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
006e221
•
1 Parent(s): bfab4a6

Training in progress, epoch 1

Browse files
Files changed (24) hide show
  1. logs/events.out.tfevents.1702101568.joseph_legion.21824.2 +2 -2
  2. logs/events.out.tfevents.1702102150.joseph_legion.21824.3 +3 -0
  3. model.safetensors +1 -1
  4. run-1/checkpoint-9575/config.json +38 -0
  5. run-1/checkpoint-9575/model.safetensors +3 -0
  6. run-1/checkpoint-9575/optimizer.pt +3 -0
  7. run-1/checkpoint-9575/rng_state.pth +3 -0
  8. run-1/checkpoint-9575/scheduler.pt +3 -0
  9. run-1/checkpoint-9575/special_tokens_map.json +37 -0
  10. run-1/checkpoint-9575/tokenizer_config.json +57 -0
  11. run-1/checkpoint-9575/trainer_state.json +100 -0
  12. run-1/checkpoint-9575/training_args.bin +3 -0
  13. run-1/checkpoint-9575/vocab.txt +0 -0
  14. run-2/checkpoint-240/config.json +38 -0
  15. run-2/checkpoint-240/model.safetensors +3 -0
  16. run-2/checkpoint-240/optimizer.pt +3 -0
  17. run-2/checkpoint-240/rng_state.pth +3 -0
  18. run-2/checkpoint-240/scheduler.pt +3 -0
  19. run-2/checkpoint-240/special_tokens_map.json +37 -0
  20. run-2/checkpoint-240/tokenizer_config.json +57 -0
  21. run-2/checkpoint-240/trainer_state.json +40 -0
  22. run-2/checkpoint-240/training_args.bin +3 -0
  23. run-2/checkpoint-240/vocab.txt +0 -0
  24. training_args.bin +1 -1
logs/events.out.tfevents.1702101568.joseph_legion.21824.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:735610ff367133154ab56d387d972c4023c52850bfd1ca05b09dc85edc24f44c
3
- size 6568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b10b0efbf14425b685c9f7a2512d066efb37b4c818975cab391e3dc08312c854
3
+ size 7402
logs/events.out.tfevents.1702102150.joseph_legion.21824.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91e0bae20ce816bdf56526f61e4c5d2417a2cdd37315528a90d4d9d59ce310b2
3
+ size 5130
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77bff236d5c588141a27efba0dc721d5c68e991663a28a8dd04423161b98ca06
3
  size 17550344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa686b0b7036a0d8c4d96e00dac2aa8248e374c048ae742e20734f2c75bcbae4
3
  size 17550344
run-1/checkpoint-9575/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-1/checkpoint-9575/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac4fc4479c00813e731e0a7dd1297892c3f221f9b067b4c8aeaec5f45987de25
3
+ size 17550344
run-1/checkpoint-9575/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b08c57a75b17d91495dec50f1bca2b08b73191120b2b79b0ebde6341275b48
3
+ size 35125946
run-1/checkpoint-9575/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d0288453a326a82f4178528ce05e83c51df799804b86c504026684eb2cc0d9a
3
+ size 14308
run-1/checkpoint-9575/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34b1680328c82dbe6ac459d7d0277f7eb6bee4acaed80bc000142e9b6bf6d5f0
3
+ size 1064
run-1/checkpoint-9575/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-1/checkpoint-9575/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-1/checkpoint-9575/trainer_state.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8761425959780622,
3
+ "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-1\\checkpoint-7660",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 9575,
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": 2.623415476779745e-05,
14
+ "loss": 0.4826,
15
+ "step": 1915
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8574040219378428,
20
+ "eval_loss": 0.484986811876297,
21
+ "eval_runtime": 10.9318,
22
+ "eval_samples_per_second": 200.15,
23
+ "eval_steps_per_second": 1.647,
24
+ "step": 1915
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 1.9675616075848086e-05,
29
+ "loss": 0.4636,
30
+ "step": 3830
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8638025594149908,
35
+ "eval_loss": 0.4823402464389801,
36
+ "eval_runtime": 10.7788,
37
+ "eval_samples_per_second": 202.991,
38
+ "eval_steps_per_second": 1.67,
39
+ "step": 3830
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 1.3117077383898726e-05,
44
+ "loss": 0.4549,
45
+ "step": 5745
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8743144424131627,
50
+ "eval_loss": 0.4747394323348999,
51
+ "eval_runtime": 10.8039,
52
+ "eval_samples_per_second": 202.519,
53
+ "eval_steps_per_second": 1.666,
54
+ "step": 5745
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 6.558538691949363e-06,
59
+ "loss": 0.4488,
60
+ "step": 7660
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8761425959780622,
65
+ "eval_loss": 0.47820988297462463,
66
+ "eval_runtime": 10.9143,
67
+ "eval_samples_per_second": 200.471,
68
+ "eval_steps_per_second": 1.649,
69
+ "step": 7660
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 0.0,
74
+ "loss": 0.4448,
75
+ "step": 9575
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8747714808043876,
80
+ "eval_loss": 0.4775071442127228,
81
+ "eval_runtime": 10.6763,
82
+ "eval_samples_per_second": 204.939,
83
+ "eval_steps_per_second": 1.686,
84
+ "step": 9575
85
+ }
86
+ ],
87
+ "logging_steps": 500,
88
+ "max_steps": 9575,
89
+ "num_input_tokens_seen": 0,
90
+ "num_train_epochs": 5,
91
+ "save_steps": 500,
92
+ "total_flos": 3867947686656.0,
93
+ "trial_name": null,
94
+ "trial_params": {
95
+ "learning_rate": 3.279269345974681e-05,
96
+ "num_train_epochs": 5,
97
+ "per_device_train_batch_size": 4,
98
+ "seed": 20
99
+ }
100
+ }
run-1/checkpoint-9575/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59411321184df9b5467011aae72cb0ff2b032602f5f6a940dcbdfbe56e8e2dd1
3
+ size 4792
run-1/checkpoint-9575/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-240/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-240/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa686b0b7036a0d8c4d96e00dac2aa8248e374c048ae742e20734f2c75bcbae4
3
+ size 17550344
run-2/checkpoint-240/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:336ef7a8436d9eeaa6b7abbc3c7af29b6c5494c8ce327a53be2d0e7664990402
3
+ size 35125946
run-2/checkpoint-240/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b32d1de4d49e4ef2585a613f18541345f75c23d6cf8aed0d3fa30077a02c2817
3
+ size 14308
run-2/checkpoint-240/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c36ef0e899c983e5ab1537de0ec0d851023c6147eb612440900b85f19f17857
3
+ size 1064
run-2/checkpoint-240/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-240/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-240/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8555758683729433,
3
+ "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-2\\checkpoint-240",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 240,
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
+ "logging_steps": 500,
28
+ "max_steps": 960,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 4,
31
+ "save_steps": 500,
32
+ "total_flos": 1567795654560.0,
33
+ "trial_name": null,
34
+ "trial_params": {
35
+ "learning_rate": 3.3937670191651984e-06,
36
+ "num_train_epochs": 4,
37
+ "per_device_train_batch_size": 32,
38
+ "seed": 33
39
+ }
40
+ }
run-2/checkpoint-240/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-240/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 sha256:59411321184df9b5467011aae72cb0ff2b032602f5f6a940dcbdfbe56e8e2dd1
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:802de4ab1ae5a718d0e69dba885378288d4b7dd699fc41de9ce8b3c785e2b6d4
3
  size 4792