Training in progress, step 50

README.md

@@ -3,8 +3,8 @@ library_name: transformers
 model_name: pakdd_tag_comcts_gemma
 tags:
 - generated_from_trainer
-- trl
 - grpo
+- trl
 licence: license
 ---
 
@@ -26,7 +26,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jylee18/tag/runs/bkwqqhra) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jylee18/tag/runs/5626hibe) 
 
 
 This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f057c762fd61cb9ca14d09d69e123415de6a4812f29de00490a4804026cf4afb
+oid sha256:bbf625ea0857f9a418b28fc331ab3233953020a699bc53fea0b6a9ca59186324
 size 12932216

preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessorFast",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "pad_size": null,
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

processor_config.json

@@ -1,43 +1,4 @@
 {
-  "image_processor": {
-    "crop_size": null,
-    "data_format": "channels_first",
-    "default_to_square": true,
-    "device": null,
-    "disable_grouping": null,
-    "do_center_crop": null,
-    "do_convert_rgb": null,
-    "do_normalize": true,
-    "do_pad": null,
-    "do_pan_and_scan": null,
-    "do_rescale": true,
-    "do_resize": true,
-    "image_mean": [
-      0.5,
-      0.5,
-      0.5
-    ],
-    "image_processor_type": "Gemma3ImageProcessorFast",
-    "image_seq_length": 256,
-    "image_std": [
-      0.5,
-      0.5,
-      0.5
-    ],
-    "input_data_format": null,
-    "pad_size": null,
-    "pan_and_scan_max_num_crops": null,
-    "pan_and_scan_min_crop_size": null,
-    "pan_and_scan_min_ratio_to_activate": null,
-    "processor_class": "Gemma3Processor",
-    "resample": 2,
-    "rescale_factor": 0.00392156862745098,
-    "return_tensors": null,
-    "size": {
-      "height": 896,
-      "width": 896
-    }
-  },
   "image_seq_length": 256,
   "processor_class": "Gemma3Processor"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e2b1931eb8e4acc0b0bac7ca3c7f637f681100fcdcbb1becd527df06588b304
-size 6136
+oid sha256:c01fdd119e8b2fe6c6f8f32bef79b2e58497a3eabaa6c75c7d51203c168d598c
+size 6904