Hugging Face's logo

dougtrajano
/
toxic-comment-classification

Text Classification
Transformers
PyTorch
Safetensors
Portuguese
bert
toxicity
portuguese
hate speech
offensive language
Generated from Trainer
Inference Endpoints
Model card Files Community
2
dougtrajano commited on
Commit
a49a044
·
1 Parent(s): 2b6befc

Training in progress, epoch 1

Browse files
Files changed (19) hide show
  1. .gitignore +1 -0
  2. config.json +40 -0
  3. last-checkpoint/config.json +40 -0
  4. last-checkpoint/optimizer.pt +3 -0
  5. last-checkpoint/pytorch_model.bin +3 -0
  6. last-checkpoint/rng_state.pth +3 -0
  7. last-checkpoint/scheduler.pt +3 -0
  8. last-checkpoint/special_tokens_map.json +7 -0
  9. last-checkpoint/tokenizer.json +0 -0
  10. last-checkpoint/tokenizer_config.json +16 -0
  11. last-checkpoint/trainer_state.json +40 -0
  12. last-checkpoint/training_args.bin +3 -0
  13. last-checkpoint/vocab.txt +0 -0
  14. pytorch_model.bin +3 -0
  15. special_tokens_map.json +7 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +16 -0
  18. training_args.bin +3 -0
  19. vocab.txt +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "neuralmind/bert-base-portuguese-cased",
3
+ "architectures": [
4
+ "ToxicityTypeForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "NOT-OFFENSIVE",
14
+ "1": "OFFENSIVE"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "NOT-OFFENSIVE": 0,
20
+ "OFFENSIVE": 1
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "bert",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "output_past": true,
28
+ "pad_token_id": 0,
29
+ "pooler_fc_size": 768,
30
+ "pooler_num_attention_heads": 12,
31
+ "pooler_num_fc_layers": 3,
32
+ "pooler_size_per_head": 128,
33
+ "pooler_type": "first_token_transform",
34
+ "position_embedding_type": "absolute",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.26.0",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 29794
40
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "neuralmind/bert-base-portuguese-cased",
3
+ "architectures": [
4
+ "ToxicityTypeForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "NOT-OFFENSIVE",
14
+ "1": "OFFENSIVE"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "NOT-OFFENSIVE": 0,
20
+ "OFFENSIVE": 1
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "bert",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "output_past": true,
28
+ "pad_token_id": 0,
29
+ "pooler_fc_size": 768,
30
+ "pooler_num_attention_heads": 12,
31
+ "pooler_num_fc_layers": 3,
32
+ "pooler_size_per_head": 128,
33
+ "pooler_type": "first_token_transform",
34
+ "position_embedding_type": "absolute",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.26.0",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 29794
40
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0493a4a8cf8f180df6b116380bce6423e3d594f2275ee32a0eca305f8e537b59
3
+ size 871513885
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dc6ef3e060899ccdefbcdbd900ff6ba7ffdd8ca39c4e90b0b7bfcad9fde7ca5
3
+ size 435769709
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:692f06c1d8ead0038ca37520dc292cc588c55b130ef4c1e037df3004fea5502f
3
+ size 14503
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74bb6545357b275e06db2c532a9dc172de544674f98c91ceb7511b4dba5bd269
3
+ size 623
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "name_or_path": "neuralmind/bert-base-portuguese-cased",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/special_tokens_map.json",
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.846971473226303,
3
+ "best_model_checkpoint": "./output/toxic-comment-classification-2023-02-12-03-38-39-438/model/checkpoint-1408",
4
+ "epoch": 1.0,
5
+ "global_step": 1408,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.36,
12
+ "learning_rate": 3.217249581414747e-05,
13
+ "loss": 0.4962,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.71,
18
+ "learning_rate": 3.1787104153700095e-05,
19
+ "loss": 0.4422,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 1.0,
24
+ "eval_accuracy": 0.8465608465608465,
25
+ "eval_f1": 0.846971473226303,
26
+ "eval_loss": 0.4196861684322357,
27
+ "eval_precision": 0.8505491368402285,
28
+ "eval_recall": 0.8465608465608465,
29
+ "eval_runtime": 14.7315,
30
+ "eval_samples_per_second": 218.104,
31
+ "eval_steps_per_second": 27.288,
32
+ "step": 1408
33
+ }
34
+ ],
35
+ "max_steps": 42240,
36
+ "num_train_epochs": 30,
37
+ "total_flos": 438284434908840.0,
38
+ "trial_name": null,
39
+ "trial_params": null
40
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c07d398af21a16d9c74ceca38be74c689e7fefb963b4f8da37b6c49e55121eea
3
+ size 3631
last-checkpoint/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dc6ef3e060899ccdefbcdbd900ff6ba7ffdd8ca39c4e90b0b7bfcad9fde7ca5
3
+ size 435769709
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "name_or_path": "neuralmind/bert-base-portuguese-cased",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/special_tokens_map.json",
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c07d398af21a16d9c74ceca38be74c689e7fefb963b4f8da37b6c49e55121eea
3
+ size 3631
vocab.txt ADDED
The diff for this file is too large to render. See raw diff