Hugging Face's logo

dgktrnh
/
codet5-fine-tuned

Text2Text Generation
Transformers
Safetensors
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
dgktrnh commited on
Commit
18224a8
•
1 Parent(s): ad8b1be

End of training

Browse files
Files changed (4) hide show
  1. README.md +25 -9
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: bsd-3-clause
3
- base_model: Salesforce/codet5p-220m-py
4
  tags:
5
  - generated_from_trainer
6
  model-index:
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # codet5-fine-tuned
15
 
16
- This model is a fine-tuned version of [Salesforce/codet5p-220m-py](https://huggingface.co/Salesforce/codet5p-220m-py) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.1679
19
 
20
  ## Model description
21
 
@@ -42,21 +42,37 @@ The following hyperparameters were used during training:
42
  - total_train_batch_size: 12
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
- - num_epochs: 4
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | No log | 0.99 | 56 | 0.1700 |
52
- | 0.1837 | 1.99 | 113 | 0.1634 |
53
- | 0.1837 | 3.0 | 170 | 0.1658 |
54
- | 0.1277 | 3.95 | 224 | 0.1679 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
 
56
 
57
  ### Framework versions
58
 
59
  - Transformers 4.39.3
60
  - Pytorch 2.1.2
61
- - Datasets 2.19.0
62
  - Tokenizers 0.15.2
 
1
  ---
2
  license: bsd-3-clause
3
+ base_model: Salesforce/codet5p-220m
4
  tags:
5
  - generated_from_trainer
6
  model-index:
 
13
 
14
  # codet5-fine-tuned
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: 0.0916
19
 
20
  ## Model description
21
 
 
42
  - total_train_batch_size: 12
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - num_epochs: 20
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | No log | 0.99 | 56 | 0.0720 |
52
+ | 0.0898 | 1.99 | 113 | 0.0694 |
53
+ | 0.0898 | 3.0 | 170 | 0.0682 |
54
+ | 0.0509 | 4.0 | 227 | 0.0693 |
55
+ | 0.0509 | 4.99 | 283 | 0.0699 |
56
+ | 0.0384 | 5.99 | 340 | 0.0725 |
57
+ | 0.0384 | 7.0 | 397 | 0.0729 |
58
+ | 0.0295 | 8.0 | 454 | 0.0758 |
59
+ | 0.0224 | 8.99 | 510 | 0.0785 |
60
+ | 0.0224 | 9.99 | 567 | 0.0806 |
61
+ | 0.0177 | 11.0 | 624 | 0.0799 |
62
+ | 0.0177 | 12.0 | 681 | 0.0835 |
63
+ | 0.0136 | 12.99 | 737 | 0.0873 |
64
+ | 0.0136 | 13.99 | 794 | 0.0881 |
65
+ | 0.0116 | 15.0 | 851 | 0.0887 |
66
+ | 0.0095 | 16.0 | 908 | 0.0899 |
67
+ | 0.0095 | 16.99 | 964 | 0.0910 |
68
+ | 0.0082 | 17.99 | 1021 | 0.0916 |
69
+ | 0.0082 | 19.0 | 1078 | 0.0912 |
70
+ | 0.0072 | 19.74 | 1120 | 0.0916 |
71
 
72
 
73
  ### Framework versions
74
 
75
  - Transformers 4.39.3
76
  - Pytorch 2.1.2
77
+ - Datasets 2.19.1
78
  - Tokenizers 0.15.2
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "Salesforce/codet5p-220m-py",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
 
1
  {
2
+ "_name_or_path": "Salesforce/codet5p-220m",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84d838173c0eaed392f275f4266edec29666cdd10dbc77d20f6f18d1260181b0
3
  size 891558696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6382b92cda66b2f00abfd47a222d9b3028e12dc8d1325545156269a62d4bc174
3
  size 891558696
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1918bff60199eb28b6d9e2bae85ccc3fb5890e28f70a17e84c2522113209742
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4c485214f86b4dab1876fc8dd147c520fa574b30fbedc8db36e73288e856ffc
3
  size 5112