Hugging Face's logo

sara-nabhani
/
ltp-roberta-large-defaultltp-roberta-large-default-2

Text Classification
Transformers
PyTorch
roberta
Inference Endpoints
Model card Files Community
sara-nabhani commited on
Commit
bbaa405
·
1 Parent(s): f375a59

Training in progress, step 200

Browse files
Files changed (21) hide show
  1. .gitignore +1 -0
  2. config.json +72 -0
  3. last-checkpoint/config.json +72 -0
  4. last-checkpoint/merges.txt +0 -0
  5. last-checkpoint/optimizer.pt +3 -0
  6. last-checkpoint/pytorch_model.bin +3 -0
  7. last-checkpoint/rng_state.pth +3 -0
  8. last-checkpoint/scheduler.pt +3 -0
  9. last-checkpoint/special_tokens_map.json +15 -0
  10. last-checkpoint/tokenizer.json +0 -0
  11. last-checkpoint/tokenizer_config.json +15 -0
  12. last-checkpoint/trainer_state.json +53 -0
  13. last-checkpoint/training_args.bin +3 -0
  14. last-checkpoint/vocab.json +0 -0
  15. merges.txt +0 -0
  16. pytorch_model.bin +3 -0
  17. special_tokens_map.json +15 -0
  18. tokenizer.json +0 -0
  19. tokenizer_config.json +15 -0
  20. training_args.bin +3 -0
  21. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-large",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12",
27
+ "13": "LABEL_13",
28
+ "14": "LABEL_14",
29
+ "15": "LABEL_15",
30
+ "16": "LABEL_16",
31
+ "17": "LABEL_17",
32
+ "18": "LABEL_18",
33
+ "19": "LABEL_19"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 4096,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_10": 10,
41
+ "LABEL_11": 11,
42
+ "LABEL_12": 12,
43
+ "LABEL_13": 13,
44
+ "LABEL_14": 14,
45
+ "LABEL_15": 15,
46
+ "LABEL_16": 16,
47
+ "LABEL_17": 17,
48
+ "LABEL_18": 18,
49
+ "LABEL_19": 19,
50
+ "LABEL_2": 2,
51
+ "LABEL_3": 3,
52
+ "LABEL_4": 4,
53
+ "LABEL_5": 5,
54
+ "LABEL_6": 6,
55
+ "LABEL_7": 7,
56
+ "LABEL_8": 8,
57
+ "LABEL_9": 9
58
+ },
59
+ "layer_norm_eps": 1e-05,
60
+ "max_position_embeddings": 514,
61
+ "model_type": "roberta",
62
+ "num_attention_heads": 16,
63
+ "num_hidden_layers": 24,
64
+ "pad_token_id": 1,
65
+ "position_embedding_type": "absolute",
66
+ "problem_type": "multi_label_classification",
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.29.2",
69
+ "type_vocab_size": 1,
70
+ "use_cache": true,
71
+ "vocab_size": 50265
72
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-large",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12",
27
+ "13": "LABEL_13",
28
+ "14": "LABEL_14",
29
+ "15": "LABEL_15",
30
+ "16": "LABEL_16",
31
+ "17": "LABEL_17",
32
+ "18": "LABEL_18",
33
+ "19": "LABEL_19"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 4096,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_10": 10,
41
+ "LABEL_11": 11,
42
+ "LABEL_12": 12,
43
+ "LABEL_13": 13,
44
+ "LABEL_14": 14,
45
+ "LABEL_15": 15,
46
+ "LABEL_16": 16,
47
+ "LABEL_17": 17,
48
+ "LABEL_18": 18,
49
+ "LABEL_19": 19,
50
+ "LABEL_2": 2,
51
+ "LABEL_3": 3,
52
+ "LABEL_4": 4,
53
+ "LABEL_5": 5,
54
+ "LABEL_6": 6,
55
+ "LABEL_7": 7,
56
+ "LABEL_8": 8,
57
+ "LABEL_9": 9
58
+ },
59
+ "layer_norm_eps": 1e-05,
60
+ "max_position_embeddings": 514,
61
+ "model_type": "roberta",
62
+ "num_attention_heads": 16,
63
+ "num_hidden_layers": 24,
64
+ "pad_token_id": 1,
65
+ "position_embedding_type": "absolute",
66
+ "problem_type": "multi_label_classification",
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.29.2",
69
+ "type_vocab_size": 1,
70
+ "use_cache": true,
71
+ "vocab_size": 50265
72
+ }
last-checkpoint/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbcda4f49ac8809e4ecc741ef376fdfb93a83b6f20d481326088b9d524741307
3
+ size 2843370360
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a791ae00773eec9a6239c7fc2239b09923dfa62424ecbf3d9db7bfc7f9781da
3
+ size 1421660981
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc46fceeab4779d466155012d51a1544ef0cd2c699e8a7b77b7b43070f604803
3
+ size 14511
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8636707e906db799535a0e24d8b11f4682008d2f9dce23ea4add566cf191f0eb
3
+ size 627
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 512,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "RobertaTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
15
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.11572875154130194,
3
+ "best_model_checkpoint": "/home2/s5432073/language-tech-project/results/ltp-roberta-large-defaultltp-roberta-large-default-2/checkpoint-200",
4
+ "epoch": 1.183431952662722,
5
+ "global_step": 200,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.18,
12
+ "learning_rate": 9.28348909657321e-06,
13
+ "loss": 0.4492,
14
+ "step": 200
15
+ },
16
+ {
17
+ "epoch": 1.18,
18
+ "eval_f1": 0.11572875154130194,
19
+ "eval_f1_all": [
20
+ 0.0,
21
+ 0.05847953216374269,
22
+ 0.0,
23
+ 0.0,
24
+ 0.4682713347921225,
25
+ 0.0,
26
+ 0.0,
27
+ 0.0,
28
+ 0.6747759282970549,
29
+ 0.520393811533052,
30
+ 0.0,
31
+ 0.0,
32
+ 0.0,
33
+ 0.0,
34
+ 0.0,
35
+ 0.0,
36
+ 0.5926544240400667,
37
+ 0.0,
38
+ 0.0,
39
+ 0.0
40
+ ],
41
+ "eval_loss": 0.36748331785202026,
42
+ "eval_runtime": 3.8035,
43
+ "eval_samples_per_second": 498.483,
44
+ "eval_steps_per_second": 15.775,
45
+ "step": 200
46
+ }
47
+ ],
48
+ "max_steps": 1690,
49
+ "num_train_epochs": 10,
50
+ "total_flos": 1490128739639568.0,
51
+ "trial_name": null,
52
+ "trial_params": null
53
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6beaf0b8b0fcf182a29d1dd62898ba668649fec5779e5ce2cc4405f199bacde5
3
+ size 4155
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a791ae00773eec9a6239c7fc2239b09923dfa62424ecbf3d9db7bfc7f9781da
3
+ size 1421660981
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 512,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "RobertaTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6beaf0b8b0fcf182a29d1dd62898ba668649fec5779e5ce2cc4405f199bacde5
3
+ size 4155
vocab.json ADDED
The diff for this file is too large to render. See raw diff