tiennvcs commited on
Commit
cf6ab4e
1 Parent(s): f5ce462

Fine tuning BERT base for InfoVQA

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: bert-base-uncased-finetuned-infovqa
7
+ results:
8
+ - task:
9
+ name: Question Answering
10
+ type: question-answering
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # bert-base-uncased-finetuned-infovqa
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: 2.8276
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 5e-05
40
+ - train_batch_size: 4
41
+ - eval_batch_size: 4
42
+ - seed: 250500
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 2
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | 3.2765 | 0.23 | 1000 | 3.0678 |
52
+ | 2.9987 | 0.46 | 2000 | 2.9525 |
53
+ | 2.826 | 0.69 | 3000 | 2.7870 |
54
+ | 2.7084 | 0.93 | 4000 | 2.7051 |
55
+ | 2.1286 | 1.16 | 5000 | 2.9286 |
56
+ | 2.0009 | 1.39 | 6000 | 3.1037 |
57
+ | 2.0323 | 1.62 | 7000 | 2.8567 |
58
+ | 1.9905 | 1.85 | 8000 | 2.8276 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - Transformers 4.10.0
64
+ - Pytorch 1.8.0+cu101
65
+ - Datasets 1.11.0
66
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.10.0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59e9b8c477b6c6c54ce0f42d58e03077e042520972bbd3e67268796e213245ca
3
+ size 435661303
runs/Oct22_23-42-50_ae94a4e6c92d/1634946184.193386/events.out.tfevents.1634946184.ae94a4e6c92d.783.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:493c4ef17d0b30bc0754dd2daa978b045e7e12e48dfc9a9270c6686d18405635
3
+ size 4280
runs/Oct22_23-42-50_ae94a4e6c92d/events.out.tfevents.1634946184.ae94a4e6c92d.783.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55612a8e0ed4dd64fdd6103f7fac9a086650a88b6d76f4f8e656cc65c685bd91
3
+ size 3626
runs/Oct22_23-49-29_ae94a4e6c92d/1634946581.8153772/events.out.tfevents.1634946581.ae94a4e6c92d.1601.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed925a3989ed491b12434325fe59965d6ca2f9253ddbd51bc43b21d81becf0fe
3
+ size 4280
runs/Oct22_23-49-29_ae94a4e6c92d/events.out.tfevents.1634946581.ae94a4e6c92d.1601.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8ceb5f96ec44426964bd9f5214e8b43f7fc56305487a22423dffce6891be3f8
3
+ size 8232
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
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": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd6145954f8486e30e66f1a425586fddab0550ef58759cf09c6b06b024af0b61
3
+ size 2671
vocab.txt ADDED
The diff for this file is too large to render. See raw diff