End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: Qwen/Qwen2.5-VL-7B-Instruct
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: ui-tars-1.5-7b-idm-full-sft-8-frames-videos
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ui-tars-1.5-7b-idm-full-sft-8-frames-videos
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) on the ui_tars_sft_data_8_frames_videos dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0389
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 6.0,
+    "eval_loss": 0.03890589252114296,
+    "eval_runtime": 4.4986,
+    "eval_samples_per_second": 18.45,
+    "eval_steps_per_second": 2.445,
+    "total_flos": 173334267789312.0,
+    "train_loss": 0.0005224605506934191,
+    "train_runtime": 510.8432,
+    "train_samples_per_second": 96.194,
+    "train_steps_per_second": 6.014
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 6.0,
+    "eval_loss": 0.03890589252114296,
+    "eval_runtime": 4.4986,
+    "eval_samples_per_second": 18.45,
+    "eval_steps_per_second": 2.445
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "total_flos": 173334267789312.0,
+    "train_loss": 0.0005224605506934191,
+    "train_runtime": 510.8432,
+    "train_samples_per_second": 96.194,
+    "train_steps_per_second": 6.014
+}