Model save

README.md

@@ -26,7 +26,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/howardzhou92-nw/huggingface/runs/5fbhajij) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/howardzhou92-nw/huggingface/runs/cuu0yr0w) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 1.0,
-    "total_flos": 4705642371612672.0,
-    "train_loss": 0.4742418575281553,
-    "train_runtime": 118145.0815,
-    "train_samples": 594015,
-    "train_samples_per_second": 4.862,
-    "train_steps_per_second": 0.038
+    "epoch": 0.9995169859925938,
+    "total_flos": 1627220267237376.0,
+    "train_loss": 0.5271049797074082,
+    "train_runtime": 41787.5323,
+    "train_samples": 112817,
+    "train_samples_per_second": 4.756,
+    "train_steps_per_second": 0.037
 }

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 1.0,
-    "total_flos": 4705642371612672.0,
-    "train_loss": 0.4742418575281553,
-    "train_runtime": 118145.0815,
-    "train_samples": 594015,
-    "train_samples_per_second": 4.862,
-    "train_steps_per_second": 0.038
+    "epoch": 0.9995169859925938,
+    "total_flos": 1627220267237376.0,
+    "train_loss": 0.5271049797074082,
+    "train_runtime": 41787.5323,
+    "train_samples": 112817,
+    "train_samples_per_second": 4.756,
+    "train_steps_per_second": 0.037
 }