Hugging Face's logo

NasimB
/
bert-dp-4

Fill-Mask
Transformers
PyTorch
bert
Generated from Trainer
Model card Files
xet
Community
2
NasimB commited on
Commit
34f2d48
·
1 Parent(s): b6f526a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +67 -46
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 [](https://huggingface.co/) on the generator dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 4.2485
19
 
20
  ## Model description
21
 
@@ -41,55 +41,76 @@ The following hyperparameters were used during training:
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: cosine
43
  - lr_scheduler_warmup_steps: 1000
44
- - num_epochs: 80
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss |
50
- |:-------------:|:-----:|:-----:|:---------------:|
51
- | 6.3492 | 1.89 | 1000 | 5.9327 |
52
- | 5.8333 | 3.78 | 2000 | 5.8515 |
53
- | 5.7604 | 5.67 | 3000 | 5.8483 |
54
- | 5.7137 | 7.56 | 4000 | 5.7914 |
55
- | 5.6597 | 9.45 | 5000 | 5.7672 |
56
- | 5.6213 | 11.34 | 6000 | 5.7594 |
57
- | 5.5798 | 13.23 | 7000 | 5.7352 |
58
- | 5.5482 | 15.12 | 8000 | 5.7275 |
59
- | 5.513 | 17.01 | 9000 | 5.7203 |
60
- | 5.485 | 18.9 | 10000 | 5.7211 |
61
- | 5.4498 | 20.79 | 11000 | 5.6947 |
62
- | 5.4175 | 22.68 | 12000 | 5.6923 |
63
- | 5.3877 | 24.57 | 13000 | 5.6879 |
64
- | 5.3635 | 26.47 | 14000 | 5.6776 |
65
- | 5.3389 | 28.36 | 15000 | 5.6757 |
66
- | 5.3166 | 30.25 | 16000 | 5.6758 |
67
- | 5.2951 | 32.14 | 17000 | 5.6676 |
68
- | 5.2793 | 34.03 | 18000 | 5.6711 |
69
- | 5.2684 | 35.92 | 19000 | 5.6687 |
70
- | 5.2609 | 37.81 | 20000 | 5.6684 |
71
- | 5.2606 | 39.7 | 21000 | 5.6719 |
72
- | 5.2624 | 41.59 | 22000 | 5.6697 |
73
- | 5.2551 | 43.48 | 23000 | 5.6718 |
74
- | 5.2461 | 45.37 | 24000 | 5.6699 |
75
- | 5.2431 | 47.26 | 25000 | 5.6692 |
76
- | 5.2414 | 49.15 | 26000 | 5.6691 |
77
- | 5.2856 | 51.04 | 27000 | 5.6823 |
78
- | 5.2753 | 52.93 | 28000 | 5.6860 |
79
- | 5.2549 | 54.82 | 29000 | 5.6877 |
80
- | 5.2276 | 56.71 | 30000 | 5.6285 |
81
- | 5.1674 | 58.6 | 31000 | 5.5439 |
82
- | 5.0894 | 60.49 | 32000 | 5.4082 |
83
- | 4.9508 | 62.38 | 33000 | 5.1598 |
84
- | 4.7453 | 64.27 | 34000 | 4.9274 |
85
- | 4.5898 | 66.16 | 35000 | 4.7884 |
86
- | 4.4656 | 68.05 | 36000 | 4.6531 |
87
- | 4.35 | 69.94 | 37000 | 4.5123 |
88
- | 4.2378 | 71.83 | 38000 | 4.4012 |
89
- | 4.1496 | 73.72 | 39000 | 4.3240 |
90
- | 4.0891 | 75.61 | 40000 | 4.2763 |
91
- | 4.0538 | 77.5 | 41000 | 4.2520 |
92
- | 4.0448 | 79.4 | 42000 | 4.2485 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
93
 
94
 
95
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [](https://huggingface.co/) on the generator dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 2.8383
19
 
