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
8cdaf90
·
verified ·
1 Parent(s): d164e5a

Training in progress, epoch 4

Browse files
Files changed (24) hide show
  1. logs/events.out.tfevents.1711303658.73e3a81c01ef.4225.40 +2 -2
  2. model.safetensors +1 -1
  3. run-40/checkpoint-576/config.json +34 -0
  4. run-40/checkpoint-576/model.safetensors +3 -0
  5. run-40/checkpoint-576/optimizer.pt +3 -0
  6. run-40/checkpoint-576/rng_state.pth +3 -0
  7. run-40/checkpoint-576/scheduler.pt +3 -0
  8. run-40/checkpoint-576/special_tokens_map.json +7 -0
  9. run-40/checkpoint-576/tokenizer.json +0 -0
  10. run-40/checkpoint-576/tokenizer_config.json +57 -0
  11. run-40/checkpoint-576/trainer_state.json +87 -0
  12. run-40/checkpoint-576/training_args.bin +3 -0
  13. run-40/checkpoint-576/vocab.txt +0 -0
  14. run-40/checkpoint-768/config.json +34 -0
  15. run-40/checkpoint-768/model.safetensors +3 -0
  16. run-40/checkpoint-768/optimizer.pt +3 -0
  17. run-40/checkpoint-768/rng_state.pth +3 -0
  18. run-40/checkpoint-768/scheduler.pt +3 -0
  19. run-40/checkpoint-768/special_tokens_map.json +7 -0
  20. run-40/checkpoint-768/tokenizer.json +0 -0
  21. run-40/checkpoint-768/tokenizer_config.json +57 -0
  22. run-40/checkpoint-768/trainer_state.json +107 -0
  23. run-40/checkpoint-768/training_args.bin +3 -0
  24. run-40/checkpoint-768/vocab.txt +0 -0
logs/events.out.tfevents.1711303658.73e3a81c01ef.4225.40 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82c5f69ae216a616f941bb46f34370e99cdfd2513216ecf25457a837c07392a7
3
- size 6137
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:578c381698a9a3254ec80943cef7f430574a3120751ce8041379ba16ba9db3c6
3
+ size 7951
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:158533c35625b9e9d25d3aa7d4b48746ba755baddd1c9d510e7d1c7c5d747968
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37b46f809be7637226b117d7d5fd64179492b64b28949537075c7d42ad6ee5ef
3
  size 17549312
run-40/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-40/checkpoint-576/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4588862ad65b73f975f4f0eca6705737c92ff535e5ede4395cfcd6fd0e278f0
3
+ size 17549312
run-40/checkpoint-576/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dc69e560f84f686e8e41911ac41a5fa58f038b4cecb6918e1120a0654882162
3
+ size 35122746
run-40/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-40/checkpoint-576/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f0d87c1cd5a368c99af3e09fa8ab0376c34d4d3c1832f0ba6334471058720f
3
+ size 1064
run-40/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-40/checkpoint-576/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-40/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-40/checkpoint-576/trainer_state.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.815068493150685,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-40/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": 7.570804595947266,
14
+ "learning_rate": 9.127982348433665e-05,
15
+ "loss": 0.5774,
16
+ "step": 192
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8033268101761253,
21
+ "eval_f1": 0.8222811671087534,
22
+ "eval_loss": 0.45489490032196045,
23
+ "eval_mcc": 0.6209445541298213,
24
+ "eval_precision": 0.75,
25
+ "eval_recall": 0.9099804305283757,
26
+ "eval_runtime": 67.0612,
27
+ "eval_samples_per_second": 15.24,
28
+ "eval_steps_per_second": 0.477,
29
+ "step": 192
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 12.614089012145996,
34
+ "learning_rate": 6.0853215656224434e-05,
35
+ "loss": 0.4642,
36
+ "step": 384
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.8091976516634051,
41
+ "eval_f1": 0.8202764976958525,
42
+ "eval_loss": 0.4278040826320648,
43
+ "eval_mcc": 0.6231493257080627,
44
+ "eval_precision": 0.7752613240418118,
45
+ "eval_recall": 0.8708414872798435,
46
+ "eval_runtime": 66.8566,
47
+ "eval_samples_per_second": 15.286,
48
+ "eval_steps_per_second": 0.479,
49
+ "step": 384
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 5.883197784423828,
54
+ "learning_rate": 3.0426607828112217e-05,
55
+ "loss": 0.4308,
56
+ "step": 576
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.815068493150685,
61
+ "eval_f1": 0.8280254777070064,
62
+ "eval_loss": 0.4256427586078644,
63
+ "eval_mcc": 0.6374150947947472,
64
+ "eval_precision": 0.7738095238095238,
65
+ "eval_recall": 0.8904109589041096,
66
+ "eval_runtime": 66.4637,
67
+ "eval_samples_per_second": 15.377,
68
+ "eval_steps_per_second": 0.481,
69
+ "step": 576
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 768,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 4,
