MoritzLaurer HF staff commited on
Commit
6b62f83
1 Parent(s): fa35672

End of training

Browse files
README.md ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/deberta-v3-large
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: deberta-v3-large-zeroshot-v1.1-none
10
+ results: []
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
+ # deberta-v3-large-zeroshot-v1.1-none
17
+
18
+ This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.2186
21
+ - F1 Macro: 0.6981
22
+ - F1 Micro: 0.7601
23
+ - Accuracy Balanced: 0.7396
24
+ - Accuracy: 0.7601
25
+ - Precision Macro: 0.7117
26
+ - Recall Macro: 0.7396
27
+ - Precision Micro: 0.7601
28
+ - Recall Micro: 0.7601
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 9e-06
48
+ - train_batch_size: 16
49
+ - eval_batch_size: 64
50
+ - seed: 42
51
+ - gradient_accumulation_steps: 2
52
+ - total_train_batch_size: 32
53
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
+ - lr_scheduler_type: linear
55
+ - lr_scheduler_warmup_ratio: 0.06
56
+ - num_epochs: 3
57
+
58
+ ### Training results
59
+
60
+ | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Micro | Accuracy Balanced | Accuracy | Precision Macro | Recall Macro | Precision Micro | Recall Micro |
61
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:-----------------:|:--------:|:---------------:|:------------:|:---------------:|:------------:|
62
+ | 0.1822 | 1.0 | 30789 | 0.3109 | 0.8675 | 0.8798 | 0.8658 | 0.8798 | 0.8692 | 0.8658 | 0.8798 | 0.8798 |
63
+ | 0.1334 | 2.0 | 61579 | 0.3410 | 0.8735 | 0.8860 | 0.8696 | 0.8860 | 0.8780 | 0.8696 | 0.8860 | 0.8860 |
64
+ | 0.0829 | 3.0 | 92367 | 0.4505 | 0.8753 | 0.8869 | 0.8737 | 0.8869 | 0.8771 | 0.8737 | 0.8869 | 0.8869 |
65
+
66
+
67
+ ### Framework versions
68
+
69
+ - Transformers 4.33.3
70
+ - Pytorch 1.11.0+cu113
71
+ - Datasets 2.14.6
72
+ - Tokenizers 0.12.1
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "id2label": {
11
+ "0": "entailment",
12
+ "1": "not_entailment"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 4096,
16
+ "label2id": {
17
+ "entailment": 0,
18
+ "not_entailment": 1
19
+ },
20
+ "layer_norm_eps": 1e-07,
21
+ "max_position_embeddings": 512,
22
+ "max_relative_positions": -1,
23
+ "model_type": "deberta-v2",
24
+ "norm_rel_ebd": "layer_norm",
25
+ "num_attention_heads": 16,
26
+ "num_hidden_layers": 24,
27
+ "pad_token_id": 0,
28
+ "pooler_dropout": 0,
29
+ "pooler_hidden_act": "gelu",
30
+ "pooler_hidden_size": 1024,
31
+ "pos_att_type": [
32
+ "p2c",
33
+ "c2p"
34
+ ],
35
+ "position_biased_input": false,
36
+ "position_buckets": 256,
37
+ "relative_attention": true,
38
+ "share_att_key": true,
39
+ "torch_dtype": "float16",
40
+ "transformers_version": "4.33.3",
41
+ "type_vocab_size": 0,
42
+ "vocab_size": 128100
43
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4def21feccad27dddc15d4fa49c771f591a5082f696a5df17fbf3a562e1382d3
3
+ size 870261293
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_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": 512,
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d5d8229f3a64792db0fb57869ef31fe230af8166a10fc18cfe1be2137ba993
3
+ size 4207