Hugging Face's logo

stulcrad
/
fine_tuned_XLMROBERTA_cs_wikann

Token Classification
Transformers
TensorBoard
Safetensors
xlm-roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
stulcrad commited on
Commit
be1c029
•
1 Parent(s): cdb11c1

Model save

Browse files
Files changed (3) hide show
  1. README.md +15 -17
  2. model.safetensors +1 -1
  3. runs/Feb05_18-45-49_n28/events.out.tfevents.1707155152.n28.3840034.0 +2 -2
README.md CHANGED
@@ -15,11 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.1855
19
- - Overall Precision: 0.9261
20
- - Overall Recall: 0.9412
21
- - Overall F1: 0.9336
22
- - Overall Accuracy: 0.9748
23
 
24
  ## Model description
25
 
@@ -39,26 +39,24 @@ More information needed
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 2e-05
42
- - train_batch_size: 64
43
- - eval_batch_size: 64
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - num_epochs: 10
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:|
53
- | 0.2249 | 1.07 | 500 | 0.1466 | 0.8452 | 0.8867 | 0.8655 | 0.9603 |
54
- | 0.0822 | 2.13 | 1000 | 0.1265 | 0.8953 | 0.9256 | 0.9102 | 0.9704 |
55
- | 0.049 | 3.2 | 1500 | 0.1349 | 0.9081 | 0.9279 | 0.9179 | 0.9722 |
56
- | 0.0315 | 4.26 | 2000 | 0.1511 | 0.9098 | 0.9295 | 0.9195 | 0.9715 |
57
- | 0.021 | 5.33 | 2500 | 0.1421 | 0.9200 | 0.9394 | 0.9296 | 0.9745 |
58
- | 0.0126 | 6.4 | 3000 | 0.1604 | 0.9239 | 0.9380 | 0.9309 | 0.9751 |
59
- | 0.0092 | 7.46 | 3500 | 0.1727 | 0.9200 | 0.9378 | 0.9288 | 0.9743 |
60
- | 0.0058 | 8.53 | 4000 | 0.1843 | 0.9208 | 0.9384 | 0.9295 | 0.9738 |
61
- | 0.0041 | 9.59 | 4500 | 0.1855 | 0.9261 | 0.9412 | 0.9336 | 0.9748 |
62
 
63
 
64
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.1203
19
+ - Overall Precision: 0.9078
20
+ - Overall Recall: 0.9326
21
+ - Overall F1: 0.9200
22
+ - Overall Accuracy: 0.9712
23
 
24
  ## Model description
25
 
 
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 2e-05
42
+ - train_batch_size: 16
43
+ - eval_batch_size: 16
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 3.0
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:|
53
+ | 0.3409 | 0.4 | 500 | 0.1931 | 0.7764 | 0.8465 | 0.8100 | 0.9495 |
54
+ | 0.1816 | 0.8 | 1000 | 0.1427 | 0.8405 | 0.8793 | 0.8595 | 0.9576 |
55
+ | 0.1401 | 1.2 | 1500 | 0.1273 | 0.8758 | 0.9068 | 0.8910 | 0.9651 |
56
+ | 0.1088 | 1.6 | 2000 | 0.1392 | 0.8868 | 0.9139 | 0.9001 | 0.9662 |
57
+ | 0.1027 | 2.0 | 2500 | 0.1096 | 0.8929 | 0.9233 | 0.9078 | 0.9699 |
58
+ | 0.0667 | 2.4 | 3000 | 0.1267 | 0.9030 | 0.9268 | 0.9148 | 0.9699 |
59
+ | 0.0601 | 2.8 | 3500 | 0.1203 | 0.9078 | 0.9326 | 0.9200 | 0.9712 |
 
 
60
 
61
 
62
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a614875e9993dcde72688e038b9d0df90969abe3a67be6d02d813bbd7be6112
3
  size 2235440556
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed64719257e7e84b14e26c4feaf8a5728cf42b0b65c3d44c860ca8e993d9be4d
3
  size 2235440556
runs/Feb05_18-45-49_n28/events.out.tfevents.1707155152.n28.3840034.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eaa1442ad87b8b15e227b080b111df508b1b93ea3b0c4edcab7ef668f83ddb86
3
- size 9294
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aeebaec8b05d1e8de74dffd7d577b3afacc7040a609f359e5c87a4d2d4850c5
3
+ size 9648