End of training

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.3069
-- Accuracy: 0.3938
+- Loss: 3.3100
+- Accuracy: 0.3934
 
 ## Model description
 

all_results.json

@@ -2,15 +2,15 @@
     "epoch": 10.0,
     "eval_accuracy": 0.39344634030453884,
     "eval_loss": 3.310047149658203,
-    "eval_runtime": 148.8618,
+    "eval_runtime": 155.1269,
     "eval_samples": 18011,
-    "eval_samples_per_second": 120.991,
-    "eval_steps_per_second": 7.564,
+    "eval_samples_per_second": 116.105,
+    "eval_steps_per_second": 7.259,
     "perplexity": 27.38641670164935,
-    "total_flos": 7.7680292069376e+17,
-    "train_loss": 3.457376794955687,
-    "train_runtime": 62616.3873,
-    "train_samples": 297293,
-    "train_samples_per_second": 47.478,
-    "train_steps_per_second": 1.484
+    "total_flos": 7.7682904989696e+17,
+    "train_loss": 3.470727823430095,
+    "train_runtime": 62641.9878,
+    "train_samples": 297303,
+    "train_samples_per_second": 47.461,
+    "train_steps_per_second": 1.483
 }

eval_results.json

@@ -2,9 +2,9 @@
     "epoch": 10.0,
     "eval_accuracy": 0.39344634030453884,
     "eval_loss": 3.310047149658203,
-    "eval_runtime": 148.8618,
+    "eval_runtime": 155.1269,
     "eval_samples": 18011,
-    "eval_samples_per_second": 120.991,
-    "eval_steps_per_second": 7.564,
+    "eval_samples_per_second": 116.105,
+    "eval_steps_per_second": 7.259,
     "perplexity": 27.38641670164935
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 10.0,
-    "total_flos": 7.7680292069376e+17,
-    "train_loss": 3.457376794955687,
-    "train_runtime": 62616.3873,
-    "train_samples": 297293,
-    "train_samples_per_second": 47.478,
-    "train_steps_per_second": 1.484
+    "total_flos": 7.7682904989696e+17,
+    "train_loss": 3.470727823430095,
+    "train_runtime": 62641.9878,
+    "train_samples": 297303,
+    "train_samples_per_second": 47.461,
+    "train_steps_per_second": 1.483
 }