Hugging Face's logo

armahlovis
/
English2AkuapemTwi

Text2Text Generation
Transformers
PyTorch
TensorBoard
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
armahlovis commited on
Commit
baa68fb
·
1 Parent(s): 0793c8f

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -11
README.md CHANGED
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [allenai/unifiedqa-t5-small](https://huggingface.co/allenai/unifiedqa-t5-small) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 2.2299
19
- - Bleu: 0.7515
20
- - Gen Len: 18.7089
21
 
22
  ## Model description
23
 
@@ -42,18 +42,23 @@ The following hyperparameters were used during training:
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
- - num_epochs: 5
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
51
- |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
52
- | 2.9036 | 1.0 | 1271 | 2.5652 | 0.1936 | 18.9528 |
53
- | 2.6319 | 2.0 | 2542 | 2.3880 | 0.2541 | 18.8674 |
54
- | 2.5455 | 3.0 | 3813 | 2.2948 | 0.5673 | 18.7748 |
55
- | 2.464 | 4.0 | 5084 | 2.2454 | 0.6242 | 18.7203 |
56
- | 2.4371 | 5.0 | 6355 | 2.2299 | 0.7515 | 18.7089 |
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [allenai/unifiedqa-t5-small](https://huggingface.co/allenai/unifiedqa-t5-small) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.7965
19
+ - Bleu: 2.9106
20
+ - Gen Len: 18.0456
21
 
22
  ## Model description
23
 
 
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - num_epochs: 10
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
51
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
52
+ | 2.3494 | 1.0 | 1271 | 2.1102 | 1.0276 | 18.5653 |
53
+ | 2.2477 | 2.0 | 2542 | 2.0249 | 1.3762 | 18.45 |
54
+ | 2.1948 | 3.0 | 3813 | 1.9608 | 1.828 | 18.2878 |
55
+ | 2.1267 | 4.0 | 5084 | 1.9098 | 2.2275 | 18.2215 |
56
+ | 2.0874 | 5.0 | 6355 | 1.8740 | 2.4207 | 18.1536 |
57
+ | 2.049 | 6.0 | 7626 | 1.8446 | 2.6023 | 18.1613 |
58
+ | 2.0445 | 7.0 | 8897 | 1.8232 | 2.7413 | 18.1157 |
59
+ | 2.0083 | 8.0 | 10168 | 1.8085 | 2.8521 | 18.0515 |
60
+ | 2.0093 | 9.0 | 11439 | 1.7994 | 2.8695 | 18.0852 |
61
+ | 1.9934 | 10.0 | 12710 | 1.7965 | 2.9106 | 18.0456 |
62
 
63
 
64
  ### Framework versions