20
  ## Model description
21
 
 
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: cosine
43
  - lr_scheduler_warmup_steps: 1000
44
+ - num_epochs: 120
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:------:|:-----:|:---------------:|
51
+ | 6.3492 | 1.89 | 1000 | 5.9327 |
52
+ | 5.8333 | 3.78 | 2000 | 5.8515 |
53
+ | 5.7604 | 5.67 | 3000 | 5.8483 |
54
+ | 5.7137 | 7.56 | 4000 | 5.7914 |
55
+ | 5.6597 | 9.45 | 5000 | 5.7672 |
56
+ | 5.6213 | 11.34 | 6000 | 5.7594 |
57
+ | 5.5798 | 13.23 | 7000 | 5.7352 |
58
+ | 5.5482 | 15.12 | 8000 | 5.7275 |
59
+ | 5.513 | 17.01 | 9000 | 5.7203 |
60
+ | 5.485 | 18.9 | 10000 | 5.7211 |
61
+ | 5.4498 | 20.79 | 11000 | 5.6947 |
62
+ | 5.4175 | 22.68 | 12000 | 5.6923 |
63
+ | 5.3877 | 24.57 | 13000 | 5.6879 |
64
+ | 5.3635 | 26.47 | 14000 | 5.6776 |
65
+ | 5.3389 | 28.36 | 15000 | 5.6757 |
66
+ | 5.3166 | 30.25 | 16000 | 5.6758 |
67
+ | 5.2951 | 32.14 | 17000 | 5.6676 |
68
+ | 5.2793 | 34.03 | 18000 | 5.6711 |
69
+ | 5.2684 | 35.92 | 19000 | 5.6687 |
70
+ | 5.2609 | 37.81 | 20000 | 5.6684 |
71
+ | 5.2606 | 39.7 | 21000 | 5.6719 |
72
+ | 5.2624 | 41.59 | 22000 | 5.6697 |
73
+ | 5.2551 | 43.48 | 23000 | 5.6718 |
74
+ | 5.2461 | 45.37 | 24000 | 5.6699 |
75
+ | 5.2431 | 47.26 | 25000 | 5.6692 |
76
+ | 5.2414 | 49.15 | 26000 | 5.6691 |
77
+ | 5.2856 | 51.04 | 27000 | 5.6823 |
78
+ | 5.2753 | 52.93 | 28000 | 5.6860 |
79
+ | 5.2549 | 54.82 | 29000 | 5.6877 |
80
+ | 5.2276 | 56.71 | 30000 | 5.6285 |
81
+ | 5.1674 | 58.6 | 31000 | 5.5439 |
82
+ | 5.0894 | 60.49 | 32000 | 5.4082 |
83
+ | 4.9508 | 62.38 | 33000 | 5.1598 |
84
+ | 4.7453 | 64.27 | 34000 | 4.9274 |
85
+ | 4.5898 | 66.16 | 35000 | 4.7884 |
86
+ | 4.4656 | 68.05 | 36000 | 4.6531 |
87
+ | 4.35 | 69.94 | 37000 | 4.5123 |
88
+ | 4.2378 | 71.83 | 38000 | 4.4012 |
89
+ | 4.1496 | 73.72 | 39000 | 4.3240 |
90
+ | 4.0891 | 75.61 | 40000 | 4.2763 |
91
+ | 4.0538 | 77.5 | 41000 | 4.2520 |
92
+ | 4.0448 | 79.4 | 42000 | 4.2485 |
93
+ | 3.9724 | 81.29 | 43000 | 3.9940 |
94
+ | 3.6527 | 83.18 | 44000 | 3.7442 |
95
+ | 3.4172 | 85.07 | 45000 | 3.5713 |
96
+ | 3.2446 | 86.96 | 46000 | 3.4403 |
97
+ | 3.4764 | 88.85 | 47000 | 3.3796 |
98
+ | 3.0543 | 90.74 | 48000 | 3.2884 |
99
+ | 2.9549 | 92.63 | 49000 | 3.2107 |
100
+ | 2.8785 | 94.52 | 50000 | 3.1466 |
101
+ | 2.8143 | 96.41 | 51000 | 3.0788 |
102
+ | 2.7605 | 98.3 | 52000 | 3.0230 |
103
+ | 2.7111 | 100.19 | 53000 | 2.9802 |
104
+ | 2.6727 | 102.08 | 54000 | 2.9414 |
105
+ | 2.6417 | 103.97 | 55000 | 2.9167 |
106
+ | 2.612 | 105.86 | 56000 | 2.8927 |
107
+ | 2.5918 | 107.75 | 57000 | 2.8769 |
108
+ | 2.5769 | 109.64 | 58000 | 2.8637 |
109
+ | 2.566 | 111.53 | 59000 | 2.8551 |
110
+ | 2.556 | 113.42 | 60000 | 2.8458 |
111
+ | 2.548 | 115.31 | 61000 | 2.8488 |
112
+ | 2.5468 | 117.2 | 62000 | 2.8412 |
113
+ | 2.5453 | 119.09 | 63000 | 2.8383 |
114
 
115
 
116
  ### Framework versions