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/v84qsetz)
+[<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)
 
 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": 2.4766,
-    "train_samples": 61134,
-    "train_samples_per_second": 24684.932,
-    "train_steps_per_second": 193.009
+    "train_runtime": 1.5296,
+    "train_samples": 100,
+    "train_samples_per_second": 65.376,
+    "train_steps_per_second": 0.654
 }

runs/Nov13_06-13-28_dvhaz-sleeper-cmh-gpu/events.out.tfevents.1731478452.dvhaz-sleeper-cmh-gpu.5306.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab55ea193f1d7151225a9eb2dae56aa705b0530c62087b26bd6722042ff1d38
+size 6758

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 1.0,
     "total_flos": 0.0,
     "train_loss": 0.0,
-    "train_runtime": 2.4766,
-    "train_samples": 61134,
-    "train_samples_per_second": 24684.932,
-    "train_steps_per_second": 193.009
+    "train_runtime": 1.5296,
+    "train_samples": 100,
+    "train_samples_per_second": 65.376,
+    "train_steps_per_second": 0.654
 }

trainer_state.json

@@ -797,13 +797,13 @@
       "step": 478,
       "total_flos": 0.0,
       "train_loss": 0.0,
-      "train_runtime": 2.4766,
-      "train_samples_per_second": 24684.932,
-      "train_steps_per_second": 193.009
+      "train_runtime": 1.5296,
+      "train_samples_per_second": 65.376,
+      "train_steps_per_second": 0.654
     }
   ],
   "logging_steps": 10,
-  "max_steps": 478,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 100,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:645079b0aa2c0ead105c842856cbf5f728fe4cef561ae2e1f7b62211fe6b92c8
+oid sha256:0b5fa183f7bf24433d32ebfb883eae3db120639c9202b1f75dbf72f3f7b0c62d
 size 7736