Hugging Face's logo

ipvikas
/
distilbert-base-uncased-finetuned-imdb

Fill-Mask
Transformers
PyTorch
TensorBoard
distilbert
Generated from Trainer
Model card Files Metrics Community
1
ipvikas commited on
Commit
7b1887d
·
1 Parent(s): 9a30223

End of training

Browse files
Files changed (4) hide show
  1. README.md +9 -9
  2. config.json +1 -1
  3. pytorch_model.bin +1 -1
  4. training_args.bin +2 -2
README.md CHANGED
@@ -1,5 +1,6 @@
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
  datasets:
@@ -16,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 2.4721
20
 
21
  ## Model description
22
 
@@ -42,20 +43,19 @@ The following hyperparameters were used during training:
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - num_epochs: 3.0
45
- - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 2.7086 | 1.0 | 157 | 2.4898 |
52
- | 2.5796 | 2.0 | 314 | 2.4230 |
53
- | 2.5269 | 3.0 | 471 | 2.4354 |
54
 
55
 
56
  ### Framework versions
57
 
58
- - Transformers 4.25.1
59
- - Pytorch 1.13.0+cu116
60
- - Datasets 2.8.0
61
- - Tokenizers 0.13.2
 
1
  ---
2
  license: apache-2.0
3
+ base_model: distilbert-base-uncased
4
  tags:
5
  - generated_from_trainer
6
  datasets:
 
17
 
18
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 2.4119
21
 
22
  ## Model description
23
 
 
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - num_epochs: 3.0
 
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 2.7024 | 1.0 | 157 | 2.4968 |
52
+ | 2.5794 | 2.0 | 314 | 2.4281 |
53
+ | 2.5354 | 3.0 | 471 | 2.4509 |
54
 
55
 
56
  ### Framework versions
57
 
58
+ - Transformers 4.34.0
59
+ - Pytorch 2.0.1+cu118
60
+ - Datasets 2.14.5
61
+ - Tokenizers 0.14.1
config.json CHANGED
@@ -19,6 +19,6 @@
19
  "sinusoidal_pos_embds": false,
20
  "tie_weights_": true,
21
  "torch_dtype": "float32",
22
- "transformers_version": "4.25.1",
23
  "vocab_size": 30522
24
  }
 
19
  "sinusoidal_pos_embds": false,
20
  "tie_weights_": true,
21
  "torch_dtype": "float32",
22
+ "transformers_version": "4.34.0",
23
  "vocab_size": 30522
24
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b8a1a1c9eb47c8628735b087e6ffa74e1814f383370cf137697ae7d5555a89b
3
  size 267978033
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b2a8c89f5dfbf3e0c47955703a9263548a2cf9f02ea9f907b6f1787e0d96534
3
  size 267978033
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:127116d1f1c6569fe5f7f033994104a471b667233b0a4fc55f0d984c0e439edd
3
- size 3451
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a51f6cfc5005db1176cfe6f043a6170ebd1536b70bbbd7d36a52eacdcf4a1ac
3
+ size 4091