Hugging Face's logo

hSterz
/
semeval_clickbait_classification

Transformers
PyTorch
roberta
Inference Endpoints
Model card Files Community
hSterz commited on
Commit
993d854
·
1 Parent(s): 1234623

Upload 8 files

Browse files
Files changed (8) hide show
  1. config.json +71 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +51 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +67 -0
  6. trainer_state.json +52 -0
  7. training_args.bin +3 -0
  8. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "deepset/roberta-base-squad2",
3
+ "adapters": {
4
+ "adapters": {},
5
+ "config_map": {},
6
+ "fusion_config_map": {},
7
+ "fusions": {}
8
+ },
9
+ "architectures": [
10
+ "RobertaAdapterModel"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
13
+ "bos_token_id": 0,
14
+ "classifier_dropout": null,
15
+ "eos_token_id": 2,
16
+ "gradient_checkpointing": false,
17
+ "hidden_act": "gelu",
18
+ "hidden_dropout_prob": 0.1,
19
+ "hidden_size": 768,
20
+ "id2label": {
21
+ "0": "LABEL_0",
22
+ "1": "LABEL_1",
23
+ "2": "LABEL_2"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 3072,
27
+ "label2id": {
28
+ "LABEL_0": 0,
29
+ "LABEL_1": 1,
30
+ "LABEL_2": 2
31
+ },
32
+ "language": "english",
33
+ "layer_norm_eps": 1e-05,
34
+ "max_position_embeddings": 514,
35
+ "model_type": "roberta",
36
+ "name": "Roberta",
37
+ "num_attention_heads": 12,
38
+ "num_hidden_layers": 12,
39
+ "pad_token_id": 1,
40
+ "position_embedding_type": "absolute",
41
+ "prediction_heads": {
42
+ "classification": {
43
+ "activation_function": "tanh",
44
+ "bias": true,
45
+ "head_type": "classification",
46
+ "label2id": {
47
+ "LABEL_0": 0,
48
+ "LABEL_1": 1,
49
+ "LABEL_2": 2
50
+ },
51
+ "layers": 2,
52
+ "num_labels": 3,
53
+ "use_pooler": false
54
+ },
55
+ "squad": {
56
+ "activation_function": "tanh",
57
+ "head_type": "question_answering",
58
+ "label2id": {
59
+ "LABEL_0": 0,
60
+ "LABEL_1": 1
61
+ },
62
+ "layers": 1,
63
+ "num_labels": 2
64
+ }
65
+ },
66
+ "torch_dtype": "float32",
67
+ "transformers_version": "4.21.3",
68
+ "type_vocab_size": 1,
69
+ "use_cache": true,
70
+ "vocab_size": 50265
71
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "do_lower_case": false,
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "errors": "replace",
29
+ "full_tokenizer_file": null,
30
+ "mask_token": {
31
+ "__type": "AddedToken",
32
+ "content": "<mask>",
33
+ "lstrip": true,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ "model_max_length": 512,
39
+ "name_or_path": "deepset/roberta-base-squad2",
40
+ "pad_token": {
41
+ "__type": "AddedToken",
42
+ "content": "<pad>",
43
+ "lstrip": false,
44
+ "normalized": true,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "sep_token": {
49
+ "__type": "AddedToken",
50
+ "content": "</s>",
51
+ "lstrip": false,
52
+ "normalized": true,
53
+ "rstrip": false,
54
+ "single_word": false
55
+ },
56
+ "special_tokens_map_file": "/root/.cache/huggingface/transformers/c9d2c178fac8d40234baa1833a3b1903d393729bf93ea34da247c07db24900d0.cb2244924ab24d706b02fd7fcedaea4531566537687a539ebb94db511fd122a0",
57
+ "tokenizer_class": "RobertaTokenizer",
58
+ "trim_offsets": true,
59
+ "unk_token": {
60
+ "__type": "AddedToken",
61
+ "content": "<unk>",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ }
67
+ }
trainer_state.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 47.51263124658075,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Clickbait/QA_model_Task2_multi_full_deepseed_2/deepset_roberta-base-squad2_1.00e-04_2.00e-01_8_512_4/checkpoint-281",
4
+ "epoch": 3.9982238010657194,
5
+ "global_step": 1124,
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_exact_match": 31.25,
13
+ "eval_f1": 47.51263124658075,
14
+ "step": 281
15
+ },
16
+ {
17
+ "epoch": 1.78,
18
+ "learning_rate": 7.407407407407407e-05,
19
+ "loss": 2.6843,
20
+ "step": 500
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_exact_match": 31.625,
25
+ "eval_f1": 46.53627356092559,
26
+ "step": 562
27
+ },
28
+ {
29
+ "epoch": 3.0,
30
+ "eval_exact_match": 28.75,
31
+ "eval_f1": 45.974443842858555,
32
+ "step": 843
33
+ },
34
+ {
35
+ "epoch": 3.56,
36
+ "learning_rate": 8.794957360029664e-05,
37
+ "loss": 1.416,
38
+ "step": 1000
39
+ },
40
+ {
41
+ "epoch": 4.0,
42
+ "eval_exact_match": 29.375,
43
+ "eval_f1": 44.6085086171145,
44
+ "step": 1124
45
+ }
46
+ ],
47
+ "max_steps": 3372,
48
+ "num_train_epochs": 12,
49
+ "total_flos": 7159534287962112.0,
50
+ "trial_name": null,
51
+ "trial_params": null
52
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15de680e20401db16f5b72bcf5ff31dda59e284c672be9ed7d287eb397ee1a73
3
+ size 3707
vocab.json ADDED
The diff for this file is too large to render. See raw diff