End of training

README.md

@@ -4,6 +4,7 @@ license: llama3.1
 base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
 tags:
 - llama-factory
+- lora
 - generated_from_trainer
 model-index:
 - name: Llama-3.1-8B-Instruct-QG-SFT
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Llama-3.1-8B-Instruct-QG-SFT
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the alpaca_en, the qg_sft, the wikiqa, the webqa and the openo1_sft datasets.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9998492272898606,
+    "total_flos": 4.746119130111803e+18,
+    "train_loss": 0.6650473316231887,
+    "train_runtime": 22780.4973,
+    "train_samples_per_second": 9.316,
+    "train_steps_per_second": 0.194
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9998492272898606,
+    "total_flos": 4.746119130111803e+18,
+    "train_loss": 0.6650473316231887,
+    "train_runtime": 22780.4973,
+    "train_samples_per_second": 9.316,
+    "train_steps_per_second": 0.194
+}