End of training

README.md

@@ -1,13 +1,13 @@
 ---
 base_model: mistralai/Mistral-7B-v0.1
 datasets:
-- generator
+- Dataset-t-t-t-t-t-t-t-t/UltraMed
 library_name: peft
 license: apache-2.0
 tags:
+- alignment-handbook
 - trl
 - sft
-- alignment-handbook
 - generated_from_trainer
 model-index:
 - name: zephyr-7b-sft-qlora
@@ -19,7 +19,9 @@ 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 Dataset-t-t-t-t-t-t-t-t/UltraMed dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2864
 
 ## Model description
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 0.265343793262575,
-    "eval_loss": 0.9861459732055664,
-    "eval_runtime": 1456.8698,
-    "eval_samples": 23109,
-    "eval_samples_per_second": 10.536,
-    "eval_steps_per_second": 0.329,
+    "eval_loss": 0.2863554060459137,
+    "eval_runtime": 9.1878,
+    "eval_samples": 500,
+    "eval_samples_per_second": 9.578,
+    "eval_steps_per_second": 0.327,
     "total_flos": 3.2343958172802744e+18,
     "train_loss": 0.0,
     "train_runtime": 0.0427,

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.265343793262575,
-    "eval_loss": 0.9861459732055664,
-    "eval_runtime": 1456.8698,
-    "eval_samples": 23109,
-    "eval_samples_per_second": 10.536,
-    "eval_steps_per_second": 0.329
+    "eval_loss": 0.2863554060459137,
+    "eval_runtime": 9.1878,
+    "eval_samples": 500,
+    "eval_samples_per_second": 9.578,
+    "eval_steps_per_second": 0.327
 }

runs/Oct07_19-29-05_dilara/events.out.tfevents.1728329453.dilara.980876.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38c4e37ed86c9be1a3c5684c5e3ca24d25c7208eaffd85d622165a39a81360d5
+size 359