Hartunka commited on
Commit
a6213a6
·
verified ·
1 Parent(s): dec70f0

Model save

Browse files
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: Hartunka/bert_base_rand_5_v2
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: bert_base_rand_5_v2_wnli
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # bert_base_rand_5_v2_wnli
17
+
18
+ This model is a fine-tuned version of [Hartunka/bert_base_rand_5_v2](https://huggingface.co/Hartunka/bert_base_rand_5_v2) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.8631
21
+ - Accuracy: 0.1549
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 256
42
+ - eval_batch_size: 256
43
+ - seed: 10
44
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 50
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 0.7423 | 1.0 | 3 | 0.7134 | 0.5352 |
53
+ | 0.695 | 2.0 | 6 | 0.7621 | 0.4366 |
54
+ | 0.6971 | 3.0 | 9 | 0.7425 | 0.5070 |
55
+ | 0.7029 | 4.0 | 12 | 0.7899 | 0.2394 |
56
+ | 0.6869 | 5.0 | 15 | 0.8494 | 0.1972 |
57
+ | 0.6901 | 6.0 | 18 | 0.8631 | 0.1549 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.50.2
63
+ - Pytorch 2.2.1+cu121
64
+ - Datasets 2.18.0
65
+ - Tokenizers 0.21.1
logs/events.out.tfevents.1745462668.s_005_m.2892304.32 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06152ad7da02cde6638a5054904512a3a88768611f3d800bf0256e5c778c3391
3
- size 5517
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c0bb08209c1c2319dd3bcfa426419d02d80d56a89afa10b0625c79776cb2e15
3
+ size 8485