Hugging Face's logo

Heather-Driver
/
distilbert-NER-Math-finetuned

Token Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Heather-Driver commited on
Commit
f9519bd
·
verified ·
1 Parent(s): d673612

NER Training

Browse files
Files changed (2) hide show
  1. README.md +15 -13
  2. runs/Jan13_07-51-07_cdcd515ae2d3/events.out.tfevents.1736754686.cdcd515ae2d3.2006.1 +2 -2
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [dslim/distilbert-NER](https://huggingface.co/dslim/distilbert-NER) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.0483
20
- - F1 Score: 0.9453
21
 
22
  ## Model description
23
 
@@ -42,22 +42,24 @@ The following hyperparameters were used during training:
42
  - seed: 42
43
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
44
  - lr_scheduler_type: linear
45
- - num_epochs: 10
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | F1 Score |
50
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
51
- | 0.1069 | 1.0 | 1534 | 0.0825 | 0.8414 |
52
- | 0.0553 | 2.0 | 3068 | 0.0587 | 0.8826 |
53
- | 0.0369 | 3.0 | 4602 | 0.0472 | 0.9125 |
54
- | 0.018 | 4.0 | 6136 | 0.0465 | 0.9206 |
55
- | 0.0127 | 5.0 | 7670 | 0.0447 | 0.9351 |
56
- | 0.0057 | 6.0 | 9204 | 0.0473 | 0.9377 |
57
- | 0.0045 | 7.0 | 10738 | 0.0465 | 0.9427 |
58
- | 0.0019 | 8.0 | 12272 | 0.0500 | 0.9409 |
59
- | 0.0026 | 9.0 | 13806 | 0.0486 | 0.9446 |
60
- | 0.0015 | 10.0 | 15340 | 0.0483 | 0.9453 |
 
 
61
 
62
 
63
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [dslim/distilbert-NER](https://huggingface.co/dslim/distilbert-NER) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.0560
20
+ - F1 Score: 0.9524
21
 
22
  ## Model description
23
 
 
42
  - seed: 42
43
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
44
  - lr_scheduler_type: linear
45
+ - num_epochs: 12
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | F1 Score |
50
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
51
+ | 0.0082 | 1.0 | 1534 | 0.0556 | 0.9337 |
52
+ | 0.0057 | 2.0 | 3068 | 0.0626 | 0.9276 |
53
+ | 0.0043 | 3.0 | 4602 | 0.0560 | 0.9380 |
54
+ | 0.0036 | 4.0 | 6136 | 0.0576 | 0.9387 |
55
+ | 0.0035 | 5.0 | 7670 | 0.0536 | 0.9437 |
56
+ | 0.0024 | 6.0 | 9204 | 0.0564 | 0.9449 |
57
+ | 0.0013 | 7.0 | 10738 | 0.0556 | 0.9496 |
58
+ | 0.001 | 8.0 | 12272 | 0.0571 | 0.9490 |
59
+ | 0.0009 | 9.0 | 13806 | 0.0570 | 0.9486 |
60
+ | 0.0016 | 10.0 | 15340 | 0.0574 | 0.9512 |
61
+ | 0.0002 | 11.0 | 16874 | 0.0563 | 0.9521 |
62
+ | 0.0001 | 12.0 | 18408 | 0.0560 | 0.9524 |
63
 
64
 
65
  ### Framework versions
runs/Jan13_07-51-07_cdcd515ae2d3/events.out.tfevents.1736754686.cdcd515ae2d3.2006.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f025ab02652e6737cb9282e0e6d6484ca222951e847b2762d63e03827de597a
3
- size 90334
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44622e91426b9fdcddcab7e6f3ccfcff1444c4d047ae899e0b96c0c19f9ea961
3
+ size 91023