End of training

README.md

@@ -4,6 +4,7 @@ license: llama3.2
 base_model: meta-llama/Llama-3.2-1B
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: llama-3.2-1B-4096-sample-2-22GB
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama-3.2-1B-4096-sample-2-22GB
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on the sample_2 dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9999003686360466,
+    "total_flos": 2400250660651008.0,
+    "train_loss": 0.8378047743086893,
+    "train_runtime": 25259.4249,
+    "train_samples_per_second": 57.218,
+    "train_steps_per_second": 0.099
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9999003686360466,
+    "total_flos": 2400250660651008.0,
+    "train_loss": 0.8378047743086893,
+    "train_runtime": 25259.4249,
+    "train_samples_per_second": 57.218,
+    "train_steps_per_second": 0.099
+}