Hugging Face's logo

JeukHwang
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
Model card Files
xet
Metrics Community
JeukHwang commited on
Commit
7252180
·
1 Parent(s): a121e78

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1699905304.b18f42e49ba4.3021.3 +2 -2
  2. logs/events.out.tfevents.1699905769.b18f42e49ba4.3021.4 +3 -0
  3. model.safetensors +1 -1
  4. run-2/checkpoint-2635/config.json +34 -0
  5. run-2/checkpoint-2635/model.safetensors +3 -0
  6. run-2/checkpoint-2635/optimizer.pt +3 -0
  7. run-2/checkpoint-2635/rng_state.pth +3 -0
  8. run-2/checkpoint-2635/scheduler.pt +3 -0
  9. run-2/checkpoint-2635/special_tokens_map.json +7 -0
  10. run-2/checkpoint-2635/tokenizer.json +0 -0
  11. run-2/checkpoint-2635/tokenizer_config.json +57 -0
  12. run-2/checkpoint-2635/trainer_state.json +99 -0
  13. run-2/checkpoint-2635/training_args.bin +3 -0
  14. run-2/checkpoint-2635/vocab.txt +0 -0
  15. run-2/checkpoint-3689/config.json +34 -0
  16. run-2/checkpoint-3689/model.safetensors +3 -0
  17. run-2/checkpoint-3689/optimizer.pt +3 -0
  18. run-2/checkpoint-3689/rng_state.pth +3 -0
  19. run-2/checkpoint-3689/scheduler.pt +3 -0
  20. run-2/checkpoint-3689/special_tokens_map.json +7 -0
  21. run-2/checkpoint-3689/tokenizer.json +0 -0
  22. run-2/checkpoint-3689/tokenizer_config.json +57 -0
  23. run-2/checkpoint-3689/trainer_state.json +129 -0
  24. run-2/checkpoint-3689/training_args.bin +3 -0
  25. run-2/checkpoint-3689/vocab.txt +0 -0
  26. run-3/checkpoint-527/config.json +34 -0
  27. run-3/checkpoint-527/model.safetensors +3 -0
  28. run-3/checkpoint-527/optimizer.pt +3 -0
  29. run-3/checkpoint-527/rng_state.pth +3 -0
  30. run-3/checkpoint-527/scheduler.pt +3 -0
  31. run-3/checkpoint-527/special_tokens_map.json +7 -0
  32. run-3/checkpoint-527/tokenizer.json +0 -0
  33. run-3/checkpoint-527/tokenizer_config.json +57 -0
  34. run-3/checkpoint-527/trainer_state.json +39 -0
  35. run-3/checkpoint-527/training_args.bin +3 -0
  36. run-3/checkpoint-527/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1699905304.b18f42e49ba4.3021.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7aaca5d3535308560273d696735f41f736d5a3de25719733ad9dd43d3a6bcfd9
3
- size 5252
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da1c09d19dc7e42089de1fa8deb522e0e904ea1dc97159512a933a75d80fc1c0
3
+ size 8006
logs/events.out.tfevents.1699905769.b18f42e49ba4.3021.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:624291773b649ccdd9c65e842167b0f1ceb228da2f45d02e39a446374fa2af75
3
+ size 4773
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d477ed36e31f8e4e5589277b43199162325ee527360d10b57cc840897204cbf0
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84a2cc595045c1c35cc3696838b3652033e41029e4c5242a8794064a691729ac
3
  size 17549312
run-2/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-2/checkpoint-2635/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ecdaf834d1b423225f1824baf117c8c7119ef3f0f0ff92092a831bfeff26e1f
3
+ size 17549312
run-2/checkpoint-2635/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b43283fe54051a5542b2628af8d73e0b329e5f6cce29f77526b73cf7322373
3
+ size 35123898
run-2/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-2/checkpoint-2635/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddfcd6d2e76cbda52f0a6f8c02e78466303a10afc799f5c29fc3106f7fe53cb6
3
+ size 1064
run-2/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-2/checkpoint-2635/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-2635/trainer_state.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8348623853211009,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-2635",
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": 5.2457406035051924e-05,
14
+ "loss": 2.0868,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.7878440366972477,
20
+ "eval_loss": 1.5512216091156006,
21
+ "eval_runtime": 0.9102,
22
+ "eval_samples_per_second": 958.05,
23
+ "eval_steps_per_second": 7.691,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 4.371726914587318e-05,
29
+ "loss": 1.135,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8096330275229358,
35
+ "eval_loss": 1.3932750225067139,
36
+ "eval_runtime": 0.9043,
37
+ "eval_samples_per_second": 964.257,
38
+ "eval_steps_per_second": 7.741,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 3.497713225669444e-05,
44
+ "loss": 0.8672,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8268348623853211,
50
+ "eval_loss": 1.3538720607757568,
51
+ "eval_runtime": 0.849,
52
+ "eval_samples_per_second": 1027.091,
53
+ "eval_steps_per_second": 8.245,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 2.6236995367515696e-05,
59
+ "loss": 0.7479,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8256880733944955,
65
+ "eval_loss": 1.3861627578735352,
66
+ "eval_runtime": 0.8211,
67
+ "eval_samples_per_second": 1062.024,
68
+ "eval_steps_per_second": 8.525,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 1.749685847833695e-05,
74
+ "loss": 0.6684,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8348623853211009,
80
+ "eval_loss": 1.3665552139282227,
81
+ "eval_runtime": 0.8279,
82
+ "eval_samples_per_second": 1053.272,
83
+ "eval_steps_per_second": 8.455,
84
+ "step": 2635
85
+ }
86
+ ],
87
+ "logging_steps": 500,
88
+ "max_steps": 3689,
89
+ "num_train_epochs": 7,
90
+ "save_steps": 500,
91
+ "total_flos": 40418309418180.0,
92
+ "trial_name": null,
93
+ "trial_params": {
94
+ "alpha": 0.3591745527435446,
95
+ "learning_rate": 6.11809582242512e-05,
96
+ "num_train_epochs": 7,
97
