Hugging Face's logo

Nared45
/
roberta-base_correlation

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Model card Files Metrics Community
Nared45 commited on
Commit
a3c09ea
·
verified ·
1 Parent(s): 646909a

End of training

Browse files
Files changed (4) hide show
  1. README.md +22 -42
  2. logs/events.out.tfevents.1712020858.74d3767e60ee.250.0 +2 -2
  3. logs/events.out.tfevents.1712032509.74d3767e60ee.250.1 +3 -0
  4. model.safetensors +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.3402
19
 
20
  ## Model description
21
 
@@ -41,52 +41,32 @@ The following hyperparameters were used during training:
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - lr_scheduler_warmup_steps: 5000
44
- - num_epochs: 40
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | 0.6392 | 1.0 | 50 | 0.6533 |
51
- | 0.6406 | 2.0 | 100 | 0.6532 |
52
- | 0.6477 | 3.0 | 150 | 0.6530 |
53
- | 0.6369 | 4.0 | 200 | 0.6528 |
54
- | 0.6443 | 5.0 | 250 | 0.6526 |
55
- | 0.6245 | 6.0 | 300 | 0.6525 |
56
- | 0.6341 | 7.0 | 350 | 0.6527 |
57
- | 0.6227 | 8.0 | 400 | 0.6525 |
58
- | 0.6451 | 9.0 | 450 | 0.6521 |
59
- | 0.6278 | 10.0 | 500 | 0.6521 |
60
- | 0.6398 | 11.0 | 550 | 0.6521 |
61
- | 0.6093 | 12.0 | 600 | 0.6506 |
62
- | 0.6149 | 13.0 | 650 | 0.6433 |
63
- | 0.6138 | 14.0 | 700 | 0.6212 |
64
- | 0.5761 | 15.0 | 750 | 0.5761 |
65
- | 0.509 | 16.0 | 800 | 0.5226 |
66
- | 0.4569 | 17.0 | 850 | 0.4574 |
67
- | 0.3864 | 18.0 | 900 | 0.4023 |
68
- | 0.3424 | 19.0 | 950 | 0.3947 |
69
- | 0.2923 | 20.0 | 1000 | 0.3781 |
70
- | 0.2587 | 21.0 | 1050 | 0.3650 |
71
- | 0.2345 | 22.0 | 1100 | 0.3402 |
72
- | 0.1768 | 23.0 | 1150 | 0.3408 |
73
- | 0.1674 | 24.0 | 1200 | 0.3497 |
74
- | 0.1604 | 25.0 | 1250 | 0.3737 |
75
- | 0.122 | 26.0 | 1300 | 0.5728 |
76
- | 0.1151 | 27.0 | 1350 | 0.4340 |
77
- | 0.1151 | 28.0 | 1400 | 0.4297 |
78
- | 0.116 | 29.0 | 1450 | 0.4773 |
79
- | 0.0843 | 30.0 | 1500 | 0.3909 |
80
- | 0.0618 | 31.0 | 1550 | 0.4650 |
81
- | 0.0778 | 32.0 | 1600 | 0.5090 |
82
- | 0.0642 | 33.0 | 1650 | 0.5138 |
83
- | 0.0468 | 34.0 | 1700 | 0.5197 |
84
- | 0.0514 | 35.0 | 1750 | 0.5815 |
85
- | 0.05 | 36.0 | 1800 | 0.6056 |
86
- | 0.0353 | 37.0 | 1850 | 0.6561 |
87
- | 0.0644 | 38.0 | 1900 | 0.7023 |
88
- | 0.0234 | 39.0 | 1950 | 0.6113 |
89
- | 0.0165 | 40.0 | 2000 | 0.7020 |
90
 
91
 
92
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.4129
19
 
20
  ## Model description
21
 
 
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - lr_scheduler_warmup_steps: 5000
44
+ - num_epochs: 20
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | 0.6673 | 1.0 | 50 | 0.6690 |
51
+ | 0.6707 | 2.0 | 100 | 0.6668 |
52
+ | 0.6593 | 3.0 | 150 | 0.6631 |
53
+ | 0.6597 | 4.0 | 200 | 0.6583 |
54
+ | 0.6476 | 5.0 | 250 | 0.6536 |
55
+ | 0.6511 | 6.0 | 300 | 0.6487 |
56
+ | 0.6342 | 7.0 | 350 | 0.6459 |
57
+ | 0.6408 | 8.0 | 400 | 0.6427 |
58
+ | 0.6318 | 9.0 | 450 | 0.6405 |
59
+ | 0.6556 | 10.0 | 500 | 0.6372 |
60
+ | 0.6141 | 11.0 | 550 | 0.6289 |
61
+ | 0.59 | 12.0 | 600 | 0.6089 |
62
+ | 0.5781 | 13.0 | 650 | 0.5815 |
63
+ | 0.5529 | 14.0 | 700 | 0.5550 |
64
+ | 0.5367 | 15.0 | 750 | 0.5355 |
65
+ | 0.5107 | 16.0 | 800 | 0.5014 |
66
+ | 0.4441 | 17.0 | 850 | 0.4775 |
67
+ | 0.4206 | 18.0 | 900 | 0.4477 |
68
+ | 0.3608 | 19.0 | 950 | 0.4302 |
69
+ | 0.3241 | 20.0 | 1000 | 0.4129 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
 
71
 
72
  ### Framework versions
logs/events.out.tfevents.1712020858.74d3767e60ee.250.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e01bf8a0058b000ebbee29505f8811222e42894188e5d5aecb4c1b49474f5a7b
3
- size 17748
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7310cca03ba25ec14f8aafe424d5290095c13fc4a1de7ff85e5986f0af99ef34
3
+ size 18795
logs/events.out.tfevents.1712032509.74d3767e60ee.250.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:736838fddaffe8fe8799a3663f1876ea8575aaed748c718e37a935fccd320b5c
3
+ size 311
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6e2bd7be7da75d5737099aec77e860013e69b4f9573e8b3540c065b18575bfe
3
  size 498612824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07852c79ebccc035ecc219550e7a72bdb3e9e0d5d12bc6dd79a7ad5e57e3240a
3
  size 498612824