Hugging Face's logo

agvidit1
/
distilbert-hate_speech18

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
agvidit1 commited on
Commit
c592ebc
·
1 Parent(s): e544bac

Training in progress, epoch 1

Browse files
Files changed (24) hide show
  1. logs/events.out.tfevents.1702155428.tron63.umiacs.umd.edu +2 -2
  2. logs/events.out.tfevents.1702155607.tron63.umiacs.umd.edu +3 -0
  3. model.safetensors +1 -1
  4. run-3/checkpoint-2192/config.json +37 -0
  5. run-3/checkpoint-2192/model.safetensors +3 -0
  6. run-3/checkpoint-2192/optimizer.pt +3 -0
  7. run-3/checkpoint-2192/rng_state.pth +3 -0
  8. run-3/checkpoint-2192/scheduler.pt +3 -0
  9. run-3/checkpoint-2192/special_tokens_map.json +37 -0
  10. run-3/checkpoint-2192/tokenizer_config.json +57 -0
  11. run-3/checkpoint-2192/trainer_state.json +86 -0
  12. run-3/checkpoint-2192/training_args.bin +3 -0
  13. run-3/checkpoint-2192/vocab.txt +0 -0
  14. run-4/checkpoint-274/config.json +37 -0
  15. run-4/checkpoint-274/model.safetensors +3 -0
  16. run-4/checkpoint-274/optimizer.pt +3 -0
  17. run-4/checkpoint-274/rng_state.pth +3 -0
  18. run-4/checkpoint-274/scheduler.pt +3 -0
  19. run-4/checkpoint-274/special_tokens_map.json +37 -0
  20. run-4/checkpoint-274/tokenizer_config.json +57 -0
  21. run-4/checkpoint-274/trainer_state.json +41 -0
  22. run-4/checkpoint-274/training_args.bin +3 -0
  23. run-4/checkpoint-274/vocab.txt +0 -0
  24. training_args.bin +1 -1
logs/events.out.tfevents.1702155428.tron63.umiacs.umd.edu CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:205865e25810208b2866a148c601f8e39b9cc9eb7f178a8b543a7f18d7670f66
3
- size 4959
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e2adc081a4b76a976ccfd2fa1f91e96839ca838ca394e951ab92bf74a487345
3
+ size 6596
logs/events.out.tfevents.1702155607.tron63.umiacs.umd.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5efe084fdd538f5a7d2d945ee703351c2bafaf98deb99231bb14a116084d20af
3
+ size 4479
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e9eef0df8ddc4200928eb2352f84d47035b93e57102dd9c77905ac528603e46
3
  size 267838720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84c42e690cbbfbc22adad6612fbf4afc14a5c2850da1b403404abd9f15ae8eb8
3
  size 267838720
run-3/checkpoint-2192/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "agvidit1/DistilledBert_HateSpeech_pretrain",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "noHate",
13
+ "1": "hate",
14
+ "2": "idk/skip",
15
+ "3": "relation"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "label2id": {
19
+ "hate": "1",
20
+ "idk/skip": "2",
21
+ "noHate": "0",
22
+ "relation": "3"
23
+ },
24
+ "max_position_embeddings": 512,
25
+ "model_type": "distilbert",
26
+ "n_heads": 12,
27
+ "n_layers": 6,
28
+ "pad_token_id": 0,
29
+ "problem_type": "single_label_classification",
30
+ "qa_dropout": 0.1,
31
+ "seq_classif_dropout": 0.2,
32
+ "sinusoidal_pos_embds": false,
33
+ "tie_weights_": true,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.35.2",
36
+ "vocab_size": 30522
37
+ }
run-3/checkpoint-2192/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:279d0bbe58c1a72da16cf4cc56cb8471174388631a13b6999ba86399e2a9456e
3
+ size 267838720
run-3/checkpoint-2192/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:075b7f203fcf17a53c7a4afce3ef611c11a7ffd87355899f26118a0bc0ecbe26
3
+ size 535739578
run-3/checkpoint-2192/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:921c0b9ea0b64c73f56faa7d24ec3177f87211447b99f175ace4d1421256967b
3
+ size 14308
run-3/checkpoint-2192/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed6f1fb9111d1a47649dc6862618a0f12f64fe60b7e8fd701d755fbe5ca20387
3
+ size 1064
run-3/checkpoint-2192/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
+ }
run-3/checkpoint-2192/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "DistilBertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-3/checkpoint-2192/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.850091407678245,
3
+ "best_model_checkpoint": "distilbert-hate_speech18/run-3/checkpoint-548",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2192,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "learning_rate": 1.4051956453022492e-06,
14
+ "loss": 0.0386,
15
+ "step": 548
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.850091407678245,
20
+ "eval_loss": 0.03658764064311981,
21
+ "eval_runtime": 2.2693,
22
+ "eval_samples_per_second": 482.089,
23
+ "eval_steps_per_second": 30.406,
24
+ "step": 548
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 9.367970968681661e-07,
29
+ "loss": 0.0368,
30
+ "step": 1096
