End of training

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [vinai/bertweet-base](https://huggingface.co/vinai/bertweet-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.3321
+- Loss: 2.6866
 
 ## Model description
 

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 19.57,
-    "eval_loss": 2.708733320236206,
-    "eval_runtime": 133.4182,
+    "eval_loss": 2.686579704284668,
+    "eval_runtime": 116.5028,
     "eval_samples": 103275,
-    "eval_samples_per_second": 774.07,
-    "eval_steps_per_second": 48.382,
-    "perplexity": 15.010250287695158,
-    "train_loss": 2.9400340771484377,
-    "train_runtime": 198144.865,
+    "eval_samples_per_second": 886.46,
+    "eval_steps_per_second": 55.406,
+    "perplexity": 14.68137530294196,
+    "train_loss": 3.268406458333333,
+    "train_runtime": 194422.9949,
     "train_samples": 1962232,
-    "train_samples_per_second": 193.798,
-    "train_steps_per_second": 12.112
+    "train_samples_per_second": 197.508,
+    "train_steps_per_second": 12.344
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 19.57,
-    "eval_loss": 2.708733320236206,
-    "eval_runtime": 133.4182,
+    "eval_loss": 2.686579704284668,
+    "eval_runtime": 116.5028,
     "eval_samples": 103275,
-    "eval_samples_per_second": 774.07,
-    "eval_steps_per_second": 48.382,
-    "perplexity": 15.010250287695158
+    "eval_samples_per_second": 886.46,
+    "eval_steps_per_second": 55.406,
+    "perplexity": 14.68137530294196
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 19.57,
-    "train_loss": 2.9400340771484377,
-    "train_runtime": 198144.865,
+    "train_loss": 3.268406458333333,
+    "train_runtime": 194422.9949,
     "train_samples": 1962232,
-    "train_samples_per_second": 193.798,
-    "train_steps_per_second": 12.112
+    "train_samples_per_second": 197.508,
+    "train_steps_per_second": 12.344
 }