End of training

README.md

@@ -4,6 +4,7 @@ license: llama3.1
 base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: prm_version2_subsample_no_ref_hf
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # prm_version2_subsample_no_ref_hf
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the prm_conversations_prm_version2_math+webinstructsub-mcq+webinstructsub-oe+apps_subsample_hf dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1824
+- Loss: 0.1797
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.999804522056428,
+    "eval_loss": 0.17974616587162018,
+    "eval_runtime": 52.0233,
+    "eval_samples_per_second": 23.855,
+    "eval_steps_per_second": 2.999,
+    "total_flos": 331183228846080.0,
+    "train_loss": 0.20316935279353193,
+    "train_runtime": 20098.2432,
+    "train_samples_per_second": 6.108,
+    "train_steps_per_second": 0.095
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.999804522056428,
+    "eval_loss": 0.17974616587162018,
+    "eval_runtime": 52.0233,
+    "eval_samples_per_second": 23.855,
+    "eval_steps_per_second": 2.999
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.999804522056428,
+    "total_flos": 331183228846080.0,
+    "train_loss": 0.20316935279353193,
+    "train_runtime": 20098.2432,
+    "train_samples_per_second": 6.108,
+    "train_steps_per_second": 0.095
+}