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: 3.3026
-- Accuracy: 0.3943
+- Loss: 3.3066
+- Accuracy: 0.3939
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.3943953146267105,
-    "eval_loss": 3.3019161224365234,
-    "eval_runtime": 189.6088,
+    "eval_accuracy": 0.3939400590267678,
+    "eval_loss": 3.3066227436065674,
+    "eval_runtime": 184.2402,
     "eval_samples": 18011,
-    "eval_samples_per_second": 94.99,
-    "eval_steps_per_second": 5.939,
-    "perplexity": 27.164639860580742,
-    "total_flos": 7.76821211136e+17,
-    "train_loss": 3.4556877505752324,
-    "train_runtime": 82552.4271,
-    "train_samples": 297300,
-    "train_samples_per_second": 36.013,
-    "train_steps_per_second": 1.125
+    "eval_samples_per_second": 97.758,
+    "eval_steps_per_second": 6.112,
+    "perplexity": 27.292794881615595,
+    "total_flos": 7.7681075945472e+17,
+    "train_loss": 3.4603127508396456,
+    "train_runtime": 79796.1096,
+    "train_samples": 297296,
+    "train_samples_per_second": 37.257,
+    "train_steps_per_second": 1.164
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.3943953146267105,
-    "eval_loss": 3.3019161224365234,
-    "eval_runtime": 189.6088,
+    "eval_accuracy": 0.3939400590267678,
+    "eval_loss": 3.3066227436065674,
+    "eval_runtime": 184.2402,
     "eval_samples": 18011,
-    "eval_samples_per_second": 94.99,
-    "eval_steps_per_second": 5.939,
-    "perplexity": 27.164639860580742
+    "eval_samples_per_second": 97.758,
+    "eval_steps_per_second": 6.112,
+    "perplexity": 27.292794881615595
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 10.0,
-    "total_flos": 7.76821211136e+17,
-    "train_loss": 3.4556877505752324,
-    "train_runtime": 82552.4271,
-    "train_samples": 297300,
-    "train_samples_per_second": 36.013,
-    "train_steps_per_second": 1.125
+    "total_flos": 7.7681075945472e+17,
+    "train_loss": 3.4603127508396456,
+    "train_runtime": 79796.1096,
+    "train_samples": 297296,
+    "train_samples_per_second": 37.257,
+    "train_steps_per_second": 1.164
 }