Hugging Face's logo

meoo225
/
FLANT5_base

Text2Text Generation
Transformers
TensorBoard
Safetensors
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
meoo225 commited on
Commit
c9d0743
•
1 Parent(s): 1547085

End of training

Browse files
Files changed (2) hide show
  1. README.md +12 -13
  2. logs/events.out.tfevents.1727583522.ff17c483a60e.1213.2 +2 -2
README.md CHANGED
@@ -19,12 +19,12 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.0941
23
- - Bleu Score: 24.9007
24
- - Precision: 6.0932
25
- - Recall: 6.0932
26
- - Gen Len: 18.8172
27
- - Err: 6.0932
28
 
29
  ## Model description
30
 
@@ -44,21 +44,20 @@ More information needed
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 0.0001
47
- - train_batch_size: 8
48
- - eval_batch_size: 8
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
- - num_epochs: 4
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Bleu Score | Precision | Recall | Gen Len | Err |
57
  |:-------------:|:-----:|:----:|:---------------:|:----------:|:---------:|:------:|:-------:|:------:|
58
- | 0.2195 | 1.0 | 838 | 0.1354 | 23.7654 | 5.0179 | 5.0179 | 18.7945 | 5.0179 |
59
- | 0.1289 | 2.0 | 1676 | 0.1085 | 24.5365 | 5.7348 | 5.7348 | 18.8053 | 5.7348 |
60
- | 0.104 | 3.0 | 2514 | 0.0969 | 24.9198 | 6.0932 | 6.0932 | 18.8112 | 6.0932 |
61
- | 0.0906 | 4.0 | 3352 | 0.0941 | 24.9007 | 6.0932 | 6.0932 | 18.8172 | 6.0932 |
62
 
63
 
64
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.1150
23
+ - Bleu Score: 24.3919
24
+ - Precision: 5.3763
25
+ - Recall: 5.3763
26
+ - Gen Len: 18.8088
27
+ - Err: 5.3763
28
 
29
  ## Model description
30
 
 
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 0.0001
47
+ - train_batch_size: 16
48
+ - eval_batch_size: 16
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 3
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Bleu Score | Precision | Recall | Gen Len | Err |
57
  |:-------------:|:-----:|:----:|:---------------:|:----------:|:---------:|:------:|:-------:|:------:|
58
+ | 0.2345 | 1.0 | 419 | 0.1435 | 23.524 | 3.9427 | 3.9427 | 18.8112 | 3.9427 |
59
+ | 0.1464 | 2.0 | 838 | 0.1197 | 24.2187 | 5.4958 | 5.4958 | 18.8053 | 5.4958 |
60
+ | 0.1238 | 3.0 | 1257 | 0.1150 | 24.3919 | 5.3763 | 5.3763 | 18.8088 | 5.3763 |
 
61
 
62
 
63
  ### Framework versions
logs/events.out.tfevents.1727583522.ff17c483a60e.1213.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:633eda28d99ecb59d8954eede731c0ce89f66b15abfb0e6baed454a70cdd0d09
3
- size 7397
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81b8b59950c53a43b4d648aaa5fa8f7dfc884330ce9df8e2076c1a0ab83d3f88
3
+ size 8488