Hugging Face's logo

bdpc
/
SciBERT_twowayloss_25K_bs64

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
bdpc commited on
Commit
ba0ce07
•
1 Parent(s): 2c0f5f2

Saving best model of SciBERT_TwoWayLoss_25K_bs64 to hub

Browse files
Files changed (5) hide show
  1. README.md +15 -15
  2. all_results.json +5 -5
  3. pytorch_model.bin +1 -1
  4. train_results.json +5 -5
  5. training_args.bin +1 -1
README.md CHANGED
@@ -8,23 +8,23 @@ metrics:
8
  - recall
9
  - f1
10
  model-index:
11
- - name: SciBERT_twowayloss_25K_bs64
12
  results: []
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
  should probably proofread and complete it, then remove this comment. -->
17
 
18
- # SciBERT_twowayloss_25K_bs64
19
 
20
  This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.0158
23
- - Accuracy: 0.9945
24
- - Precision: 0.7948
25
- - Recall: 0.5830
26
- - F1: 0.6727
27
- - Hamming: 0.0055
28
 
29
  ## Model description
30
 
@@ -44,8 +44,8 @@ More information needed
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 2e-05
47
- - train_batch_size: 64
48
- - eval_batch_size: 64
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
@@ -56,11 +56,11 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Hamming |
58
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|:-------:|
59
- | 0.0332 | 0.16 | 5000 | 0.0283 | 0.9921 | 0.8249 | 0.2410 | 0.3730 | 0.0079 |
60
- | 0.0195 | 0.32 | 10000 | 0.0186 | 0.9939 | 0.7964 | 0.4983 | 0.6131 | 0.0061 |
61
- | 0.0173 | 0.47 | 15000 | 0.0168 | 0.9943 | 0.7936 | 0.5587 | 0.6557 | 0.0057 |
62
- | 0.0165 | 0.63 | 20000 | 0.0161 | 0.9944 | 0.7949 | 0.5782 | 0.6694 | 0.0056 |
63
- | 0.0161 | 0.79 | 25000 | 0.0158 | 0.9945 | 0.7948 | 0.5830 | 0.6727 | 0.0055 |
64
 
65
 
66
  ### Framework versions
 
8
  - recall
9
  - f1
10
  model-index:
11
+ - name: SciBERT_TwoWayLoss_25K_bs64
12
  results: []
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
  should probably proofread and complete it, then remove this comment. -->
17
 
18
+ # SciBERT_TwoWayLoss_25K_bs64
19
 
20
  This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 5.7117
23
+ - Accuracy: 0.7367
24
+ - Precision: 0.0357
25
+ - Recall: 0.9994
26
+ - F1: 0.0689
27
+ - Hamming: 0.2633
28
 
29
  ## Model description
30
 
 
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 2e-05
47
+ - train_batch_size: 192
48
+ - eval_batch_size: 192
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
 
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Hamming |
58
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|:-------:|
59
+ | 6.7538 | 0.47 | 5000 | 6.4722 | 0.7208 | 0.0337 | 0.9987 | 0.0652 | 0.2792 |
60
+ | 6.1625 | 0.95 | 10000 | 6.0293 | 0.7311 | 0.0350 | 0.9991 | 0.0676 | 0.2689 |
61
+ | 5.7863 | 1.42 | 15000 | 5.8415 | 0.7362 | 0.0356 | 0.9992 | 0.0688 | 0.2638 |
62
+ | 5.6995 | 1.9 | 20000 | 5.7343 | 0.7366 | 0.0357 | 0.9994 | 0.0689 | 0.2634 |
63
+ | 5.4711 | 2.37 | 25000 | 5.7117 | 0.7367 | 0.0357 | 0.9994 | 0.0689 | 0.2633 |
64
 
65
 
66
  ### Framework versions
all_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "epoch": 0.79,
3
- "train_loss": 0.035478990478515625,
4
- "train_runtime": 37421.8729,
5
- "train_samples_per_second": 42.756,
6
- "train_steps_per_second": 0.668
7
  }
 
1
  {
2
+ "epoch": 2.37,
3
+ "train_loss": 6.40765580078125,
4
+ "train_runtime": 40238.8097,
5
+ "train_samples_per_second": 119.288,
6
+ "train_steps_per_second": 0.621
7
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:194ef24bb5654deb12d392721c5b011063d67909de835fb505fbfe5ec9bc44c2
3
  size 440249777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b47e03d0bfd48e03b50aed01a5195ecdbf8d5645c84471f38fe403229b856bda
3
  size 440249777
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "epoch": 0.79,
3
- "train_loss": 0.035478990478515625,
4
- "train_runtime": 37421.8729,
5
- "train_samples_per_second": 42.756,
6
- "train_steps_per_second": 0.668
7
  }
 
1
  {
2
+ "epoch": 2.37,
3
+ "train_loss": 6.40765580078125,
4
+ "train_runtime": 40238.8097,
5
+ "train_samples_per_second": 119.288,
6
+ "train_steps_per_second": 0.621
7
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:966cfd2427291b363134071b600212dc366ae784066861a7545e04cb453c3d0c
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bed994926f1d60d4ef894b7c02dab3a173005b5db54ee74c2f0e1711cca1f98
3
  size 4155