End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # r1_annotated_finqa
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/r1_annotated_finqa dataset.
 
 ## Model description
 

all_results.json

@@ -2,7 +2,7 @@
     "epoch": 6.955414012738854,
     "total_flos": 1.6645198251751014e+17,
     "train_loss": 0.0,
-    "train_runtime": 5.2904,
-    "train_samples_per_second": 6615.788,
-    "train_steps_per_second": 68.804
+    "train_runtime": 2.7097,
+    "train_samples_per_second": 12916.486,
+    "train_steps_per_second": 134.331
 }

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 6.955414012738854,
     "total_flos": 1.6645198251751014e+17,
     "train_loss": 0.0,
-    "train_runtime": 5.2904,
-    "train_samples_per_second": 6615.788,
-    "train_steps_per_second": 68.804
+    "train_runtime": 2.7097,
+    "train_samples_per_second": 12916.486,
+    "train_steps_per_second": 134.331
 }

trainer_state.json

@@ -2561,9 +2561,9 @@
       "step": 364,
       "total_flos": 1.6645198251751014e+17,
       "train_loss": 0.0,
-      "train_runtime": 5.2904,
-      "train_samples_per_second": 6615.788,
-      "train_steps_per_second": 68.804
+      "train_runtime": 2.7097,
+      "train_samples_per_second": 12916.486,
+      "train_steps_per_second": 134.331
     }
   ],
   "logging_steps": 1,