End of training

all_results.json

@@ -1,4 +1,9 @@
 {
+    "eval_loss": 3.6843419075012207,
+    "eval_runtime": 378.7783,
+    "eval_samples": 15692,
+    "eval_samples_per_second": 41.428,
+    "eval_steps_per_second": 1.296,
     "total_flos": 1.355217425276076e+18,
     "train_loss": 2.8033093200847907,
     "train_runtime": 20478.1713,

config.json

@@ -0,0 +1,55 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "google/paligemma2-3b-pt-224",
+  "_vocab_size": 257152,
+  "architectures": [
+    "PaliGemmaForConditionalGeneration"
+  ],
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "hidden_size": 2048,
+  "image_token_index": 257152,
+  "model_type": "paligemma",
+  "num_hidden_layers": 26,
+  "pad_token_id": 0,
+  "projection_dim": 2304,
+  "text_config": {
+    "architectures": [
+      "Gemma2ForCausalLM"
+    ],
+    "attn_logit_softcapping": 50.0,
+    "cache_implementation": "hybrid",
+    "eos_token_id": [
+      1,
+      107
+    ],
+    "final_logit_softcapping": 30.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 2304,
+    "intermediate_size": 9216,
+    "model_type": "gemma2",
+    "num_hidden_layers": 26,
+    "num_image_tokens": 256,
+    "num_key_value_heads": 4,
+    "query_pre_attn_scalar": 256,
+    "sliding_window": 4096,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 257216
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "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,
+    "num_positions": 256,
+    "patch_size": 14,
+    "projection_dim": 2304,
+    "torch_dtype": "bfloat16",
+    "vision_use_head": false
+  }
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "eval_loss": 3.6843419075012207,
+    "eval_runtime": 378.7783,
+    "eval_samples": 15692,
+    "eval_samples_per_second": 41.428,
+    "eval_steps_per_second": 1.296
+}

training.log

@@ -182,3 +182,6 @@ Navigate to x=<loc0007>, y=<loc0256>
 2025-04-26 07:36:05 - INFO - __main__ - *** Train ***
 2025-04-26 13:17:27 - WARNING - huggingface_hub.hf_api - No files have been modified since last commit. Skipping to prevent empty commit.
 2025-04-26 13:17:27 - INFO - __main__ - *** Save model ***
+2025-04-26 13:17:33 - INFO - __main__ - Model saved to data/paligemma2-3b-pt-224-sft-lora-iphonecf-only_rdp
+2025-04-26 13:17:33 - INFO - __main__ - *** Evaluate ***
+2025-04-26 13:23:52 - INFO - __main__ - Pushing to hub...