End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: Qwen/Qwen2.5-Math-7B-Instruct
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: prm_qwen25_math_version3_subsample_hf
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # prm_qwen25_math_version3_subsample_hf
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct) on the prm_conversations_prm_version3_math+webinstructsub-mcq+webinstructsub-oe+apps+gsm_mix_ref_subsample_hf dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1641
+- Loss: 0.1639
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.9999155096178218,
+    "eval_loss": 0.16392970085144043,
+    "eval_runtime": 56.9762,
+    "eval_samples_per_second": 50.372,
+    "eval_steps_per_second": 6.301,
+    "total_flos": 995060424065024.0,
+    "train_loss": 0.1932588364020722,
+    "train_runtime": 22166.8057,
+    "train_samples_per_second": 12.814,
+    "train_steps_per_second": 0.2
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.9999155096178218,
+    "eval_loss": 0.16392970085144043,
+    "eval_runtime": 56.9762,
+    "eval_samples_per_second": 50.372,
+    "eval_steps_per_second": 6.301
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9999155096178218,
+    "total_flos": 995060424065024.0,
+    "train_loss": 0.1932588364020722,
+    "train_runtime": 22166.8057,
+    "train_samples_per_second": 12.814,
+    "train_steps_per_second": 0.2
+}