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
8ef008b
·
verified ·
1 Parent(s): fcb9378

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1709807412.013ec1551212.75384.2 +2 -2
  2. logs/events.out.tfevents.1709811548.013ec1551212.75384.3 +3 -0
  3. model.safetensors +1 -1
  4. run-2/checkpoint-4596/config.json +34 -0
  5. run-2/checkpoint-4596/model.safetensors +3 -0
  6. run-2/checkpoint-4596/optimizer.pt +3 -0
  7. run-2/checkpoint-4596/rng_state.pth +3 -0
  8. run-2/checkpoint-4596/scheduler.pt +3 -0
  9. run-2/checkpoint-4596/special_tokens_map.json +7 -0
  10. run-2/checkpoint-4596/tokenizer.json +0 -0
  11. run-2/checkpoint-4596/tokenizer_config.json +57 -0
  12. run-2/checkpoint-4596/trainer_state.json +140 -0
  13. run-2/checkpoint-4596/training_args.bin +3 -0
  14. run-2/checkpoint-4596/vocab.txt +0 -0
  15. run-2/checkpoint-5362/config.json +34 -0
  16. run-2/checkpoint-5362/model.safetensors +3 -0
  17. run-2/checkpoint-5362/optimizer.pt +3 -0
  18. run-2/checkpoint-5362/rng_state.pth +3 -0
  19. run-2/checkpoint-5362/scheduler.pt +3 -0
  20. run-2/checkpoint-5362/special_tokens_map.json +7 -0
  21. run-2/checkpoint-5362/tokenizer.json +0 -0
  22. run-2/checkpoint-5362/tokenizer_config.json +57 -0
  23. run-2/checkpoint-5362/trainer_state.json +159 -0
  24. run-2/checkpoint-5362/training_args.bin +3 -0
  25. run-2/checkpoint-5362/vocab.txt +0 -0
  26. run-3/checkpoint-766/config.json +34 -0
  27. run-3/checkpoint-766/model.safetensors +3 -0
  28. run-3/checkpoint-766/optimizer.pt +3 -0
  29. run-3/checkpoint-766/rng_state.pth +3 -0
  30. run-3/checkpoint-766/scheduler.pt +3 -0
  31. run-3/checkpoint-766/special_tokens_map.json +7 -0
  32. run-3/checkpoint-766/tokenizer.json +0 -0
  33. run-3/checkpoint-766/tokenizer_config.json +57 -0
  34. run-3/checkpoint-766/trainer_state.json +45 -0
  35. run-3/checkpoint-766/training_args.bin +3 -0
  36. run-3/checkpoint-766/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1709807412.013ec1551212.75384.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4cf5819267c6dc1734c974950134229444475d02152500157b33327aa55b380
3
- size 6008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a01f96d0503da62810a65ded183f9bb1a2978be43f8a39cc1886663c8b156421
3
+ size 9777
logs/events.out.tfevents.1709811548.013ec1551212.75384.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12055096801036c20165b7e88223619b108c8cc57aaceb46d8541e4587e1ccb5
3
+ size 5326
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9dbec3f7a3848dac87dac2b7b6443f9bdb279cf3f345c84d42ae2de85ca4e0d
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72a7037fb44695b792c40b2a326ba6b501f55c628a95424effc62b5dcfc8d14b
3
  size 17549312
run-2/checkpoint-4596/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-2/checkpoint-4596/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5a9d95fe0b08c7bedd43a64228ba46d09002b2046c3e87c87cdcd9a30dba683
3
+ size 17549312
run-2/checkpoint-4596/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7c328e4713d013472b49a7512dc1477637e9d707f393434a4e9c4530a1b8648
3
+ size 35122746
run-2/checkpoint-4596/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f06e3ed5d19cc4b4c47d9aedbd704375564c004c94232d74f9d579078573040d
3
+ size 14054
run-2/checkpoint-4596/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0c88b0adff79c2eca59ac3ff9c3e9e74607850a1f16c5684e00669a85b000cb
3
+ size 1064
run-2/checkpoint-4596/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-4596/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-4596/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-4596/trainer_state.json ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7211350293542075,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-4596",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4596,
