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
40a8f30
•
1 Parent(s): c9dd73b

Training in progress, epoch 1

Browse files
Files changed (24) hide show
  1. logs/events.out.tfevents.1702102547.joseph_legion.21824.5 +2 -2
  2. logs/events.out.tfevents.1702102715.joseph_legion.21824.6 +3 -0
  3. model.safetensors +1 -1
  4. run-4/checkpoint-1916/config.json +38 -0
  5. run-4/checkpoint-1916/model.safetensors +3 -0
  6. run-4/checkpoint-1916/optimizer.pt +3 -0
  7. run-4/checkpoint-1916/rng_state.pth +3 -0
  8. run-4/checkpoint-1916/scheduler.pt +3 -0
  9. run-4/checkpoint-1916/special_tokens_map.json +37 -0
  10. run-4/checkpoint-1916/tokenizer_config.json +57 -0
  11. run-4/checkpoint-1916/trainer_state.json +85 -0
  12. run-4/checkpoint-1916/training_args.bin +3 -0
  13. run-4/checkpoint-1916/vocab.txt +0 -0
  14. run-5/checkpoint-958/config.json +38 -0
  15. run-5/checkpoint-958/model.safetensors +3 -0
  16. run-5/checkpoint-958/optimizer.pt +3 -0
  17. run-5/checkpoint-958/rng_state.pth +3 -0
  18. run-5/checkpoint-958/scheduler.pt +3 -0
  19. run-5/checkpoint-958/special_tokens_map.json +37 -0
  20. run-5/checkpoint-958/tokenizer_config.json +57 -0
  21. run-5/checkpoint-958/trainer_state.json +40 -0
  22. run-5/checkpoint-958/training_args.bin +3 -0
  23. run-5/checkpoint-958/vocab.txt +0 -0
  24. training_args.bin +1 -1
logs/events.out.tfevents.1702102547.joseph_legion.21824.5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0370111359ed057e18327442e6e40b1dd9edcdfdc0baba263f0445e44c41c74b
3
- size 6089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2cebd7a61ce101abc8b93c62d1bdd2e0920fc2b215465cdd0ecf42231cd723a
3
+ size 6923
logs/events.out.tfevents.1702102715.joseph_legion.21824.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e25a4744b6d4ab753b39ad9f7074f4871fdb2788b2e6f497f6099008e8ba3ee2
3
+ size 5129
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af7c828b9e0d414dcb6de96df8371a5c093dcaf9bc4a71ffedb0304dd569b3a6
3
  size 17550344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b86791d5630e18e657bfe0101afeb873a95dd92ff218aaa3c8933c134dfc711f
3
  size 17550344
run-4/checkpoint-1916/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-4/checkpoint-1916/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f2c7cf9bfbf60c73deb18778c5737a6092dcbfee1522cea3611025a4b1e7db2
3
+ size 17550344
run-4/checkpoint-1916/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f22e58bad34199a4b083feef6cd060c7424da6a460447f9ba1f14c9ffeff8824
3
+ size 35125946
run-4/checkpoint-1916/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8cf9cfe283cf67a92e690b090fab3d7f585bb362c5bd1b23ed3c7c56ae2325a
3
+ size 14308
run-4/checkpoint-1916/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d8c874f9ba99beaf6d6edb74f05ead12f00eccbcbe66b8393268f755cd746f
3
+ size 1064
run-4/checkpoint-1916/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-1916/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-4/checkpoint-1916/trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8555758683729433,
3
+ "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-4\\checkpoint-479",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1916,
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": 2.3576485733382427e-06,
14
+ "loss": 0.6038,
15
+ "step": 479
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8555758683729433,
20
+ "eval_loss": 0.5434475541114807,
21
+ "eval_runtime": 10.704,
22
+ "eval_samples_per_second": 204.409,
23
+ "eval_steps_per_second": 1.682,
24
+ "step": 479
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 1.5717657155588285e-06,
29
+ "loss": 0.5237,
30
+ "step": 958
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8555758683729433,
35
+ "eval_loss": 0.5071110129356384,
36
+ "eval_runtime": 10.7179,
37
+ "eval_samples_per_second": 204.144,
38
+ "eval_steps_per_second": 1.679,
39
+ "step": 958
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 7.858828577794142e-07,
44
+ "loss": 0.5001,
45
+ "step": 1437
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8555758683729433,
50
+ "eval_loss": 0.49807029962539673,
51
+ "eval_runtime": 10.7711,
52
+ "eval_samples_per_second": 203.135,
53
+ "eval_steps_per_second": 1.671,
54
+ "step": 1437
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 0.0,
59
+ "loss": 0.4937,
60
+ "step": 1916
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8555758683729433,
65
+ "eval_loss": 0.4962950348854065,
66
+ "eval_runtime": 10.8837,
67
+ "eval_samples_per_second": 201.035,
68
+ "eval_steps_per_second": 1.654,
69
+ "step": 1916
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 1916,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 4,
76
+ "save_steps": 500,
77
+ "total_flos": 4971845463840.0,
78
+ "trial_name": null,
79
+ "trial_params": {
80
+ "learning_rate": 3.143531431117657e-06,
81
+ "num_train_epochs": 4,
82
+ "per_device_train_batch_size": 16,
83
+ "seed": 14
84
+ }
85
+ }
run-4/checkpoint-1916/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe110279ecafae57f087678dca7b97c6b919bc8d623f5ffd90d09edc10788438
3
+ size 4792
run-4/checkpoint-1916/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-958/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-5/checkpoint-958/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b86791d5630e18e657bfe0101afeb873a95dd92ff218aaa3c8933c134dfc711f
3
+ size 17550344
run-5/checkpoint-958/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ce2023895577353285a4527ab6c63123af3ae54b0cdf78af0237faadb4bc496
3
+ size 35125946
run-5/checkpoint-958/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c28b8d8c2a585540ff8b5d4cd48c5af19f612d0d45d0a5fe35b26ff51643d5f
3
+ size 14308
run-5/checkpoint-958/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bd7d26c5d66245d89dcc568ded9946c461f90e84b1a74e47f0e45cbfd3b5dcf
3
+ size 1064
run-5/checkpoint-958/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-5/checkpoint-958/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-5/checkpoint-958/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8555758683729433,
3
+ "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-5\\checkpoint-958",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 958,
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": 1.3151780085887827e-05,
14
+ "loss": 0.4979,
15
+ "step": 958
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8555758683729433,
20
+ "eval_loss": 0.48700252175331116,
21
+ "eval_runtime": 10.7411,
22
+ "eval_samples_per_second": 203.703,
23
+ "eval_steps_per_second": 1.676,
24
+ "step": 958
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 3832,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 4,
31
+ "save_steps": 500,
32
+ "total_flos": 981566909760.0,
33
+ "trial_name": null,
34
+ "trial_params": {
35
+ "learning_rate": 1.7535706781183768e-05,
36
+ "num_train_epochs": 4,
37
+ "per_device_train_batch_size": 8,
38
+ "seed": 17
39
+ }
40
+ }
run-5/checkpoint-958/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d62a2892c289bfba720cfa14c57d0a1acaceeec92177b2eddad453a6ac795e20
3
+ size 4792
run-5/checkpoint-958/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:fe110279ecafae57f087678dca7b97c6b919bc8d623f5ffd90d09edc10788438
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d62a2892c289bfba720cfa14c57d0a1acaceeec92177b2eddad453a6ac795e20
3
  size 4792