-    "max_position_embeddings": 1026,
-    "model_type": "clip_text_model",
-    "num_attention_heads": 12,
-    "position_embedding_type": "absolute",
-    "torch_dtype": "float32",
-    "type_vocab_size": 1,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 128000,
+    "eos_token_id": [
+      128001,
+      128008,
+      128009
+    ],
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 3072,
+    "initializer_range": 0.02,
+    "intermediate_size": 8192,
+    "max_position_embeddings": 131072,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 24,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 8,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "factor": 32.0,
+      "high_freq_factor": 4.0,
+      "low_freq_factor": 1.0,
+      "original_max_position_embeddings": 8192,
+      "rope_type": "llama3"
+    },
+    "rope_theta": 500000.0,
+    "tie_word_embeddings": true,
+    "torch_dtype": "bfloat16",
     "use_cache": true,
-    "vocab_size": 50265
+    "vocab_size": 128256
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.44.0",
+  "transformers_version": "4.52.4",
   "vision_config": {
-    "_name_or_path": "openai/clip-vit-large-patch14-336",
+    "attention_dropout": 0.0,
     "dropout": 0.0,
+    "hidden_act": "quick_gelu",
     "hidden_size": 1024,
     "image_size": 336,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
     "intermediate_size": 4096,
+    "layer_norm_eps": 1e-05,
     "model_type": "clip_vision_model",
     "num_attention_heads": 16,
+    "num_channels": 3,
     "num_hidden_layers": 24,
     "patch_size": 14,
     "projection_dim": 768

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c45dfc162774ddbec26ef765bf4bd84758c88e2ec06c30ee07bdd1b393ba98c
-size 1715561468
+oid sha256:a8e1d29c30ce74c9631203df66094201e3f170e3df25fdaf282660f4b423e9fc
+size 2410717252

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cc20bec6f924b34961dab5381cd049283537f937818f0168241e5becc4862f0
-size 5240
+oid sha256:00d28d176492d90cb5ed9c6500071e63972afe80ff0b7f0460ddd136ecc10a5c
+size 5368