Hugging Face's logo

ccaug
/
results

Text Classification
Transformers
Safetensors
modernbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
ccaug commited on
Commit
72294ed
·
verified ·
1 Parent(s): 3fc0991

ccaug/modernbert-pcap

Browse files
Files changed (3) hide show
  1. README.md +19 -16
  2. model.safetensors +1 -1
  3. training_args.bin +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 [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.1729
25
- - Accuracy: 0.9439
26
- - F1: 0.9439
27
- - Precision: 0.9461
28
- - Recall: 0.9439
29
 
30
  ## Model description
31
 
@@ -44,7 +44,7 @@ More information needed
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
- - learning_rate: 5e-05
48
  - train_batch_size: 6
49
  - eval_batch_size: 6
50
  - seed: 42
@@ -52,22 +52,25 @@ The following hyperparameters were used during training:
52
  - total_train_batch_size: 12
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
- - num_epochs: 1
56
  - mixed_precision_training: Native AMP
57
 
58
  ### Training results
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
61
  |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
62
- | 3.3687 | 0.1111 | 25 | 1.3275 | 0.425 | 0.3703 | 0.6006 | 0.425 |
63
- | 1.9545 | 0.2222 | 50 | 0.8983 | 0.6839 | 0.6536 | 0.6803 | 0.6839 |
64
- | 1.2368 | 0.3333 | 75 | 0.4575 | 0.8367 | 0.8323 | 0.8547 | 0.8367 |
65
- | 0.9007 | 0.4444 | 100 | 0.4360 | 0.8578 | 0.8436 | 0.8784 | 0.8578 |
66
- | 0.8601 | 0.5556 | 125 | 0.2811 | 0.8856 | 0.8869 | 0.8931 | 0.8856 |
67
- | 0.5962 | 0.6667 | 150 | 0.3887 | 0.8817 | 0.8717 | 0.9074 | 0.8817 |
68
- | 0.5623 | 0.7778 | 175 | 0.2442 | 0.9128 | 0.9102 | 0.9233 | 0.9128 |
69
- | 0.295 | 0.8889 | 200 | 0.2014 | 0.9283 | 0.9264 | 0.9361 | 0.9283 |
70
- | 0.6196 | 1.0 | 225 | 0.1729 | 0.9439 | 0.9439 | 0.9461 | 0.9439 |
 
 
 
71
 
72
 
73
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.2000
25
+ - Accuracy: 0.9433
26
+ - F1: 0.9429
27
+ - Precision: 0.9508
28
+ - Recall: 0.9433
29
 
30
  ## Model description
31
 
 
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
+ - learning_rate: 4e-05
48
  - train_batch_size: 6
49
  - eval_batch_size: 6
50
  - seed: 42
 
52
  - total_train_batch_size: 12
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
+ - num_epochs: 2
56
  - mixed_precision_training: Native AMP
57
 
58
  ### Training results
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
61
  |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
62
+ | 3.8028 | 0.0833 | 25 | 1.5191 | 0.3944 | 0.2893 | 0.4598 | 0.3944 |
63
+ | 2.2046 | 0.1667 | 50 | 0.7147 | 0.75 | 0.7423 | 0.7685 | 0.75 |
64
+ | 1.2172 | 0.25 | 75 | 0.6074 | 0.7989 | 0.7727 | 0.8508 | 0.7989 |
65
+ | 0.9054 | 0.3333 | 100 | 0.3817 | 0.8656 | 0.8637 | 0.8907 | 0.8656 |
66
+ | 0.873 | 0.4167 | 125 | 0.3460 | 0.8678 | 0.8665 | 0.8810 | 0.8678 |
67
+ | 0.7074 | 0.5 | 150 | 0.2918 | 0.8889 | 0.8848 | 0.9159 | 0.8889 |
68
+ | 1.0552 | 0.5833 | 175 | 0.2550 | 0.89 | 0.8868 | 0.9130 | 0.89 |
69
+ | 0.5167 | 0.6667 | 200 | 0.2660 | 0.9044 | 0.9043 | 0.9071 | 0.9044 |
70
+ | 0.3174 | 0.75 | 225 | 0.2641 | 0.8956 | 0.8882 | 0.9235 | 0.8956 |
71
+ | 0.3369 | 0.8333 | 250 | 0.1745 | 0.9489 | 0.9490 | 0.9520 | 0.9489 |
72
+ | 0.2966 | 0.9167 | 275 | 0.1484 | 0.9567 | 0.9568 | 0.9589 | 0.9567 |
73
+ | 0.5544 | 1.0 | 300 | 0.2000 | 0.9433 | 0.9429 | 0.9508 | 0.9433 |
74
 
75
 
76
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73a22c47896844149915e77622eabcec9a3cfd867243f68d5bd0687b11a00497
3
  size 598461316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2f89595e496e2c31773377d1e8822a1b55bbae0d268e0e4fd74fe00bbac3f01
3
  size 598461316
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7ec83b42e86ca222902aeff78581a6aecbaa9bd51002bddc3f3eb0fae99720f
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1338d801601b58554a849c9ae5a59dae0269bba5783fe44b7da195e0dbd8ab49
3
  size 5777