Hugging Face's logo

henri28
/
small_dataset

Transformers
PyTorch
TensorBoard
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
 Metrics Community
1
henri28 commited on
Commit
bbb608b
·
1 Parent(s): 4c2c8f7

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -16
README.md CHANGED
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.7022
20
- - Sacrebleu: 6.3859
21
- - Gen Len: 11.5238
22
 
23
  ## Model description
24
 
@@ -38,27 +38,22 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 2e-05
41
- - train_batch_size: 16
42
- - eval_batch_size: 16
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - num_epochs: 10
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Sacrebleu | Gen Len |
51
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
52
- | No log | 1.0 | 5 | 0.7302 | 6.3859 | 11.5238 |
53
- | No log | 2.0 | 10 | 0.7235 | 6.3859 | 11.5238 |
54
- | No log | 3.0 | 15 | 0.7178 | 6.3859 | 11.5238 |
55
- | No log | 4.0 | 20 | 0.7133 | 6.3859 | 11.5238 |
56
- | No log | 5.0 | 25 | 0.7097 | 6.3859 | 11.5238 |
57
- | No log | 6.0 | 30 | 0.7070 | 6.3859 | 11.5238 |
58
- | No log | 7.0 | 35 | 0.7050 | 6.3859 | 11.5238 |
59
- | No log | 8.0 | 40 | 0.7035 | 6.3859 | 11.5238 |
60
- | No log | 9.0 | 45 | 0.7025 | 6.3859 | 11.5238 |
61
- | No log | 10.0 | 50 | 0.7022 | 6.3859 | 11.5238 |
62
 
63
 
64
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.8369
20
+ - Sacrebleu: 12.0986
21
+ - Gen Len: 11.0
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 2e-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 32
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 5
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Sacrebleu | Gen Len |
51
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
52
+ | No log | 1.0 | 3 | 0.8464 | 12.0986 | 11.0 |
53
+ | No log | 2.0 | 6 | 0.8420 | 12.0986 | 11.0 |
54
+ | No log | 3.0 | 9 | 0.8393 | 12.0986 | 11.0 |
55
+ | No log | 4.0 | 12 | 0.8375 | 12.0986 | 11.0 |
56
+ | No log | 5.0 | 15 | 0.8369 | 12.0986 | 11.0 |
 
 
 
 
 
57
 
58
 
59
  ### Framework versions