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/devamanyu/huggingface/runs/8sykkl1f)
+[<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/devamanyu/huggingface/runs/fzwz81fa)
 
 This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
 

all_results.json

@@ -2,8 +2,8 @@
     "epoch": 1.0,
     "total_flos": 0.0,
     "train_loss": 0.0,
-    "train_runtime": 1.5296,
+    "train_runtime": 1.1662,
     "train_samples": 100,
-    "train_samples_per_second": 65.376,
-    "train_steps_per_second": 0.654
+    "train_samples_per_second": 85.749,
+    "train_steps_per_second": 0.857
 }

runs/Nov13_06-18-02_dvhaz-sleeper-cmh-gpu/events.out.tfevents.1731478722.dvhaz-sleeper-cmh-gpu.6261.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b7576e43eb5098055d34a1d837cffa1b23ee08a28ef5149dbe26344028f6b36
+size 6758

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 1.0,
     "total_flos": 0.0,
     "train_loss": 0.0,
-    "train_runtime": 1.5296,
+    "train_runtime": 1.1662,
     "train_samples": 100,
-    "train_samples_per_second": 65.376,
-    "train_steps_per_second": 0.654
+    "train_samples_per_second": 85.749,
+    "train_steps_per_second": 0.857
 }

trainer_state.json

@@ -797,9 +797,9 @@
       "step": 478,
       "total_flos": 0.0,
       "train_loss": 0.0,
-      "train_runtime": 1.5296,
-      "train_samples_per_second": 65.376,
-      "train_steps_per_second": 0.654
+      "train_runtime": 1.1662,
+      "train_samples_per_second": 85.749,
+      "train_steps_per_second": 0.857
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b5fa183f7bf24433d32ebfb883eae3db120639c9202b1f75dbf72f3f7b0c62d
+oid sha256:95f5f5b31d4cf7f1916c1243a3a88e539d4832024024060439b8ee2d0df4f7d5
 size 7736