+ "temperature": 8
98
+ }
99
+ }
run-2/checkpoint-2635/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36745c74f4aff152ea75e4b4a1392a5ebf58336b5338239520d52ed4bf11ca7f
3
+ size 4600
run-2/checkpoint-2635/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-3689/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:509441b6c0c7e8f3f8f6bbc6b924554e25324ca5f8b5dc50a1b79ff379113fcd
3
+ size 17549312
run-2/checkpoint-3689/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edc4d1aa8e0893629ee8108233e4dea8335a27a17849af9b06f7469d675c16cb
3
+ size 35123898
run-2/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-2/checkpoint-3689/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9796c2b89f15e5a42202af2b5d11e4f4922b9a9c31112d4276802c7dba00c16
3
+ size 1064
run-2/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-2/checkpoint-3689/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-3689/trainer_state.json ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8348623853211009,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-2635",
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": 5.2457406035051924e-05,
14
+ "loss": 2.0868,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.7878440366972477,
20
+ "eval_loss": 1.5512216091156006,
21
+ "eval_runtime": 0.9102,
22
+ "eval_samples_per_second": 958.05,
23
+ "eval_steps_per_second": 7.691,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 4.371726914587318e-05,
29
+ "loss": 1.135,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8096330275229358,
35
+ "eval_loss": 1.3932750225067139,
36
+ "eval_runtime": 0.9043,
37
+ "eval_samples_per_second": 964.257,
38
+ "eval_steps_per_second": 7.741,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 3.497713225669444e-05,
44
+ "loss": 0.8672,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8268348623853211,
50
+ "eval_loss": 1.3538720607757568,
51
+ "eval_runtime": 0.849,
52
+ "eval_samples_per_second": 1027.091,
53
+ "eval_steps_per_second": 8.245,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 2.6236995367515696e-05,
59
+ "loss": 0.7479,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8256880733944955,
65
+ "eval_loss": 1.3861627578735352,
66
+ "eval_runtime": 0.8211,
67
+ "eval_samples_per_second": 1062.024,
68
+ "eval_steps_per_second": 8.525,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 1.749685847833695e-05,
74
+ "loss": 0.6684,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8348623853211009,
80
+ "eval_loss": 1.3665552139282227,
81
+ "eval_runtime": 0.8279,
82
+ "eval_samples_per_second": 1053.272,
83
+ "eval_steps_per_second": 8.455,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 8.75672158915821e-06,
89
+ "loss": 0.6277,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8268348623853211,
95
+ "eval_loss": 1.3895916938781738,
96
+ "eval_runtime": 0.8246,
97
+ "eval_samples_per_second": 1057.537,
98
+ "eval_steps_per_second": 8.489,
99
+ "step": 3162
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "learning_rate": 1.6584699979466303e-08,
104
+ "loss": 0.6011,
105
+ "step": 3689
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "eval_accuracy": 0.8325688073394495,
110
+ "eval_loss": 1.3949707746505737,
111
+ "eval_runtime": 0.827,
112
+ "eval_samples_per_second": 1054.371,
113
+ "eval_steps_per_second": 8.464,
114
+ "step": 3689
115
+ }
116
+ ],
117
+ "logging_steps": 500,
118
+ "max_steps": 3689,
119
+ "num_train_epochs": 7,
120
+ "save_steps": 500,
121
+ "total_flos": 56612034005400.0,
122
+ "trial_name": null,
123
+ "trial_params": {
124
+ "alpha": 0.3591745527435446,
125
+ "learning_rate": 6.11809582242512e-05,
126
+ "num_train_epochs": 7,
127
+ "temperature": 8
128
+ }
129
+ }
run-2/checkpoint-3689/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36745c74f4aff152ea75e4b4a1392a5ebf58336b5338239520d52ed4bf11ca7f
3
+ size 4600
run-2/checkpoint-3689/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": "4.35.0",
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 sha256:84a2cc595045c1c35cc3696838b3652033e41029e4c5242a8794064a691729ac
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:c7ee742064baf80473e5bba920557faf439d601b20d78e762e8fd3fc80e62946
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:ababcbf30496eb4976cce44a5faf0cf605467f452ba655745eb60d884a0042d8
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 sha256:186a1a72fbf6dea6fa7a33a5cf2ce3c4f67beb4d0a7fbd2aa790d7ad8eda8c9f
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": 0.7844036697247706,
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": 3.598599288119205e-05,
14
+ "loss": 3.37,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.7844036697247706,
20
+ "eval_loss": 2.4027223587036133,
21
+ "eval_runtime": 0.8209,
22
+ "eval_samples_per_second": 1062.259,
23
+ "eval_steps_per_second": 8.527,
24
+ "step": 527
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 2108,
29
+ "num_train_epochs": 4,
30
+ "save_steps": 500,
31
+ "total_flos": 8117476690260.0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "alpha": 0.03192688286790302,
35
+ "learning_rate": 4.795099430692341e-05,
36
+ "num_train_epochs": 4,
37
+ "temperature": 30
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:ecc175a79b2251c6cb04bf44f82ce91061574615bd4fc831925b19ea706ccac6
3
+ size 4600
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 sha256:36745c74f4aff152ea75e4b4a1392a5ebf58336b5338239520d52ed4bf11ca7f
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecc175a79b2251c6cb04bf44f82ce91061574615bd4fc831925b19ea706ccac6
3
  size 4600