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-fold8
 
-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-fold8 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0604
+- Loss: 0.0354
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 9.993365557767037,
-    "eval_loss": 0.03688763454556465,
-    "eval_runtime": 159.1529,
-    "eval_samples_per_second": 7.37,
-    "eval_steps_per_second": 7.37,
-    "total_flos": 1.6539435682200945e+18,
-    "train_loss": 0.029239414032335445,
-    "train_runtime": 72432.9733,
-    "train_samples_per_second": 1.457,
+    "epoch": 4.996682778883518,
+    "eval_loss": 0.03543492406606674,
+    "eval_runtime": 160.5577,
+    "eval_samples_per_second": 7.306,
+    "eval_steps_per_second": 7.306,
+    "total_flos": 8.269502901505229e+17,
+    "train_loss": 0.04518177697310657,
+    "train_runtime": 36119.4942,
+    "train_samples_per_second": 1.461,
     "train_steps_per_second": 0.091
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 9.993365557767037,
-    "eval_loss": 0.03688763454556465,
-    "eval_runtime": 159.1529,
-    "eval_samples_per_second": 7.37,
-    "eval_steps_per_second": 7.37
+    "epoch": 4.996682778883518,
+    "eval_loss": 0.03543492406606674,
+    "eval_runtime": 160.5577,
+    "eval_samples_per_second": 7.306,
+    "eval_steps_per_second": 7.306
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 9.993365557767037,
-    "total_flos": 1.6539435682200945e+18,
-    "train_loss": 0.029239414032335445,
-    "train_runtime": 72432.9733,
-    "train_samples_per_second": 1.457,
+    "epoch": 4.996682778883518,
+    "total_flos": 8.269502901505229e+17,
+    "train_loss": 0.04518177697310657,
+    "train_runtime": 36119.4942,
+    "train_samples_per_second": 1.461,
     "train_steps_per_second": 0.091
 }