Hugging Face's logo

joseph10
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
text-embeddings-inference
Model card Files
xet
 Metrics Community
joseph10 commited on
Commit
82ea25e
·
1 Parent(s): cd1e032

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. logs/events.out.tfevents.1701755000.joseph_legion.10272.3 +2 -2
  2. logs/events.out.tfevents.1701755822.joseph_legion.10272.4 +3 -0
  3. model.safetensors +1 -1
  4. run-2/checkpoint-3162/config.json +34 -0
  5. run-2/checkpoint-3162/model.safetensors +3 -0
  6. run-2/checkpoint-3162/optimizer.pt +3 -0
  7. run-2/checkpoint-3162/rng_state.pth +3 -0
  8. run-2/checkpoint-3162/scheduler.pt +3 -0
  9. run-2/checkpoint-3162/special_tokens_map.json +7 -0
  10. run-2/checkpoint-3162/tokenizer.json +0 -0
  11. run-2/checkpoint-3162/tokenizer_config.json +57 -0
  12. run-2/checkpoint-3162/trainer_state.json +114 -0
  13. run-2/checkpoint-3162/training_args.bin +3 -0
  14. run-2/checkpoint-3162/vocab.txt +0 -0
  15. run-3/checkpoint-527/config.json +34 -0
  16. run-3/checkpoint-527/model.safetensors +3 -0
  17. run-3/checkpoint-527/optimizer.pt +3 -0
  18. run-3/checkpoint-527/rng_state.pth +3 -0
  19. run-3/checkpoint-527/scheduler.pt +3 -0
  20. run-3/checkpoint-527/special_tokens_map.json +7 -0
  21. run-3/checkpoint-527/tokenizer.json +0 -0
  22. run-3/checkpoint-527/tokenizer_config.json +57 -0
  23. run-3/checkpoint-527/trainer_state.json +39 -0
  24. run-3/checkpoint-527/training_args.bin +3 -0
  25. run-3/checkpoint-527/vocab.txt +0 -0
  26. training_args.bin +1 -1
logs/events.out.tfevents.1701755000.joseph_legion.10272.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9659de15a695de7cf28f77353871592672e8520f90d27afecc285397a2774f5
3
- size 6214
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e2a80f528230668bed56412b814e009ea2240e985d6ab4ef77dc64567243272
3
+ size 7528
logs/events.out.tfevents.1701755822.joseph_legion.10272.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41f0f665121009a64c378af95dbeb3b7a64d83276d47fb127f031321d3b83cbc
3
+ size 4775
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85ca74426dc0db158f93b35b4211288ec4c86728da852c07aa754e3d70dff799
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f6c110fbb84cc7d7c7c259636e8a75f200c0067c45c38b1b5ff34d5e6eda8c1
3
  size 17549312
run-2/checkpoint-3162/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": "4.35.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-2/checkpoint-3162/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9591ecb7c081dc2d6171ec81ca03024fe8eea92e277de6e7d62bd68afc8082fe
3
+ size 17549312
run-2/checkpoint-3162/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:333896e3a744e78352bbdc7bd9e775df6a160600fdb30d13487d204f4a7c1d3b
3
+ size 35123898
run-2/checkpoint-3162/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a746423c1eae31cdaf6c18863e25e5c3f461a207aea91ee91f78792252ba410b
3
+ size 14308
run-2/checkpoint-3162/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7af1ad7b8a3164af79bdc9acb8ce31542af1bd94de8ed87d170879af4f37ed4
3
+ size 1064
run-2/checkpoint-3162/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-2/checkpoint-3162/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-3162/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-2/checkpoint-3162/trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8360091743119266,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-2\\checkpoint-1054",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3162,
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
+ "learning_rate": 0.00012691492700530536,
14
+ "loss": 2.1729,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8211009174311926,
20
+ "eval_loss": 1.797359585762024,
21
+ "eval_runtime": 1.9786,
22
+ "eval_samples_per_second": 440.708,
23
+ "eval_steps_per_second": 3.538,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.00010153194160424427,
29
+ "loss": 1.0171,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8360091743119266,
