Hugging Face's logo

dtorber
/
bert-base-cased

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files
xet
Metrics Community
dtorber commited on
Commit
3ab9a6b
·
verified ·
1 Parent(s): cd8fc01

Model save

Browse files
Files changed (3) hide show
  1. README.md +17 -15
  2. model.safetensors +1 -1
  3. runs/Apr06_15-43-08_tardis/events.out.tfevents.1712411533.tardis.16374.1 +3 -0
README.md CHANGED
@@ -18,14 +18,14 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.3214
22
- - F1 Macro: 0.9212
23
- - F1: 0.9476
24
- - F1 Neg: 0.8947
25
- - Acc: 0.93
26
- - Prec: 0.9547
27
  - Recall: 0.9405
28
- - Mcc: 0.8425
29
 
30
  ## Model description
31
 
@@ -51,20 +51,22 @@ The following hyperparameters were used during training:
51
  - distributed_type: multi-GPU
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
- - num_epochs: 7
55
  - mixed_precision_training: Native AMP
56
 
57
  ### Training results
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc |
60
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|
61
- | No log | 1.0 | 412 | 0.2817 | 0.8795 | 0.9151 | 0.8440 | 0.89 | 0.9046 | 0.9258 | 0.7595 |
62
- | 0.4173 | 2.0 | 824 | 0.3331 | 0.8988 | 0.9284 | 0.8693 | 0.9075 | 0.9195 | 0.9375 | 0.7980 |
63
- | 0.2108 | 3.0 | 1236 | 0.3942 | 0.9158 | 0.9396 | 0.8920 | 0.9225 | 0.9377 | 0.9414 | 0.8316 |
64
- | 0.1141 | 4.0 | 1648 | 0.4819 | 0.9092 | 0.9367 | 0.8817 | 0.9175 | 0.9208 | 0.9531 | 0.8195 |
65
- | 0.0448 | 5.0 | 2060 | 0.5918 | 0.9049 | 0.9318 | 0.8780 | 0.9125 | 0.9300 | 0.9336 | 0.8098 |
66
- | 0.0448 | 6.0 | 2472 | 0.5999 | 0.9127 | 0.9380 | 0.8873 | 0.92 | 0.9308 | 0.9453 | 0.8255 |
67
- | 0.0152 | 7.0 | 2884 | 0.6255 | 0.9127 | 0.9380 | 0.8873 | 0.92 | 0.9308 | 0.9453 | 0.8255 |
 
 
68
 
69
 
70
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.3452
22
+ - F1 Macro: 0.9122
23
+ - F1: 0.9423
24
+ - F1 Neg: 0.8821
25
+ - Acc: 0.9225
26
+ - Prec: 0.9440
27
  - Recall: 0.9405
28
+ - Mcc: 0.8244
29
 
30
  ## Model description
31
 
 
51
  - distributed_type: multi-GPU
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
+ - num_epochs: 9
55
  - mixed_precision_training: Native AMP
56
 
57
  ### Training results
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc |
60
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|
61
+ | No log | 1.0 | 412 | 0.2874 | 0.8817 | 0.9175 | 0.8459 | 0.8925 | 0.9019 | 0.9336 | 0.7644 |
62
+ | 0.4079 | 2.0 | 824 | 0.3926 | 0.8937 | 0.9243 | 0.8632 | 0.9025 | 0.9189 | 0.9297 | 0.7875 |
63
+ | 0.2262 | 3.0 | 1236 | 0.4043 | 0.9135 | 0.9373 | 0.8897 | 0.92 | 0.9409 | 0.9336 | 0.8270 |
64
+ | 0.1144 | 4.0 | 1648 | 0.4935 | 0.9055 | 0.9312 | 0.8797 | 0.9125 | 0.9368 | 0.9258 | 0.8111 |
65
+ | 0.0444 | 5.0 | 2060 | 0.6089 | 0.9063 | 0.9304 | 0.8822 | 0.9125 | 0.9474 | 0.9141 | 0.8136 |
66
+ | 0.0444 | 6.0 | 2472 | 0.6717 | 0.9063 | 0.9304 | 0.8822 | 0.9125 | 0.9474 | 0.9141 | 0.8136 |
67
+ | 0.0211 | 7.0 | 2884 | 0.7189 | 0.8963 | 0.9264 | 0.8662 | 0.905 | 0.9192 | 0.9336 | 0.7928 |
68
+ | 0.0127 | 8.0 | 3296 | 0.7510 | 0.8988 | 0.9284 | 0.8693 | 0.9075 | 0.9195 | 0.9375 | 0.7980 |
69
+ | 0.0025 | 9.0 | 3708 | 0.7730 | 0.9058 | 0.9310 | 0.8805 | 0.9125 | 0.9402 | 0.9219 | 0.8118 |
70
 
71
 
72
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7677911a55f207ded535c40f27552d428c790956686ff4c23edcd1a9699b68b0
3
  size 433270768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4075b87ed946eae75264f6c7e00b80813d211b70d3bfc753d93719ebbd9495a9
3
  size 433270768
runs/Apr06_15-43-08_tardis/events.out.tfevents.1712411533.tardis.16374.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:775b35b52a003d7d315893069f2a47dcaa4ca8b28f5b957c2b78aa19e27d0f6e
3
+ size 699