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-fold5
 
-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-fold5 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0499
+- Loss: 0.0336
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 9.994312796208531,
-    "eval_loss": 0.03343908488750458,
-    "eval_runtime": 159.5921,
-    "eval_samples_per_second": 7.35,
-    "eval_steps_per_second": 7.35,
-    "total_flos": 1.6540291828151747e+18,
-    "train_loss": 0.029386751238968258,
-    "train_runtime": 72896.2816,
-    "train_samples_per_second": 1.447,
-    "train_steps_per_second": 0.09
+    "epoch": 4.9971563981042655,
+    "eval_loss": 0.03357379883527756,
+    "eval_runtime": 154.6009,
+    "eval_samples_per_second": 7.587,
+    "eval_steps_per_second": 7.587,
+    "total_flos": 8.270218162679316e+17,
+    "train_loss": 0.045199701213737176,
+    "train_runtime": 35768.8652,
+    "train_samples_per_second": 1.475,
+    "train_steps_per_second": 0.092
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 9.994312796208531,
-    "eval_loss": 0.03343908488750458,
-    "eval_runtime": 159.5921,
-    "eval_samples_per_second": 7.35,
-    "eval_steps_per_second": 7.35
+    "epoch": 4.9971563981042655,
+    "eval_loss": 0.03357379883527756,
+    "eval_runtime": 154.6009,
+    "eval_samples_per_second": 7.587,
+    "eval_steps_per_second": 7.587
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 9.994312796208531,
-    "total_flos": 1.6540291828151747e+18,
-    "train_loss": 0.029386751238968258,
-    "train_runtime": 72896.2816,
-    "train_samples_per_second": 1.447,
-    "train_steps_per_second": 0.09
+    "epoch": 4.9971563981042655,
+    "total_flos": 8.270218162679316e+17,
+    "train_loss": 0.045199701213737176,
+    "train_runtime": 35768.8652,
+    "train_samples_per_second": 1.475,
+    "train_steps_per_second": 0.092
 }