Hugging Face's logo

Pipper
/
SolExplain

Text2Text Generation
Transformers
PyTorch
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
Pipper commited on
Commit
9839730
•
1 Parent(s): 36a9518

Model save

Browse files
Files changed (3) hide show
  1. README.md +19 -9
  2. latest +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [Salesforce/codet5p-220m](https://huggingface.co/Salesforce/codet5p-220m) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.5757
19
 
20
  ## Model description
21
 
@@ -44,17 +44,27 @@ The following hyperparameters were used during training:
44
  - total_eval_batch_size: 40
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - num_epochs: 5
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Validation Loss |
52
- |:-------------:|:-----:|:----:|:---------------:|
53
- | 0.9138 | 1.0 | 1009 | 0.7803 |
54
- | 0.7063 | 2.0 | 2018 | 0.6699 |
55
- | 0.5643 | 3.0 | 3027 | 0.6191 |
56
- | 0.4719 | 4.0 | 4036 | 0.5889 |
57
- | 0.4021 | 5.0 | 5045 | 0.5757 |
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [Salesforce/codet5p-220m](https://huggingface.co/Salesforce/codet5p-220m) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.2952
19
 
20
  ## Model description
21
 
 
44
  - total_eval_batch_size: 40
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 15
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-----:|:------:|:---------------:|
53
+ | 0.658 | 1.0 | 19184 | 0.5830 |
54
+ | 0.5403 | 2.0 | 38368 | 0.4988 |
55
+ | 0.48 | 3.0 | 57552 | 0.4473 |
56
+ | 0.4282 | 4.0 | 76736 | 0.4124 |
57
+ | 0.3918 | 5.0 | 95920 | 0.3857 |
58
+ | 0.3464 | 6.0 | 115104 | 0.3650 |
59
+ | 0.3222 | 7.0 | 134288 | 0.3503 |
60
+ | 0.3007 | 8.0 | 153472 | 0.3357 |
61
+ | 0.2782 | 9.0 | 172656 | 0.3269 |
62
+ | 0.2562 | 10.0 | 191840 | 0.3184 |
63
+ | 0.2386 | 11.0 | 211024 | 0.3101 |
64
+ | 0.2196 | 12.0 | 230208 | 0.3020 |
65
+ | 0.2042 | 13.0 | 249392 | 0.3005 |
66
+ | 0.1931 | 14.0 | 268576 | 0.2971 |
67
+ | 0.1734 | 15.0 | 287760 | 0.2952 |
68
 
69
 
70
  ### Framework versions
latest CHANGED
@@ -1 +1 @@
1
- global_step5045
 
1
+ global_step287760
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80bb02c3860274009c4e8cc3b51ab8f76a6c04d95c856aabf0695241c923dcd0
3
  size 6008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d11f751cabda0fc8a66ae6ed224335dfea16200a547f89b5ac7a0cf6426cca
3
  size 6008