End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Qwen2.5-1.5B-Instruct-AraNews
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the arabic_news_sammary_train dataset.
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 2.0,
     "eval_arabic_news_sammary_test_loss": 1.4771952629089355,
-    "eval_arabic_news_sammary_test_runtime": 1.4541,
-    "eval_arabic_news_sammary_test_samples_per_second": 6.877,
-    "eval_arabic_news_sammary_test_steps_per_second": 6.877,
+    "eval_arabic_news_sammary_test_runtime": 1.7003,
+    "eval_arabic_news_sammary_test_samples_per_second": 5.881,
+    "eval_arabic_news_sammary_test_steps_per_second": 5.881,
     "total_flos": 168628741816320.0,
-    "train_loss": 1.7585566838582356,
-    "train_runtime": 19.6571,
-    "train_samples_per_second": 1.526,
-    "train_steps_per_second": 0.305
+    "train_loss": 0.0,
+    "train_runtime": 1.3096,
+    "train_samples_per_second": 7.636,
+    "train_steps_per_second": 1.527
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 2.0,
     "eval_arabic_news_sammary_test_loss": 1.4771952629089355,
-    "eval_arabic_news_sammary_test_runtime": 1.4541,
-    "eval_arabic_news_sammary_test_samples_per_second": 6.877,
-    "eval_arabic_news_sammary_test_steps_per_second": 6.877
+    "eval_arabic_news_sammary_test_runtime": 1.7003,
+    "eval_arabic_news_sammary_test_samples_per_second": 5.881,
+    "eval_arabic_news_sammary_test_steps_per_second": 5.881
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.0,
     "total_flos": 168628741816320.0,
-    "train_loss": 1.7585566838582356,
-    "train_runtime": 19.6571,
-    "train_samples_per_second": 1.526,
-    "train_steps_per_second": 0.305
+    "train_loss": 0.0,
+    "train_runtime": 1.3096,
+    "train_samples_per_second": 7.636,
+    "train_steps_per_second": 1.527
 }

trainer_state.json

@@ -12,16 +12,16 @@
       "epoch": 2.0,
       "step": 6,
       "total_flos": 168628741816320.0,
-      "train_loss": 1.7585566838582356,
-      "train_runtime": 19.6571,
-      "train_samples_per_second": 1.526,
-      "train_steps_per_second": 0.305
+      "train_loss": 0.0,
+      "train_runtime": 1.3096,
+      "train_samples_per_second": 7.636,
+      "train_steps_per_second": 1.527
     }
   ],
   "logging_steps": 10,
-  "max_steps": 6,
+  "max_steps": 2,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 1,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {