sunssssun commited on
Commit
c5cdff1
1 Parent(s): 71b6718

commit from ssssss

Browse files
.DS_Store ADDED
Binary file (6.15 kB). View file
 
README的副本.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - glue
9
+ metrics:
10
+ - accuracy
11
+ - f1
12
+ model-index:
13
+ - name: bert-base-uncased-finetuning
14
+ results:
15
+ - task:
16
+ name: Text Classification
17
+ type: text-classification
18
+ dataset:
19
+ name: GLUE MRPC
20
+ type: glue
21
+ args: mrpc
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.8161764705882353
26
+ - name: F1
27
+ type: f1
28
+ value: 0.8739495798319329
29
+ ---
30
+
31
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
32
+ should probably proofread and complete it, then remove this comment. -->
33
+
34
+ # bert-base-uncased-finetuning
35
+
36
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE MRPC dataset.
37
+ It achieves the following results on the evaluation set:
38
+ - Loss: 0.4063
39
+ - Accuracy: 0.8162
40
+ - F1: 0.8739
41
+ - Combined Score: 0.8451
42
+
43
+ ## Model description
44
+
45
+ More information needed
46
+
47
+ ## Intended uses & limitations
48
+
49
+ More information needed
50
+
51
+ ## Training and evaluation data
52
+
53
+ More information needed
54
+
55
+ ## Training procedure
56
+
57
+ ### Training hyperparameters
58
+
59
+ The following hyperparameters were used during training:
60
+ - learning_rate: 2e-05
61
+ - train_batch_size: 8
62
+ - eval_batch_size: 8
63
+ - seed: 42
64
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
65
+ - lr_scheduler_type: linear
66
+ - num_epochs: 1.0
67
+
68
+ ### Training results
69
+
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.24.0
75
+ - Pytorch 1.13.1
76
+ - Datasets 2.10.1
77
+ - Tokenizers 0.11.0
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_accuracy": 0.8161764705882353,
4
+ "eval_combined_score": 0.8450630252100841,
5
+ "eval_f1": 0.8739495798319329,
6
+ "eval_loss": 0.40634819865226746,
7
+ "eval_runtime": 69.3579,
8
+ "eval_samples": 408,
9
+ "eval_samples_per_second": 5.883,
10
+ "eval_steps_per_second": 0.735,
11
+ "train_loss": 0.532436129833878,
12
+ "train_runtime": 1869.0143,
13
+ "train_samples": 3668,
14
+ "train_samples_per_second": 1.963,
15
+ "train_steps_per_second": 0.246
16
+ }
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "finetuning_task": "mrpc",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "not_equivalent",
15
+ "1": "equivalent"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "equivalent": 1,
21
+ "not_equivalent": 0
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.24.0",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_accuracy": 0.8161764705882353,
4
+ "eval_combined_score": 0.8450630252100841,
5
+ "eval_f1": 0.8739495798319329,
6
+ "eval_loss": 0.40634819865226746,
7
+ "eval_runtime": 69.3579,
8
+ "eval_samples": 408,
9
+ "eval_samples_per_second": 5.883,
10
+ "eval_steps_per_second": 0.735
11
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55d008588d664520a3c3a751ce81ef0e87d35d115b710ddf662d7223812ec5d5
3
+ size 438005109
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 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": true,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 512,
6
+ "name_or_path": "bert-base-uncased",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": null,
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.532436129833878,
4
+ "train_runtime": 1869.0143,
5
+ "train_samples": 3668,
6
+ "train_samples_per_second": 1.963,
7
+ "train_steps_per_second": 0.246
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 459,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "step": 459,
13
+ "total_flos": 241272837765120.0,
14
+ "train_loss": 0.532436129833878,
15
+ "train_runtime": 1869.0143,
16
+ "train_samples_per_second": 1.963,
17
+ "train_steps_per_second": 0.246
18
+ }
19
+ ],
20
+ "max_steps": 459,
21
+ "num_train_epochs": 1,
22
+ "total_flos": 241272837765120.0,
23
+ "trial_name": null,
24
+ "trial_params": null
25
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa521b464ef330094e30202c6398f12e5f78b91aa1946c7750989aec190ff442
3
+ size 3387
vocab.txt ADDED
The diff for this file is too large to render. See raw diff