Hugging Face's logo

Tirath5504
/
IPD-Text-Hinglish

Safetensors
roberta
Model card Files Community
Tirath5504 commited on
Commit
85bc363
•
1 Parent(s): af15598

Upload 11 files

Browse files
Files changed (11) hide show
  1. config.json +38 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. special_tokens_map.json +37 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +58 -0
  9. trainer_state.json +135 -0
  10. training_args.bin +3 -0
  11. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilroberta-base",
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": 768,
13
+ "id2label": {
14
+ "0": "NAG",
15
+ "1": "CAG",
16
+ "2": "OAG"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "CAG": 1,
22
+ "NAG": 0,
23
+ "OAG": 2
24
+ },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "roberta",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 6,
30
+ "pad_token_id": 1,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.42.4",
35
+ "type_vocab_size": 1,
36
+ "use_cache": true,
37
+ "vocab_size": 50265
38
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32d971938d8d3ad2d9235413af37110d8380e9e89144be76d275d01db4185c2c
3
+ size 328495356
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ed4a1d2531d1d11e44022370a871d05ca24e9c00bfec8c4aeb7a982099e0b26
3
+ size 657053754
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01add9c7ea70d2dd10f4ba72f1541c9710edb6a876087f4406f6550154086465
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a77aedcb37abf51150f6cbeefabfd88f75d0446aaa0134ca069a863a4696d7d6
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "max_len": 512,
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
trainer_state.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.923999011516571,
3
+ "best_model_checkpoint": "hinglish-multiclassifier-run-3/checkpoint-1200",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.8333333333333334,
13
+ "grad_norm": 3.3428757190704346,
14
+ "learning_rate": 1.6666666666666667e-05,
15
+ "loss": 1.0191,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_loss": 0.9894943237304688,
21
+ "eval_overall-accuracy": 0.43333333333333335,
22
+ "eval_overall-f1": 0.43333333333333335,
23
+ "eval_overall-precision": 0.43333333333333335,
24
+ "eval_overall-recall": 0.43333333333333335,
25
+ "eval_runtime": 41.8618,
26
+ "eval_samples_per_second": 57.332,
27
+ "eval_steps_per_second": 3.583,
28
+ "step": 600
29
+ },
30
+ {
31
+ "epoch": 1.6666666666666665,
32
+ "grad_norm": 3.2503693103790283,
33
+ "learning_rate": 1.3333333333333333e-05,
34
+ "loss": 0.9574,
35
+ "step": 1000
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_loss": 0.923999011516571,
40
+ "eval_overall-accuracy": 0.5283333333333333,
41
+ "eval_overall-f1": 0.5283333333333333,
42
+ "eval_overall-precision": 0.5283333333333333,
43
+ "eval_overall-recall": 0.5283333333333333,
44
+ "eval_runtime": 41.7887,
45
+ "eval_samples_per_second": 57.432,
46
+ "eval_steps_per_second": 3.589,
47
+ "step": 1200
48
+ },
49
+ {
50
+ "epoch": 2.5,
51
+ "grad_norm": 17.47089195251465,
52
+ "learning_rate": 1e-05,
53
+ "loss": 0.91,
54
+ "step": 1500
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_loss": 0.9276531934738159,
59
+ "eval_overall-accuracy": 0.5433333333333333,
60
+ "eval_overall-f1": 0.5433333333333333,
61
+ "eval_overall-precision": 0.5433333333333333,
62
+ "eval_overall-recall": 0.5433333333333333,
63
+ "eval_runtime": 41.7865,
64
+ "eval_samples_per_second": 57.435,
65
+ "eval_steps_per_second": 3.59,
66
+ "step": 1800
67
+ },
68
+ {
69
+ "epoch": 3.3333333333333335,
70
+ "grad_norm": 7.9832844734191895,
71
+ "learning_rate": 6.666666666666667e-06,
72
+ "loss": 0.8617,
73
+ "step": 2000
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_loss": 0.9282340407371521,
78
+ "eval_overall-accuracy": 0.5516666666666666,
79
+ "eval_overall-f1": 0.5516666666666666,
80
+ "eval_overall-precision": 0.5516666666666666,
81
+ "eval_overall-recall": 0.5516666666666666,
82
+ "eval_runtime": 41.8418,
83
+ "eval_samples_per_second": 57.359,
84
+ "eval_steps_per_second": 3.585,
85
+ "step": 2400
86
+ },
87
+ {
88
+ "epoch": 4.166666666666667,
89
+ "grad_norm": 10.765121459960938,
90
+ "learning_rate": 3.3333333333333333e-06,
91
+ "loss": 0.8291,
92
+ "step": 2500
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "grad_norm": 13.0308256149292,
97
+ "learning_rate": 0.0,
98
+ "loss": 0.7898,
99
+ "step": 3000
100
+ },
101
+ {
102
+ "epoch": 5.0,
103
+ "eval_loss": 0.9524471759796143,
104
+ "eval_overall-accuracy": 0.55875,
105
+ "eval_overall-f1": 0.55875,
106
+ "eval_overall-precision": 0.55875,
107
+ "eval_overall-recall": 0.55875,
108
+ "eval_runtime": 42.2387,
109
+ "eval_samples_per_second": 56.82,
110
+ "eval_steps_per_second": 3.551,
111
+ "step": 3000
112
+ }
113
+ ],
114
+ "logging_steps": 500,
115
+ "max_steps": 3000,
116
+ "num_input_tokens_seen": 0,
117
+ "num_train_epochs": 5,
118
+ "save_steps": 500,
119
+ "stateful_callbacks": {
120
+ "TrainerControl": {
121
+ "args": {
122
+ "should_epoch_stop": false,
123
+ "should_evaluate": false,
124
+ "should_log": false,
125
+ "should_save": true,
126
+ "should_training_stop": true
127
+ },
128
+ "attributes": {}
129
+ }
130
+ },
131
+ "total_flos": 6357223831541760.0,
132
+ "train_batch_size": 16,
133
+ "trial_name": null,
134
+ "trial_params": null
135
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e18729e17e8906006eba85774f402e69adddc9ee5f0f11df3fa9ac91675b753a
3
+ size 5176
vocab.txt ADDED
The diff for this file is too large to render. See raw diff