Hugging Face's logo

ghazikhanihamed
/
TooT-PLM-P2S

Text2Text Generation
Transformers
PyTorch
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
ghazikhanihamed commited on
Commit
26b21c2
·
1 Parent(s): 2231e04

PLM-Secondary-Structure-Generation

Browse files
Files changed (3) hide show
  1. README.md +13 -15
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [ElnaggarLab/ankh-base](https://huggingface.co/ElnaggarLab/ankh-base) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.1622
19
- - Q3 Accuracy: 0.4790
20
 
21
  ## Model description
22
 
@@ -35,29 +35,27 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 0.001
39
  - train_batch_size: 1
40
- - eval_batch_size: 1
41
  - seed: 7
42
  - distributed_type: multi-GPU
43
- - num_devices: 4
44
- - gradient_accumulation_steps: 4
45
- - total_train_batch_size: 16
46
- - total_eval_batch_size: 4
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
- - lr_scheduler_warmup_steps: 1000
50
- - num_epochs: 5
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Q3 Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:-----------:|
56
- | 0.3368 | 1.0 | 635 | 0.1976 | 0.4790 |
57
- | 0.1696 | 2.0 | 1271 | 0.1658 | 0.4790 |
58
- | 0.1631 | 3.0 | 1907 | 0.1645 | 0.4790 |
59
- | 0.1647 | 4.0 | 2543 | 0.1632 | 0.4790 |
60
- | 0.1638 | 4.99 | 3175 | 0.1622 | 0.4790 |
61
 
62
 
63
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [ElnaggarLab/ankh-base](https://huggingface.co/ElnaggarLab/ankh-base) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.1736
19
+ - Q3 Accuracy: 0.5107
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: 1
40
+ - eval_batch_size: 8
41
  - seed: 7
42
  - distributed_type: multi-GPU
43
+ - num_devices: 6
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 12
46
+ - total_eval_batch_size: 48
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_ratio: 0.3
50
+ - num_epochs: 3
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Q3 Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:-----------:|
56
+ | 0.2839 | 1.0 | 848 | 0.2462 | 0.3434 |
57
+ | 0.18 | 2.0 | 1696 | 0.1814 | 0.5245 |
58
+ | 0.1691 | 3.0 | 2544 | 0.1736 | 0.5107 |
 
 
59
 
60
 
61
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c0aaac696d63cb2fb5b5d5c184b10b15083d3863403836e85f968b4e7ef8704
3
  size 2946957610
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f03af4e88b7f1d44444e0af8f6791129801b996e858a68b64b7b27e44b9c7d26
3
  size 2946957610
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1ddcdd48faaa32a97b2d0bdf94096ff0d33623c556ab2a4caa01135cf0aa3d3
3
  size 5880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92e4538ec9d43680ca4f10ea9901404682f8865f418aa8b7cb9878a2bf913d7c
3
  size 5880