Hugging Face's logo

ghostdivisio
/
bert-tiny-finetuned-squad

Question Answering
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ghostdivisio commited on
Commit
4e88166
•
1 Parent(s): 2802947

End of training

Browse files
Files changed (11) hide show
  1. README.md +146 -0
  2. config.json +25 -0
  3. model.safetensors +3 -0
  4. runs/May29_10-14-55_4497ee5e0d2f/events.out.tfevents.1716978062.4497ee5e0d2f.402.0 +3 -0
  5. runs/May29_10-22-22_4497ee5e0d2f/events.out.tfevents.1716978149.4497ee5e0d2f.402.1 +3 -0
  6. runs/May29_10-23-19_4497ee5e0d2f/events.out.tfevents.1716978204.4497ee5e0d2f.402.2 +3 -0
  7. special_tokens_map.json +7 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +57 -0
  10. training_args.bin +3 -0
  11. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: prajjwal1/bert-tiny
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: bert-tiny-finetuned-squad
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # bert-tiny-finetuned-squad
15
+
16
+ This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.1478
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 2e-05
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 16
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 90
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 29 | 0.8724 |
50
+ | No log | 2.0 | 58 | 0.7989 |
51
+ | No log | 3.0 | 87 | 0.7316 |
52
+ | No log | 4.0 | 116 | 0.6691 |
53
+ | No log | 5.0 | 145 | 0.6121 |
54
+ | No log | 6.0 | 174 | 0.5597 |
55
+ | No log | 7.0 | 203 | 0.5121 |
56
+ | No log | 8.0 | 232 | 0.4690 |
57
+ | No log | 9.0 | 261 | 0.4300 |
58
+ | No log | 10.0 | 290 | 0.3950 |
59
+ | No log | 11.0 | 319 | 0.3637 |
60
+ | No log | 12.0 | 348 | 0.3358 |
61
+ | No log | 13.0 | 377 | 0.3110 |
62
+ | No log | 14.0 | 406 | 0.2891 |
63
+ | No log | 15.0 | 435 | 0.2697 |
64
+ | No log | 16.0 | 464 | 0.2527 |
65
+ | No log | 17.0 | 493 | 0.2379 |
66
+ | 0.5621 | 18.0 | 522 | 0.2247 |
67
+ | 0.5621 | 19.0 | 551 | 0.2134 |
68
+ | 0.5621 | 20.0 | 580 | 0.2035 |
69
+ | 0.5621 | 21.0 | 609 | 0.1955 |
70
+ | 0.5621 | 22.0 | 638 | 0.1886 |
71
+ | 0.5621 | 23.0 | 667 | 0.1829 |
72
+ | 0.5621 | 24.0 | 696 | 0.1776 |
73
+ | 0.5621 | 25.0 | 725 | 0.1731 |
74
+ | 0.5621 | 26.0 | 754 | 0.1694 |
75
+ | 0.5621 | 27.0 | 783 | 0.1662 |
76
+ | 0.5621 | 28.0 | 812 | 0.1635 |
77
+ | 0.5621 | 29.0 | 841 | 0.1614 |
78
+ | 0.5621 | 30.0 | 870 | 0.1597 |
79
+ | 0.5621 | 31.0 | 899 | 0.1582 |
80
+ | 0.5621 | 32.0 | 928 | 0.1570 |
81
+ | 0.5621 | 33.0 | 957 | 0.1561 |
82
+ | 0.5621 | 34.0 | 986 | 0.1551 |
83
+ | 0.1726 | 35.0 | 1015 | 0.1545 |
84
+ | 0.1726 | 36.0 | 1044 | 0.1537 |
85
+ | 0.1726 | 37.0 | 1073 | 0.1532 |
86
+ | 0.1726 | 38.0 | 1102 | 0.1528 |
87
+ | 0.1726 | 39.0 | 1131 | 0.1523 |
88
+ | 0.1726 | 40.0 | 1160 | 0.1519 |
89
+ | 0.1726 | 41.0 | 1189 | 0.1516 |
90
+ | 0.1726 | 42.0 | 1218 | 0.1512 |
91
+ | 0.1726 | 43.0 | 1247 | 0.1510 |
92
+ | 0.1726 | 44.0 | 1276 | 0.1507 |
93
+ | 0.1726 | 45.0 | 1305 | 0.1505 |
94
+ | 0.1726 | 46.0 | 1334 | 0.1503 |
95
+ | 0.1726 | 47.0 | 1363 | 0.1502 |
96
+ | 0.1726 | 48.0 | 1392 | 0.1500 |
97
+ | 0.1726 | 49.0 | 1421 | 0.1499 |