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": 2.795396089553833,
14
+ "learning_rate": 2.0226645656833037e-05,
15
+ "loss": 0.3457,
16
+ "step": 766
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5870841487279843,
21
+ "eval_f1": 0.352760736196319,
22
+ "eval_loss": 0.3146859109401703,
23
+ "eval_precision": 0.8156028368794326,
24
+ "eval_recall": 0.22504892367906065,
25
+ "eval_runtime": 132.813,
26
+ "eval_samples_per_second": 7.695,
27
+ "eval_steps_per_second": 1.928,
28
+ "step": 766
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 7.475469589233398,
33
+ "learning_rate": 1.6855538047360867e-05,
34
+ "loss": 0.3142,
35
+ "step": 1532
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.5978473581213307,
40
+ "eval_f1": 0.3763277693474962,
41
+ "eval_loss": 0.3066306710243225,
42
+ "eval_precision": 0.8378378378378378,
43
+ "eval_recall": 0.24266144814090018,
44
+ "eval_runtime": 132.6826,
45
+ "eval_samples_per_second": 7.703,
46
+ "eval_steps_per_second": 1.929,
47
+ "step": 1532
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 3.5962014198303223,
52
+ "learning_rate": 1.3484430437888691e-05,
53
+ "loss": 0.3086,
54
+ "step": 2298
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.6438356164383562,
59
+ "eval_f1": 0.5172413793103448,
60
+ "eval_loss": 0.30034366250038147,
61
+ "eval_precision": 0.8024691358024691,
62
+ "eval_recall": 0.3816046966731898,
63
+ "eval_runtime": 133.6957,
64
+ "eval_samples_per_second": 7.644,
65
+ "eval_steps_per_second": 1.915,
66
+ "step": 2298
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 5.574785232543945,
71
+ "learning_rate": 1.0113322828416519e-05,
72
+ "loss": 0.3062,
73
+ "step": 3064
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.6663405088062623,
78
+ "eval_f1": 0.5742821473158551,
79
+ "eval_loss": 0.29888635873794556,
80
+ "eval_precision": 0.7931034482758621,
81
+ "eval_recall": 0.4500978473581213,
82
+ "eval_runtime": 131.8312,
83
+ "eval_samples_per_second": 7.752,
84
+ "eval_steps_per_second": 1.942,
85
+ "step": 3064
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 5.6824212074279785,
90
+ "learning_rate": 6.7422152189443455e-06,
91
+ "loss": 0.3046,
92
+ "step": 3830
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.7084148727984344,
97
+ "eval_f1": 0.6526806526806528,
98
+ "eval_loss": 0.29940325021743774,
99
+ "eval_precision": 0.8069164265129684,
100
+ "eval_recall": 0.547945205479452,
101
+ "eval_runtime": 132.0554,
102
+ "eval_samples_per_second": 7.739,
103
+ "eval_steps_per_second": 1.939,
104
+ "step": 3830
105
+ },
106
+ {
107
+ "epoch": 6.0,
108
+ "grad_norm": 6.931075572967529,
109
+ "learning_rate": 3.3711076094721728e-06,
110
+ "loss": 0.3016,
111
+ "step": 4596
112
+ },
113
+ {
114
+ "epoch": 6.0,
115
+ "eval_accuracy": 0.7211350293542075,
116
+ "eval_f1": 0.6772366930917327,
117
+ "eval_loss": 0.29910269379615784,
118
+ "eval_precision": 0.803763440860215,
119
+ "eval_recall": 0.5851272015655578,
120
+ "eval_runtime": 132.5392,
121
+ "eval_samples_per_second": 7.711,
122
+ "eval_steps_per_second": 1.932,
123
+ "step": 4596
124
+ }
125
+ ],
126
+ "logging_steps": 500,
127
+ "max_steps": 5362,
128
+ "num_input_tokens_seen": 0,
129
+ "num_train_epochs": 7,
130
+ "save_steps": 500,
131
+ "total_flos": 1414171183680.0,
132
+ "train_batch_size": 4,
133
+ "trial_name": null,
134
+ "trial_params": {
135
+ "alpha": 0.43980036163769065,
136
+ "learning_rate": 2.359775326630521e-05,
137
+ "num_train_epochs": 7,
138
+ "temperature": 17
139
+ }
140
+ }
run-2/checkpoint-4596/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c5b12c46007d944895fac94424c52cdff3b4d51e877318f87ce441d4dd6ec61
3
+ size 4920
run-2/checkpoint-4596/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-5362/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-2/checkpoint-5362/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58506654e1cea315918b327ab07d549f41451dfc3e500bb7178389e0d61a6ca4
