Hugging Face's logo

pakawadeep
/
mt5-base-finetuned-ctfl

Text2Text Generation
Transformers
TensorFlow
TensorBoard
mt5
generated_from_keras_callback
Inference Endpoints
Model card Files Metrics Community
pakawadeep commited on
Commit
cc208fa
•
1 Parent(s): be378b6

Training in progress epoch 0

Browse files
Files changed (6) hide show
  1. README.md +11 -40
  2. config.json +1 -1
  3. logs/train/events.out.tfevents.1710271614.2a8a6974a33b.27608.0.v2 +3 -0
  4. logs/train/events.out.tfevents.1710271813.2a8a6974a33b.28587.0.v2 +3 -0
  5. logs/validation/events.out.tfevents.1710272007.2a8a6974a33b.28587.1.v2 +3 -0
  6. tf_model.h5 +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: google/mt5-base
4
  tags:
5
  - generated_from_keras_callback
6
  model-index:
@@ -13,16 +13,16 @@ probably proofread and complete it, then remove this comment. -->
13
 
14
  # pakawadeep/mt5-base-finetuned-ctfl
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: 0.8201
19
- - Validation Loss: 0.9594
20
- - Train Rouge1: 8.3805
21
- - Train Rouge2: 2.2772
22
- - Train Rougel: 8.3805
23
- - Train Rougelsum: 8.2744
24
- - Train Gen Len: 11.9208
25
- - Epoch: 29
26
 
27
  ## Model description
28
 
@@ -48,36 +48,7 @@ The following hyperparameters were used during training:
48
 
49
  | Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
50
  |:----------:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-------------:|:-----:|
51
- | 9.7980 | 4.4890 | 0.1980 | 0.0 | 0.1980 | 0.1980 | 9.6980 | 0 |
52
- | 6.1329 | 3.5320 | 0.3960 | 0.1238 | 0.3960 | 0.3960 | 7.3218 | 1 |
53
- | 4.8185 | 3.0202 | 2.2631 | 0.2970 | 2.1169 | 2.1122 | 7.6634 | 2 |
54
- | 4.0354 | 2.6768 | 4.9505 | 0.4950 | 4.9092 | 4.9505 | 8.6436 | 3 |
55
- | 3.6591 | 2.7506 | 4.0842 | 0.6931 | 4.0842 | 4.0842 | 7.9851 | 4 |
56
- | 3.2992 | 2.2973 | 5.4691 | 1.0891 | 5.3984 | 5.3984 | 9.3267 | 5 |
57
- | 2.9827 | 2.2504 | 5.4691 | 1.0891 | 5.3984 | 5.3984 | 9.4752 | 6 |
58
- | 2.7674 | 2.1726 | 5.0743 | 0.8251 | 4.9917 | 4.9505 | 9.7079 | 7 |
59
- | 2.5786 | 2.0537 | 4.5969 | 1.0891 | 4.5262 | 4.5262 | 9.8465 | 8 |
60
- | 2.4337 | 2.0867 | 5.5163 | 1.0891 | 5.5163 | 5.5163 | 10.0693 | 9 |
61
- | 2.3270 | 1.8999 | 5.0919 | 1.0891 | 5.0212 | 5.0212 | 10.2921 | 10 |
62
- | 2.1901 | 1.8007 | 6.5064 | 1.0891 | 6.4356 | 6.7185 | 10.4653 | 11 |
63
- | 1.9749 | 1.6247 | 7.0014 | 1.6832 | 7.2136 | 7.0014 | 10.9703 | 12 |
64
- | 1.8314 | 1.5309 | 6.5771 | 1.6832 | 6.5064 | 6.5064 | 11.0941 | 13 |
65
- | 1.7107 | 1.3876 | 7.4965 | 1.6832 | 7.3314 | 7.4493 | 11.4554 | 14 |
66
- | 1.5397 | 1.3214 | 7.4257 | 1.6832 | 7.4257 | 7.4140 | 11.7178 | 15 |
67
- | 1.4493 | 1.2175 | 7.7086 | 1.9802 | 7.4965 | 7.4965 | 11.8713 | 16 |
68
- | 1.3843 | 1.1976 | 7.9915 | 1.9802 | 8.0976 | 7.9915 | 11.8218 | 17 |
69
- | 1.4072 | 1.1647 | 7.9915 | 1.9802 | 8.0976 | 7.9915 | 11.7822 | 18 |
70
- | 1.3061 | 1.1119 | 8.3805 | 2.2772 | 8.3805 | 8.2744 | 11.8564 | 19 |
71
- | 1.1619 | 1.0706 | 8.3805 | 2.2772 | 8.3805 | 8.2744 | 11.8960 | 20 |
72
- | 1.1096 | 1.0577 | 8.3805 | 2.2772 | 8.3805 | 8.2744 | 11.9307 | 21 |
73
- | 1.0644 | 1.0333 | 8.3805 | 2.2772 | 8.3805 | 8.2744 | 11.9356 | 22 |
74
- | 1.0250 | 1.0155 | 8.3805 | 2.2772 | 8.3805 | 8.2744 | 11.9109 | 23 |
75
- | 0.9973 | 0.9981 | 8.3805 | 2.2772 | 8.3805 | 8.2744 | 11.9109 | 24 |
76
- | 0.9522 | 0.9961 | 8.3805 | 2.2772 | 8.3805 | 8.2744 | 11.9158 | 25 |
77
- | 0.9143 | 0.9904 | 8.3805 | 2.2772 | 8.3805 | 8.2744 | 11.9059 | 26 |
78
- | 0.8879 | 0.9770 | 8.3805 | 2.2772 | 8.3805 | 8.2744 | 11.8960 | 27 |
79
- | 0.8563 | 0.9668 | 8.3805 | 2.2772 | 8.3805 | 8.2744 | 11.9158 | 28 |
80
- | 0.8201 | 0.9594 | 8.3805 | 2.2772 | 8.3805 | 8.2744 | 11.9208 | 29 |
81
 
