Hugging Face's logo

JeukHwang
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
text-embeddings-inference
Model card Files
xet
Metrics Community
JeukHwang commited on
Commit
635dbed
·
1 Parent(s): 1dfd048

Training in progress, epoch 1

Browse files
Files changed (38) hide show
  1. logs/events.out.tfevents.1699906437.b18f42e49ba4.3021.6 +2 -2
  2. logs/events.out.tfevents.1699906976.b18f42e49ba4.3021.7 +3 -0
  3. logs/events.out.tfevents.1699907043.b18f42e49ba4.3021.8 +3 -0
  4. model.safetensors +1 -1
  5. run-5/checkpoint-3689/config.json +34 -0
  6. run-5/checkpoint-3689/model.safetensors +3 -0
  7. run-5/checkpoint-3689/optimizer.pt +3 -0
  8. run-5/checkpoint-3689/rng_state.pth +3 -0
  9. run-5/checkpoint-3689/scheduler.pt +3 -0
  10. run-5/checkpoint-3689/special_tokens_map.json +7 -0
  11. run-5/checkpoint-3689/tokenizer.json +0 -0
  12. run-5/checkpoint-3689/tokenizer_config.json +57 -0
  13. run-5/checkpoint-3689/trainer_state.json +129 -0
  14. run-5/checkpoint-3689/training_args.bin +3 -0
  15. run-5/checkpoint-3689/vocab.txt +0 -0
  16. run-5/checkpoint-4216/config.json +34 -0
  17. run-5/checkpoint-4216/model.safetensors +3 -0
  18. run-5/checkpoint-4216/optimizer.pt +3 -0
  19. run-5/checkpoint-4216/rng_state.pth +3 -0
  20. run-5/checkpoint-4216/scheduler.pt +3 -0
  21. run-5/checkpoint-4216/special_tokens_map.json +7 -0
  22. run-5/checkpoint-4216/tokenizer.json +0 -0
  23. run-5/checkpoint-4216/tokenizer_config.json +57 -0
  24. run-5/checkpoint-4216/trainer_state.json +144 -0
  25. run-5/checkpoint-4216/training_args.bin +3 -0
  26. run-5/checkpoint-4216/vocab.txt +0 -0
  27. run-7/checkpoint-527/config.json +34 -0
  28. run-7/checkpoint-527/model.safetensors +3 -0
  29. run-7/checkpoint-527/optimizer.pt +3 -0
  30. run-7/checkpoint-527/rng_state.pth +3 -0
  31. run-7/checkpoint-527/scheduler.pt +3 -0
  32. run-7/checkpoint-527/special_tokens_map.json +7 -0
  33. run-7/checkpoint-527/tokenizer.json +0 -0
  34. run-7/checkpoint-527/tokenizer_config.json +57 -0
  35. run-7/checkpoint-527/trainer_state.json +39 -0
  36. run-7/checkpoint-527/training_args.bin +3 -0
  37. run-7/checkpoint-527/vocab.txt +0 -0
  38. training_args.bin +1 -1
logs/events.out.tfevents.1699906437.b18f42e49ba4.3021.6 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4597e3d530033bbf95879ec18724385021ae5fa9fa6f7cc6567682d68b5c7e76
3
- size 5254
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb0a4cfbdab2148b071b7b8e5dc333c0d2c506277d847facc60517050166cb96
3
+ size 8488
logs/events.out.tfevents.1699906976.b18f42e49ba4.3021.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8f0299b59dbd9ed7fc09f00bb1459017090edd2d30d8cb2b5c4fba3724de0db
3
+ size 4773
logs/events.out.tfevents.1699907043.b18f42e49ba4.3021.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb015761a4b8e975d7bd66ba7b57725f1a84bf72cd07b2ac05e82199410173c7
3
+ size 4773
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79e8ce0644f4006052a1658e40bfe3b68e181c689f5acb42794240256abd30e3
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab6967214971bf17693964dfb574a7332ebf6861a31a9e87875aa765dab5f96e
3
  size 17549312
run-5/checkpoint-3689/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": "4.35.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-5/checkpoint-3689/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e03285d067b10398241288a3af3df155a1c35b0cff2c2fb2852f2c3a390917
3
+ size 17549312
run-5/checkpoint-3689/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5c0c9fb1bb2d8a3edea57cd9e7d933f4fc0ebf3923b2f23868831a037a7de2b
3
+ size 35123898
run-5/checkpoint-3689/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:959a157c8997a0f50a0954cb609f9428c4084488e4115a67b439b0d218c1fd23
3
+ size 14308
run-5/checkpoint-3689/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7af46e9957ac34862253eaeea1a451ebb35a340e86b19b02d201bd2d7a6915fa
3
+ size 1064
run-5/checkpoint-3689/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-5/checkpoint-3689/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-3689/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-5/checkpoint-3689/trainer_state.json ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8325688073394495,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-5/checkpoint-3689",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3689,
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": 0.0001244210714352971,
14
+ "loss": 2.1634,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8073394495412844,
20
+ "eval_loss": 1.7978096008300781,
21