35
+ "eval_loss": 1.7071614265441895,
36
+ "eval_runtime": 1.9801,
37
+ "eval_samples_per_second": 440.381,
38
+ "eval_steps_per_second": 3.535,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 7.61489562031832e-05,
44
+ "loss": 0.7519,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.823394495412844,
50
+ "eval_loss": 1.7907185554504395,
51
+ "eval_runtime": 1.836,
52
+ "eval_samples_per_second": 474.954,
53
+ "eval_steps_per_second": 3.813,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 5.0765970802122135e-05,
59
+ "loss": 0.6168,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.823394495412844,
65
+ "eval_loss": 1.912740707397461,
66
+ "eval_runtime": 1.7683,
67
+ "eval_samples_per_second": 493.127,
68
+ "eval_steps_per_second": 3.959,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 2.5382985401061067e-05,
74
+ "loss": 0.5414,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8245412844036697,
80
+ "eval_loss": 1.9259263277053833,
81
+ "eval_runtime": 1.8045,
82
+ "eval_samples_per_second": 483.232,
83
+ "eval_steps_per_second": 3.879,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 0.0,
89
+ "loss": 0.4922,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8211009174311926,
95
+ "eval_loss": 1.9153525829315186,
96
+ "eval_runtime": 1.7998,
97
+ "eval_samples_per_second": 484.509,
98
+ "eval_steps_per_second": 3.889,
99
+ "step": 3162
100
+ }
101
+ ],
102
+ "logging_steps": 500,
103
+ "max_steps": 3162,
104
+ "num_train_epochs": 6,
105
+ "save_steps": 500,
106
+ "total_flos": 48539627346600.0,
107
+ "trial_name": null,
108
+ "trial_params": {
109
+ "alpha": 0.09677472868557402,
110
+ "learning_rate": 0.0001522979124063664,
111
+ "num_train_epochs": 6,
112
+ "temperature": 25
113
+ }
114
+ }
run-2/checkpoint-3162/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d363d60c13fa6478f0a2b0d0670373c5f39d234514d9e255bb6d10c32b73cbfb
3
+ size 4664
run-2/checkpoint-3162/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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": "4.35.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-3/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f6c110fbb84cc7d7c7c259636e8a75f200c0067c45c38b1b5ff34d5e6eda8c1
3
+ size 17549312
run-3/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:517cebfd8bdb76141bd68f2354df2c8dc3b15c3f0f7882decb8d0822393cbca4
3
+ size 35123898
run-3/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:404cec57a6bbb572f62bd49cfe2447e0a3410a29e1c658f2617325852b27cc2d
3
+ size 14308
run-3/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9c9991e9a2b0bb6dce1557a6994131adbb0c11c00c038a69c13ba93653bcd3d
3
+ size 1064
run-3/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-3/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8245412844036697,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-3\\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
+ "learning_rate": 0.00011471098822404043,
14
+ "loss": 1.0348,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8245412844036697,
20
+ "eval_loss": 0.9528604745864868,
21
+ "eval_runtime": 1.7841,
22
+ "eval_samples_per_second": 488.773,
23
+ "eval_steps_per_second": 3.924,
24
+ "step": 527
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 2635,
29
+ "num_train_epochs": 5,
30
+ "save_steps": 500,
31
+ "total_flos": 8057768762220.0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "alpha": 0.7068839484125146,
35
+ "learning_rate": 0.00014338873528005054,
36
+ "num_train_epochs": 5,
37
+ "temperature": 15
38
+ }
39
+ }
run-3/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbe67709d5eb30b28dd7eb636d81e8b8f85c61db2e94841ea11c7912a79ea510
3
+ size 4664
run-3/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:d363d60c13fa6478f0a2b0d0670373c5f39d234514d9e255bb6d10c32b73cbfb
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbe67709d5eb30b28dd7eb636d81e8b8f85c61db2e94841ea11c7912a79ea510
3
  size 4664