Hugging Face's logo

alex2awesome
/
newsdiscourse-model

Transformers
PyTorch
roberta
Generated from Trainer
Model card Files Community
1
alex2awesome commited on
Commit
98a0c26
·
1 Parent(s): 4cfb3f0

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +74 -39
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.7194
20
- - F1: 0.5515
21
 
22
  ## Model description
23
 
@@ -36,53 +36,88 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - learning_rate: 3e-05
40
  - train_batch_size: 1
41
  - eval_batch_size: 1
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
- - num_epochs: 5.0
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | F1 |
50
  |:-------------:|:-----:|:----:|:---------------:|:------:|
51
- | No log | 0.14 | 100 | 1.3632 | 0.3762 |
52
- | No log | 0.28 | 200 | 1.2278 | 0.4162 |
53
- | No log | 0.43 | 300 | 1.1802 | 0.4159 |
54
- | No log | 0.57 | 400 | 1.3237 | 0.4879 |
55
- | 1.2 | 0.71 | 500 | 1.2971 | 0.4645 |
56
- | 1.2 | 0.85 | 600 | 1.2550 | 0.5020 |
57
- | 1.2 | 1.0 | 700 | 1.1854 | 0.4806 |
58
- | 1.2 | 1.14 | 800 | 1.1788 | 0.5012 |
59
- | 1.2 | 1.28 | 900 | 1.0935 | 0.4964 |
60
- | 0.9189 | 1.42 | 1000 | 1.2862 | 0.4986 |
61
- | 0.9189 | 1.57 | 1100 | 1.2223 | 0.4930 |
62
- | 0.9189 | 1.71 | 1200 | 1.1197 | 0.4954 |
63
- | 0.9189 | 1.85 | 1300 | 1.1257 | 0.5153 |
64
- | 0.9189 | 1.99 | 1400 | 1.1729 | 0.5264 |
65
- | 0.8143 | 2.14 | 1500 | 1.2722 | 0.5165 |
66
- | 0.8143 | 2.28 | 1600 | 1.3218 | 0.5395 |
67
- | 0.8143 | 2.42 | 1700 | 1.3383 | 0.5170 |
68
- | 0.8143 | 2.56 | 1800 | 1.2503 | 0.5139 |
69
- | 0.8143 | 2.71 | 1900 | 1.3630 | 0.5240 |
70
- | 0.6175 | 2.85 | 2000 | 1.4028 | 0.5305 |
71
- | 0.6175 | 2.99 | 2100 | 1.4017 | 0.5408 |
72
- | 0.6175 | 3.13 | 2200 | 1.5930 | 0.5413 |
73
- | 0.6175 | 3.28 | 2300 | 1.5373 | 0.5565 |
74
- | 0.6175 | 3.42 | 2400 | 1.5013 | 0.5722 |
75
- | 0.4726 | 3.56 | 2500 | 1.5704 | 0.5226 |
76
- | 0.4726 | 3.7 | 2600 | 1.5891 | 0.5484 |
77
- | 0.4726 | 3.85 | 2700 | 1.5236 | 0.5630 |
78
- | 0.4726 | 3.99 | 2800 | 1.5233 | 0.5422 |
79
- | 0.4726 | 4.13 | 2900 | 1.6105 | 0.5470 |
80
- | 0.3745 | 4.27 | 3000 | 1.7136 | 0.5525 |
81
- | 0.3745 | 4.42 | 3100 | 1.6561 | 0.5539 |
82
- | 0.3745 | 4.56 | 3200 | 1.7664 | 0.5504 |
83
- | 0.3745 | 4.7 | 3300 | 1.7505 | 0.5494 |
84
- | 0.3745 | 4.84 | 3400 | 1.7313 | 0.5516 |
85
- | 0.307 | 4.99 | 3500 | 1.7194 | 0.5515 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
86
 
