Hugging Face's logo

sibstrider
/
rubert-tiny2-finetuned-classification

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
sibstrider commited on
Commit
8dd0c9c
•
1 Parent(s): 0557a78

Training in progress, epoch 1

Browse files
Files changed (28) hide show
  1. model.safetensors +1 -1
  2. run-14/checkpoint-138/config.json +54 -0
  3. run-14/checkpoint-138/model.safetensors +3 -0
  4. run-14/checkpoint-138/optimizer.pt +3 -0
  5. run-14/checkpoint-138/rng_state.pth +3 -0
  6. run-14/checkpoint-138/scheduler.pt +3 -0
  7. run-14/checkpoint-138/special_tokens_map.json +37 -0
  8. run-14/checkpoint-138/tokenizer.json +0 -0
  9. run-14/checkpoint-138/tokenizer_config.json +64 -0
  10. run-14/checkpoint-138/trainer_state.json +35 -0
  11. run-14/checkpoint-138/training_args.bin +3 -0
  12. run-14/checkpoint-138/vocab.txt +0 -0
  13. run-16/checkpoint-138/config.json +54 -0
  14. run-16/checkpoint-138/model.safetensors +3 -0
  15. run-16/checkpoint-138/optimizer.pt +3 -0
  16. run-16/checkpoint-138/rng_state.pth +3 -0
  17. run-16/checkpoint-138/scheduler.pt +3 -0
  18. run-16/checkpoint-138/special_tokens_map.json +37 -0
  19. run-16/checkpoint-138/tokenizer.json +0 -0
  20. run-16/checkpoint-138/tokenizer_config.json +64 -0
  21. run-16/checkpoint-138/trainer_state.json +35 -0
  22. run-16/checkpoint-138/training_args.bin +3 -0
  23. run-16/checkpoint-138/vocab.txt +0 -0
  24. runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705274264.DESKTOP-RFEED41.20976.29 +3 -0
  25. runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705274337.DESKTOP-RFEED41.20976.30 +3 -0
  26. runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705274491.DESKTOP-RFEED41.20976.31 +3 -0
  27. runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705274567.DESKTOP-RFEED41.20976.32 +3 -0
  28. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:118018f1532ea28ce419b2344b3bfd47216b78c4bb9b21ea5014bd54536f9bb6
3
  size 116795404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0533c3fe8dfe17c272b839a843414d0888d824d931ca8fdcef9270a7d96f4e40
3
  size 116795404
run-14/checkpoint-138/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cointegrated/rubert-tiny2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "emb_size": 312,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 600,
28
+ "label2id": {
29
+ "LABEL_0": 0,
30
+ "LABEL_1": 1,
31
+ "LABEL_10": 10,
32
+ "LABEL_2": 2,
33
+ "LABEL_3": 3,
34
+ "LABEL_4": 4,
35
+ "LABEL_5": 5,
36
+ "LABEL_6": 6,
37
+ "LABEL_7": 7,
38
+ "LABEL_8": 8,
39
+ "LABEL_9": 9
40
+ },
41
+ "layer_norm_eps": 1e-12,
42
+ "max_position_embeddings": 2048,
43
+ "model_type": "bert",
44
+ "num_attention_heads": 12,
45
+ "num_hidden_layers": 3,
46
+ "pad_token_id": 0,
47
+ "position_embedding_type": "absolute",
48
+ "problem_type": "single_label_classification",
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.36.2",
51
+ "type_vocab_size": 2,
52
+ "use_cache": true,
53
+ "vocab_size": 83828
54
+ }
run-14/checkpoint-138/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff1129238a24bcb1f446afaf930fc327ffd0c5bb25c30bcd86b9a865064f455
3
+ size 116795404
run-14/checkpoint-138/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0b39ed09a272c0599bb862897badfc56191f8634b0993d8c6199bd4a79d5fdf
3
+ size 233621882
run-14/checkpoint-138/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bafce39aa454f1d6548cc2ab0f8f998dc40890be04bf6eeb82c29e1a2f5786d7
3
+ size 13990
run-14/checkpoint-138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca500209d286209bf5d43feb199fe766937fafe3a17bac2066410d5475012c0
3
+ size 1064
run-14/checkpoint-138/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-14/checkpoint-138/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-138/tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
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
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 512,
50
+ "model_max_length": 2048,
51
+ "never_split": null,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "stride": 0,
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]"
64
+ }
run-14/checkpoint-138/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8367346938775511,
3
+ "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-14\\checkpoint-138",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 138,
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_accuracy": 0.8367346938775511,
14
+ "eval_loss": 1.0891972780227661,
15
+ "eval_runtime": 1.414,
16
+ "eval_samples_per_second": 173.267,
17
+ "eval_steps_per_second": 11.315,
18
+ "step": 138
