Training in progress, step 1000

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "google/paligemma-3b-pt-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": "4.42.4",
+  "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/Aug23_03-37-03_a1c8a85ee2da/events.out.tfevents.1724384224.a1c8a85ee2da.11260.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fc92fbe00cda0deefcaf2cb154aae842bdb5be3420de93cc898475f62071f06
+size 5211

runs/Aug23_03-38-35_a1c8a85ee2da/events.out.tfevents.1724384315.a1c8a85ee2da.11260.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46b272e6aa01822b66a1bc4f354a1b7e4a2ec6eab00dae1e9fc25529ca87762b
+size 5211

runs/Aug23_03-39-07_a1c8a85ee2da/events.out.tfevents.1724384347.a1c8a85ee2da.11260.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38037bb28e909befcbd59b2831e456062b9dafe0d0e7853eec8075ab8efcfc25
+size 7317

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b4a6ded4b13dafbedbd1699f5a9dd1dc6188c4d7587b380ae9ba70e96a9663
+size 5112