Hugging Face's logo

kekunh
/
financial-twhin-bert-large-3labels

Text Classification
Transformers
TensorBoard
Safetensors
English
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
kekunh commited on
Commit
ea53238
•
1 Parent(s): 8ba19db

End of training

Browse files
Files changed (4) hide show
  1. README.md +19 -32
  2. model.safetensors +1 -1
  3. runs/Feb22_22-04-28_c9c4e1100ec2/events.out.tfevents.1708639471.c9c4e1100ec2.1595.6 +2 -2
  4. runs/Feb22_22-04-28_c9c4e1100ec2/events.out.tfevents.1708640098.c9c4e1100ec2.1595.7 +3 -0
README.md CHANGED
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [Twitter/twhin-bert-large](https://huggingface.co/Twitter/twhin-bert-large) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.4655
22
- - Accuracy: 0.8033
23
- - F1: 0.7707
24
 
25
  ## Model description
26
 
@@ -39,12 +39,12 @@ More information needed
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
- - learning_rate: 1.6446264239848265e-05
43
- - train_batch_size: 8
44
  - eval_batch_size: 8
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
- - lr_scheduler_type: cosine
48
  - lr_scheduler_warmup_ratio: 0.1
49
  - num_epochs: 2
50
 
@@ -52,32 +52,19 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
55
- | 0.9671 | 0.08 | 100 | 0.9526 | 0.6772 | 0.5469 |
56
- | 0.8284 | 0.15 | 200 | 0.6263 | 0.7190 | 0.6712 |
57
- | 0.69 | 0.23 | 300 | 0.6105 | 0.7003 | 0.6022 |
58
- | 0.7725 | 0.3 | 400 | 0.5843 | 0.7774 | 0.7304 |
59
- | 0.7058 | 0.38 | 500 | 0.5746 | 0.7774 | 0.7422 |
60
- | 0.7028 | 0.46 | 600 | 0.6724 | 0.7435 | 0.7204 |
61
- | 0.7257 | 0.53 | 700 | 0.6853 | 0.6542 | 0.6738 |
62
- | 0.6422 | 0.61 | 800 | 0.5631 | 0.7702 | 0.7575 |
63
- | 0.5796 | 0.68 | 900 | 0.6995 | 0.6376 | 0.6359 |
64
- | 0.6303 | 0.76 | 1000 | 0.7513 | 0.6376 | 0.6475 |
65
- | 0.5102 | 0.83 | 1100 | 0.6074 | 0.7269 | 0.7073 |
66
- | 0.589 | 0.91 | 1200 | 0.5675 | 0.7752 | 0.7327 |
67
- | 0.5131 | 0.99 | 1300 | 0.6960 | 0.5901 | 0.5939 |
68
- | 0.4298 | 1.06 | 1400 | 0.5223 | 0.7767 | 0.7384 |
69
- | 0.4798 | 1.14 | 1500 | 0.4950 | 0.7968 | 0.7596 |
70
- | 0.4033 | 1.21 | 1600 | 0.5231 | 0.7277 | 0.7069 |
71
- | 0.3675 | 1.29 | 1700 | 0.4929 | 0.7702 | 0.7598 |
72
- | 0.3561 | 1.37 | 1800 | 0.4951 | 0.7788 | 0.7509 |
73
- | 0.3933 | 1.44 | 1900 | 0.4655 | 0.8033 | 0.7707 |
74
- | 0.3836 | 1.52 | 2000 | 0.4898 | 0.7875 | 0.7594 |
75
- | 0.3925 | 1.59 | 2100 | 0.5211 | 0.7687 | 0.7488 |
76
- | 0.3484 | 1.67 | 2200 | 0.4916 | 0.7860 | 0.7588 |
77
- | 0.4128 | 1.75 | 2300 | 0.4786 | 0.7968 | 0.7708 |
78
- | 0.3847 | 1.82 | 2400 | 0.4803 | 0.7932 | 0.7651 |
79
- | 0.3146 | 1.9 | 2500 | 0.4805 | 0.7932 | 0.7651 |
80
- | 0.4201 | 1.97 | 2600 | 0.4799 | 0.7932 | 0.7651 |
81
 
82
 
83
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [Twitter/twhin-bert-large](https://huggingface.co/Twitter/twhin-bert-large) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.2959
22
+ - Accuracy: 0.8934
23
+ - F1: 0.8943
24
 
25
  ## Model description
26
 
 
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
+ - learning_rate: 2.0998212817984933e-05
43
+ - train_batch_size: 16
44
  - eval_batch_size: 8
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
49
  - num_epochs: 2
50
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
55
+ | 0.8622 | 0.15 | 100 | 0.6806 | 0.7442 | 0.6936 |
56
+ | 0.7005 | 0.3 | 200 | 0.5887 | 0.7731 | 0.7317 |
57
+ | 0.5556 | 0.46 | 300 | 0.4472 | 0.8242 | 0.8328 |
58
+ | 0.462 | 0.61 | 400 | 0.4188 | 0.8509 | 0.8546 |
59
+ | 0.4282 | 0.76 | 500 | 0.3870 | 0.8444 | 0.8498 |
60
+ | 0.4109 | 0.91 | 600 | 0.3031 | 0.8818 | 0.8813 |
61
+ | 0.3524 | 1.06 | 700 | 0.3483 | 0.8876 | 0.8859 |
62
+ | 0.2896 | 1.21 | 800 | 0.3430 | 0.8725 | 0.8757 |
63
+ | 0.2731 | 1.37 | 900 | 0.3743 | 0.8602 | 0.8659 |
64
+ | 0.2598 | 1.52 | 1000 | 0.3246 | 0.8905 | 0.8917 |
65
+ | 0.2954 | 1.67 | 1100 | 0.2988 | 0.8927 | 0.8942 |
66
+ | 0.2456 | 1.82 | 1200 | 0.2981 | 0.8912 | 0.8930 |
67
+ | 0.2428 | 1.97 | 1300 | 0.2959 | 0.8934 | 0.8943 |
 
 
 
 
 
 
 
 
 
 
 
 
 
68
 
69
 
70
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6801af0c8d61a960d04cc9b0d327759aecf17fa14aa2fbe7ba599948164de8d6
3
  size 2245906124
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da6e3f0a967931c91497c6b8501af11999d3ab38703ac1e70f6fb6388187dc37
3
  size 2245906124
runs/Feb22_22-04-28_c9c4e1100ec2/events.out.tfevents.1708639471.c9c4e1100ec2.1595.6 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce32a1926ea43038b349b3bffd41bb0035e36689809feb6b1aacef4425de36b0
3
- size 9852
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65d221ed6f741f4488bca22d65c82d31e48f24d13b95cfa26fa2bf8199368212
3
+ size 11784
runs/Feb22_22-04-28_c9c4e1100ec2/events.out.tfevents.1708640098.c9c4e1100ec2.1595.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cbc72539b861624a1089ded39c763ea3425991df8c36072162e240bf336910e
3
+ size 457