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
f78a1ad
·
verified ·
1 Parent(s): 30e2245

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1709745622.d65e8524b0f6.5185.13 +2 -2
  2. logs/events.out.tfevents.1709746175.d65e8524b0f6.5185.14 +3 -0
  3. model.safetensors +1 -1
  4. run-13/checkpoint-216/config.json +34 -0
  5. run-13/checkpoint-216/model.safetensors +3 -0
  6. run-13/checkpoint-216/optimizer.pt +3 -0
  7. run-13/checkpoint-216/rng_state.pth +3 -0
  8. run-13/checkpoint-216/scheduler.pt +3 -0
  9. run-13/checkpoint-216/special_tokens_map.json +7 -0
  10. run-13/checkpoint-216/tokenizer.json +0 -0
  11. run-13/checkpoint-216/tokenizer_config.json +57 -0
  12. run-13/checkpoint-216/trainer_state.json +103 -0
  13. run-13/checkpoint-216/training_args.bin +3 -0
  14. run-13/checkpoint-216/vocab.txt +0 -0
  15. run-13/checkpoint-270/config.json +34 -0
  16. run-13/checkpoint-270/model.safetensors +3 -0
  17. run-13/checkpoint-270/optimizer.pt +3 -0
  18. run-13/checkpoint-270/rng_state.pth +3 -0
  19. run-13/checkpoint-270/scheduler.pt +3 -0
  20. run-13/checkpoint-270/special_tokens_map.json +7 -0
  21. run-13/checkpoint-270/tokenizer.json +0 -0
  22. run-13/checkpoint-270/tokenizer_config.json +57 -0
  23. run-13/checkpoint-270/trainer_state.json +122 -0
  24. run-13/checkpoint-270/training_args.bin +3 -0
  25. run-13/checkpoint-270/vocab.txt +0 -0
  26. run-14/checkpoint-49/config.json +34 -0
  27. run-14/checkpoint-49/model.safetensors +3 -0
  28. run-14/checkpoint-49/optimizer.pt +3 -0
  29. run-14/checkpoint-49/rng_state.pth +3 -0
  30. run-14/checkpoint-49/scheduler.pt +3 -0
  31. run-14/checkpoint-49/special_tokens_map.json +7 -0
  32. run-14/checkpoint-49/tokenizer.json +0 -0
  33. run-14/checkpoint-49/tokenizer_config.json +57 -0
  34. run-14/checkpoint-49/trainer_state.json +46 -0
  35. run-14/checkpoint-49/training_args.bin +3 -0
  36. run-14/checkpoint-49/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1709745622.d65e8524b0f6.5185.13 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:080e37c65cc813441bc95d58b6c2845437c689b5743ceef5aed95738af12cac5
3
- size 5984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07a67abea2aee136d9054f95340da43f0a5e75caa20a8b21b83cbf1a8bad26ec
3
+ size 8387
logs/events.out.tfevents.1709746175.d65e8524b0f6.5185.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a36c15ac89416287bf2319b3413bb8f2d29c141f4b1c07c30185076e2f38a5e
3
+ size 5315
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06ff3cca891d60bf786666ac59d9811de8ecbb05be7e8770be82c16dbd3bfffd
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:223842b622adc2a75de7c1d0fcd965bc21c35dcb1764b0f91a2a6db8c709fdd0
3
  size 17549312
run-13/checkpoint-216/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-13/checkpoint-216/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89d2a5873010f5d7c959ece558409170d3477bafc2230c15b1d815abca1196d2
3
+ size 17549312
run-13/checkpoint-216/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ec6f20f180b9098a630dd89b31f5d303fef71b8e2741c92c94499fc38e76a0
3
+ size 35122746
run-13/checkpoint-216/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97cfc474370f53b193ee2b0107cb8cad2aecea3ecce27efe3ebdd225cfb00946
3
+ size 14054
run-13/checkpoint-216/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a345b4c43c9ce1fd7d8037155ef2430b6dd01ad2ee8d09e87de23a1c2dc33c92
3
+ size 1064
run-13/checkpoint-216/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-216/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-13/checkpoint-216/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-216/trainer_state.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8268101761252447,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/checkpoint-216",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 216,
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": 3.1670913696289062,
14
+ "learning_rate": 0.0002855230244841258,
15
+ "loss": 0.5191,
16
+ "step": 54
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7407045009784736,
21
+ "eval_f1": 0.7881694644284573,
22
+ "eval_loss": 0.47280439734458923,
23
+ "eval_precision": 0.6662162162162162,
24
+ "eval_recall": 0.9647749510763209,
25
+ "eval_runtime": 29.2616,
26
+ "eval_samples_per_second": 34.926,
27
+ "eval_steps_per_second": 1.094,
28
+ "step": 54
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 4.121979713439941,
33
+ "learning_rate": 0.00021414226836309432,
