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
af1874d
·
verified ·
1 Parent(s): 0c99174

Training in progress, epoch 1

Browse files
Files changed (27) hide show
  1. logs/events.out.tfevents.1709449620.49ae8f4e8e7b.1647.9 +2 -2
  2. logs/events.out.tfevents.1709450639.49ae8f4e8e7b.1647.10 +3 -0
  3. logs/events.out.tfevents.1709450841.49ae8f4e8e7b.1647.11 +3 -0
  4. model.safetensors +1 -1
  5. run-10/checkpoint-527/config.json +34 -0
  6. run-10/checkpoint-527/model.safetensors +3 -0
  7. run-10/checkpoint-527/optimizer.pt +3 -0
  8. run-10/checkpoint-527/rng_state.pth +3 -0
  9. run-10/checkpoint-527/scheduler.pt +3 -0
  10. run-10/checkpoint-527/special_tokens_map.json +7 -0
  11. run-10/checkpoint-527/tokenizer.json +0 -0
  12. run-10/checkpoint-527/tokenizer_config.json +57 -0
  13. run-10/checkpoint-527/trainer_state.json +42 -0
  14. run-10/checkpoint-527/training_args.bin +3 -0
  15. run-10/checkpoint-527/vocab.txt +0 -0
  16. run-8/checkpoint-2635/config.json +34 -0
  17. run-8/checkpoint-2635/model.safetensors +3 -0
  18. run-8/checkpoint-2635/optimizer.pt +3 -0
  19. run-8/checkpoint-2635/rng_state.pth +3 -0
  20. run-8/checkpoint-2635/scheduler.pt +3 -0
  21. run-8/checkpoint-2635/special_tokens_map.json +7 -0
  22. run-8/checkpoint-2635/tokenizer.json +0 -0
  23. run-8/checkpoint-2635/tokenizer_config.json +57 -0
  24. run-8/checkpoint-2635/trainer_state.json +106 -0
  25. run-8/checkpoint-2635/training_args.bin +3 -0
  26. run-8/checkpoint-2635/vocab.txt +0 -0
  27. training_args.bin +1 -1
logs/events.out.tfevents.1709449620.49ae8f4e8e7b.1647.9 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fc45cb2b380abd2f048ccef65e82f6b053190045d814d6cd1ee8d66b3aabb31
3
- size 5713
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9413f928fba72939041f3bea9ffe75645cbb58c8951bc95ea82db546257fe4fc
3
+ size 7669
logs/events.out.tfevents.1709450639.49ae8f4e8e7b.1647.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67f2067e77d2a9eb2810c324b662675087044fea911f537e769818937dc07268
3
+ size 5180
logs/events.out.tfevents.1709450841.49ae8f4e8e7b.1647.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96a2ca27ff8d6c43d8d72f85c42295e380007abce7133865596e9bbe8c224024
3
+ size 5180
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0284ce1c2f4a678f92863889d757df4e70d6103ab5df223a39957ec045287a9a
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4d5bad654032c3f7546dc4c95b7a06cc9a624f3cdab5078481ab0e1f215bc6d
3
  size 17549312
run-10/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-10/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4d5bad654032c3f7546dc4c95b7a06cc9a624f3cdab5078481ab0e1f215bc6d
3
+ size 17549312
run-10/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ebcc476927736bb72f9eb80320788120f4d8887b9431eeca4f8364a431ea9d9
3
+ size 35123898
run-10/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-10/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c40eff23edc7fa57bd46f50411d82beaed1b80e55bda0f648bb0a087b125de2
3
+ size 1064
run-10/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-10/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-10/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-10/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8165137614678899,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-10/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": 14.234737396240234,
14
+ "learning_rate": 7.828321466767788e-05,
15
+ "loss": 1.9973,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8165137614678899,
21
+ "eval_loss": 1.6924320459365845,
22
+ "eval_runtime": 2.8153,
23
+ "eval_samples_per_second": 309.737,
24
+ "eval_steps_per_second": 2.486,
25
+ "step": 527
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 1054,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 2,
32
+ "save_steps": 500,
33
+ "total_flos": 8057768762220.0,
34
+ "train_batch_size": 128,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "alpha": 0.015302977727103428,
38
+ "learning_rate": 0.00015626990200706908,
39
+ "num_train_epochs": 2,
