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: 3.2991
-- Accuracy: 0.3948
+- Loss: 3.3018
+- Accuracy: 0.3945
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.3940709857565843,
-    "eval_loss": 3.3077950477600098,
-    "eval_runtime": 182.5649,
+    "eval_accuracy": 0.3944938627959582,
+    "eval_loss": 3.301800489425659,
+    "eval_runtime": 190.0395,
     "eval_samples": 18011,
-    "eval_samples_per_second": 98.655,
-    "eval_steps_per_second": 6.168,
-    "perplexity": 27.324809099948503,
-    "total_flos": 7.7681337237504e+17,
-    "train_loss": 3.461240393532168,
-    "train_runtime": 80463.1399,
-    "train_samples": 297297,
-    "train_samples_per_second": 36.948,
-    "train_steps_per_second": 1.155
+    "eval_samples_per_second": 94.775,
+    "eval_steps_per_second": 5.925,
+    "perplexity": 27.161498913086728,
+    "total_flos": 7.76821211136e+17,
+    "train_loss": 3.4522010074032865,
+    "train_runtime": 81258.1448,
+    "train_samples": 297300,
+    "train_samples_per_second": 36.587,
+    "train_steps_per_second": 1.143
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.3940709857565843,
-    "eval_loss": 3.3077950477600098,
-    "eval_runtime": 182.5649,
+    "eval_accuracy": 0.3944938627959582,
+    "eval_loss": 3.301800489425659,
+    "eval_runtime": 190.0395,
     "eval_samples": 18011,
-    "eval_samples_per_second": 98.655,
-    "eval_steps_per_second": 6.168,
-    "perplexity": 27.324809099948503
+    "eval_samples_per_second": 94.775,
+    "eval_steps_per_second": 5.925,
+    "perplexity": 27.161498913086728
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 10.0,
-    "total_flos": 7.7681337237504e+17,
-    "train_loss": 3.461240393532168,
-    "train_runtime": 80463.1399,
-    "train_samples": 297297,
-    "train_samples_per_second": 36.948,
-    "train_steps_per_second": 1.155
+    "total_flos": 7.76821211136e+17,
+    "train_loss": 3.4522010074032865,
+    "train_runtime": 81258.1448,
+    "train_samples": 297300,
+    "train_samples_per_second": 36.587,
+    "train_steps_per_second": 1.143
 }