End of training

README.md

@@ -1,9 +1,13 @@
 ---
 base_model: Qwen/Qwen2.5-VL-3B-Instruct
+datasets: smolagents/aguvis-stage-2
 library_name: transformers
 model_name: Qwen2.5-VL-3B-Instruct-Agentic-GUI
 tags:
 - generated_from_trainer
+- open-r1
+- vision-language
+- vlm
 - trl
 - sft
 licence: license
@@ -11,7 +15,7 @@ licence: license
 
 # Model Card for Qwen2.5-VL-3B-Instruct-Agentic-GUI
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct).
+This model is a fine-tuned version of [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct) on the [smolagents/aguvis-stage-2](https://huggingface.co/datasets/smolagents/aguvis-stage-2) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,9 +1,9 @@
 {
-    "eval_loss": 0.5879997611045837,
-    "eval_runtime": 300.2318,
+    "eval_loss": 4.7405829429626465,
+    "eval_runtime": 111.8437,
     "eval_samples": 3639,
-    "eval_samples_per_second": 12.121,
-    "eval_steps_per_second": 0.38,
+    "eval_samples_per_second": 32.536,
+    "eval_steps_per_second": 1.019,
     "total_flos": 1.2125984924893184e+16,
     "train_loss": 0.0,
     "train_runtime": 1.6574,

config.json

@@ -70,7 +70,7 @@
   },
   "torch_dtype": "bfloat16",
   "transformers_version": "4.52.3",
-  "use_cache": false,
+  "use_cache": true,
   "use_sliding_window": false,
   "video_token_id": 151656,
   "vision_config": {

eval_results.json

@@ -1,7 +1,7 @@
 {
-    "eval_loss": 0.5879997611045837,
-    "eval_runtime": 300.2318,
+    "eval_loss": 4.7405829429626465,
+    "eval_runtime": 111.8437,
     "eval_samples": 3639,
-    "eval_samples_per_second": 12.121,
-    "eval_steps_per_second": 0.38
+    "eval_samples_per_second": 32.536,
+    "eval_steps_per_second": 1.019
 }