Final One

README.md

@@ -14,14 +14,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [csebuetnlp/banglat5](https://huggingface.co/csebuetnlp/banglat5) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.3061
-- eval_Val Accuracy: 0.9145
-- eval_gen_len: 2.2787
-- eval_runtime: 22.1611
-- eval_samples_per_second: 100.852
-- eval_steps_per_second: 3.159
-- epoch: 36.0
-- step: 2160
+- eval_loss: 0.3591
+- eval_Val Accuracy: 0.9154
+- eval_gen_len: 2.2689
+- eval_runtime: 20.4191
+- eval_samples_per_second: 109.456
+- eval_steps_per_second: 3.428
+- epoch: 37.0
+- step: 2220
 
 ## Model description
 
@@ -40,7 +40,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
+- learning_rate: 0.0005
 - train_batch_size: 300
 - eval_batch_size: 32
 - seed: 42

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f2b31a22a002ad2be15d3ca2cc9d87467af7a27a0a927244aa499a92c8a203a
+oid sha256:f1292ede8cc2c802578c5a923e9220de97ee792ae4eae2337dceb13a940da461
 size 990408885