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
33f4567
·
1 Parent(s): 821bc07

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1699908113.b18f42e49ba4.3021.13 +2 -2
  2. logs/events.out.tfevents.1699908581.b18f42e49ba4.3021.14 +3 -0
  3. model.safetensors +1 -1
  4. run-12/checkpoint-2635/config.json +34 -0
  5. run-12/checkpoint-2635/model.safetensors +3 -0
  6. run-12/checkpoint-2635/optimizer.pt +3 -0
  7. run-12/checkpoint-2635/rng_state.pth +3 -0
  8. run-12/checkpoint-2635/scheduler.pt +3 -0
  9. run-12/checkpoint-2635/special_tokens_map.json +7 -0
  10. run-12/checkpoint-2635/tokenizer.json +0 -0
  11. run-12/checkpoint-2635/tokenizer_config.json +57 -0
  12. run-12/checkpoint-2635/trainer_state.json +99 -0
  13. run-12/checkpoint-2635/training_args.bin +3 -0
  14. run-12/checkpoint-2635/vocab.txt +0 -0
  15. run-12/checkpoint-3162/config.json +34 -0
  16. run-12/checkpoint-3162/model.safetensors +3 -0
  17. run-12/checkpoint-3162/optimizer.pt +3 -0
  18. run-12/checkpoint-3162/rng_state.pth +3 -0
  19. run-12/checkpoint-3162/scheduler.pt +3 -0
  20. run-12/checkpoint-3162/special_tokens_map.json +7 -0
  21. run-12/checkpoint-3162/tokenizer.json +0 -0
  22. run-12/checkpoint-3162/tokenizer_config.json +57 -0
  23. run-12/checkpoint-3162/trainer_state.json +114 -0
  24. run-12/checkpoint-3162/training_args.bin +3 -0
  25. run-12/checkpoint-3162/vocab.txt +0 -0
  26. run-13/checkpoint-527/config.json +34 -0
  27. run-13/checkpoint-527/model.safetensors +3 -0
  28. run-13/checkpoint-527/optimizer.pt +3 -0
  29. run-13/checkpoint-527/rng_state.pth +3 -0
  30. run-13/checkpoint-527/scheduler.pt +3 -0
  31. run-13/checkpoint-527/special_tokens_map.json +7 -0
  32. run-13/checkpoint-527/tokenizer.json +0 -0
  33. run-13/checkpoint-527/tokenizer_config.json +57 -0
  34. run-13/checkpoint-527/trainer_state.json +39 -0
  35. run-13/checkpoint-527/training_args.bin +3 -0
  36. run-13/checkpoint-527/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1699908113.b18f42e49ba4.3021.13 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a8aea88f1e57d8757bc1cd84b8e2b2b2ce18d35f78a958d900bd5f474d7ebf9
3
- size 5255
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fac6c4e7408c04501877e3f79337bfa137481d14a799f19a00590678db25079
3
+ size 7655
logs/events.out.tfevents.1699908581.b18f42e49ba4.3021.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cec14ee55df7d169d2a6f938c2553e262476cc62b3dfe9ed2b5c01253c2a408
3
+ size 4774
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9dd88471173b3e1ba70e1110c96dacff5a8b5356ee69bb5e640ba88c282ed328
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de6eaa5ca42d84d7ef5ec2f3c8de9a3ff04ae42929a6fc5ae87f9a2dbd727cc8
3
  size 17549312
run-12/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": "4.35.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-12/checkpoint-2635/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2335abdf80779d6e0a07df48514f89a2823f000e77d0f8dbaba3fc07798b9173
3
+ size 17549312
run-12/checkpoint-2635/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed5912c6ad08cc999118ae04af27ad4a020de57917e51dac3c18b9809e873417
3
+ size 35123898
run-12/checkpoint-2635/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6495712c0480e33150a9e840df89cfbd7359c197e00213528d6031351fe6bf56
3
+ size 14308
run-12/checkpoint-2635/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39e70a318b0194a1733139cf4299bed77a0f56b5023d363e93e947a6a6489990
3
+ size 1064
run-12/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-12/checkpoint-2635/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-12/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-12/checkpoint-2635/trainer_state.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8268348623853211,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-12/checkpoint-2108",
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
+ "learning_rate": 0.00015727026233263184,
14
+ "loss": 1.8005,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8119266055045872,
20
+ "eval_loss": 1.6491965055465698,
21
+ "eval_runtime": 0.9079,
22
+ "eval_samples_per_second": 960.445,
23
+ "eval_steps_per_second": 7.71,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.00013979947222949167,
29
+ "loss": 0.8444,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8222477064220184,
35
+ "eval_loss": 1.7696919441223145,
36
+ "eval_runtime": 0.9215,
37
+ "eval_samples_per_second": 946.31,
38
+ "eval_steps_per_second": 7.597,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 0.0001223286821263515,
44
+ "loss": 0.6182,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.819954128440367,
50
+ "eval_loss": 1.7952384948730469,
51
+ "eval_runtime": 0.9118,
52
+ "eval_samples_per_second": 956.375,
53
+ "eval_steps_per_second": 7.677,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 0.00010485789202321133,
59
+ "loss": 0.4972,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8268348623853211,
65
+ "eval_loss": 1.7547180652618408,
66
+ "eval_runtime": 0.9362,
67
+ "eval_samples_per_second": 931.378,
68
+ "eval_steps_per_second": 7.477,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 8.738710192007116e-05,
74
+ "loss": 0.4093,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.819954128440367,
80
+ "eval_loss": 1.8850818872451782,
81
+ "eval_runtime": 0.9113,
82
+ "eval_samples_per_second": 956.926,
83
+ "eval_steps_per_second": 7.682,
84
+ "step": 2635
85
+ }
86
+ ],
87
+ "logging_steps": 500,
88
+ "max_steps": 5270,
89
+ "num_train_epochs": 10,
90
+ "save_steps": 500,
91
+ "total_flos": 40418309418180.0,
92
+ "trial_name": null,
93
+ "trial_params": {
94
+ "alpha": 0.20775917695370932,
95
+ "learning_rate": 0.00017470790103140175,
96
+ "num_train_epochs": 10,
97
