Hugging Face's logo

MKS3099
/
bert-base-uncased-finetuned-stationary-epoch-update

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
MKS3099 commited on
Commit
3f6a87a
·
1 Parent(s): 30dee5d

Training completed!

Browse files
Files changed (4) hide show
  1. README.md +9 -19
  2. model.safetensors +1 -1
  3. runs/Dec20_13-05-50_c76653bfe8be/events.out.tfevents.1703077556.c76653bfe8be.551.1 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.0945
22
- - Accuracy: 0.8167
23
- - F1: 0.8090
24
 
25
  ## Model description
26
 
@@ -45,27 +45,17 @@ The following hyperparameters were used during training:
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
- - num_epochs: 15
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
54
- | 0.6008 | 1.0 | 38 | 0.5006 | 0.7267 | 0.6924 |
55
- | 0.4314 | 2.0 | 76 | 0.4429 | 0.81 | 0.8107 |
56
- | 0.3104 | 3.0 | 114 | 0.4770 | 0.8067 | 0.8005 |
57
- | 0.1893 | 4.0 | 152 | 0.6433 | 0.81 | 0.7985 |
58
- | 0.1103 | 5.0 | 190 | 0.7405 | 0.8 | 0.7841 |
59
- | 0.0708 | 6.0 | 228 | 0.7971 | 0.8133 | 0.8025 |
60
- | 0.0464 | 7.0 | 266 | 0.9670 | 0.79 | 0.7727 |
61
- | 0.0224 | 8.0 | 304 | 1.0068 | 0.8067 | 0.7964 |
62
- | 0.0163 | 9.0 | 342 | 0.9835 | 0.8033 | 0.7959 |
63
- | 0.0182 | 10.0 | 380 | 1.0203 | 0.8067 | 0.7981 |
64
- | 0.0118 | 11.0 | 418 | 1.0874 | 0.8133 | 0.8034 |
65
- | 0.0052 | 12.0 | 456 | 1.1500 | 0.81 | 0.7985 |
66
- | 0.0052 | 13.0 | 494 | 1.0991 | 0.8167 | 0.8082 |
67
- | 0.0076 | 14.0 | 532 | 1.1015 | 0.82 | 0.8104 |
68
- | 0.0037 | 15.0 | 570 | 1.0945 | 0.8167 | 0.8090 |
69
 
70
 
71
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.4848
22
+ - Accuracy: 0.81
23
+ - F1: 0.8070
24
 
25
  ## Model description
26
 
 
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
+ - num_epochs: 5
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
54
+ | 0.5929 | 1.0 | 38 | 0.4930 | 0.7567 | 0.7336 |
55
+ | 0.4451 | 2.0 | 76 | 0.4422 | 0.8067 | 0.8076 |
56
+ | 0.3475 | 3.0 | 114 | 0.4470 | 0.81 | 0.8115 |
57
+ | 0.2764 | 4.0 | 152 | 0.5021 | 0.78 | 0.7693 |
58
+ | 0.2205 | 5.0 | 190 | 0.4848 | 0.81 | 0.8070 |
 
 
 
 
 
 
 
 
 
 
59
 
60
 
61
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8e02c42428e72e843603f25650872cee0668e09025a753e28e1e58c461a3490
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7db50cfc87fb3c3dac2d86b233ed07841c462c1dfd7f57de682af864f92de154
3
  size 437958648
runs/Dec20_13-05-50_c76653bfe8be/events.out.tfevents.1703077556.c76653bfe8be.551.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bee1bfa5d4d4ef539b1011e79585666ce6ac0f9b2f565f9a52aff93a7219178a
3
+ size 7260
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03abffb567733db28a5c2cda9144202ef502bd0ed3cce0e2027f2f542378b35f
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:814d442e950668b7dc941360547f602e9b516929b48542b0ec526e28886e5750
3
  size 4664