Model save

README.md

@@ -27,7 +27,7 @@ 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/nlee28/reasoning/runs/in98mfdt) 
+[<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/nlee28/reasoning/runs/o20hygkn) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 1.182462262019883e+18,
-    "train_loss": 1.8812798500061034,
-    "train_runtime": 8393.8652,
+    "train_loss": 2.9186187465985616,
+    "train_runtime": 4944.9437,
     "train_samples": 817,
-    "train_samples_per_second": 0.487,
-    "train_steps_per_second": 0.007
+    "train_samples_per_second": 0.826,
+    "train_steps_per_second": 0.012
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:000e2da3a497ee79bea231a76e7a770cff45667f458da1ff6dc48a0849bc3e26
+oid sha256:58e01e7d2d951dff37e70aec71be657f8d06b83010b75f9dbba847be08cff729
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e8aa0f4fdd29270b8708435274bce04fcba26a5cb582ea886400256af11c2b5
+oid sha256:0d37f1215e894b8fb82e502cfcf908a9d22322d4181f3e259c59dd960932fdf1
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a76075f6aa662abdad6110ba62d776730c54725d840696a349a6da8c1e654711
+oid sha256:98d6eba46181c7247e99a0d7449c8cb072fa5b84be4e5b9f5328cbb0e5c8548d
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:298826d947256459f9477fabc8e0c868421aea1f0b75ea9086e1db4d14b2950e
+oid sha256:f3c2acf9182f6e318d518a995a4aa6355f1700834e5a007b23a5012e22a7a7f8
 size 1089994880

runs/Feb26_10-47-03_na-clops-debugging-pipeline-s6tg6-049f-0/events.out.tfevents.1740566847.na-clops-debugging-pipeline-s6tg6-049f-0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c452fe4633ac5bba1f40bc540b0eaf05742438683063df48603ff2d69c16e661
-size 12035
+oid sha256:32ba7ca663df882362ee9b8ed1d8b05983b8dc58a306e68c1b0673d48cb22713
+size 14003

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 1.182462262019883e+18,
-    "train_loss": 1.8812798500061034,
-    "train_runtime": 8393.8652,
+    "train_loss": 2.9186187465985616,
+    "train_runtime": 4944.9437,
     "train_samples": 817,
-    "train_samples_per_second": 0.487,
-    "train_steps_per_second": 0.007
+    "train_samples_per_second": 0.826,
+    "train_steps_per_second": 0.012
 }