+ "temperature": 12
98
+ }
99
+ }
run-12/checkpoint-2635/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d172b68ebabe652c54551888b87f20e6865d37da307f69502f9ee08a9e47f9a8
3
+ size 4600
run-12/checkpoint-2635/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-12/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": "4.35.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-12/checkpoint-3162/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d88944d5db0923cf7bacbd8afaf0165562278881181d246ffdee3b6ff0ee3ed
3
+ size 17549312
run-12/checkpoint-3162/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e80a1d4431636c1ba469ffa36d9473f8d7d106ac5671192676b7389e8dce7c02
3
+ size 35123898
run-12/checkpoint-3162/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4a805f5b31aed4614530263d37ef452339ef59079ff627a6dd75bd82ccc8197
3
+ size 14308
run-12/checkpoint-3162/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c19c8ca19aa3881e46dc7207543f60f72639dd7ae86b1c684c39c8f09f94caca
3
+ size 1064
run-12/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-12/checkpoint-3162/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-12/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-12/checkpoint-3162/trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8291284403669725,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-12/checkpoint-3162",
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": 0.00015727026233263184,
14
+ "loss": 1.8005,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8119266055045872,
20
+ "eval_loss": 1.6491965055465698,
21
+ "eval_runtime": 0.9079,
22
+ "eval_samples_per_second": 960.445,
23
+ "eval_steps_per_second": 7.71,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.00013979947222949167,
29
+ "loss": 0.8444,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8222477064220184,
35
+ "eval_loss": 1.7696919441223145,
36
+ "eval_runtime": 0.9215,
37
+ "eval_samples_per_second": 946.31,
38
+ "eval_steps_per_second": 7.597,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 0.0001223286821263515,
44
+ "loss": 0.6182,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.819954128440367,
50
+ "eval_loss": 1.7952384948730469,
51
+ "eval_runtime": 0.9118,
52
+ "eval_samples_per_second": 956.375,
53
+ "eval_steps_per_second": 7.677,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 0.00010485789202321133,
59
+ "loss": 0.4972,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8268348623853211,
65
+ "eval_loss": 1.7547180652618408,
66
+ "eval_runtime": 0.9362,
67
+ "eval_samples_per_second": 931.378,
68
+ "eval_steps_per_second": 7.477,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 8.738710192007116e-05,
74
+ "loss": 0.4093,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.819954128440367,
80
+ "eval_loss": 1.8850818872451782,
81
+ "eval_runtime": 0.9113,
82
+ "eval_samples_per_second": 956.926,
83
+ "eval_steps_per_second": 7.682,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 6.991631181693099e-05,
89
+ "loss": 0.3569,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8291284403669725,
95
+ "eval_loss": 1.8409069776535034,
96
+ "eval_runtime": 0.9127,
97
+ "eval_samples_per_second": 955.415,
98
+ "eval_steps_per_second": 7.67,
99
+ "step": 3162
100
+ }
101
+ ],
102
+ "logging_steps": 500,
103
+ "max_steps": 5270,
104
+ "num_train_epochs": 10,
105
+ "save_steps": 500,
106
+ "total_flos": 48509902416420.0,
107
+ "trial_name": null,
108
+ "trial_params": {
109
+ "alpha": 0.20775917695370932,
110
+ "learning_rate": 0.00017470790103140175,
111
+ "num_train_epochs": 10,
112
+ "temperature": 12
113
+ }
114
+ }
run-12/checkpoint-3162/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d172b68ebabe652c54551888b87f20e6865d37da307f69502f9ee08a9e47f9a8
3
+ size 4600
run-12/checkpoint-3162/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-13/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-13/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de6eaa5ca42d84d7ef5ec2f3c8de9a3ff04ae42929a6fc5ae87f9a2dbd727cc8
3
+ size 17549312
run-13/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f12a1a34348aa4bc6d21051a6b1bcad4cf16d88efb5259f741420a409e395c43
3
+ size 35123898
run-13/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-13/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48968d1d0492123168104a56b96deeb8f5a52419baa232e39b7b0916f70df751
3
+ size 1064
run-13/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-13/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-13/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-13/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8096330275229358,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/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": 0.0001229918736660078,
14
+ "loss": 1.6529,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8096330275229358,
20
+ "eval_loss": 1.4444859027862549,
21
+ "eval_runtime": 0.8333,
22
+ "eval_samples_per_second": 1046.416,
23
+ "eval_steps_per_second": 8.4,
24
+ "step": 527
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 3689,
29
+ "num_train_epochs": 7,
30
+ "save_steps": 500,
31
+ "total_flos": 8117476690260.0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "alpha": 0.37689567573511473,
35
+ "learning_rate": 0.00014344515395317822,
36
+ "num_train_epochs": 7,
37
+ "temperature": 21
38
+ }
39
+ }
run-13/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e49f40aff2ec7cb96f539cb403f7d52e030045e5f77b8ed81730e241b115f997
3
+ size 4600
run-13/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:d172b68ebabe652c54551888b87f20e6865d37da307f69502f9ee08a9e47f9a8
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e49f40aff2ec7cb96f539cb403f7d52e030045e5f77b8ed81730e241b115f997
3
  size 4600