98
+ | 0.1726 | 50.0 | 1450 | 0.1497 |
99
+ | 0.1726 | 51.0 | 1479 | 0.1496 |
100
+ | 0.1271 | 52.0 | 1508 | 0.1496 |
101
+ | 0.1271 | 53.0 | 1537 | 0.1494 |
102
+ | 0.1271 | 54.0 | 1566 | 0.1493 |
103
+ | 0.1271 | 55.0 | 1595 | 0.1492 |
104
+ | 0.1271 | 56.0 | 1624 | 0.1491 |
105
+ | 0.1271 | 57.0 | 1653 | 0.1490 |
106
+ | 0.1271 | 58.0 | 1682 | 0.1490 |
107
+ | 0.1271 | 59.0 | 1711 | 0.1489 |
108
+ | 0.1271 | 60.0 | 1740 | 0.1489 |
109
+ | 0.1271 | 61.0 | 1769 | 0.1488 |
110
+ | 0.1271 | 62.0 | 1798 | 0.1487 |
111
+ | 0.1271 | 63.0 | 1827 | 0.1487 |
112
+ | 0.1271 | 64.0 | 1856 | 0.1486 |
113
+ | 0.1271 | 65.0 | 1885 | 0.1486 |
114
+ | 0.1271 | 66.0 | 1914 | 0.1485 |
115
+ | 0.1271 | 67.0 | 1943 | 0.1485 |
116
+ | 0.1271 | 68.0 | 1972 | 0.1484 |
117
+ | 0.1216 | 69.0 | 2001 | 0.1484 |
118
+ | 0.1216 | 70.0 | 2030 | 0.1483 |
119
+ | 0.1216 | 71.0 | 2059 | 0.1483 |
120
+ | 0.1216 | 72.0 | 2088 | 0.1482 |
121
+ | 0.1216 | 73.0 | 2117 | 0.1483 |
122
+ | 0.1216 | 74.0 | 2146 | 0.1482 |
123
+ | 0.1216 | 75.0 | 2175 | 0.1481 |
124
+ | 0.1216 | 76.0 | 2204 | 0.1481 |
125
+ | 0.1216 | 77.0 | 2233 | 0.1481 |
126
+ | 0.1216 | 78.0 | 2262 | 0.1480 |
127
+ | 0.1216 | 79.0 | 2291 | 0.1480 |
128
+ | 0.1216 | 80.0 | 2320 | 0.1479 |
129
+ | 0.1216 | 81.0 | 2349 | 0.1479 |
130
+ | 0.1216 | 82.0 | 2378 | 0.1479 |
131
+ | 0.1216 | 83.0 | 2407 | 0.1479 |
132
+ | 0.1216 | 84.0 | 2436 | 0.1479 |
133
+ | 0.1216 | 85.0 | 2465 | 0.1479 |
134
+ | 0.1216 | 86.0 | 2494 | 0.1478 |
135
+ | 0.1151 | 87.0 | 2523 | 0.1478 |
136
+ | 0.1151 | 88.0 | 2552 | 0.1478 |
137
+ | 0.1151 | 89.0 | 2581 | 0.1478 |
138
+ | 0.1151 | 90.0 | 2610 | 0.1478 |
139
+
140
+
141
+ ### Framework versions
142
+
143
+ - Transformers 4.41.1
144
+ - Pytorch 2.3.0+cu121
145
+ - Datasets 2.19.1
146
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "prajjwal1/bert-tiny",
3
+ "architectures": [
4
+ "BertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 512,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 2,
17
+ "num_hidden_layers": 2,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.41.1",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 30522
25
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30a8cea4983f46782c2e8a87af00752a80e9496de63b39772098cf6a6c7b7cb
3
+ size 17483080
runs/May29_10-14-55_4497ee5e0d2f/events.out.tfevents.1716978062.4497ee5e0d2f.402.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6906672580ebc0cbc7f84b035f721b20c19c68531c614ff533f9c29d9dc46d67
3
+ size 5891
runs/May29_10-22-22_4497ee5e0d2f/events.out.tfevents.1716978149.4497ee5e0d2f.402.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:264535974c68eeb0d41501933de730f9f1e13048d851ee823754614cb57d3f0d
3
+ size 13421
runs/May29_10-23-19_4497ee5e0d2f/events.out.tfevents.1716978204.4497ee5e0d2f.402.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f726198a6f6a18860994d10f877c8ef878c4bfabedb7f309f0412af7fb0bf64
3
+ size 30610
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3035315be1c50daccaa02f6522e884364abca37840b42f873ddf6b7c259cc5e3
3
+ size 5112
vocab.txt ADDED
The diff for this file is too large to render. See raw diff