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: 3.5344
-- Accuracy: 0.3757
+- Loss: 3.5709
+- Accuracy: 0.3680
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 28.812761993479274,
+    "eval_accuracy": 0.3679951522337063,
+    "eval_loss": 3.5708882808685303,
+    "eval_runtime": 84.1498,
+    "eval_samples": 16651,
+    "eval_samples_per_second": 197.873,
+    "eval_steps_per_second": 12.371,
+    "perplexity": 35.54815587804809,
+    "total_flos": 2.068898812526592e+18,
+    "train_loss": 3.3872425547898417,
+    "train_runtime": 73941.0651,
+    "train_samples": 274807,
+    "train_samples_per_second": 185.828,
+    "train_steps_per_second": 2.323
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 28.812761993479274,
+    "eval_accuracy": 0.3679951522337063,
+    "eval_loss": 3.5708882808685303,
+    "eval_runtime": 84.1498,
+    "eval_samples": 16651,
+    "eval_samples_per_second": 197.873,
+    "eval_steps_per_second": 12.371,
+    "perplexity": 35.54815587804809
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 28.812761993479274,
+    "total_flos": 2.068898812526592e+18,
+    "train_loss": 3.3872425547898417,
+    "train_runtime": 73941.0651,
+    "train_samples": 274807,
+    "train_samples_per_second": 185.828,
+    "train_steps_per_second": 2.323
+}