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
03b334a
·
verified ·
1 Parent(s): ea75c14

Training in progress, epoch 1

Browse files
Files changed (30) hide show
  1. logs/events.out.tfevents.1709470393.49ae8f4e8e7b.1647.45 +2 -2
  2. logs/events.out.tfevents.1709471211.49ae8f4e8e7b.1647.46 +3 -0
  3. logs/events.out.tfevents.1709471414.49ae8f4e8e7b.1647.47 +3 -0
  4. logs/events.out.tfevents.1709471617.49ae8f4e8e7b.1647.48 +3 -0
  5. logs/events.out.tfevents.1709471819.49ae8f4e8e7b.1647.49 +3 -0
  6. logs/events.out.tfevents.1709472021.49ae8f4e8e7b.1647.50 +3 -0
  7. model.safetensors +1 -1
  8. run-44/checkpoint-2108/config.json +34 -0
  9. run-44/checkpoint-2108/model.safetensors +3 -0
  10. run-44/checkpoint-2108/optimizer.pt +3 -0
  11. run-44/checkpoint-2108/rng_state.pth +3 -0
  12. run-44/checkpoint-2108/scheduler.pt +3 -0
  13. run-44/checkpoint-2108/special_tokens_map.json +7 -0
  14. run-44/checkpoint-2108/tokenizer.json +0 -0
  15. run-44/checkpoint-2108/tokenizer_config.json +57 -0
  16. run-44/checkpoint-2108/trainer_state.json +90 -0
  17. run-44/checkpoint-2108/training_args.bin +3 -0
  18. run-44/checkpoint-2108/vocab.txt +0 -0
  19. run-49/checkpoint-527/config.json +34 -0
  20. run-49/checkpoint-527/model.safetensors +3 -0
  21. run-49/checkpoint-527/optimizer.pt +3 -0
  22. run-49/checkpoint-527/rng_state.pth +3 -0
  23. run-49/checkpoint-527/scheduler.pt +3 -0
  24. run-49/checkpoint-527/special_tokens_map.json +7 -0
  25. run-49/checkpoint-527/tokenizer.json +0 -0
  26. run-49/checkpoint-527/tokenizer_config.json +57 -0
  27. run-49/checkpoint-527/trainer_state.json +42 -0
  28. run-49/checkpoint-527/training_args.bin +3 -0
  29. run-49/checkpoint-527/vocab.txt +0 -0
  30. training_args.bin +1 -1
logs/events.out.tfevents.1709470393.49ae8f4e8e7b.1647.45 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dcdaf8f2752661a48544b16d47a6d212bf78db87104667722be6a2c78297b550
3
- size 5714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c205690d64c445653a03e27645deda50b575685d33be2130bb0f23b46c32039
3
+ size 7136
logs/events.out.tfevents.1709471211.49ae8f4e8e7b.1647.46 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7b6b6ae4f22362535a96d7b446d755e487bdf16272d03b9b514030a90b8a375
3
+ size 5179
logs/events.out.tfevents.1709471414.49ae8f4e8e7b.1647.47 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b09a44db2f14ec0cd3a3e1eab7d0fda1f716fcb116cbf16afab939647be248e4
3
+ size 5180
logs/events.out.tfevents.1709471617.49ae8f4e8e7b.1647.48 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40a8002df1c2aa6d7dc52d8c6d618817b1b3de6560de143d8db37861dbfe1d46
3
+ size 5179
logs/events.out.tfevents.1709471819.49ae8f4e8e7b.1647.49 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daed06553e47981471f0de5d8ce8096478d066f3805d404d3d608f0313c91297
3
+ size 5179
logs/events.out.tfevents.1709472021.49ae8f4e8e7b.1647.50 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e6f6c3061a717e7d3a1d630830d408c0b77c11c00f1bb18524674a647b6c6fd
3
+ size 5180
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8efe2930f614ad256078f2988fd64ea24e58375b8e7c09361a59693733bbd411
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85449086d49e2251279915b317ae968e22d51ce351e95652f5246ce5a5e4f2be
3
  size 17549312
run-44/checkpoint-2108/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": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-44/checkpoint-2108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04fb3059eba7dc3d1e08bcc17b5b26e40aa7b40c514be5398ea8d9b2e84dbf55
3
+ size 17549312
run-44/checkpoint-2108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2de4811a3cd2ea9e968c9717e09ccc07bebb05587110235d177d9984b5885b68
3
+ size 35123898
run-44/checkpoint-2108/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:156b964b8b8d6a91ffdb147bae8680ec9176dd914174ff8673c354a99142bf22
3
+ size 14308
run-44/checkpoint-2108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8708041d58ebc578f111d22e1829d4bd50d07d66d0c9ab7aef4f173ab7c99a4
3
+ size 1064
run-44/checkpoint-2108/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-44/checkpoint-2108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-44/checkpoint-2108/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-44/checkpoint-2108/trainer_state.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8291284403669725,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-44/checkpoint-527",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2108,
