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-fold7
 
-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-fold7 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0536
+- Loss: 0.0324
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 9.992360580595875,
-    "eval_loss": 0.033308111131191254,
-    "eval_runtime": 185.0471,
-    "eval_samples_per_second": 6.29,
-    "eval_steps_per_second": 6.29,
-    "total_flos": 1.6427663480244142e+18,
-    "train_loss": 0.02933183570154971,
-    "train_runtime": 83631.9537,
-    "train_samples_per_second": 1.252,
-    "train_steps_per_second": 0.078
+    "epoch": 4.9961802902979375,
+    "eval_loss": 0.032429687678813934,
+    "eval_runtime": 154.0372,
+    "eval_samples_per_second": 7.557,
+    "eval_steps_per_second": 7.557,
+    "total_flos": 8.213792003390177e+17,
+    "train_loss": 0.0453332782948008,
+    "train_runtime": 35234.3821,
+    "train_samples_per_second": 1.486,
+    "train_steps_per_second": 0.093
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 9.992360580595875,
-    "eval_loss": 0.033308111131191254,
-    "eval_runtime": 185.0471,
-    "eval_samples_per_second": 6.29,
-    "eval_steps_per_second": 6.29
+    "epoch": 4.9961802902979375,
+    "eval_loss": 0.032429687678813934,
+    "eval_runtime": 154.0372,
+    "eval_samples_per_second": 7.557,
+    "eval_steps_per_second": 7.557
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 9.992360580595875,
-    "total_flos": 1.6427663480244142e+18,
-    "train_loss": 0.02933183570154971,
-    "train_runtime": 83631.9537,
-    "train_samples_per_second": 1.252,
-    "train_steps_per_second": 0.078
+    "epoch": 4.9961802902979375,
+    "total_flos": 8.213792003390177e+17,
+    "train_loss": 0.0453332782948008,
+    "train_runtime": 35234.3821,
+    "train_samples_per_second": 1.486,
+    "train_steps_per_second": 0.093
 }