Hugging Face's logo

mbiskho
/
text-to-text

Transformers
TensorBoard
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
mbiskho commited on
Commit
04dc6d2
·
1 Parent(s): 69ac36a

End of training

Browse files
Files changed (1) hide show
  1. README.md +14 -14
README.md CHANGED
@@ -18,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
18
  This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 5.1157
21
- - Rouge1: 39.263
22
- - Rouge2: 15.2946
23
- - Rougel: 32.2563
24
- - Rougelsum: 35.8226
25
  - Gen Len: 17.5447
26
 
27
  ## Model description
@@ -53,16 +53,16 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
56
- | 2.4195 | 1.0 | 287 | 2.0451 | 38.213 | 15.3789 | 32.2898 | 34.0727 | 14.9350 |
57
- | 1.5202 | 2.0 | 574 | 2.1663 | 37.3984 | 14.2896 | 30.7444 | 33.2353 | 15.6179 |
58
- | 0.8321 | 3.0 | 861 | 2.3894 | 39.8908 | 15.9311 | 32.5462 | 35.4881 | 15.9837 |
59
- | 0.8915 | 4.0 | 1148 | 2.7800 | 37.6389 | 14.1438 | 29.8417 | 33.7508 | 17.4472 |
60
- | 0.4739 | 5.0 | 1435 | 2.9443 | 38.7494 | 14.4766 | 31.3017 | 34.688 | 16.6260 |
61
- | 0.4026 | 6.0 | 1722 | 3.4132 | 38.6449 | 13.4983 | 31.1552 | 34.3175 | 17.6016 |
62
- | 0.0301 | 7.0 | 2009 | 3.9872 | 38.4768 | 14.3417 | 30.8234 | 34.5067 | 17.4959 |
63
- | 0.0504 | 8.0 | 2296 | 4.3657 | 38.3356 | 13.9429 | 30.2416 | 33.6339 | 17.1870 |
64
- | 0.0017 | 9.0 | 2583 | 5.0423 | 39.504 | 14.3981 | 31.5052 | 35.042 | 17.1382 |
65
- | 0.0038 | 10.0 | 2870 | 5.1157 | 39.263 | 15.2946 | 32.2563 | 35.8226 | 17.5447 |
66
 
67
 
68
  ### Framework versions
 
18
  This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 5.1157
21
+ - Rouge1: 39.2425
22
+ - Rouge2: 15.3791
23
+ - Rougel: 32.2803
24
+ - Rougelsum: 35.7848
25
  - Gen Len: 17.5447
26
 
27
  ## Model description
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
56
+ | 2.4195 | 1.0 | 287 | 2.0451 | 38.2732 | 15.4594 | 32.1587 | 34.1054 | 14.9350 |
57
+ | 1.5202 | 2.0 | 574 | 2.1663 | 37.2747 | 14.3187 | 30.7608 | 33.1298 | 15.6179 |
58
+ | 0.8321 | 3.0 | 861 | 2.3894 | 39.7659 | 15.9607 | 32.553 | 35.5703 | 15.9837 |
59
+ | 0.8915 | 4.0 | 1148 | 2.7800 | 37.5833 | 14.0917 | 29.9648 | 33.7803 | 17.4472 |
60
+ | 0.4739 | 5.0 | 1435 | 2.9443 | 38.6304 | 14.5346 | 31.2649 | 34.7004 | 16.6260 |
61
+ | 0.4026 | 6.0 | 1722 | 3.4132 | 38.5667 | 13.5102 | 31.2463 | 34.3462 | 17.6016 |
62
+ | 0.0301 | 7.0 | 2009 | 3.9872 | 38.4039 | 14.3773 | 30.8458 | 34.5474 | 17.4959 |
63
+ | 0.0504 | 8.0 | 2296 | 4.3657 | 38.2491 | 13.9452 | 30.3137 | 33.6681 | 17.1870 |
64
+ | 0.0017 | 9.0 | 2583 | 5.0423 | 39.4347 | 14.464 | 31.561 | 35.0523 | 17.1382 |
65
+ | 0.0038 | 10.0 | 2870 | 5.1157 | 39.2425 | 15.3791 | 32.2803 | 35.7848 | 17.5447 |
66
 
67
 
68
  ### Framework versions