End of training

README.md

@@ -1,12 +1,12 @@
 ---
 base_model: mistralai/Mistral-7B-v0.1
 datasets:
-- generator
+- yycsu/sg_90k_small
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - sft
-- alignment-handbook
 - generated_from_trainer
 model-index:
 - name: zephyr-7b-sft-qlora
@@ -18,7 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-sft-qlora
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the yycsu/sg_90k_small dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8693
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9836065573770492,
+    "eval_loss": 0.8693358898162842,
+    "eval_runtime": 83.4699,
+    "eval_samples": 18,
+    "eval_samples_per_second": 0.323,
+    "eval_steps_per_second": 0.048,
     "total_flos": 2.0918103256858624e+16,
     "train_loss": 0.0,
     "train_runtime": 0.1548,

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9836065573770492,
+    "eval_loss": 0.8693358898162842,
+    "eval_runtime": 83.4699,
+    "eval_samples": 18,
+    "eval_samples_per_second": 0.323,
+    "eval_steps_per_second": 0.048
+}

runs/Jul31_16-24-12_VM-146-67-centos/events.out.tfevents.1722414409.VM-146-67-centos.3350321.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9cee055ac6d483ecf090e9eca1ffadf9f9f26bfe647a2c486cc5a2a5e2575d3
+size 354