Hugging Face's logo

davidgaofc
/
training

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Community
davidgaofc commited on
Commit
df33857
·
1 Parent(s): dec25d6

End of training

Browse files
Files changed (3) hide show
  1. README.md +29 -24
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.5309
24
- - Accuracy: 0.8626
25
- - F1: 0.8041
26
- - Precision: 0.7530
27
- - Recall: 0.8626
28
 
29
  ## Model description
30
 
@@ -44,37 +44,42 @@ More information needed
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 2e-05
47
- - train_batch_size: 104
48
- - eval_batch_size: 104
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
- - num_epochs: 15
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
57
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
58
- | No log | 1.0 | 7 | 0.4054 | 0.8681 | 0.8069 | 0.7537 | 0.8681 |
59
- | No log | 2.0 | 14 | 0.4137 | 0.8681 | 0.8069 | 0.7537 | 0.8681 |
60
- | No log | 3.0 | 21 | 0.4167 | 0.8681 | 0.8069 | 0.7537 | 0.8681 |
61
- | No log | 4.0 | 28 | 0.4263 | 0.8681 | 0.8069 | 0.7537 | 0.8681 |
62
- | No log | 5.0 | 35 | 0.4274 | 0.8681 | 0.8069 | 0.7537 | 0.8681 |
63
- | No log | 6.0 | 42 | 0.4414 | 0.8681 | 0.8069 | 0.7537 | 0.8681 |
64
- | No log | 7.0 | 49 | 0.4516 | 0.8681 | 0.8069 | 0.7537 | 0.8681 |
65
- | No log | 8.0 | 56 | 0.4598 | 0.8681 | 0.8069 | 0.7537 | 0.8681 |
66
- | No log | 9.0 | 63 | 0.4786 | 0.8681 | 0.8069 | 0.7537 | 0.8681 |
67
- | No log | 10.0 | 70 | 0.4823 | 0.8626 | 0.8041 | 0.7530 | 0.8626 |
68
- | No log | 11.0 | 77 | 0.4963 | 0.8626 | 0.8041 | 0.7530 | 0.8626 |
69
- | No log | 12.0 | 84 | 0.5107 | 0.8626 | 0.8041 | 0.7530 | 0.8626 |
70
- | No log | 13.0 | 91 | 0.5220 | 0.8626 | 0.8041 | 0.7530 | 0.8626 |
71
- | No log | 14.0 | 98 | 0.5294 | 0.8626 | 0.8041 | 0.7530 | 0.8626 |
72
- | No log | 15.0 | 105 | 0.5309 | 0.8626 | 0.8041 | 0.7530 | 0.8626 |
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
76
 
77
  - Transformers 4.36.2
78
  - Pytorch 2.1.2+cu121
79
- - Datasets 2.15.0
80
  - Tokenizers 0.15.0
 
20
 
21
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 1.7420
24
+ - Accuracy: 0.7607
25
+ - F1: 0.7608
26
+ - Precision: 0.7611
27
+ - Recall: 0.7607
28
 
29
  ## Model description
30
 
 
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 2e-05
47
+ - train_batch_size: 20
48
+ - eval_batch_size: 20
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 20
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
57
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
58
+ | No log | 1.0 | 132 | 0.6953 | 0.4817 | 0.3630 | 0.5023 | 0.4817 |
59
+ | No log | 2.0 | 264 | 0.6493 | 0.6067 | 0.6069 | 0.6072 | 0.6067 |
60
+ | No log | 3.0 | 396 | 0.6383 | 0.6662 | 0.6662 | 0.6685 | 0.6662 |
61
+ | 0.5695 | 4.0 | 528 | 0.6615 | 0.6905 | 0.6907 | 0.6916 | 0.6905 |
62
+ | 0.5695 | 5.0 | 660 | 0.7464 | 0.7317 | 0.7314 | 0.7316 | 0.7317 |
63
+ | 0.5695 | 6.0 | 792 | 0.9271 | 0.7073 | 0.7048 | 0.7100 | 0.7073 |
64
+ | 0.5695 | 7.0 | 924 | 1.1392 | 0.7210 | 0.7204 | 0.7212 | 0.7210 |
65
+ | 0.1578 | 8.0 | 1056 | 1.2788 | 0.7149 | 0.7141 | 0.7226 | 0.7149 |
66
+ | 0.1578 | 9.0 | 1188 | 1.2960 | 0.75 | 0.7501 | 0.7504 | 0.75 |
67
+ | 0.1578 | 10.0 | 1320 | 1.4280 | 0.7287 | 0.7278 | 0.7292 | 0.7287 |
68
+ | 0.1578 | 11.0 | 1452 | 1.4865 | 0.7424 | 0.7424 | 0.7446 | 0.7424 |
69
+ | 0.0414 | 12.0 | 1584 | 1.5945 | 0.7302 | 0.7290 | 0.7312 | 0.7302 |
70
+ | 0.0414 | 13.0 | 1716 | 1.6329 | 0.7363 | 0.7364 | 0.7369 | 0.7363 |
71
+ | 0.0414 | 14.0 | 1848 | 1.6514 | 0.7454 | 0.7455 | 0.7462 | 0.7454 |
72
+ | 0.0414 | 15.0 | 1980 | 1.6811 | 0.7409 | 0.7409 | 0.7411 | 0.7409 |
73
+ | 0.0111 | 16.0 | 2112 | 1.6935 | 0.7470 | 0.7471 | 0.7481 | 0.7470 |
74
+ | 0.0111 | 17.0 | 2244 | 1.7232 | 0.7515 | 0.7515 | 0.7541 | 0.7515 |
75
+ | 0.0111 | 18.0 | 2376 | 1.7319 | 0.7546 | 0.7546 | 0.7546 | 0.7546 |
76
+ | 0.0018 | 19.0 | 2508 | 1.7385 | 0.7530 | 0.7532 | 0.7540 | 0.7530 |
77
+ | 0.0018 | 20.0 | 2640 | 1.7420 | 0.7607 | 0.7608 | 0.7611 | 0.7607 |
78
 
79
 
80
  ### Framework versions
81
 
82
  - Transformers 4.36.2
83
  - Pytorch 2.1.2+cu121
84
+ - Datasets 2.16.0
85
  - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bf4bdf7f45ebdfdd0a2e3b5ca8e8521769d1f21436bb7b32b7e60ea00730909
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:525914ec507f90a21b4c9f56ccb2201aa285ff84cab4ce1b2fdb19f17d69daf0
3
  size 267832560
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfd65a6f7a6651cc79b5b6e2fc1d25668a95c9e222683095fbf6a9c5999d1bd2
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15357dde7dea232315818fd70f8e699efc66104510f7ae9c3678b36c1dda604c
3
  size 4664