Hugging Face's logo

Dagobert42
/
mobilebert-uncased-biored-augmented

Token Classification
Transformers
Safetensors
English
mobilebert
low-resource NER
token_classification
biomedicine
medical NER
Generated from Trainer
Inference Endpoints
Model card Files Community
Dagobert42 commited on
Commit
f3277fb
•
1 Parent(s): c03605b

Push ../models/google/mobilebert-uncased/biored-augmentations-only/ trained on biored-train_200_splits.pt (200 samples)

Browse files
Files changed (3) hide show
  1. README.md +16 -12
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -28,12 +28,12 @@ should probably proofread and complete it, then remove this comment. -->
28
 
29
  This model is a fine-tuned version of [mobilebert-uncased](https://huggingface.co/mobilebert-uncased) on the bigbio/biored dataset.
30
  It achieves the following results on the evaluation set:
31
- - Loss: 0.6899
32
- - Accuracy: 0.7602
33
- - Precision: 0.3688
34
- - Recall: 0.3041
35
- - F1: 0.3156
36
- - Weighted F1: 0.7222
37
 
38
  ## Model description
39
 
@@ -64,12 +64,16 @@ The following hyperparameters were used during training:
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Weighted F1 |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-----------:|
67
- | No log | 1.0 | 25 | 0.7196 | 0.747 | 0.3378 | 0.2541 | 0.2627 | 0.6818 |
68
- | No log | 2.0 | 50 | 0.7024 | 0.7492 | 0.333 | 0.2656 | 0.2615 | 0.6836 |
69
- | No log | 3.0 | 75 | 0.6954 | 0.7518 | 0.3779 | 0.2882 | 0.2895 | 0.7058 |
70
- | No log | 4.0 | 100 | 0.6907 | 0.7554 | 0.3717 | 0.2955 | 0.3095 | 0.7122 |
71
- | No log | 5.0 | 125 | 0.7041 | 0.7503 | 0.3606 | 0.2999 | 0.3036 | 0.7167 |
72
- | No log | 6.0 | 150 | 0.6945 | 0.7466 | 0.35 | 0.3302 | 0.3314 | 0.7348 |
 
 
 
 
73
 
74
 
75
  ### Framework versions
 
28
 
29
  This model is a fine-tuned version of [mobilebert-uncased](https://huggingface.co/mobilebert-uncased) on the bigbio/biored dataset.
30
  It achieves the following results on the evaluation set:
31
+ - Loss: 0.5602
32
+ - Accuracy: 0.8057
33
+ - Precision: 0.6022
34
+ - Recall: 0.4577
35
+ - F1: 0.5007
36
+ - Weighted F1: 0.7931
37
 
38
  ## Model description
39
 
 
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Weighted F1 |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-----------:|
67
+ | No log | 1.0 | 25 | 0.6641 | 0.7644 | 0.5563 | 0.3256 | 0.3768 | 0.7254 |
68
+ | No log | 2.0 | 50 | 0.6506 | 0.7728 | 0.5735 | 0.369 | 0.4057 | 0.7457 |
69
+ | No log | 3.0 | 75 | 0.6352 | 0.7779 | 0.5671 | 0.413 | 0.4527 | 0.768 |
70
+ | No log | 4.0 | 100 | 0.6147 | 0.7886 | 0.6221 | 0.4133 | 0.4523 | 0.7723 |
71
+ | No log | 5.0 | 125 | 0.6223 | 0.7885 | 0.6176 | 0.4051 | 0.4416 | 0.7684 |
72
+ | No log | 6.0 | 150 | 0.6020 | 0.7913 | 0.584 | 0.4496 | 0.4928 | 0.7811 |
73
+ | No log | 7.0 | 175 | 0.6081 | 0.7913 | 0.5508 | 0.4964 | 0.5183 | 0.7876 |
74
+ | No log | 8.0 | 200 | 0.5935 | 0.799 | 0.6333 | 0.4461 | 0.4926 | 0.7826 |
75
+ | No log | 9.0 | 225 | 0.6110 | 0.7941 | 0.5998 | 0.4656 | 0.5078 | 0.7825 |
76
+ | No log | 10.0 | 250 | 0.5990 | 0.798 | 0.6332 | 0.4564 | 0.5099 | 0.7777 |
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c244510df4dd1255ec689b43e285681884bd787d49edb73284b14d4907e3b26a
3
  size 98480380
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c013b2a404e13e3a222902d470b93d4c5bea1e940d902a74a086e6cbc379c1e1
3
  size 98480380
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b5c9765189889e1f774d93101f74bd5a4f0f3a12a9e7e47d382bfe6fb71b388
3
  size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cb5730f553c88f409b73ff819e9301648905360890c51444c85eb22dfff4e3c
3
  size 4219