87
 
88
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.9458
20
+ - F1: 0.5610
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 1e-05
40
  - train_batch_size: 1
41
  - eval_batch_size: 1
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - num_epochs: 10.0
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | F1 |
50
  |:-------------:|:-----:|:----:|:---------------:|:------:|
51
+ | No log | 0.14 | 100 | 1.4843 | 0.2881 |
52
+ | No log | 0.28 | 200 | 1.3307 | 0.3841 |
53
+ | No log | 0.43 | 300 | 1.2427 | 0.3991 |
54
+ | No log | 0.57 | 400 | 1.2590 | 0.4899 |
55
+ | 1.2399 | 0.71 | 500 | 1.2648 | 0.4658 |
56
+ | 1.2399 | 0.85 | 600 | 1.2064 | 0.4988 |
57
+ | 1.2399 | 1.0 | 700 | 1.2564 | 0.4668 |
58
+ | 1.2399 | 1.14 | 800 | 1.2062 | 0.4912 |
59
+ | 1.2399 | 1.28 | 900 | 1.1202 | 0.4904 |
60
+ | 0.9315 | 1.42 | 1000 | 1.1924 | 0.5188 |
61
+ | 0.9315 | 1.57 | 1100 | 1.1627 | 0.5034 |
62
+ | 0.9315 | 1.71 | 1200 | 1.1093 | 0.5111 |
63
+ | 0.9315 | 1.85 | 1300 | 1.1332 | 0.5166 |
64
+ | 0.9315 | 1.99 | 1400 | 1.1558 | 0.5285 |
65
+ | 0.8604 | 2.14 | 1500 | 1.2531 | 0.5122 |
66
+ | 0.8604 | 2.28 | 1600 | 1.2830 | 0.5414 |
67
+ | 0.8604 | 2.42 | 1700 | 1.2550 | 0.5335 |
68
+ | 0.8604 | 2.56 | 1800 | 1.1928 | 0.5120 |
69
+ | 0.8604 | 2.71 | 1900 | 1.2441 | 0.5308 |
70
+ | 0.7406 | 2.85 | 2000 | 1.2791 | 0.5400 |
71
+ | 0.7406 | 2.99 | 2100 | 1.2354 | 0.5485 |
72
+ | 0.7406 | 3.13 | 2200 | 1.3047 | 0.5258 |
73
+ | 0.7406 | 3.28 | 2300 | 1.3636 | 0.5640 |
74
+ | 0.7406 | 3.42 | 2400 | 1.2963 | 0.5747 |
75
+ | 0.6355 | 3.56 | 2500 | 1.2897 | 0.5123 |
76
+ | 0.6355 | 3.7 | 2600 | 1.3225 | 0.5481 |
77
+ | 0.6355 | 3.85 | 2700 | 1.3197 | 0.5467 |
78
+ | 0.6355 | 3.99 | 2800 | 1.2346 | 0.5353 |
79
+ | 0.6355 | 4.13 | 2900 | 1.3397 | 0.5629 |
80
+ | 0.5698 | 4.27 | 3000 | 1.4259 | 0.5622 |
81
+ | 0.5698 | 4.42 | 3100 | 1.3702 | 0.5607 |
82
+ | 0.5698 | 4.56 | 3200 | 1.4294 | 0.5584 |
83
+ | 0.5698 | 4.7 | 3300 | 1.5041 | 0.5459 |
84
+ | 0.5698 | 4.84 | 3400 | 1.4156 | 0.5394 |
85
+ | 0.5069 | 4.99 | 3500 | 1.4384 | 0.5527 |
86
+ | 0.5069 | 5.13 | 3600 | 1.5322 | 0.5439 |
87
+ | 0.5069 | 5.27 | 3700 | 1.4899 | 0.5557 |
88
+ | 0.5069 | 5.41 | 3800 | 1.4526 | 0.5391 |
89
+ | 0.5069 | 5.56 | 3900 | 1.5027 | 0.5607 |
90
+ | 0.4127 | 5.7 | 4000 | 1.5458 | 0.5662 |
91
+ | 0.4127 | 5.84 | 4100 | 1.5080 | 0.5537 |
92
+ | 0.4127 | 5.98 | 4200 | 1.5936 | 0.5483 |
93
+ | 0.4127 | 6.13 | 4300 | 1.7079 | 0.5401 |
94
+ | 0.4127 | 6.27 | 4400 | 1.5939 | 0.5521 |
95
+ | 0.3574 | 6.41 | 4500 | 1.5588 | 0.5702 |
96
+ | 0.3574 | 6.55 | 4600 | 1.6363 | 0.5568 |
97
+ | 0.3574 | 6.7 | 4700 | 1.6629 | 0.5535 |
98
+ | 0.3574 | 6.84 | 4800 | 1.6523 | 0.5662 |
99
+ | 0.3574 | 6.98 | 4900 | 1.7245 | 0.5461 |
100
+ | 0.3417 | 7.12 | 5000 | 1.6766 | 0.5629 |
101
+ | 0.3417 | 7.26 | 5100 | 1.8219 | 0.5450 |
102
+ | 0.3417 | 7.41 | 5200 | 1.7422 | 0.5533 |
103
+ | 0.3417 | 7.55 | 5300 | 1.8250 | 0.5564 |
104
+ | 0.3417 | 7.69 | 5400 | 1.7744 | 0.5600 |
105
+ | 0.2852 | 7.83 | 5500 | 1.7919 | 0.5549 |
106
+ | 0.2852 | 7.98 | 5600 | 1.7604 | 0.5639 |
107
+ | 0.2852 | 8.12 | 5700 | 1.7660 | 0.5599 |
108
+ | 0.2852 | 8.26 | 5800 | 1.7323 | 0.5600 |
109
+ | 0.2852 | 8.4 | 5900 | 1.9174 | 0.5529 |
110
+ | 0.2606 | 8.55 | 6000 | 1.8664 | 0.5611 |
111
+ | 0.2606 | 8.69 | 6100 | 1.9191 | 0.5568 |
112
+ | 0.2606 | 8.83 | 6200 | 1.8900 | 0.5565 |
113
+ | 0.2606 | 8.97 | 6300 | 1.9376 | 0.5524 |
114
+ | 0.2606 | 9.12 | 6400 | 1.9220 | 0.5594 |
115
+ | 0.2274 | 9.26 | 6500 | 1.9188 | 0.5585 |
116
+ | 0.2274 | 9.4 | 6600 | 1.9459 | 0.5527 |
117
+ | 0.2274 | 9.54 | 6700 | 1.9439 | 0.5543 |
118
+ | 0.2274 | 9.69 | 6800 | 1.9437 | 0.5596 |
119
+ | 0.2274 | 9.83 | 6900 | 1.9484 | 0.5581 |
120
+ | 0.2258 | 9.97 | 7000 | 1.9458 | 0.5610 |
121
 
122
 
123
  ### Framework versions