Hugging Face's logo

n3wtou
/
mt5-small-finedtuned-4-swahili

Text2Text Generation
Transformers
TensorFlow
Swahili
mt5
generated_from_keras_callback
Inference Endpoints
Model card Files Community
1
n3wtou commited on
Commit
6ee9f5c
·
1 Parent(s): bd43c62

Training in progress epoch 2

Browse files
Files changed (2) hide show
  1. README.md +4 -3
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 3.7789
18
- - Validation Loss: 2.7822
19
- - Epoch: 1
20
 
21
  ## Model description
22
 
@@ -44,6 +44,7 @@ The following hyperparameters were used during training:
44
  |:----------:|:---------------:|:-----:|
45
  | 5.6636 | 2.9818 | 0 |
46
  | 3.7789 | 2.7822 | 1 |
 
47
 
48
 
49
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 3.3841
18
+ - Validation Loss: 2.6840
19
+ - Epoch: 2
20
 
21
  ## Model description
22
 
 
44
  |:----------:|:---------------:|:-----:|
45
  | 5.6636 | 2.9818 | 0 |
46
  | 3.7789 | 2.7822 | 1 |
47
+ | 3.3841 | 2.6840 | 2 |
48
 
49
 
50
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f8bd370743a6b5638b71f3a3016631ff877cd99ddc3589e3c50950048984ef6
3
  size 2225556280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01fbcb6b9414d19ce25942ba7be954df96fd76aaebf82addb448acf4de67795a
3
  size 2225556280