vd-77 commited on
Commit
9c05b92
·
verified ·
1 Parent(s): f509e56

Training complete

Browse files
Files changed (1) hide show
  1. README.md +21 -9
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [distilbert/distilbert-base-cased](https://huggingface.co/distilbert/distilbert-base-cased) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.2964
25
- - Precision: 0.4528
26
- - Recall: 0.4443
27
- - F1: 0.4485
28
- - Accuracy: 0.9120
29
 
30
  ## Model description
31
 
@@ -50,15 +50,27 @@ The following hyperparameters were used during training:
50
  - seed: 42
51
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: linear
53
- - num_epochs: 3
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
- | No log | 1.0 | 56 | 0.3496 | 0.5 | 0.1149 | 0.1869 | 0.8840 |
60
- | No log | 2.0 | 112 | 0.3027 | 0.4729 | 0.4048 | 0.4362 | 0.9096 |
61
- | No log | 3.0 | 168 | 0.2964 | 0.4528 | 0.4443 | 0.4485 | 0.9120 |
 
 
 
 
 
 
 
 
 
 
 
 
62
 
63
 
64
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [distilbert/distilbert-base-cased](https://huggingface.co/distilbert/distilbert-base-cased) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.4142
25
+ - Precision: 0.5949
26
+ - Recall: 0.6021
27
+ - F1: 0.5985
28
+ - Accuracy: 0.9297
29
 
30
  ## Model description
31
 
 
50
  - seed: 42
51
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: linear
53
+ - num_epochs: 15
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
+ | No log | 1.0 | 56 | 0.2800 | 0.4550 | 0.4854 | 0.4697 | 0.9137 |
60
+ | No log | 2.0 | 112 | 0.2701 | 0.5275 | 0.5918 | 0.5578 | 0.9250 |
61
+ | No log | 3.0 | 168 | 0.2836 | 0.5364 | 0.6072 | 0.5696 | 0.9248 |
62
+ | No log | 4.0 | 224 | 0.3103 | 0.5953 | 0.5626 | 0.5785 | 0.9287 |
63
+ | No log | 5.0 | 280 | 0.3210 | 0.5794 | 0.5883 | 0.5838 | 0.9284 |
64
+ | No log | 6.0 | 336 | 0.3376 | 0.5574 | 0.5832 | 0.5700 | 0.9254 |
65
+ | No log | 7.0 | 392 | 0.3717 | 0.6014 | 0.5849 | 0.5930 | 0.9304 |
66
+ | No log | 8.0 | 448 | 0.3788 | 0.6017 | 0.6038 | 0.6027 | 0.9297 |
67
+ | 0.0751 | 9.0 | 504 | 0.3832 | 0.5972 | 0.5901 | 0.5936 | 0.9296 |
68
+ | 0.0751 | 10.0 | 560 | 0.3943 | 0.5686 | 0.5969 | 0.5824 | 0.9265 |
69
+ | 0.0751 | 11.0 | 616 | 0.3914 | 0.6042 | 0.5969 | 0.6005 | 0.9306 |
70
+ | 0.0751 | 12.0 | 672 | 0.4034 | 0.5892 | 0.6003 | 0.5947 | 0.9286 |
71
+ | 0.0751 | 13.0 | 728 | 0.4093 | 0.5963 | 0.6003 | 0.5983 | 0.9297 |
72
+ | 0.0751 | 14.0 | 784 | 0.4122 | 0.5973 | 0.6003 | 0.5988 | 0.9294 |
73
+ | 0.0751 | 15.0 | 840 | 0.4142 | 0.5949 | 0.6021 | 0.5985 | 0.9297 |
74
 
75
 
76
  ### Framework versions