Hugging Face's logo

anuragrawal
/
distilbert-base-uncased-finetuned

Text Classification
Transformers
PyTorch
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Community
anuragrawal commited on
Commit
af6b16d
•
1 Parent(s): 74810a0

Training in progress, epoch 1

Browse files
Files changed (3) hide show
  1. README.md +18 -8
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
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 the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.7875
21
- - Accuracy: 0.8361
22
 
23
  ## Model description
24
 
@@ -43,17 +43,27 @@ 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: 5
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
52
- | 0.4516 | 1.0 | 3272 | 0.4798 | 0.7979 |
53
- | 0.3258 | 2.0 | 6544 | 0.4744 | 0.8218 |
54
- | 0.217 | 3.0 | 9816 | 0.5014 | 0.8340 |
55
- | 0.1633 | 4.0 | 13088 | 0.6027 | 0.8474 |
56
- | 0.1122 | 5.0 | 16360 | 0.7875 | 0.8361 |
 
 
 
 
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.9967
21
+ - Accuracy: 0.9032
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: 15
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
52
+ | 0.3072 | 1.0 | 5250 | 0.2747 | 0.8940 |
53
+ | 0.2381 | 2.0 | 10500 | 0.2871 | 0.8986 |
54
+ | 0.1858 | 3.0 | 15750 | 0.3444 | 0.8996 |
55
+ | 0.1385 | 4.0 | 21000 | 0.4799 | 0.8937 |
56
+ | 0.1057 | 5.0 | 26250 | 0.5324 | 0.8961 |
57
+ | 0.0779 | 6.0 | 31500 | 0.6222 | 0.8969 |
58
+ | 0.0654 | 7.0 | 36750 | 0.6665 | 0.8968 |
59
+ | 0.046 | 8.0 | 42000 | 0.7111 | 0.8989 |
60
+ | 0.0384 | 9.0 | 47250 | 0.7815 | 0.8987 |
61
+ | 0.0348 | 10.0 | 52500 | 0.8023 | 0.9029 |
62
+ | 0.0224 | 11.0 | 57750 | 0.8676 | 0.9011 |
63
+ | 0.0172 | 12.0 | 63000 | 0.8881 | 0.8999 |
64
+ | 0.0068 | 13.0 | 68250 | 0.9122 | 0.9025 |
65
+ | 0.0032 | 14.0 | 73500 | 0.9938 | 0.9005 |
66
+ | 0.0071 | 15.0 | 78750 | 0.9967 | 0.9032 |
67
 
68
 
69
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e3e542fce6f7096a11244823482c6253dfeec2fca36b39f6dadf94b4c8bc143
3
  size 267858605
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77b4d98e40ef9504866d0e13ff472c26ea734845abd557cc7712998c1e2db373
3
  size 267858605
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0102ae287fb6dface96a1bdd4c296e62c7e2707c1c840546ed8e56b94a747d16
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5e4b1afdef3fa021ffed4cd6ae83b8ed552c11af28d92e6d42cc02460483e65
3
  size 4091