Hugging Face's logo

gokulsrinivasagan
/
bert_uncased_L-2_H-128_A-2_cola

Text Classification
Transformers
TensorBoard
Safetensors
English
bert
Generated from Trainer
Eval Results
Model card Files Metrics Community
gokulsrinivasagan commited on
Commit
f40e439
·
verified ·
1 Parent(s): 495d2b2

Model save

Browse files
Files changed (3) hide show
  1. README.md +76 -0
  2. logs/events.out.tfevents.1733343189.ki-g0008.1759256.18 +2 -2
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: google/bert_uncased_L-2_H-128_A-2
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - matthews_correlation
9
+ - accuracy
10
+ model-index:
11
+ - name: bert_uncased_L-2_H-128_A-2_cola
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
+ # bert_uncased_L-2_H-128_A-2_cola
19
+
20
+ This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.6423
23
+ - Matthews Correlation: 0.0951
24
+ - Accuracy: 0.6433
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: 256
45
+ - eval_batch_size: 256
46
+ - seed: 10
47
+ - optimizer: Use 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: 50
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation | Accuracy |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------------------:|:--------:|
55
+ | 0.6288 | 1.0 | 34 | 0.6191 | 0.0 | 0.6913 |
56
+ | 0.6087 | 2.0 | 68 | 0.6184 | 0.0 | 0.6913 |
57
+ | 0.6076 | 3.0 | 102 | 0.6176 | 0.0 | 0.6913 |
58
+ | 0.6066 | 4.0 | 136 | 0.6169 | 0.0 | 0.6913 |
59
+ | 0.605 | 5.0 | 170 | 0.6170 | 0.0 | 0.6913 |
60
+ | 0.6018 | 6.0 | 204 | 0.6164 | 0.0 | 0.6913 |
61
+ | 0.5976 | 7.0 | 238 | 0.6163 | 0.0 | 0.6913 |
62
+ | 0.5871 | 8.0 | 272 | 0.6159 | 0.0464 | 0.6922 |
63
+ | 0.5824 | 9.0 | 306 | 0.6155 | 0.0029 | 0.6903 |
64
+ | 0.5711 | 10.0 | 340 | 0.6198 | 0.0198 | 0.6702 |
65
+ | 0.5591 | 11.0 | 374 | 0.6221 | 0.0685 | 0.6721 |
66
+ | 0.5496 | 12.0 | 408 | 0.6284 | 0.1240 | 0.6702 |
67
+ | 0.5397 | 13.0 | 442 | 0.6350 | 0.1096 | 0.6548 |
68
+ | 0.529 | 14.0 | 476 | 0.6423 | 0.0951 | 0.6433 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.46.3
74
+ - Pytorch 2.2.1+cu118
75
+ - Datasets 2.17.0
76
+ - Tokenizers 0.20.3
logs/events.out.tfevents.1733343189.ki-g0008.1759256.18 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69c63cb2cf60eb24f84ed73dc5425cfe1c1c2c48db9b45029638f3e62d45e714
3
- size 12856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:267131a90cecbc402f7adcb48a09b099a478ec93c2b324f40b8b969979c27a25
3
+ size 13808
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73f46e5441e04b02c2dd627173d65a39621a73a3c66d18479e6711d890bb9678
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:379c6234914a016137a0926e95fb58596050445ee0258328b11bb54c1917262c
3
  size 17549312