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.850091407678245,
35
+ "eval_loss": 0.03648461028933525,
36
+ "eval_runtime": 2.2686,
37
+ "eval_samples_per_second": 482.228,
38
+ "eval_steps_per_second": 30.415,
39
+ "step": 1096
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 4.6839854843408306e-07,
44
+ "loss": 0.0367,
45
+ "step": 1644
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.850091407678245,
50
+ "eval_loss": 0.03644398972392082,
51
+ "eval_runtime": 2.2755,
52
+ "eval_samples_per_second": 480.772,
53
+ "eval_steps_per_second": 30.323,
54
+ "step": 1644
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 0.0,
59
+ "loss": 0.0366,
60
+ "step": 2192
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.850091407678245,
65
+ "eval_loss": 0.03641996905207634,
66
+ "eval_runtime": 2.2729,
67
+ "eval_samples_per_second": 481.324,
68
+ "eval_steps_per_second": 30.358,
69
+ "step": 2192
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 2192,
74
+ "num_train_epochs": 4,
75
+ "save_steps": 500,
76
+ "total_flos": 591189451198416.0,
77
+ "trial_name": null,
78
+ "trial_params": {
79
+ "alpha": 0.028474853697725067,
80
+ "learning_rate": 1.8735941937363323e-06,
81
+ "num_train_epochs": 4,
82
+ "per_device_eval_batch_size": 16,
83
+ "per_device_train_batch_size": 16,
84
+ "temperature": 25
85
+ }
86
+ }
run-3/checkpoint-2192/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffb539c4216955fec5d643cfd2eb07d02c3ca2cbb6ebfb5083e1e0c198318fe7
3
+ size 4664
run-3/checkpoint-2192/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-274/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "agvidit1/DistilledBert_HateSpeech_pretrain",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "noHate",
13
+ "1": "hate",
14
+ "2": "idk/skip",
15
+ "3": "relation"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "label2id": {
19
+ "hate": "1",
20
+ "idk/skip": "2",
21
+ "noHate": "0",
22
+ "relation": "3"
23
+ },
24
+ "max_position_embeddings": 512,
25
+ "model_type": "distilbert",
26
+ "n_heads": 12,
27
+ "n_layers": 6,
28
+ "pad_token_id": 0,
29
+ "problem_type": "single_label_classification",
30
+ "qa_dropout": 0.1,
31
+ "seq_classif_dropout": 0.2,
32
+ "sinusoidal_pos_embds": false,
33
+ "tie_weights_": true,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.35.2",
36
+ "vocab_size": 30522
37
+ }
run-4/checkpoint-274/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84c42e690cbbfbc22adad6612fbf4afc14a5c2850da1b403404abd9f15ae8eb8
3
+ size 267838720
run-4/checkpoint-274/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca4b96e33d2e53b90187d8de3b78f0225ad2de2023b51a7b8814392de734b689
3
+ size 535739578
run-4/checkpoint-274/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc4eaeac1bf0418c63b696ef91dde26fd34647662785831d683b9ad0cf64eab3
3
+ size 14308
run-4/checkpoint-274/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b2a44b8681e7a4e872b74b0227670b06751cf4c7618591bbc0da55481088a10
3
+ size 1064
run-4/checkpoint-274/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
+ }
run-4/checkpoint-274/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "DistilBertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-4/checkpoint-274/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.850091407678245,
3
+ "best_model_checkpoint": "distilbert-hate_speech18/run-4/checkpoint-274",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 274,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "learning_rate": 8.15331111796953e-07,
14
+ "loss": 0.6946,
15
+ "step": 274
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.850091407678245,
20
+ "eval_loss": 0.5388411283493042,
21
+ "eval_runtime": 2.6594,
22
+ "eval_samples_per_second": 411.373,
23
+ "eval_steps_per_second": 13.161,
24
+ "step": 274
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 822,
29
+ "num_train_epochs": 3,
30
+ "save_steps": 500,
31
+ "total_flos": 185725916995584.0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "alpha": 0.7674697347517282,
35
+ "learning_rate": 1.2229966676954296e-06,
36
+ "num_train_epochs": 3,
37
+ "per_device_eval_batch_size": 32,
38
+ "per_device_train_batch_size": 32,
39
+ "temperature": 18
40
+ }
41
+ }
run-4/checkpoint-274/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f119c2c47c2ddc105a364fdbf6e72870d737cf46fe71df9314db160fb0f336d2
3
+ size 4664
run-4/checkpoint-274/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffb539c4216955fec5d643cfd2eb07d02c3ca2cbb6ebfb5083e1e0c198318fe7
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f119c2c47c2ddc105a364fdbf6e72870d737cf46fe71df9314db160fb0f336d2
3
  size 4664