fia24
/

annotator

text2text-generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

fia24 commited on Oct 27, 2023

Commit

22c2e02

·

1 Parent(s): f9ccaad

Final One

Files changed (2) hide show

README.md +9 -9
pytorch_model.bin +1 -1

README.md CHANGED Viewed

@@ -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: 0.2687
-- eval_Val Accuracy: 0.9199
-- eval_gen_len: 2.9891
-- eval_runtime: 38.8355
-- eval_samples_per_second: 91.9
-- eval_steps_per_second: 2.884
-- epoch: 16.0
-- step: 2288
 ## Model description
@@ -41,7 +41,7 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 0.0005
-- train_batch_size: 200
 - eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08

 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: 0.1905
+- eval_Val Accuracy: 0.9204
+- eval_gen_len: 3.0017
+- eval_runtime: 35.1301
+- eval_samples_per_second: 101.252
+- eval_steps_per_second: 3.188
+- epoch: 6.0
+- step: 684
 ## Model description
 The following hyperparameters were used during training:
 - learning_rate: 0.0005
+- train_batch_size: 250
 - eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b49a21c89fa44010cd77970520eb18851c42e86a108b56597d5ae211f3b596ab
 size 990408885

 version https://git-lfs.github.com/spec/v1
+oid sha256:2c3eb4d3733684dfc181d84db5c041228431f4fae7671d0cc5e396411c8973cd
 size 990408885