3
+ size 17549312
run-2/checkpoint-5362/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89252576a4edb67084db799346eed48945e7d88a20466e6286b55ef17a5670a5
3
+ size 35122746
run-2/checkpoint-5362/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7fd4350c7218219d68fdc6005665ff445af21f9f1ee459645f23da0c02474a0
3
+ size 14054
run-2/checkpoint-5362/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91d4084c7bb377a7eb48afe68fe1f314a4622f9335f13f2f22f72b7e2ddbf4bb
3
+ size 1064
run-2/checkpoint-5362/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-5362/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-5362/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-5362/trainer_state.json ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7211350293542075,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-4596",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5362,
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": 2.795396089553833,
14
+ "learning_rate": 2.0226645656833037e-05,
15
+ "loss": 0.3457,
16
+ "step": 766
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5870841487279843,
21
+ "eval_f1": 0.352760736196319,
22
+ "eval_loss": 0.3146859109401703,
23
+ "eval_precision": 0.8156028368794326,
24
+ "eval_recall": 0.22504892367906065,
25
+ "eval_runtime": 132.813,
26
+ "eval_samples_per_second": 7.695,
27
+ "eval_steps_per_second": 1.928,
28
+ "step": 766
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 7.475469589233398,
33
+ "learning_rate": 1.6855538047360867e-05,
34
+ "loss": 0.3142,
35
+ "step": 1532
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.5978473581213307,
40
+ "eval_f1": 0.3763277693474962,
41
+ "eval_loss": 0.3066306710243225,
42
+ "eval_precision": 0.8378378378378378,
43
+ "eval_recall": 0.24266144814090018,
44
+ "eval_runtime": 132.6826,
45
+ "eval_samples_per_second": 7.703,
46
+ "eval_steps_per_second": 1.929,
47
+ "step": 1532
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 3.5962014198303223,
52
+ "learning_rate": 1.3484430437888691e-05,
53
+ "loss": 0.3086,
54
+ "step": 2298
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.6438356164383562,
59
+ "eval_f1": 0.5172413793103448,
60
+ "eval_loss": 0.30034366250038147,
61
+ "eval_precision": 0.8024691358024691,
62
+ "eval_recall": 0.3816046966731898,
63
+ "eval_runtime": 133.6957,
64
+ "eval_samples_per_second": 7.644,
65
+ "eval_steps_per_second": 1.915,
66
+ "step": 2298
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 5.574785232543945,
71
+ "learning_rate": 1.0113322828416519e-05,
72
+ "loss": 0.3062,
73
+ "step": 3064
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.6663405088062623,
78
+ "eval_f1": 0.5742821473158551,
79
+ "eval_loss": 0.29888635873794556,
80
+ "eval_precision": 0.7931034482758621,
81
+ "eval_recall": 0.4500978473581213,
82
+ "eval_runtime": 131.8312,
83
+ "eval_samples_per_second": 7.752,
84
+ "eval_steps_per_second": 1.942,
85
+ "step": 3064
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 5.6824212074279785,
90
+ "learning_rate": 6.7422152189443455e-06,
91
+ "loss": 0.3046,
92
+ "step": 3830
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.7084148727984344,
97
+ "eval_f1": 0.6526806526806528,
98
+ "eval_loss": 0.29940325021743774,
99
+ "eval_precision": 0.8069164265129684,
100
+ "eval_recall": 0.547945205479452,
101
+ "eval_runtime": 132.0554,
102
+ "eval_samples_per_second": 7.739,
103
+ "eval_steps_per_second": 1.939,
104
+ "step": 3830
105
+ },
106
+ {
107
+ "epoch": 6.0,
108
+ "grad_norm": 6.931075572967529,
109
+ "learning_rate": 3.3711076094721728e-06,
110
+ "loss": 0.3016,
111
+ "step": 4596
112
+ },
113
+ {
114
+ "epoch": 6.0,
115
+ "eval_accuracy": 0.7211350293542075,
116
+ "eval_f1": 0.6772366930917327,
