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/ahmed-alhammadi-technology-innovation-institute/huggingface/runs/wv8lb74o)
+[<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/ahmed-alhammadi-technology-innovation-institute/huggingface/runs/ko2in0ot)
 
 This model was trained with SFT.
 

all_results.json

@@ -2,8 +2,8 @@
     "epoch": 1.0,
     "total_flos": 2783887138750464.0,
     "train_loss": 0.0,
-    "train_runtime": 2.0139,
+    "train_runtime": 2.1036,
     "train_samples": 12593,
-    "train_samples_per_second": 5275.378,
-    "train_steps_per_second": 82.428
+    "train_samples_per_second": 5050.348,
+    "train_steps_per_second": 78.912
 }

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 1.0,
     "total_flos": 2783887138750464.0,
     "train_loss": 0.0,
-    "train_runtime": 2.0139,
+    "train_runtime": 2.1036,
     "train_samples": 12593,
-    "train_samples_per_second": 5275.378,
-    "train_steps_per_second": 82.428
+    "train_samples_per_second": 5050.348,
+    "train_steps_per_second": 78.912
 }

trainer_state.json

@@ -251,9 +251,9 @@
       "step": 166,
       "total_flos": 2783887138750464.0,
       "train_loss": 0.0,
-      "train_runtime": 2.0139,
-      "train_samples_per_second": 5275.378,
-      "train_steps_per_second": 82.428
+      "train_runtime": 2.1036,
+      "train_samples_per_second": 5050.348,
+      "train_steps_per_second": 78.912
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e1c52f5e7a8e2c32303711415b9abf494c4a80f0806761e9bd2a558debe5800
+oid sha256:913957d6054f6e5ea6f74c42c0d9a0677172c09442d4a7cc5c221f9dd1764c4f
 size 5752