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_version3_full_hf
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # prm_version3_full_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_version3_math+webinstructsub-mcq+webinstructsub-oe+apps+gsm_mix_ref_hf dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.1166
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.999953931911365,
+    "eval_loss": 0.11656492948532104,
+    "eval_runtime": 300.7975,
+    "eval_samples_per_second": 23.328,
+    "eval_steps_per_second": 2.919,
+    "total_flos": 1908258935930880.0,
+    "train_loss": 0.14796658507510943,
+    "train_runtime": 123515.0295,
+    "train_samples_per_second": 5.624,
+    "train_steps_per_second": 0.088
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.999953931911365,
+    "eval_loss": 0.11656492948532104,
+    "eval_runtime": 300.7975,
+    "eval_samples_per_second": 23.328,
+    "eval_steps_per_second": 2.919
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.999953931911365,
+    "total_flos": 1908258935930880.0,
+    "train_loss": 0.14796658507510943,
+    "train_runtime": 123515.0295,
+    "train_samples_per_second": 5.624,
+    "train_steps_per_second": 0.088
+}