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-fold9
 
-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-fold9 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0639
+- Loss: 0.0368
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 9.994242947610823,
-    "eval_loss": 0.03734986111521721,
-    "eval_runtime": 153.902,
-    "eval_samples_per_second": 7.531,
-    "eval_steps_per_second": 7.531,
-    "total_flos": 1.63500612552858e+18,
-    "train_loss": 0.029361989410361097,
-    "train_runtime": 69901.4467,
-    "train_samples_per_second": 1.491,
-    "train_steps_per_second": 0.093
+    "epoch": 4.997121473805412,
+    "eval_loss": 0.036797065287828445,
+    "eval_runtime": 158.8622,
+    "eval_samples_per_second": 7.296,
+    "eval_steps_per_second": 7.296,
+    "total_flos": 8.175027015212728e+17,
+    "train_loss": 0.04520614844061629,
+    "train_runtime": 35604.7112,
+    "train_samples_per_second": 1.464,
+    "train_steps_per_second": 0.091
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 9.994242947610823,
-    "eval_loss": 0.03734986111521721,
-    "eval_runtime": 153.902,
-    "eval_samples_per_second": 7.531,
-    "eval_steps_per_second": 7.531
+    "epoch": 4.997121473805412,
+    "eval_loss": 0.036797065287828445,
+    "eval_runtime": 158.8622,
+    "eval_samples_per_second": 7.296,
+    "eval_steps_per_second": 7.296
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 9.994242947610823,
-    "total_flos": 1.63500612552858e+18,
-    "train_loss": 0.029361989410361097,
-    "train_runtime": 69901.4467,
-    "train_samples_per_second": 1.491,
-    "train_steps_per_second": 0.093
+    "epoch": 4.997121473805412,
+    "total_flos": 8.175027015212728e+17,
+    "train_loss": 0.04520614844061629,
+    "train_runtime": 35604.7112,
+    "train_samples_per_second": 1.464,
+    "train_steps_per_second": 0.091
 }