82
 
83
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: pakawadeep/mt5-base-finetuned-ctfl
4
  tags:
5
  - generated_from_keras_callback
6
  model-index:
 
13
 
14
  # pakawadeep/mt5-base-finetuned-ctfl
15
 
16
+ This model is a fine-tuned version of [pakawadeep/mt5-base-finetuned-ctfl](https://huggingface.co/pakawadeep/mt5-base-finetuned-ctfl) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 1.1067
19
+ - Validation Loss: 1.0353
20
+ - Train Rouge1: 7.4965
21
+ - Train Rouge2: 1.6832
22
+ - Train Rougel: 7.4257
23
+ - Train Rougelsum: 7.3904
24
+ - Train Gen Len: 11.8762
25
+ - Epoch: 0
26
 
27
  ## Model description
28
 
 
48
 
49
  | Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
50
  |:----------:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-------------:|:-----:|
51
+ | 1.1067 | 1.0353 | 7.4965 | 1.6832 | 7.4257 | 7.3904 | 11.8762 | 0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
 
53
 
54
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "google/mt5-base",
3
  "architectures": [
4
  "MT5ForConditionalGeneration"
5
  ],
 
1
  {
2
+ "_name_or_path": "pakawadeep/mt5-base-finetuned-ctfl",
3
  "architectures": [
4
  "MT5ForConditionalGeneration"
5
  ],
logs/train/events.out.tfevents.1710271614.2a8a6974a33b.27608.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82d0ad95d8597ea70d3f7d386fabe6b7430182a0a22813064c554cf1e4aec279
3
+ size 78
logs/train/events.out.tfevents.1710271813.2a8a6974a33b.28587.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26ed7adca630f6f74a2cee4803ca8500b34446994b8b2c72ba38da28fb06c406
3
+ size 6724451
logs/validation/events.out.tfevents.1710272007.2a8a6974a33b.28587.1.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b53c0e0a382206299c57c1c51b46526db3dc135fd965671e24d8e3bd712f1047
3
+ size 232
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e329dd285cf2f4d4b4686a6f2c470d62925684539667a1868879e13d3626d379
3
  size 3866872432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81aa4227d8d08b71a68fa380848bad333bea8ec22d7b83de3d02a127389af796
3
  size 3866872432