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: 3.2988
-- Accuracy: 0.3947
+- Loss: 3.3078
+- Accuracy: 0.3941
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.3932824917497146,
-    "eval_loss": 3.3091650009155273,
-    "eval_runtime": 184.8493,
+    "eval_accuracy": 0.3940709857565843,
+    "eval_loss": 3.3077950477600098,
+    "eval_runtime": 179.6473,
     "eval_samples": 18011,
-    "eval_samples_per_second": 97.436,
-    "eval_steps_per_second": 6.091,
-    "perplexity": 27.3622684613255,
-    "total_flos": 7.7681859821568e+17,
-    "train_loss": 3.468291573590681,
-    "train_runtime": 80362.6457,
-    "train_samples": 297299,
-    "train_samples_per_second": 36.995,
-    "train_steps_per_second": 1.156
+    "eval_samples_per_second": 100.258,
+    "eval_steps_per_second": 6.268,
+    "perplexity": 27.324809099948503,
+    "total_flos": 7.7680292069376e+17,
+    "train_loss": 3.459367900807741,
+    "train_runtime": 79732.1586,
+    "train_samples": 297293,
+    "train_samples_per_second": 37.286,
+    "train_steps_per_second": 1.165
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.3932824917497146,
-    "eval_loss": 3.3091650009155273,
-    "eval_runtime": 184.8493,
+    "eval_accuracy": 0.3940709857565843,
+    "eval_loss": 3.3077950477600098,
+    "eval_runtime": 179.6473,
     "eval_samples": 18011,
-    "eval_samples_per_second": 97.436,
-    "eval_steps_per_second": 6.091,
-    "perplexity": 27.3622684613255
+    "eval_samples_per_second": 100.258,
+    "eval_steps_per_second": 6.268,
+    "perplexity": 27.324809099948503
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 10.0,
-    "total_flos": 7.7681859821568e+17,
-    "train_loss": 3.468291573590681,
-    "train_runtime": 80362.6457,
-    "train_samples": 297299,
-    "train_samples_per_second": 36.995,
-    "train_steps_per_second": 1.156
+    "total_flos": 7.7680292069376e+17,
+    "train_loss": 3.459367900807741,
+    "train_runtime": 79732.1586,
+    "train_samples": 297293,
+    "train_samples_per_second": 37.286,
+    "train_steps_per_second": 1.165
 }