34
+ "loss": 0.4574,
35
+ "step": 108
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.7798434442270059,
40
+ "eval_f1": 0.7770069375619425,
41
+ "eval_loss": 0.42865216732025146,
42
+ "eval_precision": 0.7871485943775101,
43
+ "eval_recall": 0.7671232876712328,
44
+ "eval_runtime": 28.412,
45
+ "eval_samples_per_second": 35.971,
46
+ "eval_steps_per_second": 1.126,
47
+ "step": 108
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 1.5867382287979126,
52
+ "learning_rate": 0.0001427615122420629,
53
+ "loss": 0.4287,
54
+ "step": 162
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.815068493150685,
59
+ "eval_f1": 0.8205128205128206,
60
+ "eval_loss": 0.40865078568458557,
61
+ "eval_precision": 0.7970479704797048,
62
+ "eval_recall": 0.8454011741682974,
63
+ "eval_runtime": 28.2445,
64
+ "eval_samples_per_second": 36.184,
65
+ "eval_steps_per_second": 1.133,
66
+ "step": 162
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 1.5582785606384277,
71
+ "learning_rate": 7.138075612103145e-05,
72
+ "loss": 0.4101,
73
+ "step": 216
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.8268101761252447,
78
+ "eval_f1": 0.8392370572207084,
79
+ "eval_loss": 0.3997044265270233,
80
+ "eval_precision": 0.7830508474576271,
81
+ "eval_recall": 0.9041095890410958,
82
+ "eval_runtime": 28.2876,
83
+ "eval_samples_per_second": 36.129,
84
+ "eval_steps_per_second": 1.131,
85
+ "step": 216
86
+ }
87
+ ],
88
+ "logging_steps": 500,
89
+ "max_steps": 270,
90
+ "num_input_tokens_seen": 0,
91
+ "num_train_epochs": 5,
92
+ "save_steps": 500,
93
+ "total_flos": 942780789120.0,
94
+ "train_batch_size": 57,
95
+ "trial_name": null,
96
+ "trial_params": {
97
+ "alpha": 0.7778146133600564,
98
+ "learning_rate": 0.0003569037806051572,
99
+ "num_train_epochs": 5,
100
+ "per_device_train_batch_size": 57,
101
+ "temperature": 18
102
+ }
103
+ }
run-13/checkpoint-216/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fc0c138c932c086ad949bc38e18b3ac6fe3a128253e2b1f521aa8c2d349d81b
3
+ size 4920
run-13/checkpoint-216/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-13/checkpoint-270/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-13/checkpoint-270/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:654ebea2ac16dff996cff8d4fd2ca1f884196daa2e50f49ece5a6f5b52c353ed
3
+ size 17549312
run-13/checkpoint-270/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66fc138d9700d1e64b3eb14a240137d8b55f4a27f6012122c8e67387eb42ab08
3
+ size 35122746
run-13/checkpoint-270/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d74a98f8e02a3a5b3d09204f5a09de3425262ec2e951a99c07e510e5f7960d57
3
+ size 14054
run-13/checkpoint-270/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6350ede7f5e2a512dda5d36ded46309925bcfd1ba98aa728a8ec1f97849ab2a
3
+ size 1064
run-13/checkpoint-270/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-270/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-13/checkpoint-270/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-270/trainer_state.json ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8268101761252447,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/checkpoint-216",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 270,
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": 3.1670913696289062,
14
+ "learning_rate": 0.0002855230244841258,
15
+ "loss": 0.5191,
16
+ "step": 54
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7407045009784736,
21
+ "eval_f1": 0.7881694644284573,
22
+ "eval_loss": 0.47280439734458923,
23
+ "eval_precision": 0.6662162162162162,
24
+ "eval_recall": 0.9647749510763209,
25
+ "eval_runtime": 29.2616,
26
+ "eval_samples_per_second": 34.926,
27
+ "eval_steps_per_second": 1.094,
28
+ "step": 54
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 4.121979713439941,
33
+ "learning_rate": 0.00021414226836309432,
34
+ "loss": 0.4574,
35
+ "step": 108
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.7798434442270059,
40
+ "eval_f1": 0.7770069375619425,
41
+ "eval_loss": 0.42865216732025146,
42
+ "eval_precision": 0.7871485943775101,
43
+ "eval_recall": 0.7671232876712328,
44
+ "eval_runtime": 28.412,
45
+ "eval_samples_per_second": 35.971,
46
+ "eval_steps_per_second": 1.126,
47
+ "step": 108
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 1.5867382287979126,
52
+ "learning_rate": 0.0001427615122420629,
53
+ "loss": 0.4287,
54
+ "step": 162
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.815068493150685,
