Hugging Face's logo

jgammack
/
MTL-bert-base-uncased

Fill-Mask
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Model card Files
xet
Metrics Community
2
jgammack commited on
Commit
5eb276c
·
1 Parent(s): ed6dadd

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -18
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 2.2486
18
 
19
  ## Model description
20
 
@@ -34,32 +34,33 @@ More information needed
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 2e-05
37
- - train_batch_size: 8
38
- - eval_batch_size: 8
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
  - num_epochs: 15
 
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
- | No log | 1.0 | 94 | 2.6014 |
49
- | No log | 2.0 | 188 | 2.3898 |
50
- | No log | 3.0 | 282 | 2.3706 |
51
- | No log | 4.0 | 376 | 2.2708 |
52
- | No log | 5.0 | 470 | 2.2666 |
53
- | 2.5403 | 6.0 | 564 | 2.2639 |
54
- | 2.5403 | 7.0 | 658 | 2.3061 |
55
- | 2.5403 | 8.0 | 752 | 2.2659 |
56
- | 2.5403 | 9.0 | 846 | 2.1882 |
57
- | 2.5403 | 10.0 | 940 | 2.2198 |
58
- | 2.2739 | 11.0 | 1034 | 2.1124 |
59
- | 2.2739 | 12.0 | 1128 | 2.1887 |
60
- | 2.2739 | 13.0 | 1222 | 2.1740 |
61
- | 2.2739 | 14.0 | 1316 | 2.1517 |
62
- | 2.2739 | 15.0 | 1410 | 2.1510 |
63
 
64
 
65
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 1.9283
18
 
19
  ## Model description
20
 
 
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 2e-05
37
+ - train_batch_size: 7
38
+ - eval_batch_size: 7
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
  - num_epochs: 15
43
+ - mixed_precision_training: Native AMP
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 2.4409 | 1.0 | 99 | 2.1982 |
50
+ | 2.2905 | 2.0 | 198 | 2.1643 |
51
+ | 2.1974 | 3.0 | 297 | 2.1168 |
52
+ | 2.15 | 4.0 | 396 | 2.0023 |
53
+ | 2.0823 | 5.0 | 495 | 2.0199 |
54
+ | 2.0752 | 6.0 | 594 | 1.9061 |
55
+ | 2.0408 | 7.0 | 693 | 1.9770 |
56
+ | 1.9984 | 8.0 | 792 | 1.9322 |
57
+ | 1.9933 | 9.0 | 891 | 1.9167 |
58
+ | 1.9806 | 10.0 | 990 | 1.9652 |
59
+ | 1.9436 | 11.0 | 1089 | 1.9308 |
60
+ | 1.9491 | 12.0 | 1188 | 1.9064 |
61
+ | 1.929 | 13.0 | 1287 | 1.8831 |
62
+ | 1.9096 | 14.0 | 1386 | 1.8927 |
63
+ | 1.9032 | 15.0 | 1485 | 1.9117 |
64
 
65
 
66
  ### Framework versions