+ "eval_runtime": 0.92,
22
+ "eval_samples_per_second": 947.846,
23
+ "eval_steps_per_second": 7.609,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.00010665144957990372,
29
+ "loss": 1.0247,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8314220183486238,
35
+ "eval_loss": 1.9133273363113403,
36
+ "eval_runtime": 0.8955,
37
+ "eval_samples_per_second": 973.786,
38
+ "eval_steps_per_second": 7.817,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 8.888182772451034e-05,
44
+ "loss": 0.7577,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8268348623853211,
50
+ "eval_loss": 1.900517463684082,
51
+ "eval_runtime": 0.9325,
52
+ "eval_samples_per_second": 935.137,
53
+ "eval_steps_per_second": 7.507,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 7.111220586911697e-05,
59
+ "loss": 0.6259,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8211009174311926,
65
+ "eval_loss": 1.8958754539489746,
66
+ "eval_runtime": 0.9848,
67
+ "eval_samples_per_second": 885.469,
68
+ "eval_steps_per_second": 7.108,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 5.334258401372358e-05,
74
+ "loss": 0.5282,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8245412844036697,
80
+ "eval_loss": 1.9947131872177124,
81
+ "eval_runtime": 0.9259,
82
+ "eval_samples_per_second": 941.752,
83
+ "eval_steps_per_second": 7.56,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 3.55729621583302e-05,
89
+ "loss": 0.4726,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8256880733944955,
95
+ "eval_loss": 1.9554692506790161,
96
+ "eval_runtime": 0.9054,
97
+ "eval_samples_per_second": 963.145,
98
+ "eval_steps_per_second": 7.732,
99
+ "step": 3162
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "learning_rate": 1.7803340302936823e-05,
104
+ "loss": 0.4323,
105
+ "step": 3689
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "eval_accuracy": 0.8325688073394495,
110
+ "eval_loss": 1.9441158771514893,
111
+ "eval_runtime": 0.8298,
112
+ "eval_samples_per_second": 1050.862,
113
+ "eval_steps_per_second": 8.436,
114
+ "step": 3689
115
+ }
116
+ ],
117
+ "logging_steps": 500,
118
+ "max_steps": 4216,
119
+ "num_train_epochs": 8,
120
+ "save_steps": 500,
121
+ "total_flos": 56612034005400.0,
122
+ "trial_name": null,
123
+ "trial_params": {
124
+ "alpha": 0.10702478077127464,
125
+ "learning_rate": 0.00014215697484314704,
126
+ "num_train_epochs": 8,
127
+ "temperature": 30
128
+ }
129
+ }
run-5/checkpoint-3689/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:296db979eca092ce7396cd9509850c8dd40fdce13dfed2ce7efeefca33233a59
3
+ size 4600
run-5/checkpoint-3689/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-4216/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": "4.35.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-5/checkpoint-4216/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce2d47f34336977b30508ec6953c2c8bdb3273ca078931e76d027e345fe16453
3
+ size 17549312
run-5/checkpoint-4216/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a0a57b4330273e1e3e645b74ca2d3e0ad3f0f32a0bf115f874e3c9ccdc4672a
3
+ size 35123898
run-5/checkpoint-4216/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8cc4b5d3811a9bdab419053416300344cc89ce599bbd17ed6dd7156beee0ca8
3
+ size 14308
run-5/checkpoint-4216/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:564e19b42c50a763e855172b9e083c420a9a633dc83aafc34fe9f52ad2cfdf24
3
+ size 1064
run-5/checkpoint-4216/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-5/checkpoint-4216/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-4216/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-5/checkpoint-4216/trainer_state.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8325688073394495,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-5/checkpoint-3689",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4216,
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": 0.0001244210714352971,
14
+ "loss": 2.1634,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8073394495412844,
20
+ "eval_loss": 1.7978096008300781,
21
+ "eval_runtime": 0.92,
22
+ "eval_samples_per_second": 947.846,
23
+ "eval_steps_per_second": 7.609,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.00010665144957990372,
29
+ "loss": 1.0247,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8314220183486238,
35
+ "eval_loss": 1.9133273363113403,
36
+ "eval_runtime": 0.8955,
37
+ "eval_samples_per_second": 973.786,
38
+ "eval_steps_per_second": 7.817,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 8.888182772451034e-05,
44
