End of training

README.md

@@ -3,6 +3,7 @@ library_name: transformers
 base_model: ahmedheakl/vlm-r1-base
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: vlm-r1-ex10
@@ -14,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vlm-r1-ex10
 
-This model is a fine-tuned version of [ahmedheakl/vlm-r1-base](https://huggingface.co/ahmedheakl/vlm-r1-base) on the None dataset.
+This model is a fine-tuned version of [ahmedheakl/vlm-r1-base](https://huggingface.co/ahmedheakl/vlm-r1-base) on the open_r1, the r1_onevision_90k, the ai2d-r1, the pixmoqa-r1, the redstar-geo-r1, the clevr-cogent-r1, the clevr-coagent-r1, the llavacot-think and the qvq-r1 datasets.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 1.5291376926195712e+16,
+    "train_loss": 0.44257565271410876,
+    "train_runtime": 104008.927,
+    "train_samples_per_second": 8.666,
+    "train_steps_per_second": 0.068
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 1.5291376926195712e+16,
+    "train_loss": 0.44257565271410876,
+    "train_runtime": 104008.927,
+    "train_samples_per_second": 8.666,
+    "train_steps_per_second": 0.068
+}