End of training

README.md

@@ -4,6 +4,7 @@ license: llama3.1
 base_model: meta-llama/Llama-3.1-8B-Instruct
 tags:
 - llama-factory
+- lora
 - generated_from_trainer
 model-index:
 - name: Llama-3.1-8B-Instruct-PsyCourse-fold2
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Llama-3.1-8B-Instruct-PsyCourse-fold2
 
-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-fold2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1044
+- Loss: 0.0342
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.03416348248720169,
+    "eval_runtime": 157.8776,
+    "eval_samples_per_second": 7.265,
+    "eval_steps_per_second": 7.265,
+    "total_flos": 1.6192537625198592e+18,
+    "train_loss": 0.02916080290347865,
+    "train_runtime": 73674.4309,
+    "train_samples_per_second": 1.401,
+    "train_steps_per_second": 0.088
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.03416348248720169,
+    "eval_runtime": 157.8776,
+    "eval_samples_per_second": 7.265,
+    "eval_steps_per_second": 7.265
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "total_flos": 1.6192537625198592e+18,
+    "train_loss": 0.02916080290347865,
+    "train_runtime": 73674.4309,
+    "train_samples_per_second": 1.401,
+    "train_steps_per_second": 0.088
+}