Hugging Face's logo

din0s
/
t5-base-asqa-ob

Text2Text Generation
Transformers
PyTorch
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
1
din0s commited on
Commit
1cc3b1a
•
1 Parent(s): 69e47ec

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +23 -10
README.md CHANGED
@@ -14,8 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 2.2086
18
- - Rougelsum: 11.8466
19
 
20
  ## Model description
21
 
@@ -34,7 +34,7 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - learning_rate: 0.0005
38
  - train_batch_size: 8
39
  - eval_batch_size: 8
40
  - seed: 42
@@ -47,13 +47,26 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Rougelsum |
49
  |:-------------:|:-----:|:----:|:---------------:|:---------:|
50
- | No log | 1.0 | 355 | 1.7972 | 11.9539 |
51
- | 1.9198 | 2.0 | 710 | 1.8071 | 12.2057 |
52
- | 1.504 | 3.0 | 1065 | 1.8566 | 11.9288 |
53
- | 1.504 | 4.0 | 1420 | 1.9225 | 11.9550 |
54
- | 1.232 | 5.0 | 1775 | 2.0097 | 11.9038 |
55
- | 1.0016 | 6.0 | 2130 | 2.0912 | 11.9418 |
56
- | 1.0016 | 7.0 | 2485 | 2.2086 | 11.8466 |
 
 
 
 
 
 
 
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 1.7356
18
+ - Rougelsum: 12.0879
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 1e-05
38
  - train_batch_size: 8
39
  - eval_batch_size: 8
40
  - seed: 42
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Rougelsum |
49
  |:-------------:|:-----:|:----:|:---------------:|:---------:|
50
+ | No log | 1.0 | 355 | 1.8545 | 11.6549 |
51
+ | 2.4887 | 2.0 | 710 | 1.8050 | 11.7533 |
52
+ | 1.9581 | 3.0 | 1065 | 1.7843 | 11.8327 |
53
+ | 1.9581 | 4.0 | 1420 | 1.7722 | 11.9442 |
54
+ | 1.9252 | 5.0 | 1775 | 1.7648 | 11.9331 |
55
+ | 1.8853 | 6.0 | 2130 | 1.7567 | 11.9788 |
56
+ | 1.8853 | 7.0 | 2485 | 1.7519 | 12.0300 |
57
+ | 1.8512 | 8.0 | 2840 | 1.7483 | 12.0225 |
58
+ | 1.8328 | 9.0 | 3195 | 1.7451 | 12.0402 |
59
+ | 1.8115 | 10.0 | 3550 | 1.7436 | 12.0444 |
60
+ | 1.8115 | 11.0 | 3905 | 1.7419 | 12.0850 |
61
+ | 1.7878 | 12.0 | 4260 | 1.7408 | 12.1047 |
62
+ | 1.774 | 13.0 | 4615 | 1.7394 | 12.0839 |
63
+ | 1.774 | 14.0 | 4970 | 1.7390 | 12.0910 |
64
+ | 1.7787 | 15.0 | 5325 | 1.7381 | 12.0880 |
65
+ | 1.7632 | 16.0 | 5680 | 1.7380 | 12.1088 |
66
+ | 1.7623 | 17.0 | 6035 | 1.7370 | 12.1046 |
67
+ | 1.7623 | 18.0 | 6390 | 1.7368 | 12.0997 |
68
+ | 1.7508 | 19.0 | 6745 | 1.7359 | 12.0902 |
69
+ | 1.7597 | 20.0 | 7100 | 1.7356 | 12.0879 |
70
 
71
 
72
  ### Framework versions