117
+ "eval_loss": 0.29910269379615784,
118
+ "eval_precision": 0.803763440860215,
119
+ "eval_recall": 0.5851272015655578,
120
+ "eval_runtime": 132.5392,
121
+ "eval_samples_per_second": 7.711,
122
+ "eval_steps_per_second": 1.932,
123
+ "step": 4596
124
+ },
125
+ {
126
+ "epoch": 7.0,
127
+ "grad_norm": 2.585300922393799,
128
+ "learning_rate": 0.0,
129
+ "loss": 0.3018,
130
+ "step": 5362
131
+ },
132
+ {
133
+ "epoch": 7.0,
134
+ "eval_accuracy": 0.6947162426614482,
135
+ "eval_f1": 0.625,
136
+ "eval_loss": 0.29733312129974365,
137
+ "eval_precision": 0.8099688473520249,
138
+ "eval_recall": 0.5088062622309197,
139
+ "eval_runtime": 133.4769,
140
+ "eval_samples_per_second": 7.657,
141
+ "eval_steps_per_second": 1.918,
142
+ "step": 5362
143
+ }
144
+ ],
145
+ "logging_steps": 500,
146
+ "max_steps": 5362,
147
+ "num_input_tokens_seen": 0,
148
+ "num_train_epochs": 7,
149
+ "save_steps": 500,
150
+ "total_flos": 1649866380960.0,
151
+ "train_batch_size": 4,
152
+ "trial_name": null,
153
+ "trial_params": {
154
+ "alpha": 0.43980036163769065,
155
+ "learning_rate": 2.359775326630521e-05,
156
+ "num_train_epochs": 7,
157
+ "temperature": 17
158
+ }
159
+ }
run-2/checkpoint-5362/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c5b12c46007d944895fac94424c52cdff3b4d51e877318f87ce441d4dd6ec61
3
+ size 4920
run-2/checkpoint-5362/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-766/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-3/checkpoint-766/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72a7037fb44695b792c40b2a326ba6b501f55c628a95424effc62b5dcfc8d14b
3
+ size 17549312
run-3/checkpoint-766/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10955d278efdb53107d8b83d91aab4151fdb8964e97ee6bf80e8de45d4f80e5b
3
+ size 35122746
run-3/checkpoint-766/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a29b5a9fab412f426bae759e459d7d9236aab6602ae439ea13f5bd437e1b98a4
3
+ size 14054
run-3/checkpoint-766/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8094f3ad95181debf9a7195773881ed7deb4059c055dbdadda112cb2de973aa3
3
+ size 1064
run-3/checkpoint-766/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-766/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-766/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-766/trainer_state.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7475538160469667,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-766",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 766,
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": 2.53190279006958,
14
+ "learning_rate": 0.00016492442050886904,
15
+ "loss": 0.4371,
16
+ "step": 766
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7475538160469667,
21
+ "eval_f1": 0.7465618860510805,
22
+ "eval_loss": 0.4075860381126404,
23
+ "eval_precision": 0.7495069033530573,
24
+ "eval_recall": 0.7436399217221135,
25
+ "eval_runtime": 132.2506,
26
+ "eval_samples_per_second": 7.728,
27
+ "eval_steps_per_second": 1.936,
28
+ "step": 766
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 6894,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 9,
35
+ "save_steps": 500,
36
+ "total_flos": 235695197280.0,
37
+ "train_batch_size": 4,
38
+ "trial_name": null,
39
+ "trial_params": {
40
+ "alpha": 0.6411063430664922,
41
+ "learning_rate": 0.00018553997307247768,
42
+ "num_train_epochs": 9,
43
+ "temperature": 23
44
+ }
45
+ }
run-3/checkpoint-766/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:666474cc7672b9c9b0f515c0a8777dc0bd3add95917dfa0d532a1cc5f7f4503b
3
+ size 4920
run-3/checkpoint-766/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 sha256:1c5b12c46007d944895fac94424c52cdff3b4d51e877318f87ce441d4dd6ec61
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:666474cc7672b9c9b0f515c0a8777dc0bd3add95917dfa0d532a1cc5f7f4503b
3
  size 4920