yuwenz commited on
Commit
5dee588
·
1 Parent(s): 39e7a6e

upload fp32 model

Browse files

Signed-off-by: yuwenzho <[email protected]>

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: deberta-v3-base-mrpc
14
+ results:
15
+ - task:
16
+ name: Text Classification
17
+ type: text-classification
18
+ dataset:
19
+ name: GLUE MRPC
20
+ type: glue
21
+ config: mrpc
22
+ split: validation
23
+ args: mrpc
24
+ metrics:
25
+ - name: Accuracy
26
+ type: accuracy
27
+ value: 0.8946078431372549
28
+ - name: F1
29
+ type: f1
30
+ value: 0.9244288224956063
31
  ---
32
+
33
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
34
+ should probably proofread and complete it, then remove this comment. -->
35
+
36
+ # deberta-v3-base-mrpc
37
+
38
+ This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the GLUE MRPC dataset.
39
+ It achieves the following results on the evaluation set:
40
+ - Loss: 0.5681
41
+ - Accuracy: 0.8946
42
+ - F1: 0.9244
43
+ - Combined Score: 0.9095
44
+
45
+ ## Model description
46
+
47
+ More information needed
48
+
49
+ ## Intended uses & limitations
50
+
51
+ More information needed
52
+
53
+ ## Training and evaluation data
54
+
55
+ More information needed
56
+
57
+ ## Training procedure
58
+
59
+ ### Training hyperparameters
60
+
61
+ The following hyperparameters were used during training:
62
+ - learning_rate: 2e-05
63
+ - train_batch_size: 16
64
+ - eval_batch_size: 8
65
+ - seed: 42
66
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
67
+ - lr_scheduler_type: linear
68
+ - lr_scheduler_warmup_steps: 500
69
+ - num_epochs: 5.0
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.28.1
75
+ - Pytorch 1.12.1+cu113
76
+ - Datasets 2.11.0
77
+ - Tokenizers 0.13.3
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.8946078431372549,
4
+ "eval_combined_score": 0.9095183328164307,
5
+ "eval_f1": 0.9244288224956063,
6
+ "eval_loss": 0.5681403875350952,
7
+ "eval_runtime": 2.2149,
8
+ "eval_samples": 408,
9
+ "eval_samples_per_second": 184.204,
10
+ "eval_steps_per_second": 23.026,
11
+ "train_loss": 0.2895339061902917,
12
+ "train_runtime": 312.3775,
13
+ "train_samples": 3668,
14
+ "train_samples_per_second": 58.711,
15
+ "train_steps_per_second": 3.681
16
+ }
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "finetuning_task": "mrpc",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "not_equivalent",
13
+ "1": "equivalent"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "equivalent": 1,
19
+ "not_equivalent": 0
20
+ },
21
+ "layer_norm_eps": 1e-07,
22
+ "max_position_embeddings": 512,
23
+ "max_relative_positions": -1,
24
+ "model_type": "deberta-v2",
25
+ "norm_rel_ebd": "layer_norm",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "pooler_dropout": 0,
30
+ "pooler_hidden_act": "gelu",
31
+ "pooler_hidden_size": 768,
32
+ "pos_att_type": [
33
+ "p2c",
34
+ "c2p"
35
+ ],
36
+ "position_biased_input": false,
37
+ "position_buckets": 256,
38
+ "relative_attention": true,
39
+ "share_att_key": true,
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.28.1",
42
+ "type_vocab_size": 0,
43
+ "vocab_size": 128100
44
+ }
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.8946078431372549,
4
+ "eval_combined_score": 0.9095183328164307,
5
+ "eval_f1": 0.9244288224956063,
6
+ "eval_loss": 0.5681403875350952,
7
+ "eval_runtime": 2.2149,
8
+ "eval_samples": 408,
9
+ "eval_samples_per_second": 184.204,
10
+ "eval_steps_per_second": 23.026
11
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc5014fcb029b15c1842c71e95a4c931cf7f854170cdf3b08c1f25ae5479ee4c
3
+ size 737766955
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": false,
6
+ "eos_token": "[SEP]",
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 1000000000000000019884624838656,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "sp_model_kwargs": {},
12
+ "split_by_punct": false,
13
+ "tokenizer_class": "DebertaV2Tokenizer",
14
+ "unk_token": "[UNK]",
15
+ "vocab_type": "spm"
16
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.2895339061902917,
4
+ "train_runtime": 312.3775,
5
+ "train_samples": 3668,
6
+ "train_samples_per_second": 58.711,
7
+ "train_steps_per_second": 3.681
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 2e-05,
13
+ "loss": 0.4803,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 2.17,
18
+ "eval_accuracy": 0.8872549019607843,
19
+ "eval_combined_score": 0.9028473091364206,
20
+ "eval_f1": 0.9184397163120569,
21
+ "eval_loss": 0.34769126772880554,
22
+ "eval_runtime": 2.2258,
23
+ "eval_samples_per_second": 183.303,
24
+ "eval_steps_per_second": 22.913,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 4.35,
29
+ "learning_rate": 4.615384615384616e-06,
30
+ "loss": 0.164,
31
+ "step": 1000
32
+ },
33
+ {
34
+ "epoch": 4.35,
35
+ "eval_accuracy": 0.8995098039215687,
36
+ "eval_combined_score": 0.9138529755159507,
37
+ "eval_f1": 0.9281961471103327,
38
+ "eval_loss": 0.5612154006958008,
39
+ "eval_runtime": 2.2216,
40
+ "eval_samples_per_second": 183.653,
41
+ "eval_steps_per_second": 22.957,
42
+ "step": 1000
43
+ },
44
+ {
45
+ "epoch": 5.0,
46
+ "step": 1150,
47
+ "total_flos": 2412771647139840.0,
48
+ "train_loss": 0.2895339061902917,
49
+ "train_runtime": 312.3775,
50
+ "train_samples_per_second": 58.711,
51
+ "train_steps_per_second": 3.681
52
+ }
53
+ ],
54
+ "max_steps": 1150,
55
+ "num_train_epochs": 5,
56
+ "total_flos": 2412771647139840.0,
57
+ "trial_name": null,
58
+ "trial_params": null
59
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88b935da2fc29ff764933e67ec9a25632110be5c295e82771fdd9768e4302e60
3
+ size 3503