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
513accd
•
1 Parent(s): 92f4c4f

Training in progress, epoch 3

Browse files
Files changed (23) hide show
  1. model.safetensors +1 -1
  2. run-4/checkpoint-1038/config.json +40 -0
  3. run-4/checkpoint-1038/model.safetensors +3 -0
  4. run-4/checkpoint-1038/optimizer.pt +3 -0
  5. run-4/checkpoint-1038/rng_state.pth +3 -0
  6. run-4/checkpoint-1038/scheduler.pt +3 -0
  7. run-4/checkpoint-1038/special_tokens_map.json +51 -0
  8. run-4/checkpoint-1038/tokenizer.json +0 -0
  9. run-4/checkpoint-1038/tokenizer_config.json +59 -0
  10. run-4/checkpoint-1038/trainer_state.json +65 -0
  11. run-4/checkpoint-1038/training_args.bin +3 -0
  12. run-4/checkpoint-1038/vocab.txt +0 -0
  13. run-4/checkpoint-692/config.json +40 -0
  14. run-4/checkpoint-692/model.safetensors +3 -0
  15. run-4/checkpoint-692/optimizer.pt +3 -0
  16. run-4/checkpoint-692/rng_state.pth +3 -0
  17. run-4/checkpoint-692/scheduler.pt +3 -0
  18. run-4/checkpoint-692/special_tokens_map.json +51 -0
  19. run-4/checkpoint-692/tokenizer.json +0 -0
  20. run-4/checkpoint-692/tokenizer_config.json +59 -0
  21. run-4/checkpoint-692/trainer_state.json +50 -0
  22. run-4/checkpoint-692/training_args.bin +3 -0
  23. run-4/checkpoint-692/vocab.txt +0 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c639803864668b00e1fb9129c2f13d6b653c444bcfd0e96b0cd8f093e038f0ef
3
  size 442505820
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07b67f7f1e862d1899d48851163115c3a67fa577cad2a9e1b461635dd9e15284
3
  size 442505820
run-4/checkpoint-1038/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-4/checkpoint-1038/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07b67f7f1e862d1899d48851163115c3a67fa577cad2a9e1b461635dd9e15284
3
+ size 442505820
run-4/checkpoint-1038/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4af1cf9a4a76ae39fc68bc30eb69d4bf6f8dd63bc8edc53e51655b093b8bdff0
3
+ size 885131514
run-4/checkpoint-1038/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28d7d551d32a0f6d2e99995aec6101a90914579e7af1e8b919ed3595ecd01e53
3
+ size 14244
run-4/checkpoint-1038/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc7a3deeb6ff70b463a94c95b0d8f819fd22f44a9ea5ef85e44edcd8967cf9a5
3
+ size 1064
run-4/checkpoint-1038/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-4/checkpoint-1038/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-1038/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-4/checkpoint-1038/trainer_state.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6359803825635763,
3
+ "best_model_checkpoint": "test-klue/ynat/run-4/checkpoint-692",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1038,
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": 0.6349053963006231,
14
+ "eval_loss": 0.8050844669342041,
15
+ "eval_runtime": 9.4523,
16
+ "eval_samples_per_second": 250.626,
17
+ "eval_steps_per_second": 2.01,
18
+ "step": 346
19
+ },
20
+ {
21
+ "epoch": 1.45,
22
+ "learning_rate": 1.5458921984247287e-05,
23
+ "loss": 0.7983,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_f1": 0.6359803825635763,
29
+ "eval_loss": 0.820810079574585,
30
+ "eval_runtime": 9.5072,
31
+ "eval_samples_per_second": 249.181,
32
+ "eval_steps_per_second": 1.998,
33
+ "step": 692
34
+ },
35
+ {
36
+ "epoch": 2.89,
37
+ "learning_rate": 6.7151878302612646e-06,
38
+ "loss": 0.5122,
39
+ "step": 1000
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "eval_f1": 0.6358373590219538,
44
+ "eval_loss": 0.9183709025382996,
45
+ "eval_runtime": 9.5449,
46
+ "eval_samples_per_second": 248.195,
47
+ "eval_steps_per_second": 1.991,
48
+ "step": 1038
49
+ }
50
+ ],
51
+ "logging_steps": 500,
52
+ "max_steps": 1384,
53
+ "num_input_tokens_seen": 0,
54
+ "num_train_epochs": 4,
55
+ "save_steps": 500,
56
+ "total_flos": 673157179094904.0,
57
+ "train_batch_size": 16,
58
+ "trial_name": null,
59
+ "trial_params": {
60
+ "learning_rate": 2.402778145515359e-05,
61
+ "num_train_epochs": 4,
62
+ "per_device_train_batch_size": 16,
63
+ "seed": 12
64
+ }
65
+ }
run-4/checkpoint-1038/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46c1f7acf9dfb60e3287c48b224e7f5c73404535f43b5b6b6065999408ced52a
3
+ size 4728
run-4/checkpoint-1038/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-692/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-4/checkpoint-692/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c543705023e920bdbbc7f1a5a98e97493197550fed3e3cd7eb1f8b156168665a
3
+ size 442505820
run-4/checkpoint-692/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b66225f53b8716a4ea6217ec233d1ab36b669ce26be5f2044804bc364b8467f
3
+ size 885131514
run-4/checkpoint-692/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac904407f284e00f98c9fbdc98dc5241a0c1ef008673d8c78ecf2b3e6bfdc8d6
3
+ size 14244
run-4/checkpoint-692/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3829f86d52cd5e5d71ced22e030e3aa9751eeb660166a6454e900122875ead0
3
+ size 1064
run-4/checkpoint-692/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-4/checkpoint-692/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-692/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-4/checkpoint-692/trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6359803825635763,
3
+ "best_model_checkpoint": "test-klue/ynat/run-4/checkpoint-692",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 692,
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": 0.6349053963006231,
14
+ "eval_loss": 0.8050844669342041,
15
+ "eval_runtime": 9.4523,
16
+ "eval_samples_per_second": 250.626,
17
+ "eval_steps_per_second": 2.01,
18
+ "step": 346
19
+ },
20
+ {
21
+ "epoch": 1.45,
22
+ "learning_rate": 1.5458921984247287e-05,
23
+ "loss": 0.7983,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_f1": 0.6359803825635763,
29
+ "eval_loss": 0.820810079574585,
30
+ "eval_runtime": 9.5072,
31
+ "eval_samples_per_second": 249.181,
32
+ "eval_steps_per_second": 1.998,
33
+ "step": 692
34
+ }
35
+ ],
36
+ "logging_steps": 500,
37
+ "max_steps": 1384,
38
+ "num_input_tokens_seen": 0,
39
+ "num_train_epochs": 4,
40
+ "save_steps": 500,
41
+ "total_flos": 336578589547452.0,
42
+ "train_batch_size": 16,
43
+ "trial_name": null,
44
+ "trial_params": {
45
+ "learning_rate": 2.402778145515359e-05,
46
+ "num_train_epochs": 4,
47
+ "per_device_train_batch_size": 16,
48
+ "seed": 12
49
+ }
50
+ }
run-4/checkpoint-692/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46c1f7acf9dfb60e3287c48b224e7f5c73404535f43b5b6b6065999408ced52a
3
+ size 4728
run-4/checkpoint-692/vocab.txt ADDED
The diff for this file is too large to render. See raw diff