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": 15.370396614074707,
14
+ "learning_rate": 0.000199328116615274,
15
+ "loss": 0.9859,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8291284403669725,
21
+ "eval_loss": 1.0127737522125244,
22
+ "eval_runtime": 2.815,
23
+ "eval_samples_per_second": 309.77,
24
+ "eval_steps_per_second": 2.487,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 7.43062162399292,
30
+ "learning_rate": 0.00013288541107684933,
31
+ "loss": 0.4754,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.8268348623853211,
37
+ "eval_loss": 1.1078842878341675,
38
+ "eval_runtime": 2.8191,
39
+ "eval_samples_per_second": 309.317,
40
+ "eval_steps_per_second": 2.483,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 44.074180603027344,
46
+ "learning_rate": 6.644270553842467e-05,
47
+ "loss": 0.3475,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8176605504587156,
53
+ "eval_loss": 1.210789442062378,
54
+ "eval_runtime": 2.8179,
55
+ "eval_samples_per_second": 309.454,
56
+ "eval_steps_per_second": 2.484,
57
+ "step": 1581
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 6.042885780334473,
62
+ "learning_rate": 0.0,
63
+ "loss": 0.2836,
64
+ "step": 2108
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.823394495412844,
69
+ "eval_loss": 1.17649245262146,
70
+ "eval_runtime": 2.8084,
71
+ "eval_samples_per_second": 310.498,
72
+ "eval_steps_per_second": 2.493,
73
+ "step": 2108
74
+ }
75
+ ],
76
+ "logging_steps": 500,
77
+ "max_steps": 2108,
78
+ "num_input_tokens_seen": 0,
79
+ "num_train_epochs": 4,
80
+ "save_steps": 500,
81
+ "total_flos": 32337743850420.0,
82
+ "train_batch_size": 128,
83
+ "trial_name": null,
84
+ "trial_params": {
85
+ "alpha": 0.6434351873812945,
86
+ "learning_rate": 0.00026577082215369866,
87
+ "num_train_epochs": 4,
88
+ "temperature": 15
89
+ }
90
+ }
run-44/checkpoint-2108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d991bc95836a675aff1d1def1fe88079b9249a92348211dab61394ffdea3d5a1
3
+ size 4984
run-44/checkpoint-2108/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-49/checkpoint-527/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": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-49/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85449086d49e2251279915b317ae968e22d51ce351e95652f5246ce5a5e4f2be
3
+ size 17549312
run-49/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89edc306bb9dbba4fad336419c0f349bf25d7f30af36458efd446576ae16fbdc
3
+ size 35123898
run-49/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a32291cb0c1329fbb9596dcc47c5d9b0d1f71ecc09dad1791e0b193314659e4
3
+ size 14308
run-49/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc4b6d30dbdd9ba7de1e279cf299b9123e11fe2f6a2f5ead0623f5353d672443
3
+ size 1064
run-49/checkpoint-527/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-49/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-49/checkpoint-527/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-49/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.841743119266055,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-49/checkpoint-527",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 527,
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": 16.317338943481445,
14
+ "learning_rate": 0.00023241919324802282,
15
+ "loss": 1.235,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.841743119266055,
21
+ "eval_loss": 1.2949353456497192,
22
+ "eval_runtime": 2.8266,
23
+ "eval_samples_per_second": 308.503,
24
+ "eval_steps_per_second": 2.477,
25
+ "step": 527
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 1581,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 3,
32
+ "save_steps": 500,
33
+ "total_flos": 8057768762220.0,
34
+ "train_batch_size": 128,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "alpha": 0.4445543641350709,
38
+ "learning_rate": 0.00034862878987203423,
39
+ "num_train_epochs": 3,
40
+ "temperature": 27
41
+ }
42
+ }
run-49/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:479b8a380a005811d966d493b2276d97715440d980a1b8891abdd0e2823c1947
3
+ size 4984
run-49/checkpoint-527/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:d991bc95836a675aff1d1def1fe88079b9249a92348211dab61394ffdea3d5a1
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:479b8a380a005811d966d493b2276d97715440d980a1b8891abdd0e2823c1947
3
  size 4984