59
+ "eval_f1": 0.8205128205128206,
60
+ "eval_loss": 0.40865078568458557,
61
+ "eval_precision": 0.7970479704797048,
62
+ "eval_recall": 0.8454011741682974,
63
+ "eval_runtime": 28.2445,
64
+ "eval_samples_per_second": 36.184,
65
+ "eval_steps_per_second": 1.133,
66
+ "step": 162
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 1.5582785606384277,
71
+ "learning_rate": 7.138075612103145e-05,
72
+ "loss": 0.4101,
73
+ "step": 216
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.8268101761252447,
78
+ "eval_f1": 0.8392370572207084,
79
+ "eval_loss": 0.3997044265270233,
80
+ "eval_precision": 0.7830508474576271,
81
+ "eval_recall": 0.9041095890410958,
82
+ "eval_runtime": 28.2876,
83
+ "eval_samples_per_second": 36.129,
84
+ "eval_steps_per_second": 1.131,
85
+ "step": 216
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 1.5253950357437134,
90
+ "learning_rate": 0.0,
91
+ "loss": 0.3979,
92
+ "step": 270
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.8268101761252447,
97
+ "eval_f1": 0.837763519706691,
98
+ "eval_loss": 0.3981335759162903,
99
+ "eval_precision": 0.7879310344827586,
100
+ "eval_recall": 0.8943248532289628,
101
+ "eval_runtime": 28.8031,
102
+ "eval_samples_per_second": 35.482,
103
+ "eval_steps_per_second": 1.111,
104
+ "step": 270
105
+ }
106
+ ],
107
+ "logging_steps": 500,
108
+ "max_steps": 270,
109
+ "num_input_tokens_seen": 0,
110
+ "num_train_epochs": 5,
111
+ "save_steps": 500,
112
+ "total_flos": 1178475986400.0,
113
+ "train_batch_size": 57,
114
+ "trial_name": null,
115
+ "trial_params": {
116
+ "alpha": 0.7778146133600564,
117
+ "learning_rate": 0.0003569037806051572,
118
+ "num_train_epochs": 5,
119
+ "per_device_train_batch_size": 57,
120
+ "temperature": 18
121
+ }
122
+ }
run-13/checkpoint-270/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fc0c138c932c086ad949bc38e18b3ac6fe3a128253e2b1f521aa8c2d349d81b
3
+ size 4920
run-13/checkpoint-270/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-49/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-14/checkpoint-49/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:223842b622adc2a75de7c1d0fcd965bc21c35dcb1764b0f91a2a6db8c709fdd0
3
+ size 17549312
run-14/checkpoint-49/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca5cabac94259982914b5eaff881587aff43d7ae8b516cbf3aecf0b41321b713
3
+ size 35122746
run-14/checkpoint-49/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73318c69f3978e5f3bd6ef2cc87309851566e0971a68b7c5e3ee79ff600c42c4
3
+ size 14054
run-14/checkpoint-49/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3220f1da182890b4a2e6f46dc2c6da1cb2d69fa62d83dd24296a62e7129a3ada
3
+ size 1064
run-14/checkpoint-49/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-14/checkpoint-49/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-49/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-14/checkpoint-49/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7720156555772995,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/checkpoint-49",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 49,
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": 1.3073023557662964,
14
+ "learning_rate": 0.00021800841920007835,
15
+ "loss": 0.5666,
16
+ "step": 49
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7720156555772995,
21
+ "eval_f1": 0.8010247651579846,
22
+ "eval_loss": 0.48246321082115173,
23
+ "eval_precision": 0.7106060606060606,
24
+ "eval_recall": 0.9178082191780822,
25
+ "eval_runtime": 28.2754,
26
+ "eval_samples_per_second": 36.145,
27
+ "eval_steps_per_second": 1.132,
28
+ "step": 49
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 245,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 5,
35
+ "save_steps": 500,
36
+ "total_flos": 235695197280.0,
37
+ "train_batch_size": 63,
38
+ "trial_name": null,
39
+ "trial_params": {
40
+ "alpha": 0.8444228810359851,
41
+ "learning_rate": 0.00027251052400009793,
42
+ "num_train_epochs": 5,
43
+ "per_device_train_batch_size": 63,
44
+ "temperature": 21
45
+ }
46
+ }
run-14/checkpoint-49/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a93046ce295ef56d7e5753c2ad419c6bb89f07af26dc70719f2b8f995444c3d
3
+ size 4920
run-14/checkpoint-49/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 sha256:9e3bbdb4e3659e78e11bd3dd728828bd0d60a7b872ca6afbd011a6c807e9f19d
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a93046ce295ef56d7e5753c2ad419c6bb89f07af26dc70719f2b8f995444c3d
3
  size 4920