Hugging Face's logo

Gozde
/
modernbert-tr-classifier

Text Classification
Transformers
TensorBoard
Safetensors
modernbert
Generated from Trainer
Model card Files
xet
Metrics Community
Gozde commited on
Commit
a6c88ca
·
verified ·
1 Parent(s): 9bdc43e

End of training

Browse files
Files changed (2) hide show
  1. README.md +30 -28
  2. runs/Jan23_15-47-00_ultramarine/events.out.tfevents.1737636421.ultramarine.3980114.0 +2 -2
README.md CHANGED
@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.6006
23
- - F1: 0.9060
24
- - Accuracy: 0.9061
25
 
26
  ## Model description
27
 
@@ -41,37 +41,39 @@ More information needed
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 8e-05
44
- - train_batch_size: 64
45
- - eval_batch_size: 64
46
  - seed: 42
 
 
47
  - optimizer: Use adamw_torch with betas=(0.9,0.98) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
48
- - lr_scheduler_type: linear
 
49
  - num_epochs: 20
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
54
- |:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
55
- | 1.7403 | 1.0 | 73 | 1.2040 | 0.5117 | 0.5429 |
56
- | 1.036 | 2.0 | 146 | 0.7293 | 0.7292 | 0.7347 |
57
- | 0.6043 | 3.0 | 219 | 0.5232 | 0.8202 | 0.8163 |
58
- | 0.3395 | 4.0 | 292 | 0.3972 | 0.8602 | 0.8571 |
59
- | 0.173 | 5.0 | 365 | 0.4365 | 0.8548 | 0.8571 |
60
- | 0.0784 | 6.0 | 438 | 0.4332 | 0.8667 | 0.8653 |
61
- | 0.0445 | 7.0 | 511 | 0.5221 | 0.8856 | 0.8857 |
62
- | 0.0354 | 8.0 | 584 | 0.5177 | 0.9023 | 0.9020 |
63
- | 0.0239 | 9.0 | 657 | 0.8380 | 0.8676 | 0.8653 |
64
- | 0.0199 | 10.0 | 730 | 0.6887 | 0.8755 | 0.8735 |
65
- | 0.017 | 11.0 | 803 | 0.6245 | 0.9013 | 0.9020 |
66
- | 0.0058 | 12.0 | 876 | 0.5052 | 0.9147 | 0.9143 |
67
- | 0.0051 | 13.0 | 949 | 0.6583 | 0.8834 | 0.8816 |
68
- | 0.0049 | 14.0 | 1022 | 0.6444 | 0.8889 | 0.8898 |
69
- | 0.0021 | 15.0 | 1095 | 0.7612 | 0.8761 | 0.8776 |
70
- | 0.001 | 16.0 | 1168 | 0.6017 | 0.9143 | 0.9143 |
71
- | 0.0005 | 17.0 | 1241 | 0.6069 | 0.9016 | 0.9020 |
72
- | 0.0005 | 18.0 | 1314 | 0.6110 | 0.9019 | 0.9020 |
73
- | 0.0004 | 19.0 | 1387 | 0.6050 | 0.9019 | 0.9020 |
74
- | 0.0004 | 20.0 | 1460 | 0.6006 | 0.9060 | 0.9061 |
75
 
76
 
77
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.8071
23
+ - F1: 0.7980
24
+ - Accuracy: 0.7959
25
 
26
  ## Model description
27
 
 
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 8e-05
44
+ - train_batch_size: 128
45
+ - eval_batch_size: 128
46
  - seed: 42
47
+ - gradient_accumulation_steps: 2
48
+ - total_train_batch_size: 256
49
  - optimizer: Use adamw_torch with betas=(0.9,0.98) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
50
+ - lr_scheduler_type: cosine
51
+ - lr_scheduler_warmup_steps: 500
52
  - num_epochs: 20
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
57
+ |:-------------:|:-------:|:----:|:---------------:|:------:|:--------:|
58
+ | 3.981 | 1.0 | 19 | 1.9665 | 0.0904 | 0.1633 |
59
+ | 3.6781 | 2.0 | 38 | 1.8383 | 0.1882 | 0.2449 |
60
+ | 3.1283 | 3.0 | 57 | 1.4232 | 0.4896 | 0.5061 |
61
+ | 2.4044 | 4.0 | 76 | 1.2398 | 0.5488 | 0.5673 |
62
+ | 1.9166 | 5.0 | 95 | 1.1468 | 0.5726 | 0.6041 |
63
+ | 1.7122 | 6.0 | 114 | 1.0013 | 0.6649 | 0.6653 |
64
+ | 1.4626 | 7.0 | 133 | 0.8954 | 0.7198 | 0.7224 |
65
+ | 1.2173 | 8.0 | 152 | 0.7306 | 0.7611 | 0.7592 |
66
+ | 1.0648 | 9.0 | 171 | 0.7449 | 0.7412 | 0.7388 |
67
+ | 0.9008 | 10.0 | 190 | 0.6874 | 0.7754 | 0.7714 |
68
+ | 0.856 | 11.0 | 209 | 0.6584 | 0.8071 | 0.8082 |
69
+ | 0.7557 | 12.0 | 228 | 0.6046 | 0.7854 | 0.7837 |
70
+ | 0.472 | 13.0 | 247 | 0.8246 | 0.7428 | 0.7429 |
71
+ | 0.4386 | 14.0 | 266 | 0.7892 | 0.8042 | 0.8082 |
72
+ | 0.3418 | 15.0 | 285 | 0.6727 | 0.8248 | 0.8286 |
73
+ | 0.2662 | 16.0 | 304 | 0.8244 | 0.8144 | 0.8163 |
74
+ | 0.1774 | 17.0 | 323 | 0.7832 | 0.8083 | 0.8041 |
75
+ | 0.1246 | 18.0 | 342 | 0.5501 | 0.8703 | 0.8694 |
76
+ | 0.121 | 18.9730 | 360 | 0.8071 | 0.7980 | 0.7959 |
 
77
 
78
 
79
  ### Framework versions
runs/Jan23_15-47-00_ultramarine/events.out.tfevents.1737636421.ultramarine.3980114.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20f4e748ecf2ac6ed63341ebe55229c9ce6fa0507be5b51386f1b8125e9d966b
3
- size 16305
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f99b2200119d579778cd9b124d300698feef1c95674f293ecb7f1a3bc1030eb6
3
+ size 17239