Hugging Face's logo

yefo-ufpe
/
bert-large-uncased-swag

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
yefo-ufpe commited on
Commit
545869d
·
verified ·
1 Parent(s): b523769

Adapting `google-bert/bert-large-uncased` for `swag`.

Browse files
Files changed (9) hide show
  1. README.md +108 -0
  2. adapter_config.json +29 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Aug25_23-56-59_b007ed356559/events.out.tfevents.1724630220.b007ed356559.2046.0 +3 -0
  5. special_tokens_map.json +7 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +55 -0
  8. training_args.bin +3 -0
  9. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: google-bert/bert-large-uncased
3
+ library_name: peft
4
+ license: apache-2.0
5
+ metrics:
6
+ - accuracy
7
+ tags:
8
+ - trl
9
+ - sft
10
+ - generated_from_trainer
11
+ model-index:
12
+ - name: bert-large-uncased-swag
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # bert-large-uncased-swag
20
+
21
+ This model is a fine-tuned version of [google-bert/bert-large-uncased](https://huggingface.co/google-bert/bert-large-uncased) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.4643
24
+ - Accuracy: 0.8295
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 5e-05
44
+ - train_batch_size: 16
45
+ - eval_batch_size: 16
46
+ - seed: 42
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 5
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
+ |:-------------:|:------:|:-----:|:---------------:|:--------:|
55
+ | 1.2132 | 0.1088 | 500 | 0.8717 | 0.6959 |
56
+ | 0.908 | 0.2175 | 1000 | 0.7149 | 0.7473 |
57
+ | 0.8353 | 0.3263 | 1500 | 0.6474 | 0.7575 |
58
+ | 0.8075 | 0.4351 | 2000 | 0.6142 | 0.7798 |
59
+ | 0.8011 | 0.5438 | 2500 | 0.5785 | 0.7867 |
60
+ | 0.7727 | 0.6526 | 3000 | 0.5643 | 0.7936 |
61
+ | 0.7647 | 0.7614 | 3500 | 0.5698 | 0.7956 |
62
+ | 0.7731 | 0.8701 | 4000 | 0.5453 | 0.8011 |
63
+ | 0.7489 | 0.9789 | 4500 | 0.5336 | 0.8052 |
64
+ | 0.7496 | 1.0877 | 5000 | 0.5431 | 0.8033 |
65
+ | 0.735 | 1.1964 | 5500 | 0.5231 | 0.8083 |
66
+ | 0.7194 | 1.3052 | 6000 | 0.5147 | 0.8096 |
67
+ | 0.7307 | 1.4140 | 6500 | 0.5102 | 0.8112 |
68
+ | 0.7355 | 1.5227 | 7000 | 0.5223 | 0.8133 |
69
+ | 0.7085 | 1.6315 | 7500 | 0.5054 | 0.8142 |
70
+ | 0.7206 | 1.7403 | 8000 | 0.5026 | 0.8157 |
71
+ | 0.7143 | 1.8490 | 8500 | 0.5126 | 0.8144 |
72
+ | 0.7045 | 1.9578 | 9000 | 0.5035 | 0.8162 |
73
+ | 0.6972 | 2.0666 | 9500 | 0.4948 | 0.8178 |
74
+ | 0.6885 | 2.1753 | 10000 | 0.4890 | 0.8202 |
75
+ | 0.7079 | 2.2841 | 10500 | 0.4910 | 0.8193 |
76
+ | 0.6874 | 2.3929 | 11000 | 0.4907 | 0.8222 |
77
+ | 0.6832 | 2.5016 | 11500 | 0.4875 | 0.8217 |
78
+ | 0.6807 | 2.6104 | 12000 | 0.4824 | 0.8224 |
79
+ | 0.6865 | 2.7192 | 12500 | 0.4877 | 0.8227 |
80
+ | 0.6863 | 2.8279 | 13000 | 0.4821 | 0.8232 |
81
+ | 0.6913 | 2.9367 | 13500 | 0.4914 | 0.8229 |
82
+ | 0.6996 | 3.0455 | 14000 | 0.4843 | 0.8241 |
83
+ | 0.687 | 3.1542 | 14500 | 0.4753 | 0.8250 |
84
+ | 0.6896 | 3.2630 | 15000 | 0.4762 | 0.8251 |
85
+ | 0.6745 | 3.3718 | 15500 | 0.4753 | 0.8242 |
86
+ | 0.6735 | 3.4805 | 16000 | 0.4713 | 0.8267 |
87
+ | 0.6764 | 3.5893 | 16500 | 0.4715 | 0.8259 |
88
+ | 0.6521 | 3.6981 | 17000 | 0.4669 | 0.8285 |
89
+ | 0.6686 | 3.8068 | 17500 | 0.4726 | 0.8269 |
90
+ | 0.6721 | 3.9156 | 18000 | 0.4703 | 0.8273 |
91
+ | 0.6682 | 4.0244 | 18500 | 0.4660 | 0.8274 |
92
+ | 0.6533 | 4.1331 | 19000 | 0.4690 | 0.8281 |
93
+ | 0.6547 | 4.2419 | 19500 | 0.4697 | 0.8282 |
94
+ | 0.6589 | 4.3507 | 20000 | 0.4640 | 0.8291 |
95
+ | 0.6518 | 4.4594 | 20500 | 0.4638 | 0.8294 |
96
+ | 0.6739 | 4.5682 | 21000 | 0.4669 | 0.8285 |
97
+ | 0.6763 | 4.6770 | 21500 | 0.4628 | 0.8304 |
98
+ | 0.6503 | 4.7857 | 22000 | 0.4640 | 0.8296 |
99
+ | 0.6659 | 4.8945 | 22500 | 0.4643 | 0.8295 |
100
+
101
+
102
+ ### Framework versions
103
+
104
+ - PEFT 0.12.1.dev0
105
+ - Transformers 4.45.0.dev0
106
+ - Pytorch 2.3.1+cu121
107
+ - Datasets 2.21.0
108
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google-bert/bert-large-uncased",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "query",
24
+ "value"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1faef6ed1fe00917ee1e3fe9383c3306e9b9f90ebc854bb8c2c4230f16103d5a
3
+ size 3159288
runs/Aug25_23-56-59_b007ed356559/events.out.tfevents.1724630220.b007ed356559.2046.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca3d172de0128cd1c4b1a340677089597c35ec4aa29a79197cac7e08d0d2dd43
3
+ size 29770
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4b7e58b17ab5e76d84a661fa5c93ca0a43ac52bdcbce01c5669792108176056
3
+ size 5432
vocab.txt ADDED
The diff for this file is too large to render. See raw diff