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-fold4
 
-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-fold4 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0622
+- Loss: 0.0344
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 9.999045892567503,
-    "eval_loss": 0.035647086799144745,
-    "eval_runtime": 158.9637,
-    "eval_samples_per_second": 7.329,
-    "eval_steps_per_second": 7.329,
-    "total_flos": 1.6441614685569024e+18,
-    "train_loss": 0.029180648955241032,
-    "train_runtime": 72321.8375,
-    "train_samples_per_second": 1.449,
-    "train_steps_per_second": 0.091
+    "epoch": 4.999522946283752,
+    "eval_loss": 0.03436192870140076,
+    "eval_runtime": 157.8575,
+    "eval_samples_per_second": 7.38,
+    "eval_steps_per_second": 7.38,
+    "total_flos": 8.22077121848279e+17,
+    "train_loss": 0.04503766617872788,
+    "train_runtime": 36493.551,
+    "train_samples_per_second": 1.436,
+    "train_steps_per_second": 0.09
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 9.999045892567503,
-    "eval_loss": 0.035647086799144745,
-    "eval_runtime": 158.9637,
-    "eval_samples_per_second": 7.329,
-    "eval_steps_per_second": 7.329
+    "epoch": 4.999522946283752,
+    "eval_loss": 0.03436192870140076,
+    "eval_runtime": 157.8575,
+    "eval_samples_per_second": 7.38,
+    "eval_steps_per_second": 7.38
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 9.999045892567503,
-    "total_flos": 1.6441614685569024e+18,
-    "train_loss": 0.029180648955241032,
-    "train_runtime": 72321.8375,
-    "train_samples_per_second": 1.449,
-    "train_steps_per_second": 0.091
+    "epoch": 4.999522946283752,
+    "total_flos": 8.22077121848279e+17,
+    "train_loss": 0.04503766617872788,
+    "train_runtime": 36493.551,
+    "train_samples_per_second": 1.436,
+    "train_steps_per_second": 0.09
 }