End of training

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: riotu-lab/ArabianGPT-01B
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: test-aragpt
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # test-aragpt
 
 This model is a fine-tuned version of [riotu-lab/ArabianGPT-01B](https://huggingface.co/riotu-lab/ArabianGPT-01B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.3387
+- Accuracy: 0.2541
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.25405778786754485,
-    "eval_loss": 4.3386945724487305,
-    "eval_runtime": 27.8088,
+    "eval_accuracy": 0.2540569865270625,
+    "eval_loss": 4.338694095611572,
+    "eval_runtime": 27.7402,
     "eval_samples": 1627,
-    "eval_samples_per_second": 58.507,
-    "eval_steps_per_second": 7.336,
-    "perplexity": 76.60746853485647,
+    "eval_samples_per_second": 58.651,
+    "eval_steps_per_second": 7.354,
+    "perplexity": 76.60743200557758,
     "total_flos": 534995435520000.0,
     "train_loss": 4.0715499788697,
-    "train_runtime": 69.2711,
+    "train_runtime": 64.1161,
     "train_samples": 455,
-    "train_samples_per_second": 19.705,
-    "train_steps_per_second": 2.469
+    "train_samples_per_second": 21.29,
+    "train_steps_per_second": 2.667
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.25405778786754485,
-    "eval_loss": 4.3386945724487305,
-    "eval_runtime": 27.8088,
+    "eval_accuracy": 0.2540569865270625,
+    "eval_loss": 4.338694095611572,
+    "eval_runtime": 27.7402,
     "eval_samples": 1627,
-    "eval_samples_per_second": 58.507,
-    "eval_steps_per_second": 7.336,
-    "perplexity": 76.60746853485647
+    "eval_samples_per_second": 58.651,
+    "eval_steps_per_second": 7.354,
+    "perplexity": 76.60743200557758
 }

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 3.0,
     "total_flos": 534995435520000.0,
     "train_loss": 4.0715499788697,
-    "train_runtime": 69.2711,
+    "train_runtime": 64.1161,
     "train_samples": 455,
-    "train_samples_per_second": 19.705,
-    "train_steps_per_second": 2.469
+    "train_samples_per_second": 21.29,
+    "train_steps_per_second": 2.667
 }

trainer_state.json

@@ -13,9 +13,9 @@
       "step": 171,
       "total_flos": 534995435520000.0,
       "train_loss": 4.0715499788697,
-      "train_runtime": 69.2711,
-      "train_samples_per_second": 19.705,
-      "train_steps_per_second": 2.469
+      "train_runtime": 64.1161,
+      "train_samples_per_second": 21.29,
+      "train_steps_per_second": 2.667
     }
   ],
   "logging_steps": 500,