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
71a8be9
·
verified ·
1 Parent(s): 003d6c2

End of training

Browse files
Files changed (4) hide show
  1. README.md +42 -22
  2. logs/events.out.tfevents.1712003589.ea1121bc863c.333.2 +2 -2
  3. logs/events.out.tfevents.1712004524.ea1121bc863c.333.3 +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: 0.3771
19
 
20
  ## Model description
21
 
@@ -41,32 +41,52 @@ 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: 20
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | 0.6872 | 1.0 | 50 | 0.6900 |
51
- | 0.6855 | 2.0 | 100 | 0.6860 |
52
- | 0.6796 | 3.0 | 150 | 0.6798 |
53
- | 0.6749 | 4.0 | 200 | 0.6724 |
54
- | 0.6663 | 5.0 | 250 | 0.6638 |
55
- | 0.6589 | 6.0 | 300 | 0.6536 |
56
- | 0.6578 | 7.0 | 350 | 0.6435 |
57
- | 0.6511 | 8.0 | 400 | 0.6326 |
58
- | 0.6414 | 9.0 | 450 | 0.6269 |
59
- | 0.6357 | 10.0 | 500 | 0.6199 |
60
- | 0.6512 | 11.0 | 550 | 0.6125 |
61
- | 0.6468 | 12.0 | 600 | 0.6035 |
62
- | 0.6238 | 13.0 | 650 | 0.5905 |
63
- | 0.6032 | 14.0 | 700 | 0.5627 |
64
- | 0.5662 | 15.0 | 750 | 0.5342 |
65
- | 0.5177 | 16.0 | 800 | 0.4790 |
66
- | 0.4832 | 17.0 | 850 | 0.4662 |
67
- | 0.4338 | 18.0 | 900 | 0.4259 |
68
- | 0.3974 | 19.0 | 950 | 0.3981 |
69
- | 0.3195 | 20.0 | 1000 | 0.3771 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
 
71
 
72
  ### 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: 0.3402
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: 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
logs/events.out.tfevents.1712003589.ea1121bc863c.333.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae17d89a02cd142b4d58698f4288fafde3891455aabea6c750963c3e8f45433b
3
- size 31608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b1fa62ea9ed12fe032dc0eeaae2efc0428511bad56f00b6fc7be2ffa2aba94
3
+ size 32655
logs/events.out.tfevents.1712004524.ea1121bc863c.333.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c18605450ec8d4bf7b9f03fb783d538e1ba318bd1c33cab673cbf71b31340406
3
+ size 311
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e6161e08756ffc99147e5778f9b8538ede64972fbdf10c444310d989410c2c5
3
  size 498612824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16fc0777d7a6b8a246baf15c29484929863e6313b221a4a67601c0bc189aa38b
3
  size 498612824