End of training

README.md

@@ -1,8 +1,12 @@
 ---
+datasets: smolagents/aguvis-stage-2
 library_name: transformers
 model_name: SmolVLM2-2.2B-Instruct-Agentic-GUI
 tags:
 - generated_from_trainer
+- open-r1
+- vision-language
+- vlm
 - trl
 - sft
 licence: license
@@ -10,7 +14,7 @@ licence: license
 
 # Model Card for SmolVLM2-2.2B-Instruct-Agentic-GUI
 
-This model is a fine-tuned version of [None](https://huggingface.co/None).
+This model is a fine-tuned version of [None](https://huggingface.co/None) 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

@@ -1,4 +1,9 @@
 {
+    "eval_loss": 0.6482115983963013,
+    "eval_runtime": 149.9453,
+    "eval_samples": 3639,
+    "eval_samples_per_second": 24.269,
+    "eval_steps_per_second": 0.76,
     "total_flos": 1.0314062938243072e+16,
     "train_loss": 0.7184352108531378,
     "train_runtime": 49977.4428,

config.json

@@ -120,7 +120,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.54.1",
-  "use_cache": false,
+  "use_cache": true,
   "use_reentrant_checkpointing": false,
   "vision_config": {
     "attention_dropout": 0.0,

eval_results.json

@@ -1,7 +1,7 @@
 {
-    "eval_loss": 0.5039201974868774,
-    "eval_runtime": 159.8129,
+    "eval_loss": 0.6482115983963013,
+    "eval_runtime": 149.9453,
     "eval_samples": 3639,
-    "eval_samples_per_second": 22.77,
-    "eval_steps_per_second": 0.713
+    "eval_samples_per_second": 24.269,
+    "eval_steps_per_second": 0.76
 }