End of training

README.md

@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Llama-3.1-8B-Instruct-PsyCourse-fold10
 
-This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the course-train-fold10 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0545
+- Loss: 0.0346
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 9.989417989417989,
-    "eval_loss": 0.03459745645523071,
-    "eval_runtime": 155.0667,
-    "eval_samples_per_second": 7.448,
-    "eval_steps_per_second": 7.448,
-    "total_flos": 1.6307842783863767e+18,
-    "train_loss": 0.029858223626566607,
-    "train_runtime": 70104.8536,
-    "train_samples_per_second": 1.483,
-    "train_steps_per_second": 0.093
+    "epoch": 4.994708994708994,
+    "eval_loss": 0.03463359922170639,
+    "eval_runtime": 157.9693,
+    "eval_samples_per_second": 7.312,
+    "eval_steps_per_second": 7.312,
+    "total_flos": 8.15387262412456e+17,
+    "train_loss": 0.04645328171757869,
+    "train_runtime": 35336.8306,
+    "train_samples_per_second": 1.471,
+    "train_steps_per_second": 0.092
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 9.989417989417989,
-    "eval_loss": 0.03459745645523071,
-    "eval_runtime": 155.0667,
-    "eval_samples_per_second": 7.448,
-    "eval_steps_per_second": 7.448
+    "epoch": 4.994708994708994,
+    "eval_loss": 0.03463359922170639,
+    "eval_runtime": 157.9693,
+    "eval_samples_per_second": 7.312,
+    "eval_steps_per_second": 7.312
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 9.989417989417989,
-    "total_flos": 1.6307842783863767e+18,
-    "train_loss": 0.029858223626566607,
-    "train_runtime": 70104.8536,
-    "train_samples_per_second": 1.483,
-    "train_steps_per_second": 0.093
+    "epoch": 4.994708994708994,
+    "total_flos": 8.15387262412456e+17,
+    "train_loss": 0.04645328171757869,
+    "train_runtime": 35336.8306,
+    "train_samples_per_second": 1.471,
+    "train_steps_per_second": 0.092
 }