End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: Qwen/Qwen2.5-7B-Instruct
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: llama3-1_8b_4o_annotated_olympiads
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-1_8b_4o_annotated_olympiads
 
-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/4o_annotated_olympiads dataset.
 
 ## Model description
 

all_results.json

@@ -1,12 +1,8 @@
 {
     "epoch": 3.0,
-    "eval_loss": 0.764080822467804,
-    "eval_runtime": 2.7378,
-    "eval_samples_per_second": 242.898,
-    "eval_steps_per_second": 1.096,
-    "total_flos": 125627793408000.0,
-    "train_loss": 0.78931853612264,
-    "train_runtime": 843.7096,
-    "train_samples_per_second": 44.88,
-    "train_steps_per_second": 0.089
+    "total_flos": 171917700349952.0,
+    "train_loss": 0.6223782367549592,
+    "train_runtime": 3879.5995,
+    "train_samples_per_second": 26.353,
+    "train_steps_per_second": 0.275
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "total_flos": 125627793408000.0,
-    "train_loss": 0.78931853612264,
-    "train_runtime": 843.7096,
-    "train_samples_per_second": 44.88,
-    "train_steps_per_second": 0.089
+    "total_flos": 171917700349952.0,
+    "train_loss": 0.6223782367549592,
+    "train_runtime": 3879.5995,
+    "train_samples_per_second": 26.353,
+    "train_steps_per_second": 0.275
 }