76
+ "save_steps": 500,
77
+ "total_flos": 707085591840.0,
78
+ "train_batch_size": 16,
79
+ "trial_name": null,
80
+ "trial_params": {
81
+ "alpha": 0.9602502972445941,
82
+ "learning_rate": 0.00012170643131244887,
83
+ "num_train_epochs": 4,
84
+ "per_device_train_batch_size": 16,
85
+ "temperature": 29
86
+ }
87
+ }
run-40/checkpoint-576/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9eb176719296b7eda907810ef79c5712ba925be55e9de51dc1da95d3b26e91c
3
+ size 4984
run-40/checkpoint-576/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-40/checkpoint-768/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-40/checkpoint-768/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37b46f809be7637226b117d7d5fd64179492b64b28949537075c7d42ad6ee5ef
3
+ size 17549312
run-40/checkpoint-768/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1609ea4c9355f9177890554e0238b87f6bace0b97e01f6a1746226053baea2f9
3
+ size 35122746
run-40/checkpoint-768/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ed72394efd052c27a025cbbb902950bb9336778a32545e8b891d3c9c80c35d9
3
+ size 14054
run-40/checkpoint-768/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b29cb8552657ad4f094e56aebdc940a0cb4ae28b5b084d900055ffed5f2d29b3
3
+ size 1064
run-40/checkpoint-768/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-40/checkpoint-768/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-40/checkpoint-768/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-40/checkpoint-768/trainer_state.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8160469667318982,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-40/checkpoint-768",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 768,
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": 7.570804595947266,
14
+ "learning_rate": 9.127982348433665e-05,
15
+ "loss": 0.5774,
16
+ "step": 192
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8033268101761253,
21
+ "eval_f1": 0.8222811671087534,
22
+ "eval_loss": 0.45489490032196045,
23
+ "eval_mcc": 0.6209445541298213,
24
+ "eval_precision": 0.75,
25
+ "eval_recall": 0.9099804305283757,
26
+ "eval_runtime": 67.0612,
27
+ "eval_samples_per_second": 15.24,
28
+ "eval_steps_per_second": 0.477,
29
+ "step": 192
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 12.614089012145996,
34
+ "learning_rate": 6.0853215656224434e-05,
35
+ "loss": 0.4642,
36
+ "step": 384
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.8091976516634051,
41
+ "eval_f1": 0.8202764976958525,
42
+ "eval_loss": 0.4278040826320648,
43
+ "eval_mcc": 0.6231493257080627,
44
+ "eval_precision": 0.7752613240418118,
45
+ "eval_recall": 0.8708414872798435,
46
+ "eval_runtime": 66.8566,
47
+ "eval_samples_per_second": 15.286,
48
+ "eval_steps_per_second": 0.479,
49
+ "step": 384
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 5.883197784423828,
54
+ "learning_rate": 3.0426607828112217e-05,
55
+ "loss": 0.4308,
56
+ "step": 576
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.815068493150685,
61
+ "eval_f1": 0.8280254777070064,
62
+ "eval_loss": 0.4256427586078644,
63
+ "eval_mcc": 0.6374150947947472,
64
+ "eval_precision": 0.7738095238095238,
65
+ "eval_recall": 0.8904109589041096,
66
+ "eval_runtime": 66.4637,
67
+ "eval_samples_per_second": 15.377,
68
+ "eval_steps_per_second": 0.481,
69
+ "step": 576
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 3.9493777751922607,
74
+ "learning_rate": 0.0,
75
+ "loss": 0.421,
76
+ "step": 768
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.8160469667318982,
81
+ "eval_f1": 0.8324420677361855,
82
+ "eval_loss": 0.42437195777893066,
83
+ "eval_mcc": 0.6445565206113043,
84
+ "eval_precision": 0.7643207855973814,
85
+ "eval_recall": 0.913894324853229,
86
+ "eval_runtime": 66.8546,
87
+ "eval_samples_per_second": 15.287,
88
+ "eval_steps_per_second": 0.479,
89
+ "step": 768
90
+ }
91
+ ],
92
+ "logging_steps": 500,
93
+ "max_steps": 768,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 4,
96
+ "save_steps": 500,
97
+ "total_flos": 942780789120.0,
98
+ "train_batch_size": 16,
99
+ "trial_name": null,
100
+ "trial_params": {
101
+ "alpha": 0.9602502972445941,
102
+ "learning_rate": 0.00012170643131244887,
103
+ "num_train_epochs": 4,
104
+ "per_device_train_batch_size": 16,
105
+ "temperature": 29
106
+ }
107
+ }
run-40/checkpoint-768/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9eb176719296b7eda907810ef79c5712ba925be55e9de51dc1da95d3b26e91c
3
+ size 4984
run-40/checkpoint-768/vocab.txt ADDED
The diff for this file is too large to render. See raw diff