Training in progress, step 70

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "google/paligemma-3b-mix-224",
+  "architectures": [
+    "PaliGemmaForConditionalGeneration"
+  ],
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "hidden_size": 2048,
+  "ignore_index": -100,
+  "image_token_index": 257152,
+  "model_type": "paligemma",
+  "pad_token_id": 0,
+  "projection_dim": 2048,
+  "text_config": {
+    "hidden_size": 2048,
+    "intermediate_size": 16384,
+    "model_type": "gemma",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 18,
+    "num_image_tokens": 256,
+    "num_key_value_heads": 1,
+    "torch_dtype": "float32",
+    "vocab_size": 257216
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.0.dev0",
+  "vision_config": {
+    "hidden_size": 1152,
+    "intermediate_size": 4304,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "num_image_tokens": 256,
+    "patch_size": 14,
+    "projection_dim": 2048,
+    "projector_hidden_act": "gelu_fast",
+    "vision_use_head": false
+  },
+  "vocab_size": 257216
+}

runs/Jun30_00-32-13_c8711203a466/events.out.tfevents.1719707540.c8711203a466.4939.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:938e2a68892acdb955d9999bdabc0b4d23a9a6e87323cc28dd1d24e42fd24e21
+size 5665

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:703157cd3b3bd774dd00a3b68171759fb736daa7d7f5fe97744c75286fc4a00c
+size 5176