End of training

README.md

@@ -4,6 +4,7 @@ library_name: peft
 license: mit
 tags:
 - llama-factory
+- lora
 - full
 - generated_from_trainer
 model-index:
@@ -17,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/dongfu/huggingface/runs/vdittf2b)
 # PairRM-V2-phi3-3-mini-ultra-feedback-binarized-lora
 
-This model is a fine-tuned version of [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) on the ultra-feedback-binarized dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2640
+- Loss: 0.2605
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 1.9994796635157401,
-    "eval_loss": 0.4639037847518921,
-    "eval_runtime": 767.9829,
-    "eval_samples_per_second": 12.644,
-    "eval_steps_per_second": 1.581,
-    "total_flos": 420396754255872.0,
-    "train_loss": 0.3626429720482505,
-    "train_runtime": 106139.7498,
-    "train_samples_per_second": 3.476,
-    "train_steps_per_second": 0.027
+    "epoch": 0.9992793658419409,
+    "eval_loss": 0.2604576349258423,
+    "eval_runtime": 270.7958,
+    "eval_samples_per_second": 19.421,
+    "eval_steps_per_second": 2.43,
+    "total_flos": 2.0573294793064448e+18,
+    "train_loss": 0.29625688539101525,
+    "train_runtime": 10334.3449,
+    "train_samples_per_second": 9.668,
+    "train_steps_per_second": 0.075
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 1.9994796635157401,
-    "eval_loss": 0.4639037847518921,
-    "eval_runtime": 767.9829,
-    "eval_samples_per_second": 12.644,
-    "eval_steps_per_second": 1.581
+    "epoch": 0.9992793658419409,
+    "eval_loss": 0.2604576349258423,
+    "eval_runtime": 270.7958,
+    "eval_samples_per_second": 19.421,
+    "eval_steps_per_second": 2.43
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 1.9994796635157401,
-    "total_flos": 420396754255872.0,
-    "train_loss": 0.3626429720482505,
-    "train_runtime": 106139.7498,
-    "train_samples_per_second": 3.476,
-    "train_steps_per_second": 0.027
+    "epoch": 0.9992793658419409,
+    "total_flos": 2.0573294793064448e+18,
+    "train_loss": 0.29625688539101525,
+    "train_runtime": 10334.3449,
+    "train_samples_per_second": 9.668,
+    "train_steps_per_second": 0.075
 }