Hugging Face's logo

cezeozue
/
distilbert-base-uncased-finetuned-clinc

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
cezeozue commited on
Commit
58cfa3e
•
1 Parent(s): 2bf0ea8

Training completed!

Browse files
Files changed (3) hide show
  1. README.md +9 -14
  2. model.safetensors +1 -1
  3. runs/Jan25_16-53-31_bf0d58b9da20/events.out.tfevents.1706201616.bf0d58b9da20.4758.0 +2 -2
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.1038
21
- - Accuracy: 0.9423
22
 
23
  ## Model description
24
 
@@ -43,22 +43,17 @@ The following hyperparameters were used during training:
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - num_epochs: 10
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
- | No log | 1.0 | 318 | 0.6213 | 0.7371 |
53
- | 0.8038 | 2.0 | 636 | 0.3111 | 0.8816 |
54
- | 0.8038 | 3.0 | 954 | 0.1936 | 0.9232 |
55
- | 0.3007 | 4.0 | 1272 | 0.1484 | 0.9323 |
56
- | 0.1681 | 5.0 | 1590 | 0.1274 | 0.9365 |
57
- | 0.1681 | 6.0 | 1908 | 0.1168 | 0.9403 |
58
- | 0.1286 | 7.0 | 2226 | 0.1104 | 0.9423 |
59
- | 0.1124 | 8.0 | 2544 | 0.1067 | 0.9410 |
60
- | 0.1124 | 9.0 | 2862 | 0.1046 | 0.9419 |
61
- | 0.1047 | 10.0 | 3180 | 0.1038 | 0.9423 |
62
 
63
 
64
  ### Framework versions
@@ -66,4 +61,4 @@ The following hyperparameters were used during training:
66
  - Transformers 4.35.2
67
  - Pytorch 2.1.0+cu121
68
  - Datasets 2.16.1
69
- - Tokenizers 0.15.0
 
17
 
18
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.7730
21
+ - Accuracy: 0.9161
22
 
23
  ## Model description
24
 
 
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 5
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | No log | 1.0 | 318 | 3.2776 | 0.7287 |
53
+ | 3.7835 | 2.0 | 636 | 1.8647 | 0.8358 |
54
+ | 3.7835 | 3.0 | 954 | 1.1524 | 0.8977 |
55
+ | 1.6878 | 4.0 | 1272 | 0.8547 | 0.9129 |
56
+ | 0.8994 | 5.0 | 1590 | 0.7730 | 0.9161 |
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
 
61
  - Transformers 4.35.2
62
  - Pytorch 2.1.0+cu121
63
  - Datasets 2.16.1
64
+ - Tokenizers 0.15.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5e0d587170ac2323ac1fe2a8458aad15150b357a0528fc30f41915cf6b44227
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9b8b382dead0c9977e1766ac12e7a4a3a070c056810c562a8c5a0cbf4a73781
3
  size 268290900
runs/Jan25_16-53-31_bf0d58b9da20/events.out.tfevents.1706201616.bf0d58b9da20.4758.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b9de398710c9c4110c52326a886f7e409d675181f845684ff60d22c89018822
3
- size 13513
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92980195a1d3314f9c5c5a6953093bb4be2b7ec58ee07c5f91d72afa97f974d4
3
+ size 14190