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: 3.3045
-- Accuracy: 0.3938
+- Loss: 3.3100
+- Accuracy: 0.3934
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.3940823943098048,
-    "eval_loss": 3.3038175106048584,
-    "eval_runtime": 188.5528,
+    "eval_accuracy": 0.39344634030453884,
+    "eval_loss": 3.310047149658203,
+    "eval_runtime": 146.2717,
     "eval_samples": 18011,
-    "eval_samples_per_second": 95.522,
-    "eval_steps_per_second": 5.972,
-    "perplexity": 27.216339520393753,
-    "total_flos": 7.7681598529536e+17,
-    "train_loss": 3.4615205547984353,
-    "train_runtime": 81693.8548,
-    "train_samples": 297298,
-    "train_samples_per_second": 36.392,
-    "train_steps_per_second": 1.137
+    "eval_samples_per_second": 123.134,
+    "eval_steps_per_second": 7.698,
+    "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
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.3940823943098048,
-    "eval_loss": 3.3038175106048584,
-    "eval_runtime": 188.5528,
+    "eval_accuracy": 0.39344634030453884,
+    "eval_loss": 3.310047149658203,
+    "eval_runtime": 146.2717,
     "eval_samples": 18011,
-    "eval_samples_per_second": 95.522,
-    "eval_steps_per_second": 5.972,
-    "perplexity": 27.216339520393753
+    "eval_samples_per_second": 123.134,
+    "eval_steps_per_second": 7.698,
+    "perplexity": 27.38641670164935
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 10.0,
-    "total_flos": 7.7681598529536e+17,
-    "train_loss": 3.4615205547984353,
-    "train_runtime": 81693.8548,
-    "train_samples": 297298,
-    "train_samples_per_second": 36.392,
-    "train_steps_per_second": 1.137
+    "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
 }