Hugging Face's logo

Pipper
/
SolCoderFuncs

Transformers
PyTorch
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
1
Pipper commited on
Commit
04aef16
·
1 Parent(s): 839e1ce

training latge t5 comment 2 code done 12/22/2023, 16:05:26

Browse files
Files changed (3) hide show
  1. README.md +44 -24
  2. pytorch_model.bin +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: 0.5510
19
 
20
  ## Model description
21
 
@@ -44,32 +44,52 @@ The following hyperparameters were used during training:
44
  - total_eval_batch_size: 148
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - num_epochs: 20
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Validation Loss |
52
- |:-------------:|:-----:|:-----:|:---------------:|
53
- | 0.8793 | 1.0 | 3600 | 0.7881 |
54
- | 0.7622 | 2.0 | 7200 | 0.7190 |
55
- | 0.7077 | 3.0 | 10800 | 0.6769 |
56
- | 0.659 | 4.0 | 14400 | 0.6518 |
57
- | 0.6212 | 5.0 | 18000 | 0.6300 |
58
- | 0.589 | 6.0 | 21600 | 0.6119 |
59
- | 0.562 | 7.0 | 25200 | 0.6014 |
60
- | 0.5361 | 8.0 | 28800 | 0.5905 |
61
- | 0.5171 | 9.0 | 32400 | 0.5799 |
62
- | 0.4973 | 10.0 | 36000 | 0.5747 |
63
- | 0.4772 | 11.0 | 39600 | 0.5666 |
64
- | 0.4619 | 12.0 | 43200 | 0.5610 |
65
- | 0.4443 | 13.0 | 46800 | 0.5588 |
66
- | 0.4335 | 14.0 | 50400 | 0.5571 |
67
- | 0.4192 | 15.0 | 54000 | 0.5534 |
68
- | 0.4062 | 16.0 | 57600 | 0.5512 |
69
- | 0.3977 | 17.0 | 61200 | 0.5513 |
70
- | 0.3864 | 18.0 | 64800 | 0.5515 |
71
- | 0.3791 | 19.0 | 68400 | 0.5507 |
72
- | 0.3718 | 20.0 | 72000 | 0.5510 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
73
 
74
 
75
  ### 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: 0.5574
19
 
20
  ## Model description
21
 
 
44
  - total_eval_batch_size: 148
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 40
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-----:|:------:|:---------------:|
53
+ | 0.8793 | 1.0 | 3600 | 0.7881 |
54
+ | 0.7622 | 2.0 | 7200 | 0.7190 |
55
+ | 0.7077 | 3.0 | 10800 | 0.6769 |
56
+ | 0.659 | 4.0 | 14400 | 0.6518 |
57
+ | 0.6212 | 5.0 | 18000 | 0.6300 |
58
+ | 0.589 | 6.0 | 21600 | 0.6119 |
59
+ | 0.562 | 7.0 | 25200 | 0.6014 |
60
+ | 0.5361 | 8.0 | 28800 | 0.5905 |
61
+ | 0.5171 | 9.0 | 32400 | 0.5799 |
62
+ | 0.4973 | 10.0 | 36000 | 0.5747 |
63
+ | 0.4772 | 11.0 | 39600 | 0.5666 |
64
+ | 0.4619 | 12.0 | 43200 | 0.5610 |
65
+ | 0.4443 | 13.0 | 46800 | 0.5588 |
66
+ | 0.4335 | 14.0 | 50400 | 0.5571 |
67
+ | 0.4192 | 15.0 | 54000 | 0.5534 |
68
+ | 0.4062 | 16.0 | 57600 | 0.5512 |
69
+ | 0.3977 | 17.0 | 61200 | 0.5513 |
70
+ | 0.3864 | 18.0 | 64800 | 0.5515 |
71
+ | 0.3791 | 19.0 | 68400 | 0.5507 |
72
+ | 0.3718 | 20.0 | 72000 | 0.5510 |
73
+ | 0.4132 | 21.0 | 75600 | 0.5551 |
74
+ | 0.4079 | 22.0 | 79200 | 0.5499 |
75
+ | 0.3957 | 23.0 | 82800 | 0.5522 |
76
+ | 0.3895 | 24.0 | 86400 | 0.5482 |
77
+ | 0.3797 | 25.0 | 90000 | 0.5477 |
78
+ | 0.3686 | 26.0 | 93600 | 0.5486 |
79
+ | 0.3628 | 27.0 | 97200 | 0.5491 |
80
+ | 0.3518 | 28.0 | 100800 | 0.5502 |
81
+ | 0.3452 | 29.0 | 104400 | 0.5494 |
82
+ | 0.3379 | 30.0 | 108000 | 0.5546 |
83
+ | 0.3292 | 31.0 | 111600 | 0.5486 |
84
+ | 0.3232 | 32.0 | 115200 | 0.5522 |
85
+ | 0.3146 | 33.0 | 118800 | 0.5524 |
86
+ | 0.31 | 34.0 | 122400 | 0.5505 |
87
+ | 0.3057 | 35.0 | 126000 | 0.5538 |
88
+ | 0.301 | 36.0 | 129600 | 0.5549 |
89
+ | 0.2955 | 37.0 | 133200 | 0.5557 |
90
+ | 0.2901 | 38.0 | 136800 | 0.5554 |
91
+ | 0.2872 | 39.0 | 140400 | 0.5564 |
92
+ | 0.2844 | 40.0 | 144000 | 0.5574 |
93
 
94
 
95
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e69ecf6f2c7fd4885fa39bc8eae8e52a2a05d69034cce7076a058a90bc71da8
3
  size 891617358
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14f709d39abafa12c300b44f0e41b586eb52c1b72ed7d38267f49663a97a31fd
3
  size 891617358
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccd68918ee13c5b8ce0b8e1a99bdc42ff1f52077b384ac5d445488118733acde
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e591cec8f9932b2cd7910607889a693d0b780d510d609149bde117f46261ab07
3
  size 4664