Hugging Face's logo

joseph10
/
berttiny-hate_speech18-bothpretrained

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
joseph10 commited on
Commit
aa19bb6
•
1 Parent(s): 42fd157

Training in progress, epoch 1

Browse files
Files changed (24) hide show
  1. logs/events.out.tfevents.1702102150.joseph_legion.21824.3 +2 -2
  2. logs/events.out.tfevents.1702102317.joseph_legion.21824.4 +3 -0
  3. model.safetensors +1 -1
  4. run-2/checkpoint-960/config.json +38 -0
  5. run-2/checkpoint-960/model.safetensors +3 -0
  6. run-2/checkpoint-960/optimizer.pt +3 -0
  7. run-2/checkpoint-960/rng_state.pth +3 -0
  8. run-2/checkpoint-960/scheduler.pt +3 -0
  9. run-2/checkpoint-960/special_tokens_map.json +37 -0
  10. run-2/checkpoint-960/tokenizer_config.json +57 -0
  11. run-2/checkpoint-960/trainer_state.json +85 -0
  12. run-2/checkpoint-960/training_args.bin +3 -0
  13. run-2/checkpoint-960/vocab.txt +0 -0
  14. run-3/checkpoint-1915/config.json +38 -0
  15. run-3/checkpoint-1915/model.safetensors +3 -0
  16. run-3/checkpoint-1915/optimizer.pt +3 -0
  17. run-3/checkpoint-1915/rng_state.pth +3 -0
  18. run-3/checkpoint-1915/scheduler.pt +3 -0
  19. run-3/checkpoint-1915/special_tokens_map.json +37 -0
  20. run-3/checkpoint-1915/tokenizer_config.json +57 -0
  21. run-3/checkpoint-1915/trainer_state.json +40 -0
  22. run-3/checkpoint-1915/training_args.bin +3 -0
  23. run-3/checkpoint-1915/vocab.txt +0 -0
  24. training_args.bin +1 -1
logs/events.out.tfevents.1702102150.joseph_legion.21824.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:201ffe436d05c6275d682027fd31018e217041bce19e539d5112d93ff6e14e68
3
- size 5610
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1289af7022ba0f9f7c58c051f8c21d716dbde1239fdf0d76f9cc6a9ff035cd1
3
+ size 6924
logs/events.out.tfevents.1702102317.joseph_legion.21824.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d40e1ddd8e325c11f84d8c197b13bc9c593b6ceb7287707266d2eac5cd76ad4a
3
+ size 5128
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f93590bfa1773dee23ba85ef265565f61a3007abe13b9c3193cb72439bc394fc
3
  size 17550344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:764731460d2951401705beb2d8a7fc459e104c0e44830939a75182284035dab7
3
  size 17550344
run-2/checkpoint-960/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "agvidit1/GoogleTinyBert_HateSpeech_pretrain",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "noHate",
13
+ "1": "hate",
14
+ "2": "idk/skip",
15
+ "3": "relation"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 512,
19
+ "label2id": {
20
+ "hate": "1",
21
+ "idk/skip": "2",
22
+ "noHate": "0",
23
+ "relation": "3"
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 512,
27
+ "model_type": "bert",
28
+ "num_attention_heads": 2,
29
+ "num_hidden_layers": 2,
30
+ "pad_token_id": 0,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.36.0.dev0",
35
+ "type_vocab_size": 2,
36
+ "use_cache": true,
37
+ "vocab_size": 30522
38
+ }
run-2/checkpoint-960/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1c2206bef77e3bd1ba89260deebf7dc2d706bf32b8eec034221f99625c76811
3
+ size 17550344
run-2/checkpoint-960/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1212d84199e41bb004fe8af5aa7720dd8bbf784c3cd56a3007940d8d1bf7359c
3
+ size 35125946
run-2/checkpoint-960/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51e4f0cb5cbde254e32937cd829fc1661029e09dfe3c0fd71602dcbfb416e14f
3
+ size 14308
run-2/checkpoint-960/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:669b2814a5fbe8b5dd47db344a70ed868fa736c23bedd9daf34a8b44f05ebc02
3
+ size 1064
run-2/checkpoint-960/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-2/checkpoint-960/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": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-2/checkpoint-960/trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8555758683729433,
3
+ "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-2\\checkpoint-240",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 960,
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": 2.5453252643738987e-06,
14
+ "loss": 0.637,
15
+ "step": 240
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8555758683729433,
20
+ "eval_loss": 0.5853705406188965,
21
+ "eval_runtime": 10.8628,
22
+ "eval_samples_per_second": 201.422,
23
+ "eval_steps_per_second": 1.657,
24
+ "step": 240
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 1.6968835095825992e-06,
29
