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-fold3
 
-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-fold3 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0553
+- Loss: 0.0352
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 9.995295888606643,
-    "eval_loss": 0.03600074350833893,
-    "eval_runtime": 161.709,
-    "eval_samples_per_second": 7.303,
-    "eval_steps_per_second": 7.303,
-    "total_flos": 1.667956184857903e+18,
-    "train_loss": 0.0289062451225399,
-    "train_runtime": 73167.6228,
-    "train_samples_per_second": 1.453,
-    "train_steps_per_second": 0.091
+    "epoch": 4.9976479443033215,
+    "eval_loss": 0.035182420164346695,
+    "eval_runtime": 160.1929,
+    "eval_samples_per_second": 7.372,
+    "eval_steps_per_second": 7.372,
+    "total_flos": 8.339771893214085e+17,
+    "train_loss": 0.04500684966052692,
+    "train_runtime": 39650.0346,
+    "train_samples_per_second": 1.34,
+    "train_steps_per_second": 0.084
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 9.995295888606643,
-    "eval_loss": 0.03600074350833893,
-    "eval_runtime": 161.709,
-    "eval_samples_per_second": 7.303,
-    "eval_steps_per_second": 7.303
+    "epoch": 4.9976479443033215,
+    "eval_loss": 0.035182420164346695,
+    "eval_runtime": 160.1929,
+    "eval_samples_per_second": 7.372,
+    "eval_steps_per_second": 7.372
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 9.995295888606643,
-    "total_flos": 1.667956184857903e+18,
-    "train_loss": 0.0289062451225399,
-    "train_runtime": 73167.6228,
-    "train_samples_per_second": 1.453,
-    "train_steps_per_second": 0.091
+    "epoch": 4.9976479443033215,
+    "total_flos": 8.339771893214085e+17,
+    "train_loss": 0.04500684966052692,
+    "train_runtime": 39650.0346,
+    "train_samples_per_second": 1.34,
+    "train_steps_per_second": 0.084
 }