Hugging Face's logo

andi611
/
bert-base-uncased-ner-conll2003

Token Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Model card Files
xet
Metrics Community
3
EC2 Default User commited on
Commit
efdf72f
·
1 Parent(s): cfb3200

add model

Browse files
Files changed (5) hide show
  1. README.md +10 -13
  2. pytorch_model.bin +1 -1
  3. runs/Jul07_09-30-05_ip-172-31-49-109.ec2.internal/1625650275.570915/events.out.tfevents.1625650275.ip-172-31-49-109.ec2.internal +0 -0
  4. runs/Jul07_09-30-05_ip-172-31-49-109.ec2.internal/events.out.tfevents.1625650275.ip-172-31-49-109.ec2.internal +0 -0
  5. training_args.bin +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model_index:
22
  metric:
23
  name: Accuracy
24
  type: accuracy
25
- value: 0.986576008388009
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,11 +32,11 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the conll2003 dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.0638
36
- - Precision: 0.9417
37
- - Recall: 0.9507
38
- - F1: 0.9462
39
- - Accuracy: 0.9866
40
 
41
  ## Model description
42
 
@@ -55,23 +55,20 @@ More information needed
55
  ### Training hyperparameters
56
 
57
  The following hyperparameters were used during training:
58
- - learning_rate: 5e-05
59
  - train_batch_size: 16
60
  - eval_batch_size: 32
61
  - seed: 42
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
- - lr_scheduler_warmup_steps: 1000
65
- - num_epochs: 4
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
70
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
71
- | 0.5266 | 1.0 | 878 | 0.0664 | 0.9217 | 0.9289 | 0.9253 | 0.9826 |
72
- | 0.0589 | 2.0 | 1756 | 0.0570 | 0.9238 | 0.9399 | 0.9318 | 0.9836 |
73
- | 0.0227 | 3.0 | 2634 | 0.0635 | 0.9344 | 0.9455 | 0.9399 | 0.9850 |
74
- | 0.0087 | 4.0 | 3512 | 0.0638 | 0.9417 | 0.9507 | 0.9462 | 0.9866 |
75
 
76
 
77
  ### Framework versions
 
22
  metric:
23
  name: Accuracy
24
  type: accuracy
25
+ value: 0.19881805328292054
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the conll2003 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 2.1258
36
+ - Precision: 0.0269
37
+ - Recall: 0.1379
38
+ - F1: 0.0451
39
+ - Accuracy: 0.1988
40
 
41
  ## Model description
42
 
 
55
  ### Training hyperparameters
56
 
57
  The following hyperparameters were used during training:
58
+ - learning_rate: 2e-05
59
  - train_batch_size: 16
60
  - eval_batch_size: 32
61
  - seed: 42
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
+ - num_epochs: 2
 
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
70
+ | No log | 1.0 | 4 | 2.1296 | 0.0270 | 0.1389 | 0.0452 | 0.1942 |
71
+ | No log | 2.0 | 8 | 2.1258 | 0.0269 | 0.1379 | 0.0451 | 0.1988 |
 
 
72
 
73
 
74
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4033747447709d759a780db6871329f6fbf29971fa9354a7965187f63e3ee14d
3
  size 435682807
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e398de492c039df4d2d8dd0149e9168355003de3dc833e79bfcfc030d360984a
3
  size 435682807
runs/Jul07_09-30-05_ip-172-31-49-109.ec2.internal/1625650275.570915/events.out.tfevents.1625650275.ip-172-31-49-109.ec2.internal ADDED
Binary file (4.18 kB). View file
 
runs/Jul07_09-30-05_ip-172-31-49-109.ec2.internal/events.out.tfevents.1625650275.ip-172-31-49-109.ec2.internal ADDED
Binary file (4.72 kB). View file
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d937823f6404d763409b0f4c494419d41111fe64245fe29363f5593a5bcf0a3
3
- size 2671
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dabc1b732e8239965e4c3a21c80c330cfb9c8703d3fbdc7d2293a3d9f29526cb
3
+ size 2735