Hugging Face's logo

credentek
/
TenaliAI-FinTech-v1

Text Classification
Transformers
PyTorch
TensorBoard
Joblib
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
credentek commited on
Commit
6441086
•
1 Parent(s): b1fc962

End of training

Browse files
Files changed (5) hide show
  1. README.md +31 -30
  2. config.json +1 -1
  3. label_encoder.joblib +1 -1
  4. model.safetensors +1 -1
  5. training_args.bin +2 -2
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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.1134
19
 
20
  ## Model description
21
 
@@ -35,8 +35,8 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 2e-05
38
- - train_batch_size: 8
39
- - eval_batch_size: 8
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
@@ -46,35 +46,36 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | No log | 1.0 | 224 | 2.5812 |
50
- | No log | 2.0 | 448 | 1.2454 |
51
- | 2.5217 | 3.0 | 672 | 0.4337 |
52
- | 2.5217 | 4.0 | 896 | 0.1572 |
53
- | 0.4296 | 5.0 | 1120 | 0.1191 |
54
- | 0.4296 | 6.0 | 1344 | 0.1208 |
55
- | 0.0629 | 7.0 | 1568 | 0.1140 |
56
- | 0.0629 | 8.0 | 1792 | 0.1212 |
57
- | 0.0254 | 9.0 | 2016 | 0.1215 |
58
- | 0.0254 | 10.0 | 2240 | 0.1213 |
59
- | 0.0254 | 11.0 | 2464 | 0.1136 |
60
- | 0.0118 | 12.0 | 2688 | 0.1134 |
61
- | 0.0118 | 13.0 | 2912 | 0.1161 |
62
- | 0.0092 | 14.0 | 3136 | 0.1191 |
63
- | 0.0092 | 15.0 | 3360 | 0.1305 |
64
- | 0.0056 | 16.0 | 3584 | 0.1332 |
65
- | 0.0056 | 17.0 | 3808 | 0.1343 |
66
- | 0.0055 | 18.0 | 4032 | 0.1362 |
67
- | 0.0055 | 19.0 | 4256 | 0.1362 |
68
- | 0.0055 | 20.0 | 4480 | 0.1450 |
69
- | 0.0037 | 21.0 | 4704 | 0.1421 |
70
- | 0.0037 | 22.0 | 4928 | 0.1460 |
71
- | 0.003 | 23.0 | 5152 | 0.1472 |
72
- | 0.003 | 24.0 | 5376 | 0.1428 |
73
- | 0.0026 | 25.0 | 5600 | 0.1493 |
74
 
75
 
76
  ### Framework versions
77
 
78
- - Transformers 4.43.4
79
- - Pytorch 2.4.0
 
80
  - Tokenizers 0.19.1
 
15
 
16
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0884
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 2e-05
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 16
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 112 | 2.8140 |
50
+ | No log | 2.0 | 224 | 1.6127 |
51
+ | No log | 3.0 | 336 | 0.8216 |
52
+ | No log | 4.0 | 448 | 0.3850 |
53
+ | 1.7871 | 5.0 | 560 | 0.2000 |
54
+ | 1.7871 | 6.0 | 672 | 0.1192 |
55
+ | 1.7871 | 7.0 | 784 | 0.0953 |
56
+ | 1.7871 | 8.0 | 896 | 0.0994 |
57
+ | 0.1041 | 9.0 | 1008 | 0.0953 |
58
+ | 0.1041 | 10.0 | 1120 | 0.0884 |
59
+ | 0.1041 | 11.0 | 1232 | 0.0910 |
60
+ | 0.1041 | 12.0 | 1344 | 0.0924 |
61
+ | 0.1041 | 13.0 | 1456 | 0.0915 |
62
+ | 0.0226 | 14.0 | 1568 | 0.0933 |
63
+ | 0.0226 | 15.0 | 1680 | 0.0987 |
64
+ | 0.0226 | 16.0 | 1792 | 0.0980 |
65
+ | 0.0226 | 17.0 | 1904 | 0.1006 |
66
+ | 0.0115 | 18.0 | 2016 | 0.1014 |
67
+ | 0.0115 | 19.0 | 2128 | 0.0996 |
68
+ | 0.0115 | 20.0 | 2240 | 0.1034 |
69
+ | 0.0115 | 21.0 | 2352 | 0.0989 |
70
+ | 0.0115 | 22.0 | 2464 | 0.1076 |
71
+ | 0.0089 | 23.0 | 2576 | 0.1051 |
72
+ | 0.0089 | 24.0 | 2688 | 0.1040 |
73
+ | 0.0089 | 25.0 | 2800 | 0.1058 |
74
 
75
 
76
  ### Framework versions
77
 
78
+ - Transformers 4.41.2
79
+ - Pytorch 2.3.1+cu121
80
+ - Datasets 2.21.0
81
  - Tokenizers 0.19.1
config.json CHANGED
@@ -124,7 +124,7 @@
124
  "position_embedding_type": "absolute",
125
  "problem_type": "single_label_classification",
126
  "torch_dtype": "float32",
127
- "transformers_version": "4.43.4",
128
  "type_vocab_size": 2,
129
  "use_cache": true,
130
  "vocab_size": 30522
 
124
  "position_embedding_type": "absolute",
125
  "problem_type": "single_label_classification",
126
  "torch_dtype": "float32",
127
+ "transformers_version": "4.41.2",
128
  "type_vocab_size": 2,
129
  "use_cache": true,
130
  "vocab_size": 30522
label_encoder.joblib CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e68c9713e6240949b42fdcd30258422ebc26e901adf9627f555bcf6d8abf89bf
3
  size 4903
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b37cbcefb4ac0135f1ddb9c7930f7f13142db6c0a2e34e970bc6b794f42073a
3
  size 4903
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18318fd23a1e6b887c0773267dbfa725e6b77e48eacd63a0c20db044995c05f9
3
  size 438106296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ff289470b23919d6f2ceaac69d40f6dab224936c04e88c9532b3b078bf72e4
3
  size 438106296
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfd6695bbc4faa62c6d1ca7f870d0bd80deb4af04a86be34b9e39528340cf99b
3
- size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58f0aba16ec9604168d04a4766bac02ef3e95b043479124161a71273a64d1c19
3
+ size 5176