pyrac commited on
Commit
4719594
·
verified ·
1 Parent(s): a299bc6

End of training

Browse files
Files changed (2) hide show
  1. README.md +75 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: EuroBERT/EuroBERT-210m
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ model-index:
11
+ - name: euro_biodiversity
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # euro_biodiversity
19
+
20
+ This model is a fine-tuned version of [EuroBERT/EuroBERT-210m](https://huggingface.co/EuroBERT/EuroBERT-210m) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.0427
23
+ - Accuracy: 0.9912
24
+ - F1: 0.9912
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 5e-05
44
+ - train_batch_size: 4
45
+ - eval_batch_size: 4
46
+ - seed: 42
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 15
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
55
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
56
+ | 1.8497 | 1.0 | 510 | 1.2038 | 0.5608 | 0.4813 |
57
+ | 1.0041 | 2.0 | 1020 | 0.6259 | 0.7922 | 0.7569 |
58
+ | 0.6072 | 3.0 | 1530 | 0.3784 | 0.8907 | 0.8871 |
59
+ | 0.4545 | 4.0 | 2040 | 0.2004 | 0.9456 | 0.9461 |
60
+ | 0.3165 | 5.0 | 2550 | 0.1290 | 0.9676 | 0.9675 |
61
+ | 0.1852 | 6.0 | 3060 | 0.1372 | 0.9706 | 0.9706 |
62
+ | 0.1357 | 7.0 | 3570 | 0.0722 | 0.9838 | 0.9838 |
63
+ | 0.1025 | 8.0 | 4080 | 0.0734 | 0.9868 | 0.9868 |
64
+ | 0.101 | 9.0 | 4590 | 0.0497 | 0.9902 | 0.9902 |
65
+ | 0.0775 | 10.0 | 5100 | 0.0423 | 0.9887 | 0.9887 |
66
+ | 0.0653 | 11.0 | 5610 | 0.0463 | 0.9907 | 0.9907 |
67
+ | 0.0624 | 12.0 | 6120 | 0.0427 | 0.9912 | 0.9912 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.48.3
73
+ - Pytorch 2.5.1+cu124
74
+ - Datasets 3.3.2
75
+ - Tokenizers 0.21.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe0c42364fc4f6acf3edc4f751e3374f54d1a49ccb77ba75b144b1b6f2ebccae
3
  size 849460516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c283db1ea337c44fc2576b2c5ff89b861a092350655b9a89cf3b205a9927710
3
  size 849460516