xinhe commited on
Commit
f6b72c0
1 Parent(s): 86e5cd5

upload mrpc fine-tuned model

Browse files
README.md CHANGED
@@ -1,3 +1,77 @@
1
  ---
 
 
2
  license: mit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - en
4
  license: mit
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - glue
9
+ metrics:
10
+ - accuracy
11
+ - f1
12
+ model-index:
13
+ - name: MiniLM-L12-H384-uncased-mrpc
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: 0.875
26
+ - name: F1
27
+ type: f1
28
+ value: 0.9097345132743363
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
+ # MiniLM-L12-H384-uncased-mrpc
35
+
36
+ This model is a fine-tuned version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) on the GLUE MRPC dataset.
37
+ It achieves the following results on the evaluation set:
38
+ - Loss: 0.4319
39
+ - Accuracy: 0.875
40
+ - F1: 0.9097
41
+ - Combined Score: 0.8924
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: 16
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: 5.0
67
+
68
+ ### Training results
69
+
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.18.0
75
+ - Pytorch 1.11.0+cu102
76
+ - Datasets 2.2.2
77
+ - Tokenizers 0.12.1
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.875,
4
+ "eval_combined_score": 0.8923672566371681,
5
+ "eval_f1": 0.9097345132743363,
6
+ "eval_loss": 0.43185245990753174,
7
+ "eval_runtime": 3.0165,
8
+ "eval_samples": 408,
9
+ "eval_samples_per_second": 135.255,
10
+ "eval_steps_per_second": 16.907,
11
+ "train_loss": 0.29514418560525646,
12
+ "train_runtime": 616.8399,
13
+ "train_samples": 3668,
14
+ "train_samples_per_second": 29.732,
15
+ "train_steps_per_second": 1.864
16
+ }
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/MiniLM-L12-H384-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "finetuning_task": "mrpc",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 384,
12
+ "id2label": {
13
+ "0": "not_equivalent",
14
+ "1": "equivalent"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 1536,
18
+ "label2id": {
19
+ "equivalent": 1,
20
+ "not_equivalent": 0
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "bert",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "problem_type": "single_label_classification",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.18.0",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 30522
35
+ }
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.875,
4
+ "eval_combined_score": 0.8923672566371681,
5
+ "eval_f1": 0.9097345132743363,
6
+ "eval_loss": 0.43185245990753174,
7
+ "eval_runtime": 3.0165,
8
+ "eval_samples": 408,
9
+ "eval_samples_per_second": 135.255,
10
+ "eval_steps_per_second": 16.907
11
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00d4a7d6b0409e0587fd4b06a4796cf41ad69438e3a3878b9074b924c0bc2291
3
+ size 133511277
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, "special_tokens_map_file": "/home2/xinhe/.cache/huggingface/transformers/1e5909e4dfaa904617797ed35a6105a23daa56cbefca48fef329f772584699fb.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "microsoft/MiniLM-L12-H384-uncased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.29514418560525646,
4
+ "train_runtime": 616.8399,
5
+ "train_samples": 3668,
6
+ "train_samples_per_second": 29.732,
7
+ "train_steps_per_second": 1.864
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 1150,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.17,
12
+ "learning_rate": 1.1304347826086957e-05,
13
+ "loss": 0.4222,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 4.35,
18
+ "learning_rate": 2.6086956521739132e-06,
19
+ "loss": 0.2095,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 5.0,
24
+ "step": 1150,
25
+ "total_flos": 302026467563520.0,
26
+ "train_loss": 0.29514418560525646,
27
+ "train_runtime": 616.8399,
28
+ "train_samples_per_second": 29.732,
29
+ "train_steps_per_second": 1.864
30
+ }
31
+ ],
32
+ "max_steps": 1150,
33
+ "num_train_epochs": 5,
34
+ "total_flos": 302026467563520.0,
35
+ "trial_name": null,
36
+ "trial_params": null
37
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:116fe6c5264391eac7d9a8935fac4c151d34392600f814bb492145fd7d6b1324
3
+ size 3119
vocab.txt ADDED
The diff for this file is too large to render. See raw diff