Hugging Face's logo

Minata
/
plbart-base-finetuned-ut-generator

Text2Text Generation
Transformers
PyTorch
TensorBoard
plbart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Minata commited on
Commit
d317e10
•
1 Parent(s): 0d7043f

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -24
README.md CHANGED
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model is a fine-tuned version of [uclanlp/plbart-base](https://huggingface.co/uclanlp/plbart-base) on the None dataset.
15
  It achieves the following results on the evaluation set:
16
- - Loss: 0.3141
17
 
18
  ## Model description
19
 
@@ -38,35 +38,26 @@ The following hyperparameters were used during training:
38
  - seed: 42
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: linear
41
- - num_epochs: 2
42
  - mixed_precision_training: Native AMP
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
- | 1.3625 | 0.09 | 100 | 0.4305 |
49
- | 0.4651 | 0.18 | 200 | 0.3991 |
50
- | 0.4273 | 0.27 | 300 | 0.3831 |
51
- | 0.4021 | 0.36 | 400 | 0.3722 |
52
- | 0.4101 | 0.44 | 500 | 0.3628 |
53
- | 0.4004 | 0.53 | 600 | 0.3550 |
54
- | 0.3877 | 0.62 | 700 | 0.3483 |
55
- | 0.3835 | 0.71 | 800 | 0.3431 |
56
- | 0.4012 | 0.8 | 900 | 0.3379 |
57
- | 0.3537 | 0.89 | 1000 | 0.3343 |
58
- | 0.3696 | 0.98 | 1100 | 0.3308 |
59
- | 0.3574 | 1.07 | 1200 | 0.3278 |
60
- | 0.3474 | 1.16 | 1300 | 0.3255 |
61
- | 0.3564 | 1.24 | 1400 | 0.3228 |
62
- | 0.3353 | 1.33 | 1500 | 0.3210 |
63
- | 0.3233 | 1.42 | 1600 | 0.3191 |
64
- | 0.3799 | 1.51 | 1700 | 0.3174 |
65
- | 0.3565 | 1.6 | 1800 | 0.3164 |
66
- | 0.3281 | 1.69 | 1900 | 0.3156 |
67
- | 0.3272 | 1.78 | 2000 | 0.3150 |
68
- | 0.3559 | 1.87 | 2100 | 0.3143 |
69
- | 0.3486 | 1.96 | 2200 | 0.3141 |
70
 
71
 
72
  ### Framework versions
 
13
 
14
  This model is a fine-tuned version of [uclanlp/plbart-base](https://huggingface.co/uclanlp/plbart-base) on the None dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 0.2744
17
 
18
  ## Model description
19
 
 
38
  - seed: 42
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: linear
41
+ - num_epochs: 6
42
  - mixed_precision_training: Native AMP
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
+ | 0.6096 | 0.44 | 500 | 0.3797 |
49
+ | 0.3706 | 0.89 | 1000 | 0.3465 |
50
+ | 0.3534 | 1.33 | 1500 | 0.3283 |
51
+ | 0.3132 | 1.78 | 2000 | 0.3142 |
52
+ | 0.305 | 2.22 | 2500 | 0.3044 |
53
+ | 0.2923 | 2.67 | 3000 | 0.2972 |
54
+ | 0.2908 | 3.11 | 3500 | 0.2911 |
55
+ | 0.2796 | 3.56 | 4000 | 0.2856 |
56
+ | 0.2731 | 4.0 | 4500 | 0.2814 |
57
+ | 0.2663 | 4.44 | 5000 | 0.2785 |
58
+ | 0.2638 | 4.89 | 5500 | 0.2764 |
59
+ | 0.2597 | 5.33 | 6000 | 0.2750 |
60
+ | 0.2522 | 5.78 | 6500 | 0.2744 |
 
 
 
 
 
 
 
 
 
61
 
62
 
63
  ### Framework versions