antalvdb commited on
Commit
7784305
·
verified ·
1 Parent(s): 2adc494

Training completed!

Browse files
README.md CHANGED
@@ -1,5 +1,7 @@
1
  ---
 
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
  metrics:
@@ -17,9 +19,9 @@ 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: 0.2049
21
- - Accuracy: 0.929
22
- - F1: 0.9292
23
 
24
  ## Model description
25
 
@@ -42,7 +44,7 @@ The following hyperparameters were used during training:
42
  - train_batch_size: 64
43
  - eval_batch_size: 64
44
  - seed: 42
45
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - num_epochs: 2
48
 
@@ -50,13 +52,13 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
53
- | 0.8158 | 1.0 | 250 | 0.2970 | 0.916 | 0.9147 |
54
- | 0.2369 | 2.0 | 500 | 0.2049 | 0.929 | 0.9292 |
55
 
56
 
57
  ### Framework versions
58
 
59
- - Transformers 4.16.2
60
- - Pytorch 2.1.0+cu121
61
- - Datasets 1.16.1
62
- - Tokenizers 0.15.1
 
1
  ---
2
+ library_name: transformers
3
  license: apache-2.0
4
+ base_model: distilbert-base-uncased
5
  tags:
6
  - generated_from_trainer
7
  metrics:
 
19
 
20
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.2113
23
+ - Accuracy: 0.9265
24
+ - F1: 0.9264
25
 
26
  ## Model description
27
 
 
44
  - train_batch_size: 64
45
  - eval_batch_size: 64
46
  - seed: 42
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
  - num_epochs: 2
50
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
55
+ | 0.8253 | 1.0 | 250 | 0.3003 | 0.9145 | 0.9135 |
56
+ | 0.2455 | 2.0 | 500 | 0.2113 | 0.9265 | 0.9264 |
57
 
58
 
59
  ### Framework versions
60
 
61
+ - Transformers 4.47.1
62
+ - Pytorch 2.5.1+cu121
63
+ - Datasets 3.2.0
64
+ - Tokenizers 0.21.0
config.json CHANGED
@@ -36,6 +36,6 @@
36
  "sinusoidal_pos_embds": false,
37
  "tie_weights_": true,
38
  "torch_dtype": "float32",
39
- "transformers_version": "4.16.2",
40
  "vocab_size": 30522
41
  }
 
36
  "sinusoidal_pos_embds": false,
37
  "tie_weights_": true,
38
  "torch_dtype": "float32",
39
+ "transformers_version": "4.47.1",
40
  "vocab_size": 30522
41
  }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fd28027d35108f45ad3ea963b7e7d8157c2158b6cfe7873de366ddfd504a832
3
+ size 267844872
special_tokens_map.json CHANGED
@@ -1 +1,7 @@
1
- {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json CHANGED
@@ -1 +1,56 @@
1
- {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92891e347eda008e6be2c093145c6bf2a6c2c85919d67f9303a6f31c1b359d5d
3
- size 3512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92f330b65bb2f7e429679bec0f139f18ebdcf39ead0eefc62918ac0eba264caa
3
+ size 5368