mrm8488 commited on
Commit
15f8696
1 Parent(s): 8dde9d6

Initial commit from mrm8488

Browse files
README.md ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: mit
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - glue
9
+ metrics:
10
+ - matthews_correlation
11
+ model-index:
12
+ - name: deberta-v3-small
13
+ results:
14
+ - task:
15
+ name: Text Classification
16
+ type: text-classification
17
+ dataset:
18
+ name: GLUE COLA
19
+ type: glue
20
+ args: cola
21
+ metrics:
22
+ - name: Matthews Correlation
23
+ type: matthews_correlation
24
+ value: 0.6333205721749096
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # deberta-v3-small
31
+
32
+ This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the GLUE COLA dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.4051
35
+ - Matthews Correlation: 0.6333
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 3e-05
55
+ - train_batch_size: 16
56
+ - eval_batch_size: 8
57
+ - seed: 42
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - num_epochs: 5.0
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
65
+ |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
66
+ | No log | 1.0 | 535 | 0.4051 | 0.6333 |
67
+ | 0.3371 | 2.0 | 1070 | 0.4455 | 0.6531 |
68
+ | 0.3371 | 3.0 | 1605 | 0.5755 | 0.6499 |
69
+ | 0.1305 | 4.0 | 2140 | 0.7188 | 0.6553 |
70
+ | 0.1305 | 5.0 | 2675 | 0.8047 | 0.6700 |
71
+
72
+
73
+ ### Framework versions
74
+
75
+ - Transformers 4.13.0.dev0
76
+ - Pytorch 1.10.0+cu111
77
+ - Datasets 1.16.1
78
+ - Tokenizers 0.10.3
added_tokens.json ADDED
@@ -0,0 +1 @@
 
1
+ {"[MASK]": 128000}
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 0.4050879180431366,
4
+ "eval_matthews_correlation": 0.6333205721749096,
5
+ "eval_runtime": 2.0441,
6
+ "eval_samples": 1043,
7
+ "eval_samples_per_second": 510.242,
8
+ "eval_steps_per_second": 64.086,
9
+ "train_loss": 0.19247490570923992,
10
+ "train_runtime": 168.1314,
11
+ "train_samples": 8551,
12
+ "train_samples_per_second": 254.295,
13
+ "train_steps_per_second": 15.91
14
+ }
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-small",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "finetuning_task": "cola",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "unacceptable",
13
+ "1": "acceptable"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "acceptable": 1,
19
+ "unacceptable": 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": 6,
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": "4.13.0.dev0",
42
+ "type_vocab_size": 0,
43
+ "vocab_size": 128100
44
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 0.4050879180431366,
4
+ "eval_matthews_correlation": 0.6333205721749096,
5
+ "eval_runtime": 2.0441,
6
+ "eval_samples": 1043,
7
+ "eval_samples_per_second": 510.242,
8
+ "eval_steps_per_second": 64.086
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41a2eb48f8a23e0b06964e87aec6ef4b1dc985814839082748c064456481e213
3
+ size 567632875
runs/events.out.tfevents.1638896689.fbe054181d38.464.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48ea8fd2b61c6a32468a4a0e2d7e652f377160ab9113da34a720766d09d4fecb
3
+ size 5893
runs/events.out.tfevents.1638896860.fbe054181d38.464.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4182510f029363fdf0b3afec212accd36114402b15864ab31458246483d6537
3
+ size 375
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": false, "sp_model_kwargs": {}, "vocab_type": "spm", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "microsoft/deberta-v3-small", "tokenizer_class": "DebertaV2Tokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.19247490570923992,
4
+ "train_runtime": 168.1314,
5
+ "train_samples": 8551,
6
+ "train_samples_per_second": 254.295,
7
+ "train_steps_per_second": 15.91
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4050879180431366,
3
+ "best_model_checkpoint": "/content/deberta-v3-small/checkpoint-535",
4
+ "epoch": 5.0,
5
+ "global_step": 2675,
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
+ "eval_loss": 0.4050879180431366,
13
+ "eval_matthews_correlation": 0.6333205721749096,
14
+ "eval_runtime": 2.031,
15
+ "eval_samples_per_second": 513.528,
16
+ "eval_steps_per_second": 64.499,
17
+ "step": 535
18
+ },
19
+ {
20
+ "epoch": 1.87,
21
+ "learning_rate": 1.8785046728971963e-05,
22
+ "loss": 0.3371,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "eval_loss": 0.4455100893974304,
28
+ "eval_matthews_correlation": 0.6530734183134956,
29
+ "eval_runtime": 2.0334,
30
+ "eval_samples_per_second": 512.931,
31
+ "eval_steps_per_second": 64.424,
32
+ "step": 1070
33
+ },
34
+ {
35
+ "epoch": 3.0,
36
+ "eval_loss": 0.5754692554473877,
37
+ "eval_matthews_correlation": 0.6499333084534608,
38
+ "eval_runtime": 2.0345,
39
+ "eval_samples_per_second": 512.647,
40
+ "eval_steps_per_second": 64.388,
41
+ "step": 1605
42
+ },
43
+ {
44
+ "epoch": 3.74,
45
+ "learning_rate": 7.570093457943924e-06,
46
+ "loss": 0.1305,
47
+ "step": 2000
48
+ },
49
+ {
50
+ "epoch": 4.0,
51
+ "eval_loss": 0.7188061475753784,
52
+ "eval_matthews_correlation": 0.6553451139053764,
53
+ "eval_runtime": 2.0152,
54
+ "eval_samples_per_second": 517.554,
55
+ "eval_steps_per_second": 65.004,
56
+ "step": 2140
57
+ },
58
+ {
59
+ "epoch": 5.0,
60
+ "eval_loss": 0.8047384023666382,
61
+ "eval_matthews_correlation": 0.6700089525749314,
62
+ "eval_runtime": 2.0026,
63
+ "eval_samples_per_second": 520.818,
64
+ "eval_steps_per_second": 65.414,
65
+ "step": 2675
66
+ },
67
+ {
68
+ "epoch": 5.0,
69
+ "step": 2675,
70
+ "total_flos": 1415961343234560.0,
71
+ "train_loss": 0.19247490570923992,
72
+ "train_runtime": 168.1314,
73
+ "train_samples_per_second": 254.295,
74
+ "train_steps_per_second": 15.91
75
+ }
76
+ ],
77
+ "max_steps": 2675,
78
+ "num_train_epochs": 5,
79
+ "total_flos": 1415961343234560.0,
80
+ "trial_name": null,
81
+ "trial_params": null
82
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88a4cd8abdc7501e9f667c3605f9282b8e62a2fe1ba2844b1934d379173a587e
3
+ size 2927