+ "loss": 0.7577,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8268348623853211,
50
+ "eval_loss": 1.900517463684082,
51
+ "eval_runtime": 0.9325,
52
+ "eval_samples_per_second": 935.137,
53
+ "eval_steps_per_second": 7.507,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 7.111220586911697e-05,
59
+ "loss": 0.6259,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8211009174311926,
65
+ "eval_loss": 1.8958754539489746,
66
+ "eval_runtime": 0.9848,
67
+ "eval_samples_per_second": 885.469,
68
+ "eval_steps_per_second": 7.108,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 5.334258401372358e-05,
74
+ "loss": 0.5282,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8245412844036697,
80
+ "eval_loss": 1.9947131872177124,
81
+ "eval_runtime": 0.9259,
82
+ "eval_samples_per_second": 941.752,
83
+ "eval_steps_per_second": 7.56,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 3.55729621583302e-05,
89
+ "loss": 0.4726,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8256880733944955,
95
+ "eval_loss": 1.9554692506790161,
96
+ "eval_runtime": 0.9054,
97
+ "eval_samples_per_second": 963.145,
98
+ "eval_steps_per_second": 7.732,
99
+ "step": 3162
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "learning_rate": 1.7803340302936823e-05,
104
+ "loss": 0.4323,
105
+ "step": 3689
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "eval_accuracy": 0.8325688073394495,
110
+ "eval_loss": 1.9441158771514893,
111
+ "eval_runtime": 0.8298,
112
+ "eval_samples_per_second": 1050.862,
113
+ "eval_steps_per_second": 8.436,
114
+ "step": 3689
115
+ },
116
+ {
117
+ "epoch": 8.0,
118
+ "learning_rate": 6.74368950868819e-08,
119
+ "loss": 0.4051,
120
+ "step": 4216
121
+ },
122
+ {
123
+ "epoch": 8.0,
124
+ "eval_accuracy": 0.8302752293577982,
125
+ "eval_loss": 1.9669746160507202,
126
+ "eval_runtime": 0.8349,
127
+ "eval_samples_per_second": 1044.426,
128
+ "eval_steps_per_second": 8.384,
129
+ "step": 4216
130
+ }
131
+ ],
132
+ "logging_steps": 500,
133
+ "max_steps": 4216,
134
+ "num_train_epochs": 8,
135
+ "save_steps": 500,
136
+ "total_flos": 64677008811300.0,
137
+ "trial_name": null,
138
+ "trial_params": {
139
+ "alpha": 0.10702478077127464,
140
+ "learning_rate": 0.00014215697484314704,
141
+ "num_train_epochs": 8,
142
+ "temperature": 30
143
+ }
144
+ }
run-5/checkpoint-4216/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:296db979eca092ce7396cd9509850c8dd40fdce13dfed2ce7efeefca33233a59
3
+ size 4600
run-5/checkpoint-4216/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/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": "4.35.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-7/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab6967214971bf17693964dfb574a7332ebf6861a31a9e87875aa765dab5f96e
3
+ size 17549312
run-7/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdbd7a074bd534a017b60a277a364805af30aaf3a81bddb5ec652f66254aae82
3
+ size 35123898
run-7/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ababcbf30496eb4976cce44a5faf0cf605467f452ba655745eb60d884a0042d8
3
+ size 14308
run-7/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5eae90a1ae82d1495a6a4429f775bf55add24e2b96baa5f8fb98386b25157d5
3
+ size 1064
run-7/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-7/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/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-7/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8153669724770642,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-7/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": 0.0006483137812430133,
14
+ "loss": 1.4329,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8153669724770642,
20
+ "eval_loss": 1.7355903387069702,
21
+ "eval_runtime": 0.9503,
22
+ "eval_samples_per_second": 917.634,
23
+ "eval_steps_per_second": 7.366,
24
+ "step": 527
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 3162,
29
+ "num_train_epochs": 6,
30
+ "save_steps": 500,
31
+ "total_flos": 8117476690260.0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "alpha": 0.14334837282224033,
35
+ "learning_rate": 0.0007779765374916159,
36
+ "num_train_epochs": 6,
37
+ "temperature": 27
38
+ }
39
+ }
run-7/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:806ae42596d54c22720aa3a78ba8e832b7e98ba0160c60b7c181bc0d45da910b
3
+ size 4600
run-7/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 sha256:296db979eca092ce7396cd9509850c8dd40fdce13dfed2ce7efeefca33233a59
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:806ae42596d54c22720aa3a78ba8e832b7e98ba0160c60b7c181bc0d45da910b
3
  size 4600