Hugging Face's logo

haryoaw
/
scenario-KD-SCR-DIV2-data-glue-qnli-model-bert-base-uncased-run-1

Transformers
PyTorch
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
haryoaw commited on
Commit
d1b6e45
•
1 Parent(s): 7e4a3e8

Initial Commit

Browse files
Files changed (4) hide show
  1. README.md +25 -22
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. training_args.bin +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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.9762
21
- - Accuracy: 0.8739
22
 
23
  ## Model description
24
 
@@ -51,27 +51,30 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
54
- | 1.5564 | 1.0 | 3273 | 1.2134 | 0.8580 |
55
- | 1.0321 | 2.0 | 6547 | 1.2086 | 0.8484 |
56
- | 0.7719 | 3.0 | 9820 | 1.0734 | 0.8658 |
57
- | 0.6442 | 4.0 | 13094 | 1.0303 | 0.8708 |
58
- | 0.5748 | 5.0 | 16367 | 1.0708 | 0.8697 |
59
- | 0.5294 | 6.0 | 19641 | 1.0210 | 0.8699 |
60
- | 0.4891 | 7.0 | 22914 | 0.9795 | 0.8763 |
61
- | 0.4704 | 8.0 | 26188 | 0.9826 | 0.8750 |
62
- | 0.4382 | 9.0 | 29461 | 0.9420 | 0.8726 |
63
- | 0.4238 | 10.0 | 32735 | 1.0060 | 0.8724 |
64
- | 0.4066 | 11.0 | 36008 | 0.9511 | 0.8788 |
65
- | 0.3885 | 12.0 | 39282 | 0.9843 | 0.8741 |
66
- | 0.3793 | 13.0 | 42555 | 0.9625 | 0.8763 |
67
- | 0.3663 | 14.0 | 45829 | 0.9639 | 0.8768 |
68
- | 0.3575 | 15.0 | 49102 | 0.9728 | 0.8761 |
69
- | 0.3498 | 16.0 | 52376 | 0.9762 | 0.8739 |
 
 
 
70
 
71
 
72
  ### Framework versions
73
 
74
- - Transformers 4.33.3
75
- - Pytorch 2.1.1
76
- - Datasets 2.14.5
77
- - Tokenizers 0.13.3
 
17
 
18
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.7514
21
+ - Accuracy: 0.8627
22
 
23
  ## Model description
24
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
54
+ | 2.4263 | 1.0 | 3273 | 1.6907 | 0.8545 |
55
+ | 1.7748 | 2.0 | 6547 | 1.8491 | 0.8499 |
56
+ | 1.1414 | 3.0 | 9820 | 1.9422 | 0.8545 |
57
+ | 0.8965 | 4.0 | 13094 | 1.7533 | 0.8552 |
58
+ | 0.7756 | 5.0 | 16367 | 1.7103 | 0.8570 |
59
+ | 0.6527 | 6.0 | 19641 | 1.6665 | 0.8569 |
60
+ | 0.6056 | 7.0 | 22914 | 1.5879 | 0.8620 |
61
+ | 0.5559 | 8.0 | 26188 | 1.6570 | 0.8618 |
62
+ | 0.5154 | 9.0 | 29461 | 1.5519 | 0.8658 |
63
+ | 0.4752 | 10.0 | 32735 | 1.6905 | 0.8612 |
64
+ | 0.4581 | 11.0 | 36008 | 1.6075 | 0.8644 |
65
+ | 0.4322 | 12.0 | 39282 | 1.6963 | 0.8614 |
66
+ | 0.3969 | 13.0 | 42555 | 1.6467 | 0.8660 |
67
+ | 0.393 | 14.0 | 45829 | 1.6735 | 0.8680 |
68
+ | 0.3651 | 15.0 | 49102 | 1.7631 | 0.8614 |
69
+ | 0.3464 | 16.0 | 52376 | 1.7957 | 0.8645 |
70
+ | 0.3455 | 17.0 | 55649 | 1.7008 | 0.8680 |
71
+ | 0.3276 | 18.0 | 58923 | 1.7183 | 0.8669 |
72
+ | 0.3239 | 19.0 | 62196 | 1.7514 | 0.8627 |
73
 
74
 
75
  ### Framework versions
76
 
77
+ - Transformers 4.36.2
78
+ - Pytorch 2.1.2
79
+ - Datasets 2.16.0
80
+ - Tokenizers 0.15.0
config.json CHANGED
@@ -20,7 +20,7 @@
20
  "position_embedding_type": "absolute",
21
  "problem_type": "single_label_classification",
22
  "torch_dtype": "float32",
23
- "transformers_version": "4.33.3",
24
  "type_vocab_size": 2,
25
  "use_cache": true,
26
  "vocab_size": 30522
 
20
  "position_embedding_type": "absolute",
21
  "problem_type": "single_label_classification",
22
  "torch_dtype": "float32",
23
+ "transformers_version": "4.36.2",
24
  "type_vocab_size": 2,
25
  "use_cache": true,
26
  "vocab_size": 30522
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bc14f7184d8ed4a8516ce671e6e888c732a7b6d4cc4f203df2bd32c0ce61f9e
3
  size 267838384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3abd9a6b54b10b91f2373c441d4ed4f2051c6c5bc043165d20ebc968813e399c
3
  size 267838384
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a082dca989a4ab896f2138189f46df935142e30050c745f80244e7c30301de9
3
- size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0d095acf7ef98422db3a62f55fdaecb8ac3047d0cf5f7d6e3091ebd54f3bac3
3
+ size 4920