Hugging Face's logo

Sybghat
/
BERT_Base_Uncase_FineTuned

Question Answering
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Model card Files
xet
Metrics Community
Sybghat commited on
Commit
56318b9
路
verified 路
1 Parent(s): cdd8cc9

Model save

Browse files
Files changed (4) hide show
  1. README.md +7 -54
  2. model.safetensors +1 -1
  3. runs/Feb19_10-19-47_99df4c8bd387/events.out.tfevents.1708337987.99df4c8bd387.171.3 +2 -2
  4. runs/Feb19_10-19-47_99df4c8bd387/events.out.tfevents.1708338526.99df4c8bd387.171.4 +3 -0
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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.0001
19
 
20
  ## Model description
21
 
@@ -34,73 +34,26 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - learning_rate: 0.001
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
43
- - num_epochs: 50
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | No log | 1.0 | 1 | 4.8954 |
50
- | No log | 2.0 | 2 | 2.6904 |
51
- | No log | 3.0 | 3 | 2.2356 |
52
- | No log | 4.0 | 4 | 4.8808 |
53
- | No log | 5.0 | 5 | 1.5454 |
54
- | No log | 6.0 | 6 | 3.2389 |
55
- | No log | 7.0 | 7 | 0.6490 |
56
- | No log | 8.0 | 8 | 0.0044 |
57
- | No log | 9.0 | 9 | 0.0014 |
58
- | No log | 10.0 | 10 | 0.0010 |
59
- | No log | 11.0 | 11 | 0.0006 |
60
- | No log | 12.0 | 12 | 0.0004 |
61
- | No log | 13.0 | 13 | 0.0003 |
62
- | No log | 14.0 | 14 | 0.0003 |
63
- | No log | 15.0 | 15 | 0.0002 |
64
- | No log | 16.0 | 16 | 1.1187 |
65
- | No log | 17.0 | 17 | 1.0980 |
66
- | No log | 18.0 | 18 | 1.6005 |
67
- | No log | 19.0 | 19 | 1.3744 |
68
- | No log | 20.0 | 20 | 1.0966 |
69
- | No log | 21.0 | 21 | 1.1044 |
70
- | No log | 22.0 | 22 | 1.2535 |
71
- | No log | 23.0 | 23 | 0.0002 |
72
- | No log | 24.0 | 24 | 0.0002 |
73
- | No log | 25.0 | 25 | 0.0002 |
74
- | No log | 26.0 | 26 | 0.0012 |
75
- | No log | 27.0 | 27 | 0.0009 |
76
- | No log | 28.0 | 28 | 0.0032 |
77
- | No log | 29.0 | 29 | 0.0004 |
78
- | No log | 30.0 | 30 | 0.0002 |
79
- | No log | 31.0 | 31 | 0.0001 |
80
- | No log | 32.0 | 32 | 0.0001 |
81
- | No log | 33.0 | 33 | 0.0001 |
82
- | No log | 34.0 | 34 | 0.0001 |
83
- | No log | 35.0 | 35 | 0.0001 |
84
- | No log | 36.0 | 36 | 0.0001 |
85
- | No log | 37.0 | 37 | 0.0001 |
86
- | No log | 38.0 | 38 | 0.0001 |
87
- | No log | 39.0 | 39 | 0.0001 |
88
- | No log | 40.0 | 40 | 0.0001 |
89
- | No log | 41.0 | 41 | 0.0001 |
90
- | No log | 42.0 | 42 | 0.0001 |
91
- | No log | 43.0 | 43 | 0.0001 |
92
- | No log | 44.0 | 44 | 0.0001 |
93
- | No log | 45.0 | 45 | 0.0001 |
94
- | No log | 46.0 | 46 | 0.0001 |
95
- | No log | 47.0 | 47 | 0.0001 |
96
- | No log | 48.0 | 48 | 0.0001 |
97
- | No log | 49.0 | 49 | 0.0001 |
98
- | No log | 50.0 | 50 | 0.0001 |
99
 
100
 
101
  ### Framework versions
102
 
103
  - Transformers 4.37.2
104
  - Pytorch 2.1.0+cu121
105
- - Datasets 2.17.0
106
  - Tokenizers 0.15.2
 
15
 
16
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.1044
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
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
43
+ - num_epochs: 3
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 0.0075 | 1.0 | 217 | 0.1947 |
50
+ | 0.1745 | 2.0 | 434 | 0.1224 |
51
+ | 0.0023 | 3.0 | 651 | 0.1044 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
 
53
 
54
  ### Framework versions
55
 
56
  - Transformers 4.37.2
57
  - Pytorch 2.1.0+cu121
58
+ - Datasets 2.17.1
59
  - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee3067bec83e324211552f1f36c1aa92ebd0bc63ecabd3551111e90e471c8f9a
3
  size 265470032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b056d7364fdb28edc6c362dff8a84eb34baad7533a892aa67076a122a3365c02
3
  size 265470032
runs/Feb19_10-19-47_99df4c8bd387/events.out.tfevents.1708337987.99df4c8bd387.171.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c5c423d3d7f3d3c3f9a5acff900b23236e49b70f8d4bf17b9d624b7ad8ef991
3
- size 83230
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6d7fd4c39e703fb79bbe6a505a7d5a8fca78c3444e03a15babbaa6def44365c
3
+ size 107248
runs/Feb19_10-19-47_99df4c8bd387/events.out.tfevents.1708338526.99df4c8bd387.171.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f862210b12f77c3d0ca730086f91f17b9cd16fd94a7f2325124294d878d3004a
3
+ size 359