Hugging Face's logo

fixthemusic
/
ftm-zone-classifier

Token Classification
Transformers
Safetensors
modernbert
Generated from Trainer
Model card Files
xet
Community
fmnxl commited on
Commit
967f7e2
·
verified ·
1 Parent(s): 6c85e53

End of training

Browse files
Files changed (2) hide show
  1. README.md +12 -14
  2. model.safetensors +1 -1
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [jhu-clsp/mmBERT-base](https://huggingface.co/jhu-clsp/mmBERT-base) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.2218
25
- - Precision: 0.6827
26
- - Recall: 0.7433
27
- - F1: 0.7117
28
- - Accuracy: 0.8090
29
 
30
  ## Model description
31
 
@@ -45,25 +45,23 @@ More information needed
45
 
46
  The following hyperparameters were used during training:
47
  - learning_rate: 2e-05
48
- - train_batch_size: 16
49
- - eval_batch_size: 32
50
  - seed: 42
51
- - gradient_accumulation_steps: 4
52
  - total_train_batch_size: 64
53
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
54
  - lr_scheduler_type: linear
55
  - lr_scheduler_warmup_ratio: 0.1
56
- - num_epochs: 5
57
 
58
  ### Training results
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
61
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
62
- | 0.2553 | 1.0 | 342 | 0.2404 | 0.6501 | 0.7494 | 0.6962 | 0.8119 |
63
- | 0.2284 | 2.0 | 684 | 0.2320 | 0.6823 | 0.7437 | 0.7117 | 0.8194 |
64
- | 0.2127 | 3.0 | 1026 | 0.2218 | 0.6827 | 0.7433 | 0.7117 | 0.8090 |
65
- | 0.1901 | 4.0 | 1368 | 0.2282 | 0.6684 | 0.7470 | 0.7055 | 0.8351 |
66
- | 0.1634 | 5.0 | 1710 | 0.2494 | 0.6580 | 0.7418 | 0.6974 | 0.8368 |
67
 
68
 
69
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [jhu-clsp/mmBERT-base](https://huggingface.co/jhu-clsp/mmBERT-base) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.4678
25
+ - Precision: 0.7161
26
+ - Recall: 0.7207
27
+ - F1: 0.7184
28
+ - Accuracy: 0.8243
29
 
30
  ## Model description
31
 
 
45
 
46
  The following hyperparameters were used during training:
47
  - learning_rate: 2e-05
48
+ - train_batch_size: 8
49
+ - eval_batch_size: 16
50
  - seed: 42
51
+ - gradient_accumulation_steps: 8
52
  - total_train_batch_size: 64
53
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
54
  - lr_scheduler_type: linear
55
  - lr_scheduler_warmup_ratio: 0.1
56
+ - num_epochs: 3
57
 
58
  ### Training results
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
61
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
62
+ | 0.4626 | 1.0 | 342 | 0.4884 | 0.6803 | 0.7225 | 0.7008 | 0.8146 |
63
+ | 0.4385 | 2.0 | 684 | 0.4678 | 0.7161 | 0.7207 | 0.7184 | 0.8243 |
64
+ | 0.4073 | 3.0 | 1026 | 0.4387 | 0.6786 | 0.7252 | 0.7011 | 0.8255 |
 
 
65
 
66
 
67
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67e875a7ac6a0005eb11b39d6e3d716d96f0c97fb57d0b77682fd43591702546
3
  size 1230156812
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7cd5549fc0e9cdd841072f30db7a69589e64003fac1dbffe6210e0661b39860
3
  size 1230156812