Hugging Face's logo

xuancoblab2023
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
xuancoblab2023 commited on
Commit
e7b5ed8
·
verified ·
1 Parent(s): 98cec1b

Training in progress, epoch 1

Browse files
Files changed (27) hide show
  1. logs/events.out.tfevents.1711297410.73e3a81c01ef.4225.27 +2 -2
  2. logs/events.out.tfevents.1711298266.73e3a81c01ef.4225.28 +3 -0
  3. logs/events.out.tfevents.1711298549.73e3a81c01ef.4225.29 +3 -0
  4. model.safetensors +1 -1
  5. run-27/checkpoint-576/config.json +34 -0
  6. run-27/checkpoint-576/model.safetensors +3 -0
  7. run-27/checkpoint-576/optimizer.pt +3 -0
  8. run-27/checkpoint-576/rng_state.pth +3 -0
  9. run-27/checkpoint-576/scheduler.pt +3 -0
  10. run-27/checkpoint-576/special_tokens_map.json +7 -0
  11. run-27/checkpoint-576/tokenizer.json +0 -0
  12. run-27/checkpoint-576/tokenizer_config.json +57 -0
  13. run-27/checkpoint-576/trainer_state.json +87 -0
  14. run-27/checkpoint-576/training_args.bin +3 -0
  15. run-27/checkpoint-576/vocab.txt +0 -0
  16. run-29/checkpoint-192/config.json +34 -0
  17. run-29/checkpoint-192/model.safetensors +3 -0
  18. run-29/checkpoint-192/optimizer.pt +3 -0
  19. run-29/checkpoint-192/rng_state.pth +3 -0
  20. run-29/checkpoint-192/scheduler.pt +3 -0
  21. run-29/checkpoint-192/special_tokens_map.json +7 -0
  22. run-29/checkpoint-192/tokenizer.json +0 -0
  23. run-29/checkpoint-192/tokenizer_config.json +57 -0
  24. run-29/checkpoint-192/trainer_state.json +47 -0
  25. run-29/checkpoint-192/training_args.bin +3 -0
  26. run-29/checkpoint-192/vocab.txt +0 -0
  27. training_args.bin +2 -2
logs/events.out.tfevents.1711297410.73e3a81c01ef.4225.27 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50a68e4dc5b56d1cc79faa1bd36bdefec72f737cc60011ebf4aae3ac86965e25
3
- size 6136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de60f8458fad9acdd28c8b5c8a7ebfb3d92f75b8a8e1065a257de7a03bad36c8
3
+ size 7220
logs/events.out.tfevents.1711298266.73e3a81c01ef.4225.28 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dc258b955de9fa2e8985dfd8d1e6855896bba20f1eb74a46722646ab6468bb2
3
+ size 5407
logs/events.out.tfevents.1711298549.73e3a81c01ef.4225.29 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd04eb3a8f024c5e9f7d2986e8cc3fd6c43dbc39ac0fb5469d536c1054cd4e7e
3
+ size 5406
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff4554ee453a468d8736484622640d670f45ff6a0d07577da051c4711a8fa5f0
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dca4c3b1be06dfb542a7011ce28be0c2ff7b2999e48959449b5ad02505b6a3ce
3
  size 17549312
run-27/checkpoint-576/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
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": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.39.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-27/checkpoint-576/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50c2d866a312cd874f3628764580f448cacc8bb69169297f777ee77486103c5a
3
+ size 17549312
run-27/checkpoint-576/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:444e093788e4ead6e89ef38a995401516d931b1c5319fb5a45e1f944d05ef1f5
3
+ size 35122746
run-27/checkpoint-576/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77649db78380b105203c3be0753a0a47e20be3ccd8ec2455a7d4db9d8ae85766
3
+ size 14054
run-27/checkpoint-576/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9d3e247585f7c48c2d51a84a46c4c6360d9fb77a189effbc44f0f5774ed97f7
3
+ size 1064
run-27/checkpoint-576/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
+ }
run-27/checkpoint-576/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-27/checkpoint-576/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-27/checkpoint-576/trainer_state.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8140900195694716,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-27/checkpoint-576",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 576,
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
+ "grad_norm": 5.356992244720459,
14
+ "learning_rate": 8.28536608591822e-05,
15
+ "loss": 0.547,
16
+ "step": 192
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.799412915851272,
21
+ "eval_f1": 0.820647419072616,
22
+ "eval_loss": 0.4454892873764038,
23
+ "eval_mcc": 0.6163545180480211,
24
+ "eval_precision": 0.7420886075949367,
25
+ "eval_recall": 0.9178082191780822,
26
+ "eval_runtime": 66.9011,
27
+ "eval_samples_per_second": 15.276,
28
+ "eval_steps_per_second": 0.478,
29
+ "step": 192
