Hugging Face's logo

exala-e
/
db_himp_4.2

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
exala-e commited on
Commit
2ad5253
·
verified ·
1 Parent(s): 46c457e

End of training

Browse files
Files changed (3) hide show
  1. README.md +21 -21
  2. runs/Jul10_22-26-45_4bf1c756ff9a/events.out.tfevents.1783722405.4bf1c756ff9a.30887.0 +3 -0
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,14 +18,14 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6417
22
- - Accuracy: 0.9284
23
- - F1 Weighted: 0.9278
24
- - F1 Macro: 0.9312
25
- - Precision Weighted: 0.9282
26
- - Recall Weighted: 0.9284
27
- - Precision Macro: 0.9293
28
- - Recall Macro: 0.9338
29
 
30
  ## Model description
31
 
@@ -45,28 +45,28 @@ More information needed
45
 
46
  The following hyperparameters were used during training:
47
  - learning_rate: 2.5e-05
48
- - train_batch_size: 32
49
  - eval_batch_size: 64
50
  - seed: 42
51
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
- - lr_scheduler_type: linear
53
  - lr_scheduler_warmup_steps: 0.1
54
  - num_epochs: 9
55
  - label_smoothing_factor: 0.05
56
 
57
  ### Training results
58
 
59
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Weighted | F1 Macro | Precision Weighted | Recall Weighted | Precision Macro | Recall Macro |
60
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|:-----------:|:--------:|:------------------:|:---------------:|:---------------:|:------------:|
61
- | 1.0224 | 1.0 | 1544 | 0.9326 | 0.8284 | 0.8256 | 0.8259 | 0.8307 | 0.8284 | 0.8315 | 0.8288 |
62
- | 0.7276 | 2.0 | 3088 | 0.7358 | 0.8947 | 0.8927 | 0.8963 | 0.8950 | 0.8947 | 0.8940 | 0.9019 |
63
- | 0.6030 | 3.0 | 4632 | 0.6847 | 0.9094 | 0.9085 | 0.9115 | 0.9098 | 0.9094 | 0.9102 | 0.9147 |
64
- | 0.5850 | 4.0 | 6176 | 0.6584 | 0.9202 | 0.9199 | 0.9231 | 0.9210 | 0.9202 | 0.9228 | 0.9246 |
65
- | 0.4994 | 5.0 | 7720 | 0.6502 | 0.9231 | 0.9224 | 0.9264 | 0.9234 | 0.9231 | 0.9244 | 0.9297 |
66
- | 0.4802 | 6.0 | 9264 | 0.6446 | 0.9260 | 0.9253 | 0.9287 | 0.9256 | 0.9260 | 0.9270 | 0.9312 |
67
- | 0.4585 | 7.0 | 10808 | 0.6499 | 0.9251 | 0.9244 | 0.9280 | 0.9257 | 0.9251 | 0.9268 | 0.9307 |
68
- | 0.4431 | 8.0 | 12352 | 0.6426 | 0.9273 | 0.9267 | 0.9302 | 0.9273 | 0.9273 | 0.9283 | 0.9330 |
69
- | 0.4204 | 9.0 | 13896 | 0.6417 | 0.9284 | 0.9278 | 0.9312 | 0.9282 | 0.9284 | 0.9293 | 0.9338 |
70
 
71
 
72
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.6350
22
+ - Accuracy: 0.9290
23
+ - F1 Weighted: 0.9284
24
+ - F1 Macro: 0.9315
25
+ - Precision Weighted: 0.9289
26
+ - Recall Weighted: 0.9290
27
+ - Precision Macro: 0.9297
28
+ - Recall Macro: 0.9339
29
 
30
  ## Model description
31
 
 
45
 
46
  The following hyperparameters were used during training:
47
  - learning_rate: 2.5e-05
48
+ - train_batch_size: 64
49
  - eval_batch_size: 64
50
  - seed: 42
51
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: cosine
53
  - lr_scheduler_warmup_steps: 0.1
54
  - num_epochs: 9
55
  - label_smoothing_factor: 0.05
56
 
57
  ### Training results
58
 
59
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Weighted | F1 Macro | Precision Weighted | Recall Weighted | Precision Macro | Recall Macro |
60
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:--------:|:------------------:|:---------------:|:---------------:|:------------:|
61
+ | 1.3724 | 1.0 | 772 | 1.0129 | 0.8106 | 0.8086 | 0.8082 | 0.8128 | 0.8106 | 0.8117 | 0.8114 |
62
+ | 0.8057 | 2.0 | 1544 | 0.7635 | 0.8810 | 0.8796 | 0.8828 | 0.8818 | 0.8810 | 0.8815 | 0.8872 |
63
+ | 0.6641 | 3.0 | 2316 | 0.7049 | 0.9038 | 0.9027 | 0.9052 | 0.9038 | 0.9038 | 0.9043 | 0.9081 |
64
+ | 0.5781 | 4.0 | 3088 | 0.6703 | 0.9156 | 0.9152 | 0.9181 | 0.9163 | 0.9156 | 0.9181 | 0.9195 |
65
+ | 0.5372 | 5.0 | 3860 | 0.6480 | 0.9226 | 0.9219 | 0.9248 | 0.9225 | 0.9226 | 0.9229 | 0.9277 |
66
+ | 0.5081 | 6.0 | 4632 | 0.6425 | 0.9253 | 0.9248 | 0.9275 | 0.9256 | 0.9253 | 0.9259 | 0.9300 |
67
+ | 0.4850 | 7.0 | 5404 | 0.6362 | 0.9280 | 0.9276 | 0.9305 | 0.9282 | 0.9280 | 0.9297 | 0.9320 |
68
+ | 0.4638 | 8.0 | 6176 | 0.6352 | 0.9288 | 0.9283 | 0.9312 | 0.9288 | 0.9288 | 0.9298 | 0.9334 |
69
+ | 0.4603 | 9.0 | 6948 | 0.6350 | 0.9290 | 0.9284 | 0.9315 | 0.9289 | 0.9290 | 0.9297 | 0.9339 |
70
 
71
 
72
  ### Framework versions
runs/Jul10_22-26-45_4bf1c756ff9a/events.out.tfevents.1783722405.4bf1c756ff9a.30887.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a88acae055c3d598197703597db69f96e9d693ac8b66d315550fa1199dd04e4
3
+ size 26609
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4768b43b4d0bf9d26f23146a3ae04944a99bc5703432913df75b68bea5041afb
3
  size 5265
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a04cf66020e10730add713e96ad56f5b08ededcbb1f0d98a14bc6a5d9b630190
3
  size 5265