Hugging Face's logo

vinnyy
/
results

Transformers
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
vinnyy commited on
Commit
a622328
·
verified ·
1 Parent(s): 69fb14e

vinnyy/codet5-finetuned-42epochs

Browse files
Files changed (4) hide show
  1. README.md +28 -36
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  library_name: transformers
3
  license: apache-2.0
4
- base_model: vinzur/results
5
  tags:
6
  - generated_from_trainer
7
  model-index:
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # results
16
 
17
- This model is a fine-tuned version of [vinzur/results](https://huggingface.co/vinzur/results) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.6053
20
 
21
  ## Model description
22
 
@@ -35,53 +35,45 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 2e-05
39
  - train_batch_size: 2
40
  - eval_batch_size: 2
41
  - seed: 42
42
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
- - num_epochs: 30
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | No log | 1.0 | 62 | 0.9665 |
51
- | 1.5431 | 2.0 | 124 | 0.8184 |
52
- | 1.5431 | 3.0 | 186 | 0.7439 |
53
- | 0.8654 | 4.0 | 248 | 0.7027 |
54
- | 0.688 | 5.0 | 310 | 0.6795 |
55
- | 0.688 | 6.0 | 372 | 0.6600 |
56
- | 0.6288 | 7.0 | 434 | 0.6505 |
57
- | 0.6288 | 8.0 | 496 | 0.6444 |
58
- | 0.5713 | 9.0 | 558 | 0.6402 |
59
- | 0.5478 | 10.0 | 620 | 0.6392 |
60
- | 0.5478 | 11.0 | 682 | 0.6371 |
61
- | 0.5366 | 12.0 | 744 | 0.6302 |
62
- | 0.5056 | 13.0 | 806 | 0.6141 |
63
- | 0.5056 | 14.0 | 868 | 0.6183 |
64
- | 0.4948 | 15.0 | 930 | 0.6163 |
65
- | 0.4948 | 16.0 | 992 | 0.6125 |
66
- | 0.4468 | 17.0 | 1054 | 0.6136 |
67
- | 0.4398 | 18.0 | 1116 | 0.6130 |
68
- | 0.4398 | 19.0 | 1178 | 0.6123 |
69
- | 0.4284 | 20.0 | 1240 | 0.6128 |
70
- | 0.4322 | 21.0 | 1302 | 0.6138 |
71
- | 0.4322 | 22.0 | 1364 | 0.6067 |
72
- | 0.4203 | 23.0 | 1426 | 0.6108 |
73
- | 0.4203 | 24.0 | 1488 | 0.6085 |
74
- | 0.4064 | 25.0 | 1550 | 0.6088 |
75
- | 0.4085 | 26.0 | 1612 | 0.6108 |
76
- | 0.4085 | 27.0 | 1674 | 0.6069 |
77
- | 0.4132 | 28.0 | 1736 | 0.6037 |
78
- | 0.4132 | 29.0 | 1798 | 0.6067 |
79
- | 0.3854 | 30.0 | 1860 | 0.6053 |
80
 
81
 
82
  ### Framework versions
83
 
84
  - Transformers 4.46.3
85
  - Pytorch 2.5.1+cu121
86
- - Datasets 3.1.0
87
  - Tokenizers 0.20.3
 
1
  ---
2
  library_name: transformers
3
  license: apache-2.0
4
+ base_model: vinnyy/results
5
  tags:
6
  - generated_from_trainer
7
  model-index:
 
14
 
15
  # results
16
 
17
+ This model is a fine-tuned version of [vinnyy/results](https://huggingface.co/vinnyy/results) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.4479
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 1e-05
39
  - train_batch_size: 2
40
  - eval_batch_size: 2
41
  - seed: 42
42
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
+ - num_epochs: 25
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | No log | 1.0 | 87 | 0.5600 |
51
+ | 0.6043 | 2.0 | 174 | 0.5312 |
52
+ | 0.5608 | 3.0 | 261 | 0.4930 |
53
+ | 0.4626 | 4.0 | 348 | 0.4837 |
54
+ | 0.4311 | 5.0 | 435 | 0.4736 |
55
+ | 0.4456 | 6.0 | 522 | 0.4793 |
56
+ | 0.391 | 7.0 | 609 | 0.4676 |
57
+ | 0.391 | 8.0 | 696 | 0.4674 |
58
+ | 0.383 | 9.0 | 783 | 0.4656 |
59
+ | 0.3735 | 10.0 | 870 | 0.4637 |
60
+ | 0.4062 | 11.0 | 957 | 0.4614 |
61
+ | 0.3528 | 12.0 | 1044 | 0.4588 |
62
+ | 0.3622 | 13.0 | 1131 | 0.4592 |
63
+ | 0.3245 | 14.0 | 1218 | 0.4574 |
64
+ | 0.3267 | 15.0 | 1305 | 0.4564 |
65
+ | 0.3267 | 16.0 | 1392 | 0.4479 |
66
+ | 0.3176 | 17.0 | 1479 | 0.4500 |
67
+ | 0.3127 | 18.0 | 1566 | 0.4499 |
68
+ | 0.3053 | 19.0 | 1653 | 0.4506 |
69
+ | 0.2925 | 20.0 | 1740 | 0.4506 |
70
+ | 0.3064 | 21.0 | 1827 | 0.4498 |
71
+ | 0.2953 | 22.0 | 1914 | 0.4503 |
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
75
 
76
  - Transformers 4.46.3
77
  - Pytorch 2.5.1+cu121
78
+ - Datasets 3.2.0
79
  - Tokenizers 0.20.3
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "vinzur/results",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
 
1
  {
2
+ "_name_or_path": "vinnyy/results",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e959db6a7d0a7936f927d2810801d41cdb00b08675d7268e7ae32c377ec48858
3
  size 891558696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d4ac4c24da1d5a48e4fbca581dd5f4772ac1ae58f7a3a26c0fd39b30c0e1a34
3
  size 891558696
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28a24f4b2c98de876d9ec15ddd7be331cca5a2aee8b5fc1cbf2a4d15545914c2
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc5c8409fd8d48c62aa8892279f6ad90a5898c36e3701a6ec2d0c09028d28854
3
  size 5240