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 5.9460296630859375,
34
+ "learning_rate": 4.14268304295911e-05,
35
+ "loss": 0.4534,
36
+ "step": 384
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.8111545988258317,
41
+ "eval_f1": 0.8237442922374429,
42
+ "eval_loss": 0.42414745688438416,
43
+ "eval_mcc": 0.6287581698708938,
44
+ "eval_precision": 0.7722602739726028,
45
+ "eval_recall": 0.8825831702544031,
46
+ "eval_runtime": 66.3484,
47
+ "eval_samples_per_second": 15.404,
48
+ "eval_steps_per_second": 0.482,
49
+ "step": 384
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 4.355434894561768,
54
+ "learning_rate": 0.0,
55
+ "loss": 0.4285,
56
+ "step": 576
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.8140900195694716,
61
+ "eval_f1": 0.8297491039426522,
62
+ "eval_loss": 0.4249483346939087,
63
+ "eval_mcc": 0.6390860201862151,
64
+ "eval_precision": 0.7652892561983471,
65
+ "eval_recall": 0.9060665362035225,
66
+ "eval_runtime": 66.8424,
67
+ "eval_samples_per_second": 15.29,
68
+ "eval_steps_per_second": 0.479,
69
+ "step": 576
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 576,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 3,
76
+ "save_steps": 500,
77
+ "total_flos": 707085591840.0,
78
+ "train_batch_size": 16,
79
+ "trial_name": null,
80
+ "trial_params": {
81
+ "alpha": 0.8507816113188046,
82
+ "learning_rate": 0.0001242804912887733,
83
+ "num_train_epochs": 3,
84
+ "per_device_train_batch_size": 16,
85
+ "temperature": 24
86
+ }
87
+ }
run-27/checkpoint-576/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f91d80d8fa16254fc8cafbdb71abffe2e808a53378473794805afa08c4e2bbeb
3
+ size 4984
run-27/checkpoint-576/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-29/checkpoint-192/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
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": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.39.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-29/checkpoint-192/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dca4c3b1be06dfb542a7011ce28be0c2ff7b2999e48959449b5ad02505b6a3ce
3
+ size 17549312
run-29/checkpoint-192/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc1b72c87b9f57d337b4d2de8c5b1c253e96991cfc88fbd55ad2f070ec0cefa4
3
+ size 35122746
run-29/checkpoint-192/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee09ea0d216727b799a80771850b95d7d61b646360702c64b2ec889cdc725399
3
+ size 14054
run-29/checkpoint-192/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaa642c5f59c0a8deb13c3c8ce78f4fb01f2e0cc4cdb16ce98804b92f57b37e4
3
+ size 1064
run-29/checkpoint-192/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
+ }
run-29/checkpoint-192/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-29/checkpoint-192/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-29/checkpoint-192/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7827788649706457,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-29/checkpoint-192",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 192,
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
+ "grad_norm": 3.586991786956787,
14
+ "learning_rate": 3.692143561656546e-05,
15
+ "loss": 0.6017,
16
+ "step": 192
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7827788649706457,
21
+ "eval_f1": 0.8069565217391305,
22
+ "eval_loss": 0.4981837570667267,
23
+ "eval_mcc": 0.5841818055857166,
24
+ "eval_precision": 0.7261345852895149,
25
+ "eval_recall": 0.9080234833659491,
26
+ "eval_runtime": 66.722,
27
+ "eval_samples_per_second": 15.317,
28
+ "eval_steps_per_second": 0.48,
29
+ "step": 192
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 384,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 2,
36
+ "save_steps": 500,
37
+ "total_flos": 235695197280.0,
38
+ "train_batch_size": 16,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.9213628300882283,
42
+ "learning_rate": 7.384287123313092e-05,
43
+ "num_train_epochs": 2,
44
+ "per_device_train_batch_size": 16,
45
+ "temperature": 21
46
+ }
47
+ }
run-29/checkpoint-192/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:082ccacbf20ed2e5f12a8657057e2759074f79e8de35cb8d580c36b197471a5a
3
+ size 4984
run-29/checkpoint-192/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 sha256:71bb8fa8d66b34ebd7e14a9356f6426aa55d1b931f391a77c3b0cb47e80b8b88
3
- size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:082ccacbf20ed2e5f12a8657057e2759074f79e8de35cb8d580c36b197471a5a
3
+ size 4984