End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # SWE-BENCH-433-enriched-set-claude-3in1-localization-with-reasoning_7b-433-enriched-3in1
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on the SWE-BENCH-433-enriched-set-claude-3in1-localization-with-reasoning dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.93048128342246,
     "total_flos": 9.35169742560297e+16,
-    "train_loss": 0.686019714160632,
-    "train_runtime": 9873.9611,
-    "train_samples_per_second": 0.454,
-    "train_steps_per_second": 0.009
+    "train_loss": 0.0,
+    "train_runtime": 1.09,
+    "train_samples_per_second": 4109.216,
+    "train_steps_per_second": 85.322
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.93048128342246,
     "total_flos": 9.35169742560297e+16,
-    "train_loss": 0.686019714160632,
-    "train_runtime": 9873.9611,
-    "train_samples_per_second": 0.454,
-    "train_steps_per_second": 0.009
+    "train_loss": 0.0,
+    "train_runtime": 1.09,
+    "train_samples_per_second": 4109.216,
+    "train_steps_per_second": 85.322
 }

trainer_state.json

@@ -663,10 +663,10 @@
       "epoch": 2.93048128342246,
       "step": 93,
       "total_flos": 9.35169742560297e+16,
-      "train_loss": 0.686019714160632,
-      "train_runtime": 9873.9611,
-      "train_samples_per_second": 0.454,
-      "train_steps_per_second": 0.009
+      "train_loss": 0.0,
+      "train_runtime": 1.09,
+      "train_samples_per_second": 4109.216,
+      "train_steps_per_second": 85.322
     }
   ],
   "logging_steps": 1,