ekiprop commited on
Commit
33cbafb
·
verified ·
1 Parent(s): 235ff16

Model save

Browse files
Files changed (2) hide show
  1. README.md +86 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: roberta-base
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - matthews_correlation
9
+ model-index:
10
+ - name: CoLA-FULL_FT-seed52
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # CoLA-FULL_FT-seed52
18
+
19
+ This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.5096
22
+ - Matthews Correlation: 0.6243
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 3e-05
42
+ - train_batch_size: 32
43
+ - eval_batch_size: 32
44
+ - seed: 42
45
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
+ - lr_scheduler_type: linear
47
+ - num_epochs: 5
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
52
+ |:-------------:|:------:|:----:|:---------------:|:--------------------:|
53
+ | 0.601 | 0.1866 | 50 | 0.5357 | 0.3677 |
54
+ | 0.4939 | 0.3731 | 100 | 0.4507 | 0.5107 |
55
+ | 0.4695 | 0.5597 | 150 | 0.5413 | 0.5023 |
56
+ | 0.4575 | 0.7463 | 200 | 0.4571 | 0.4852 |
57
+ | 0.4168 | 0.9328 | 250 | 0.5088 | 0.4793 |
58
+ | 0.3487 | 1.1194 | 300 | 0.5122 | 0.5129 |
59
+ | 0.3246 | 1.3060 | 350 | 0.4747 | 0.5547 |
60
+ | 0.3062 | 1.4925 | 400 | 0.4388 | 0.5679 |
61
+ | 0.329 | 1.6791 | 450 | 0.4701 | 0.5600 |
62
+ | 0.2978 | 1.8657 | 500 | 0.4991 | 0.5206 |
63
+ | 0.2628 | 2.0522 | 550 | 0.6130 | 0.5366 |
64
+ | 0.1783 | 2.2388 | 600 | 0.5369 | 0.5880 |
65
+ | 0.218 | 2.4254 | 650 | 0.5440 | 0.6035 |
66
+ | 0.2125 | 2.6119 | 700 | 0.5582 | 0.5994 |
67
+ | 0.1886 | 2.7985 | 750 | 0.5096 | 0.6243 |
68
+ | 0.1935 | 2.9851 | 800 | 0.5404 | 0.5727 |
69
+ | 0.1393 | 3.1716 | 850 | 0.5751 | 0.6026 |
70
+ | 0.1425 | 3.3582 | 900 | 0.5575 | 0.6046 |
71
+ | 0.1289 | 3.5448 | 950 | 0.8048 | 0.5296 |
72
+ | 0.1262 | 3.7313 | 1000 | 0.6417 | 0.5976 |
73
+ | 0.1313 | 3.9179 | 1050 | 0.5886 | 0.6012 |
74
+ | 0.1145 | 4.1045 | 1100 | 0.7044 | 0.5992 |
75
+ | 0.0759 | 4.2910 | 1150 | 0.7681 | 0.5957 |
76
+ | 0.0932 | 4.4776 | 1200 | 0.7648 | 0.5946 |
77
+ | 0.0686 | 4.6642 | 1250 | 0.7940 | 0.5889 |
78
+ | 0.0758 | 4.8507 | 1300 | 0.8412 | 0.5981 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.54.1
84
+ - Pytorch 2.5.1+cu121
85
+ - Datasets 4.0.0
86
+ - Tokenizers 0.21.4
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed953a3065107b5bef7ee3b4afbbe585d3d79789042bc170f6e15c4a77a00d4e
3
  size 498612824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9d9079cfc698899752d145ab8fe77561f26ff79813c0faa2514caf32d681449
3
  size 498612824