Hugging Face's logo

DayCardoso
/
roberta-base-multi-head

Transformers
Safetensors
roberta
Generated from Trainer
Model card Files
xet
Community
DayCardoso commited on
Commit
a479887
·
verified ·
1 Parent(s): 9377a3b

Model save

Browse files
Files changed (2) hide show
  1. README.md +37 -12
  2. model.safetensors +1 -1
README.md CHANGED
@@ -4,6 +4,8 @@ license: mit
4
  base_model: roberta-base
5
  tags:
6
  - generated_from_trainer
 
 
7
  model-index:
8
  - name: roberta-base-multi-head
9
  results: []
@@ -16,8 +18,13 @@ 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 the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.5495
20
- - F1 Macro: 0.5468
 
 
 
 
 
21
 
22
  ## Model description
23
 
@@ -45,19 +52,37 @@ The following hyperparameters were used during training:
45
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.05
48
- - num_epochs: 20
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | F1 Macro |
53
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|
54
- | 0.4938 | 1.0 | 1534 | 0.4783 | 0.4162 |
55
- | 0.4484 | 2.0 | 3068 | 0.4548 | 0.5062 |
56
- | 0.4161 | 3.0 | 4602 | 0.4607 | 0.5396 |
57
- | 0.3832 | 4.0 | 6136 | 0.4730 | 0.5522 |
58
- | 0.3416 | 5.0 | 7670 | 0.4896 | 0.5505 |
59
- | 0.3172 | 6.0 | 9204 | 0.5243 | 0.5516 |
60
- | 0.2798 | 7.0 | 10738 | 0.5495 | 0.5468 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
 
62
 
63
  ### Framework versions
 
4
  base_model: roberta-base
5
  tags:
6
  - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
  model-index:
10
  - name: roberta-base-multi-head
11
  results: []
 
18
 
19
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.4702
22
+ - Accuracy: 0.5675
23
+ - F1 Macro: 0.5441
24
+ - F1 Micro: 0.5675
25
+ - Precision Macro: 0.5454
26
+ - Recall Macro: 0.5461
27
+ - Roc Auc: 0.7877
28
 
29
  ## Model description
30
 
 
52
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
53
  - lr_scheduler_type: linear
54
  - lr_scheduler_warmup_ratio: 0.05
55
+ - num_epochs: 40
56
 
57
  ### Training results
58
 
59
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro | Precision Macro | Recall Macro | Roc Auc |
60
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|:--------:|:---------------:|:------------:|:-------:|
61
+ | No log | 0.1304 | 200 | 0.6700 | 0.1505 | 0.0654 | 0.1505 | 0.0376 | 0.25 | 0.5065 |
62
+ | No log | 0.2609 | 400 | 0.5908 | 0.3307 | 0.2185 | 0.3307 | 0.3478 | 0.2628 | 0.5265 |
63
+ | 0.6418 | 0.3913 | 600 | 0.5682 | 0.3965 | 0.2420 | 0.3965 | 0.3131 | 0.2958 | 0.5826 |
64
+ | 0.6418 | 0.5217 | 800 | 0.5511 | 0.4446 | 0.2752 | 0.4446 | 0.3725 | 0.3348 | 0.6511 |
65
+ | 0.56 | 0.6522 | 1000 | 0.5183 | 0.4796 | 0.3397 | 0.4796 | 0.5998 | 0.3752 | 0.7004 |
66
+ | 0.56 | 0.7826 | 1200 | 0.5027 | 0.4951 | 0.3960 | 0.4951 | 0.4765 | 0.4243 | 0.7210 |
67
+ | 0.56 | 0.9130 | 1400 | 0.5012 | 0.4936 | 0.4203 | 0.4936 | 0.4761 | 0.4461 | 0.7341 |
68
+ | 0.5136 | 1.0430 | 1600 | 0.4898 | 0.5228 | 0.4273 | 0.5228 | 0.5111 | 0.4450 | 0.7377 |
69
+ | 0.5136 | 1.1735 | 1800 | 0.4818 | 0.5304 | 0.4723 | 0.5304 | 0.4987 | 0.4752 | 0.7504 |
70
+ | 0.4842 | 1.3039 | 2000 | 0.4809 | 0.5330 | 0.4931 | 0.5330 | 0.5035 | 0.4966 | 0.7580 |
71
+ | 0.4842 | 1.4343 | 2200 | 0.4754 | 0.5412 | 0.5091 | 0.5412 | 0.5109 | 0.5110 | 0.7651 |
72
+ | 0.4842 | 1.5648 | 2400 | 0.4689 | 0.5523 | 0.5072 | 0.5523 | 0.5307 | 0.5061 | 0.7695 |
73
+ | 0.4695 | 1.6952 | 2600 | 0.4785 | 0.5380 | 0.4809 | 0.5380 | 0.5346 | 0.4907 | 0.7663 |
74
+ | 0.4695 | 1.8256 | 2800 | 0.4649 | 0.5545 | 0.5144 | 0.5545 | 0.5301 | 0.5081 | 0.7745 |
75
+ | 0.4655 | 1.9561 | 3000 | 0.4652 | 0.5495 | 0.5210 | 0.5495 | 0.5276 | 0.5245 | 0.7757 |
76
+ | 0.4655 | 2.0861 | 3200 | 0.4610 | 0.5654 | 0.5286 | 0.5654 | 0.5444 | 0.5224 | 0.7813 |
77
+ | 0.4655 | 2.2165 | 3400 | 0.4654 | 0.5498 | 0.5186 | 0.5498 | 0.5400 | 0.5255 | 0.7809 |
78
+ | 0.4414 | 2.3469 | 3600 | 0.4660 | 0.5530 | 0.5192 | 0.5530 | 0.5427 | 0.5267 | 0.7817 |
79
+ | 0.4414 | 2.4774 | 3800 | 0.4593 | 0.5644 | 0.5393 | 0.5644 | 0.5431 | 0.5388 | 0.7855 |
80
+ | 0.433 | 2.6078 | 4000 | 0.4605 | 0.5583 | 0.5309 | 0.5583 | 0.5405 | 0.5347 | 0.7849 |
81
+ | 0.433 | 2.7382 | 4200 | 0.4673 | 0.5486 | 0.5245 | 0.5486 | 0.5430 | 0.5359 | 0.7851 |
82
+ | 0.433 | 2.8687 | 4400 | 0.4532 | 0.5686 | 0.5358 | 0.5686 | 0.5499 | 0.5319 | 0.7869 |
83
+ | 0.435 | 2.9991 | 4600 | 0.4587 | 0.5696 | 0.5394 | 0.5696 | 0.5470 | 0.5386 | 0.7865 |
84
+ | 0.435 | 3.1291 | 4800 | 0.4601 | 0.5660 | 0.5352 | 0.5660 | 0.5485 | 0.5373 | 0.7869 |
85
+ | 0.4056 | 3.2596 | 5000 | 0.4702 | 0.5675 | 0.5441 | 0.5675 | 0.5454 | 0.5461 | 0.7877 |
86
 
87
 
88
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c8df9e3ef2e04004c738ae5f2e230c0876ade55d5398752ef0950ed7a30468a
3
  size 498619448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:754db8ece04f08afc8ad51fe96261658a14c2f2cf315405e4fac824ffbad390c
3
  size 498619448