End of training

README.md

@@ -17,8 +17,8 @@ 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: 3.5487
-- Accuracy: 0.3747
+- Loss: 3.5524
+- Accuracy: 0.3701
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 29.103924080111785,
+    "eval_accuracy": 0.37006880401040776,
+    "eval_loss": 3.5523860454559326,
+    "eval_runtime": 82.3256,
+    "eval_samples": 16651,
+    "eval_samples_per_second": 202.258,
+    "eval_steps_per_second": 12.645,
+    "perplexity": 34.896482824279595,
+    "total_flos": 2.089804004130816e+18,
+    "train_loss": 0.6325379557800292,
+    "train_runtime": 14824.291,
+    "train_samples": 274807,
+    "train_samples_per_second": 926.881,
+    "train_steps_per_second": 11.589
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 29.103924080111785,
+    "eval_accuracy": 0.37006880401040776,
+    "eval_loss": 3.5523860454559326,
+    "eval_runtime": 82.3256,
+    "eval_samples": 16651,
+    "eval_samples_per_second": 202.258,
+    "eval_steps_per_second": 12.645,
+    "perplexity": 34.896482824279595
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 29.103924080111785,
+    "total_flos": 2.089804004130816e+18,
+    "train_loss": 0.6325379557800292,
+    "train_runtime": 14824.291,
+    "train_samples": 274807,
+    "train_samples_per_second": 926.881,
+    "train_steps_per_second": 11.589
+}