Hugging Face's logo

Doowon96
/
roberta-base-finetuned-hate_speech

Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
Doowon96 commited on
Commit
c6c9eae
•
1 Parent(s): 8bac8e9

Training in progress, epoch 4

Browse files
Files changed (23) hide show
  1. model.safetensors +1 -1
  2. run-2/checkpoint-261/config.json +40 -0
  3. run-2/checkpoint-261/model.safetensors +3 -0
  4. run-2/checkpoint-261/optimizer.pt +3 -0
  5. run-2/checkpoint-261/rng_state.pth +3 -0
  6. run-2/checkpoint-261/scheduler.pt +3 -0
  7. run-2/checkpoint-261/special_tokens_map.json +51 -0
  8. run-2/checkpoint-261/tokenizer.json +0 -0
  9. run-2/checkpoint-261/tokenizer_config.json +59 -0
  10. run-2/checkpoint-261/trainer_state.json +53 -0
  11. run-2/checkpoint-261/training_args.bin +3 -0
  12. run-2/checkpoint-261/vocab.txt +0 -0
  13. run-2/checkpoint-348/config.json +40 -0
  14. run-2/checkpoint-348/model.safetensors +3 -0
  15. run-2/checkpoint-348/optimizer.pt +3 -0
  16. run-2/checkpoint-348/rng_state.pth +3 -0
  17. run-2/checkpoint-348/scheduler.pt +3 -0
  18. run-2/checkpoint-348/special_tokens_map.json +51 -0
  19. run-2/checkpoint-348/tokenizer.json +0 -0
  20. run-2/checkpoint-348/tokenizer_config.json +59 -0
  21. run-2/checkpoint-348/trainer_state.json +62 -0
  22. run-2/checkpoint-348/training_args.bin +3 -0
  23. run-2/checkpoint-348/vocab.txt +0 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b628dba522c4d3946db6e2e87de5f11ceb5c93256bcd55a84125f853ed7d7bc5
3
  size 442505820
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b3ed690b4b53c40dd40d9228d24739afb1d140a1cae991426c7d3e2aaf5af9e
3
  size 442505820
run-2/checkpoint-261/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "klue/roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "LABEL_0": 0,
23
+ "LABEL_1": 1,
24
+ "LABEL_2": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "tokenizer_class": "BertTokenizer",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.37.2",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 32000
40
+ }
run-2/checkpoint-261/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdee298287c6ad29bc4435997109f63fc60107afc72033b77b9fb5fc893286fc
3
+ size 442505820
run-2/checkpoint-261/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e33d6debbf7df14b733048d856ffa49814ff37ea5843bc99bf0544a7810d75ce
3
+ size 885131514
run-2/checkpoint-261/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52fc88124d0c2e2b5936cd1006d8a680e5fd5e033b0d82aa43598e051a79194c
3
+ size 14244
run-2/checkpoint-261/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cde05869d38d08830bb18e44f9cd0cd3596472f4e1ad5b6933ef5f5ce376e3e4
3
+ size 1064
run-2/checkpoint-261/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
run-2/checkpoint-261/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-261/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[CLS]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[PAD]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": false,
49
+ "eos_token": "[SEP]",
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
run-2/checkpoint-261/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6193320854823038,
3
+ "best_model_checkpoint": "test-klue/ynat/run-2/checkpoint-261",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 261,
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
+ "eval_f1": 0.5269240698183681,
14
+ "eval_loss": 0.9749890565872192,
15
+ "eval_runtime": 9.3462,
16
+ "eval_samples_per_second": 253.471,
17
+ "eval_steps_per_second": 2.033,
18
+ "step": 87
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_f1": 0.5891366613697401,
23
+ "eval_loss": 0.8359125852584839,
24
+ "eval_runtime": 9.3824,
25
+ "eval_samples_per_second": 252.493,
26
+ "eval_steps_per_second": 2.025,
27
+ "step": 174
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_f1": 0.6193320854823038,
32
+ "eval_loss": 0.9428530335426331,
33
+ "eval_runtime": 9.3908,
34
+ "eval_samples_per_second": 252.268,
35
+ "eval_steps_per_second": 2.023,
36
+ "step": 261
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 348,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 4,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 64,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 8.256323465193199e-05,
49
+ "num_train_epochs": 4,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 15
52
+ }
53
+ }
run-2/checkpoint-261/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22ed46b6856ccf8084e8eeeb98144e5a1eaa32c607cf0974675c4becd0d7ce66
3
+ size 4728
run-2/checkpoint-261/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-348/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "klue/roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "LABEL_0": 0,
23
+ "LABEL_1": 1,
24
+ "LABEL_2": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "tokenizer_class": "BertTokenizer",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.37.2",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 32000
40
+ }
run-2/checkpoint-348/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b3ed690b4b53c40dd40d9228d24739afb1d140a1cae991426c7d3e2aaf5af9e
3
+ size 442505820
run-2/checkpoint-348/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:468328d171eacee97a3bea3d17c8eb338d7baf0ad538efb7bddfab77e354535b
3
+ size 885131514
run-2/checkpoint-348/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8da90ff33bfa558a4ce1c6bdf4c6bbe156f628d3afeb2bc64657ed3bfd57ae8f
3
+ size 14244
run-2/checkpoint-348/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae105909bbd022bb0f6c91694afba17bdb7b65bfa2b55d028be95c3b1230c92a
3
+ size 1064
run-2/checkpoint-348/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
run-2/checkpoint-348/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-348/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[CLS]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[PAD]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": false,
49
+ "eos_token": "[SEP]",
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
run-2/checkpoint-348/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6314101444719962,
3
+ "best_model_checkpoint": "test-klue/ynat/run-2/checkpoint-348",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 348,
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
+ "eval_f1": 0.5269240698183681,
14
+ "eval_loss": 0.9749890565872192,
15
+ "eval_runtime": 9.3462,
16
+ "eval_samples_per_second": 253.471,
17
+ "eval_steps_per_second": 2.033,
18
+ "step": 87
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_f1": 0.5891366613697401,
23
+ "eval_loss": 0.8359125852584839,
24
+ "eval_runtime": 9.3824,
25
+ "eval_samples_per_second": 252.493,
26
+ "eval_steps_per_second": 2.025,
27
+ "step": 174
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_f1": 0.6193320854823038,
32
+ "eval_loss": 0.9428530335426331,
33
+ "eval_runtime": 9.3908,
34
+ "eval_samples_per_second": 252.268,
35
+ "eval_steps_per_second": 2.023,
36
+ "step": 261
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_f1": 0.6314101444719962,
41
+ "eval_loss": 1.1509172916412354,
42
+ "eval_runtime": 9.4376,
43
+ "eval_samples_per_second": 251.016,
44
+ "eval_steps_per_second": 2.013,
45
+ "step": 348
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 348,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 4,
52
+ "save_steps": 500,
53
+ "total_flos": 0,
54
+ "train_batch_size": 64,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 8.256323465193199e-05,
58
+ "num_train_epochs": 4,
59
+ "per_device_train_batch_size": 64,
60
+ "seed": 15
61
+ }
62
+ }
run-2/checkpoint-348/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22ed46b6856ccf8084e8eeeb98144e5a1eaa32c607cf0974675c4becd0d7ce66
3
+ size 4728
run-2/checkpoint-348/vocab.txt ADDED
The diff for this file is too large to render. See raw diff