Hugging Face's logo

mgh6
/
TCS_Pair

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
esm
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
mgh6 commited on
Commit
ca844a3
·
1 Parent(s): 3c476d9

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +113 -0
README.md ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: TCS_Pair
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # TCS_Pair
13
+
14
+ This model is a fine-tuned version of [mgh6/esm_cluster_35M_linear](https://huggingface.co/mgh6/esm_cluster_35M_linear) on the None dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 0.1395
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 0.001
36
+ - train_batch_size: 80
37
+ - eval_batch_size: 80
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 8
42
+
43
+ ### Training results
44
+
45
+ | Training Loss | Epoch | Step | Validation Loss |
46
+ |:-------------:|:-----:|:----:|:---------------:|
47
+ | 0.1829 | 0.13 | 100 | 0.2207 |
48
+ | 0.1137 | 0.27 | 200 | 0.1531 |
49
+ | 0.0984 | 0.4 | 300 | 0.1516 |
50
+ | 0.0945 | 0.54 | 400 | 0.1510 |
51
+ | 0.0862 | 0.67 | 500 | 0.1676 |
52
+ | 0.0855 | 0.81 | 600 | 0.1601 |
53
+ | 0.0798 | 0.94 | 700 | 0.1429 |
54
+ | 0.0664 | 1.07 | 800 | 0.1770 |
55
+ | 0.0567 | 1.21 | 900 | 0.1344 |
56
+ | 0.0584 | 1.34 | 1000 | 0.1395 |
57
+ | 0.0608 | 1.48 | 1100 | 0.1423 |
58
+ | 0.0577 | 1.61 | 1200 | 0.1389 |
59
+ | 0.0591 | 1.74 | 1300 | 0.1519 |
60
+ | 0.0618 | 1.88 | 1400 | 0.1268 |
61
+ | 0.0505 | 2.01 | 1500 | 0.1313 |
62
+ | 0.035 | 2.15 | 1600 | 0.1426 |
63
+ | 0.0422 | 2.28 | 1700 | 0.1324 |
64
+ | 0.0408 | 2.42 | 1800 | 0.1403 |
65
+ | 0.0415 | 2.55 | 1900 | 0.1328 |
66
+ | 0.0424 | 2.68 | 2000 | 0.1684 |
67
+ | 0.043 | 2.82 | 2100 | 0.1509 |
68
+ | 0.0412 | 2.95 | 2200 | 0.1266 |
69
+ | 0.0301 | 3.09 | 2300 | 0.1552 |
70
+ | 0.0234 | 3.22 | 2400 | 0.1291 |
71
+ | 0.0285 | 3.36 | 2500 | 0.1329 |
72
+ | 0.0299 | 3.49 | 2600 | 0.1441 |
73
+ | 0.0283 | 3.62 | 2700 | 0.1442 |
74
+ | 0.0286 | 3.76 | 2800 | 0.1264 |
75
+ | 0.0293 | 3.89 | 2900 | 0.1486 |
76
+ | 0.0255 | 4.03 | 3000 | 0.1309 |
77
+ | 0.0171 | 4.16 | 3100 | 0.1476 |
78
+ | 0.0175 | 4.3 | 3200 | 0.1469 |
79
+ | 0.015 | 4.43 | 3300 | 0.1454 |
80
+ | 0.0168 | 4.56 | 3400 | 0.1426 |
81
+ | 0.0185 | 4.7 | 3500 | 0.1431 |
82
+ | 0.0202 | 4.83 | 3600 | 0.1313 |
83
+ | 0.0212 | 4.97 | 3700 | 0.1499 |
84
+ | 0.0131 | 5.1 | 3800 | 0.1316 |
85
+ | 0.0112 | 5.23 | 3900 | 0.1548 |
86
+ | 0.0121 | 5.37 | 4000 | 0.1525 |
87
+ | 0.012 | 5.5 | 4100 | 0.1437 |
88
+ | 0.012 | 5.64 | 4200 | 0.1417 |
89
+ | 0.0116 | 5.77 | 4300 | 0.1511 |
90
+ | 0.0115 | 5.91 | 4400 | 0.1335 |
91
+ | 0.0096 | 6.04 | 4500 | 0.1332 |
92
+ | 0.0067 | 6.17 | 4600 | 0.1330 |
93
+ | 0.0063 | 6.31 | 4700 | 0.1348 |
94
+ | 0.0081 | 6.44 | 4800 | 0.1398 |
95
+ | 0.008 | 6.58 | 4900 | 0.1391 |
96
+ | 0.0065 | 6.71 | 5000 | 0.1375 |
97
+ | 0.0078 | 6.85 | 5100 | 0.1513 |
98
+ | 0.0067 | 6.98 | 5200 | 0.1376 |
99
+ | 0.0053 | 7.11 | 5300 | 0.1389 |
100
+ | 0.0039 | 7.25 | 5400 | 0.1435 |
101
+ | 0.0051 | 7.38 | 5500 | 0.1382 |
102
+ | 0.0036 | 7.52 | 5600 | 0.1398 |
103
+ | 0.0046 | 7.65 | 5700 | 0.1367 |
104
+ | 0.0052 | 7.79 | 5800 | 0.1384 |
105
+ | 0.004 | 7.92 | 5900 | 0.1395 |
106
+
107
+
108
+ ### Framework versions
109
+
110
+ - Transformers 4.30.2
111
+ - Pytorch 2.0.1+cu117
112
+ - Datasets 2.13.1
113
+ - Tokenizers 0.13.3