Model save

README.md

@@ -9,7 +9,7 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/costa-huang/huggingface/runs/a7ha08nl)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/costa-huang/huggingface/runs/and6d28l)
 # online_dpo
 
 This model was trained from scratch on an unknown dataset.

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e25b97b80704647f61fbc5a5359098d49bba09f375ec0beea3b0d3d4caf92b0
+oid sha256:8b770bbd2b157e494cea03db919d0e7280ec55966212ff28ca9c563d6e5b5217
 size 2023586384

runs/Jul15_15-27-16_ip-26-0-167-9/events.out.tfevents.1721057315.ip-26-0-167-9.235582.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2317027bac46328f29f0ce3fd88750a0af691d4a62437db19b05a547fb77482
+size 519631

runs/Jul15_15-47-35_ip-26-0-172-142/events.out.tfevents.1721058536.ip-26-0-172-142.1767221.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc0610b68f38cc12109a8c93ae91746144c1360ef579d4212bc454711444b073
+size 2363065

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0173c986e3584ee8d94070ec8281ef58547122d96ff2b7ca00e6f14f766ae78
+oid sha256:f9d3fb9e61f587b370fda85d130b0cde7417ea258acc9dcda1f31a24bc3b935b
 size 7480