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 690,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 5,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 16,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 4.990356799262781e-05,
31
+ "num_train_epochs": 5,
32
+ "per_device_train_batch_size": 16,
33
+ "seed": 35
34
+ }
35
+ }
run-14/checkpoint-138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:281ff2cee775dc43400bae86d21c89e40b9d059b5e4a759d8bef15e642db36b2
3
+ size 4728
run-14/checkpoint-138/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-16/checkpoint-138/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cointegrated/rubert-tiny2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "emb_size": 312,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 600,
28
+ "label2id": {
29
+ "LABEL_0": 0,
30
+ "LABEL_1": 1,
31
+ "LABEL_10": 10,
32
+ "LABEL_2": 2,
33
+ "LABEL_3": 3,
34
+ "LABEL_4": 4,
35
+ "LABEL_5": 5,
36
+ "LABEL_6": 6,
37
+ "LABEL_7": 7,
38
+ "LABEL_8": 8,
39
+ "LABEL_9": 9
40
+ },
41
+ "layer_norm_eps": 1e-12,
42
+ "max_position_embeddings": 2048,
43
+ "model_type": "bert",
44
+ "num_attention_heads": 12,
45
+ "num_hidden_layers": 3,
46
+ "pad_token_id": 0,
47
+ "position_embedding_type": "absolute",
48
+ "problem_type": "single_label_classification",
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.36.2",
51
+ "type_vocab_size": 2,
52
+ "use_cache": true,
53
+ "vocab_size": 83828
54
+ }
run-16/checkpoint-138/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0533c3fe8dfe17c272b839a843414d0888d824d931ca8fdcef9270a7d96f4e40
3
+ size 116795404
run-16/checkpoint-138/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32b03ac02838f628269429175f25b0118ad13183799f8aa73955116f32d0c53e
3
+ size 233621882
run-16/checkpoint-138/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eea7185f7e6884bf3ce22aeb6f7919826a7b65c0344bd569a9d32eadbc4fe57a
3
+ size 14054
run-16/checkpoint-138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:444371054c1682545de938b90fdaef6ef10a3a7341e3791244f7ec0597ef150f
3
+ size 1064
run-16/checkpoint-138/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-16/checkpoint-138/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-16/checkpoint-138/tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
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
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 512,
50
+ "model_max_length": 2048,
51
+ "never_split": null,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "stride": 0,
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]"
64
+ }
run-16/checkpoint-138/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8530612244897959,
3
+ "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-16\\checkpoint-138",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 138,
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_accuracy": 0.8530612244897959,
14
+ "eval_loss": 0.852445125579834,
15
+ "eval_runtime": 1.294,
16
+ "eval_samples_per_second": 189.336,
17
+ "eval_steps_per_second": 12.365,
18
+ "step": 138
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 690,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 5,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 16,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 6.872788644651594e-05,
31
+ "num_train_epochs": 5,
32
+ "per_device_train_batch_size": 16,
33
+ "seed": 30
34
+ }
35
+ }
run-16/checkpoint-138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f67b06e21a6870fd2733594aa91c9dd238faa0664a8c718b6b9172b39f108cb0
3
+ size 4728
run-16/checkpoint-138/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705274264.DESKTOP-RFEED41.20976.29 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbd665d85fc23c128ea2e5a12af76a8956fd2dd76357ac846e4354c6c8bfef66
3
+ size 5276
runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705274337.DESKTOP-RFEED41.20976.30 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f22251f545a734d68fac48ae631264752c5ca63d0978c79933560ecbe5182c3
3
+ size 5598
runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705274491.DESKTOP-RFEED41.20976.31 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1800790389cfdb1c9c497b01dc07f0c8cf36f65074de9a5d1289bf4e10b93544
3
+ size 5276
runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705274567.DESKTOP-RFEED41.20976.32 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c20784b6fc96ba965e3f44d55acde58f2f47f3d724f41b6a1b584761675f16ab
3
+ size 5598
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a063ad752c2d132e20523b12b9bfcca65dcaf9dbe52f3f12fda681d921f569dd
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f67b06e21a6870fd2733594aa91c9dd238faa0664a8c718b6b9172b39f108cb0
3
  size 4728