+ "loss": 0.5701,
30
+ "step": 480
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8555758683729433,
35
+ "eval_loss": 0.545884907245636,
36
+ "eval_runtime": 11.0146,
37
+ "eval_samples_per_second": 198.645,
38
+ "eval_steps_per_second": 1.634,
39
+ "step": 480
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 8.484417547912996e-07,
44
+ "loss": 0.5422,
45
+ "step": 720
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8555758683729433,
50
+ "eval_loss": 0.5303202867507935,
51
+ "eval_runtime": 10.9437,
52
+ "eval_samples_per_second": 199.933,
53
+ "eval_steps_per_second": 1.645,
54
+ "step": 720
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 0.0,
59
+ "loss": 0.5316,
60
+ "step": 960
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8555758683729433,
65
+ "eval_loss": 0.5260117650032043,
66
+ "eval_runtime": 10.9305,
67
+ "eval_samples_per_second": 200.173,
68
+ "eval_steps_per_second": 1.647,
69
+ "step": 960
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 960,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 4,
76
+ "save_steps": 500,
77
+ "total_flos": 6253424431104.0,
78
+ "trial_name": null,
79
+ "trial_params": {
80
+ "learning_rate": 3.3937670191651984e-06,
81
+ "num_train_epochs": 4,
82
+ "per_device_train_batch_size": 32,
83
+ "seed": 33
84
+ }
85
+ }
run-2/checkpoint-960/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:802de4ab1ae5a718d0e69dba885378288d4b7dd699fc41de9ce8b3c785e2b6d4
3
+ size 4792
run-2/checkpoint-960/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-1915/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "agvidit1/GoogleTinyBert_HateSpeech_pretrain",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "noHate",
13
+ "1": "hate",
14
+ "2": "idk/skip",
15
+ "3": "relation"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 512,
19
+ "label2id": {
20
+ "hate": "1",
21
+ "idk/skip": "2",
22
+ "noHate": "0",
23
+ "relation": "3"
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 512,
27
+ "model_type": "bert",
28
+ "num_attention_heads": 2,
29
+ "num_hidden_layers": 2,
30
+ "pad_token_id": 0,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.36.0.dev0",
35
+ "type_vocab_size": 2,
36
+ "use_cache": true,
37
+ "vocab_size": 30522
38
+ }
run-3/checkpoint-1915/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:764731460d2951401705beb2d8a7fc459e104c0e44830939a75182284035dab7
3
+ size 17550344
run-3/checkpoint-1915/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce34311f67beda6d8bfd2c16bc39d67c2aa605bbc6abc9a06d31981cc2c2b43a
3
+ size 35125946
run-3/checkpoint-1915/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27b22bd161dc95b34777c0a39b2d0efe83e4d02ead16e416fd8ba0e5bee58cf7
3
+ size 14244
run-3/checkpoint-1915/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:827d333b5969c4f6c60e1cdde058ab219add4e3c4451a2d8b9fc8e2fd85642dc
3
+ size 1064
run-3/checkpoint-1915/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-1915/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": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-3/checkpoint-1915/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8555758683729433,
3
+ "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-3\\checkpoint-1915",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1915,
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": 2.367245739559703e-06,
14
+ "loss": 0.51,
15
+ "step": 1915
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8555758683729433,
20
+ "eval_loss": 0.493995726108551,
21
+ "eval_runtime": 10.7092,
22
+ "eval_samples_per_second": 204.311,
23
+ "eval_steps_per_second": 1.681,
24
+ "step": 1915
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 3830,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 2,
31
+ "save_steps": 500,
32
+ "total_flos": 776006954976.0,
33
+ "trial_name": null,
34
+ "trial_params": {
35
+ "learning_rate": 4.734491479119406e-06,
36
+ "num_train_epochs": 2,
37
+ "per_device_train_batch_size": 4,
38
+ "seed": 28
39
+ }
40
+ }
run-3/checkpoint-1915/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7633ff80c7b4eaa072f542d40a5cca66d3a6e795160102b0ad55e47f7982397d
3
+ size 4792
run-3/checkpoint-1915/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 sha256:802de4ab1ae5a718d0e69dba885378288d4b7dd699fc41de9ce8b3c785e2b6d4
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7633ff80c7b4eaa072f542d40a5cca66d3a6e795160102b0ad55e47f7982397d
3
  size 4792