Hugging Face's logo

kaytoo2022
/
t5_technical

TensorFlow
t5
generated_from_keras_callback
Model card Files
xet
 Community
kaytoo2022 commited on
Commit
c28b639
·
1 Parent(s): c2a3e6e

Training in progress epoch 0

Browse files
Files changed (2) hide show
  1. README.md +4 -4
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -15,8 +15,8 @@ probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 3.4554
19
- - Validation Loss: 2.9833
20
  - Epoch: 0
21
 
22
  ## Model description
@@ -43,12 +43,12 @@ The following hyperparameters were used during training:
43
 
44
  | Train Loss | Validation Loss | Epoch |
45
  |:----------:|:---------------:|:-----:|
46
- | 3.4554 | 2.9833 | 0 |
47
 
48
 
49
  ### Framework versions
50
 
51
  - Transformers 4.42.4
52
- - TensorFlow 2.17.0
53
  - Datasets 2.20.0
54
  - Tokenizers 0.19.1
 
15
 
16
  This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 3.4682
19
+ - Validation Loss: 3.0347
20
  - Epoch: 0
21
 
22
  ## Model description
 
43
 
44
  | Train Loss | Validation Loss | Epoch |
45
  |:----------:|:---------------:|:-----:|
46
+ | 3.4682 | 3.0347 | 0 |
47
 
48
 
49
  ### Framework versions
50
 
51
  - Transformers 4.42.4
52
+ - TensorFlow 2.15.0
53
  - Datasets 2.20.0
54
  - Tokenizers 0.19.1
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb1304cffc68bec2580b280e952bb8cf068947992d6893b4b1b729e3a4462c6e
3
  size 1188285040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d61b4239aa550fe50d743d929bac8f5b111b1c949bf7c1f39655853cff149942
3
  size 1188285040