Hugging Face's logo

hawalurahman
/
mt5-base-qa_v2

Text2Text Generation
Transformers
Safetensors
mt5
Generated from Trainer
Inference Endpoints
Model card Files Community
hawalurahman commited on
Commit
ae0e14f
·
verified ·
1 Parent(s): c35debf

End of training

Browse files
Files changed (2) hide show
  1. README.md +13 -13
  2. model.safetensors +1 -1
README.md CHANGED
@@ -19,13 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 1.9335
23
- - Rouge1: 0.5694
24
- - Rouge2: 0.3180
25
- - Rougel: 0.5689
26
- - Rougelsum: 0.5691
27
- - Bleu: 0.3589
28
- - Exact Match: 0.375
29
 
30
  ## Model description
31
 
@@ -44,7 +44,7 @@ More information needed
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
- - learning_rate: 0.0003
48
  - train_batch_size: 8
49
  - eval_batch_size: 8
50
  - seed: 42
@@ -56,11 +56,11 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu | Exact Match |
58
  |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:------:|:-----------:|
59
- | 0.5527 | 1.0 | 2200 | 1.1981 | 0.5364 | 0.3114 | 0.5367 | 0.5363 | 0.3358 | 0.3414 |
60
- | 0.2206 | 2.0 | 4400 | 1.3928 | 0.5602 | 0.3095 | 0.5598 | 0.5597 | 0.3468 | 0.3486 |
61
- | 0.0885 | 3.0 | 6600 | 1.5233 | 0.5657 | 0.3118 | 0.5654 | 0.5658 | 0.3575 | 0.3630 |
62
- | 0.0313 | 4.0 | 8800 | 1.8523 | 0.5684 | 0.3246 | 0.5678 | 0.5683 | 0.3796 | 0.3698 |
63
- | 0.0149 | 5.0 | 11000 | 1.9335 | 0.5694 | 0.3180 | 0.5689 | 0.5691 | 0.3589 | 0.375 |
64
 
65
 
66
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 1.5989
23
+ - Rouge1: 0.6780
24
+ - Rouge2: 0.3874
25
+ - Rougel: 0.6773
26
+ - Rougelsum: 0.6775
27
+ - Bleu: 0.4518
28
+ - Exact Match: 0.4502
29
 
30
  ## Model description
31
 
 
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
+ - learning_rate: 0.0001
48
  - train_batch_size: 8
49
  - eval_batch_size: 8
50
  - seed: 42
 
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu | Exact Match |
58
  |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:------:|:-----------:|
59
+ | 0.5705 | 1.0 | 2100 | 0.8504 | 0.6538 | 0.3810 | 0.6534 | 0.6539 | 0.4289 | 0.4369 |
60
+ | 0.2728 | 2.0 | 4200 | 1.0248 | 0.6644 | 0.3734 | 0.6637 | 0.6646 | 0.4145 | 0.4360 |
61
+ | 0.1418 | 3.0 | 6300 | 1.3020 | 0.6664 | 0.3812 | 0.6657 | 0.6661 | 0.4362 | 0.4269 |
62
+ | 0.0834 | 4.0 | 8400 | 1.4760 | 0.6739 | 0.3790 | 0.6731 | 0.6737 | 0.4233 | 0.4431 |
63
+ | 0.0568 | 5.0 | 10500 | 1.5989 | 0.6780 | 0.3874 | 0.6773 | 0.6775 | 0.4518 | 0.4502 |
64
 
65
 
66
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9090288bbfd3371cef90f26f4c73177234f2a4f6e56bf17925b308293ccb847c
3
  size 2329638768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6651b557c03ecba81f150e2cf0926f882a9c2041370a730a6771858a1754697a
3
  size 2329638768