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/648848014/huggingface/runs/vkjcv7v0) 
+[<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/648848014/huggingface/runs/7eblkip7) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 2.926914460515809e+17,
     "train_loss": 0.0,
-    "train_runtime": 2.1702,
+    "train_runtime": 1.5655,
     "train_samples": 3472,
-    "train_samples_per_second": 889.317,
-    "train_steps_per_second": 59.902
+    "train_samples_per_second": 1232.8,
+    "train_steps_per_second": 83.038
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 2.926914460515809e+17,
     "train_loss": 0.0,
-    "train_runtime": 2.1702,
+    "train_runtime": 1.5655,
     "train_samples": 3472,
-    "train_samples_per_second": 889.317,
-    "train_steps_per_second": 59.902
+    "train_samples_per_second": 1232.8,
+    "train_steps_per_second": 83.038
 }

trainer_state.json

@@ -195,9 +195,9 @@
       "step": 130,
       "total_flos": 2.926914460515809e+17,
       "train_loss": 0.0,
-      "train_runtime": 2.1702,
-      "train_samples_per_second": 889.317,
-      "train_steps_per_second": 59.902
+      "train_runtime": 1.5655,
+      "train_samples_per_second": 1232.8,
+      "train_steps_per_second": 83.038
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6140fd50f7ce58a82d15f27857674eecd42e2c5e8a6f47ccb5ac67f35bcf864
+oid sha256:d2683402f47f184f88ebb5677ad3c0f89f543f6d5eef08d8d5c3d0e0082354e2
 size 6200