40
+ "temperature": 5
41
+ }
42
+ }
run-10/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c813937f5361535904236d6226bb7c636462c8c71d2d084fc9c0254deb40861a
3
+ size 4984
run-10/checkpoint-527/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-2635/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-8/checkpoint-2635/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cce85883ad6c5570755b95dce5a40f600b90eb97a922b0de0d31812ebf48a433
3
+ size 17549312
run-8/checkpoint-2635/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86f66bd4505bb5b6612a9b2ae4ae250a8f8f84b99506883be211ce375b85c2c0
3
+ size 35123898
run-8/checkpoint-2635/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bd37da819cfe1c92aea202c8f190c02a65fdc71a17fd2af0ed4760f9222ae02
3
+ size 14308
run-8/checkpoint-2635/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1d87f6fbba694f0e411ce5e4f6766901dace7ee2b95e4d459047b54ef56ae4f
3
+ size 1064
run-8/checkpoint-2635/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-8/checkpoint-2635/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-2635/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-8/checkpoint-2635/trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8302752293577982,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-8/checkpoint-527",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2635,
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": 10.257322311401367,
14
+ "learning_rate": 0.0005386391253190077,
15
+ "loss": 1.2539,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8302752293577982,
21
+ "eval_loss": 1.5333763360977173,
22
+ "eval_runtime": 2.8188,
23
+ "eval_samples_per_second": 309.352,
24
+ "eval_steps_per_second": 2.483,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": NaN,
30
+ "learning_rate": 0.0004042348653959536,
31
+ "loss": 0.5485,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.801605504587156,
37
+ "eval_loss": 1.7583402395248413,
38
+ "eval_runtime": 2.8148,
39
+ "eval_samples_per_second": 309.788,
40
+ "eval_steps_per_second": 2.487,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 25.133913040161133,
46
+ "learning_rate": 0.0002695750840662017,
47
+ "loss": 0.3506,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8096330275229358,
53
+ "eval_loss": 1.8196579217910767,
54
+ "eval_runtime": 2.8113,
55
+ "eval_samples_per_second": 310.174,
56
+ "eval_steps_per_second": 2.49,
57
+ "step": 1581
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 8.44449234008789,
62
+ "learning_rate": 0.00013491530273644975,
63
+ "loss": 0.2467,
64
+ "step": 2108
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.8107798165137615,
69
+ "eval_loss": 1.8072972297668457,
70
+ "eval_runtime": 2.8135,
71
+ "eval_samples_per_second": 309.934,
72
+ "eval_steps_per_second": 2.488,
73
+ "step": 2108
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 8.500100135803223,
78
+ "learning_rate": 2.555214066978215e-07,
79
+ "loss": 0.19,
80
+ "step": 2635
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_accuracy": 0.8153669724770642,
85
+ "eval_loss": 1.8087736368179321,
86
+ "eval_runtime": 2.8195,
87
+ "eval_samples_per_second": 309.277,
88
+ "eval_steps_per_second": 2.483,
89
+ "step": 2635
90
+ }
91
+ ],
92
+ "logging_steps": 500,
93
+ "max_steps": 2635,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 5,
96
+ "save_steps": 500,
97
+ "total_flos": 40447180739880.0,
98
+ "train_batch_size": 128,
99
+ "trial_name": null,
100
+ "trial_params": {
101
+ "alpha": 0.31906439494819705,
102
+ "learning_rate": 0.0006732989066487597,
103
+ "num_train_epochs": 5,
104
+ "temperature": 15
105
+ }
106
+ }
run-8/checkpoint-2635/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0a1c6ed3b9b470bdad8206f712f552c6d3df46b69bf2eb2fc56cbd2db7df836
3
+ size 4984
run-8/checkpoint-2635/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:c0a1c6ed3b9b470bdad8206f712f552c6d3df46b69bf2eb2fc56cbd2db7df836
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c813937f5361535904236d6226bb7c636462c8c71d2d084fc9c0254deb40861a
3
  size 4984