Hugging Face's logo

iManay
/
fil-bic-mt5b

Text2Text Generation
Transformers
TensorFlow
mt5
generated_from_keras_callback
Inference Endpoints
Model card Files Community
iManay commited on
Commit
dc1a966
•
1 Parent(s): 5ad8846

End of training

Browse files
Files changed (2) hide show
  1. README.md +24 -14
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_keras_callback
5
- base_model: google/mt5-base
6
  model-index:
7
  - name: fil-bic-mt5b
8
  results: []
@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 2.7310
19
- - Validation Loss: 2.8968
20
- - Epoch: 9
21
 
22
  ## Model description
23
 
@@ -43,16 +43,26 @@ The following hyperparameters were used during training:
43
 
44
  | Train Loss | Validation Loss | Epoch |
45
  |:----------:|:---------------:|:-----:|
46
- | 5.6830 | 3.9591 | 0 |
47
- | 3.9193 | 3.4118 | 1 |
48
- | 3.4188 | 3.1931 | 2 |
49
- | 4.6409 | 5.8359 | 3 |
50
- | 5.4986 | 4.8224 | 4 |
51
- | 5.0763 | 4.3305 | 5 |
52
- | 3.7572 | 3.2735 | 6 |
53
- | 3.1140 | 3.0649 | 7 |
54
- | 2.8746 | 2.9594 | 8 |
55
- | 2.7310 | 2.8968 | 9 |
 
 
 
 
 
 
 
 
 
 
56
 
57
 
58
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: google/mt5-base
4
  tags:
5
  - generated_from_keras_callback
 
6
  model-index:
7
  - name: fil-bic-mt5b
8
  results: []
 
15
 
16
  This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.2155
19
+ - Validation Loss: 2.4691
20
+ - Epoch: 19
21
 
22
  ## Model description
23
 
 
43
 
44
  | Train Loss | Validation Loss | Epoch |
45
  |:----------:|:---------------:|:-----:|
46
+ | 4.8782 | 3.0764 | 0 |
47
+ | 3.0550 | 2.4897 | 1 |
48
+ | 2.4361 | 2.1678 | 2 |
49
+ | 2.0424 | 1.9982 | 3 |
50
+ | 1.7454 | 1.8860 | 4 |
51
+ | 1.5089 | 1.8502 | 5 |
52
+ | 1.3137 | 1.8682 | 6 |
53
+ | 1.1487 | 1.8252 | 7 |
54
+ | 0.9793 | 1.8486 | 8 |
55
+ | 0.8428 | 1.8815 | 9 |
56
+ | 0.7107 | 1.9716 | 10 |
57
+ | 0.6015 | 2.0271 | 11 |
58
+ | 0.5106 | 2.1239 | 12 |
59
+ | 0.4392 | 2.2095 | 13 |
60
+ | 0.3786 | 2.2045 | 14 |
61
+ | 0.3315 | 2.2884 | 15 |
62
+ | 0.2882 | 2.3419 | 16 |
63
+ | 0.2587 | 2.4029 | 17 |
64
+ | 0.2354 | 2.4173 | 18 |
65
+ | 0.2155 | 2.4691 | 19 |
66
 
67
 
68
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21008d04a7f309138b7b33217a7b482082cf46584eeb22ecdd0fe9a17947595d
3
  size 3866872432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c67e864ce326aef8c7359d86c1e63536f6c245900e862938d3ad6e71e34f9f6c
3
  size 3866872432