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
33b4607
·
verified ·
1 Parent(s): f9d3f0f

Training in progress, epoch 1

Browse files
Files changed (39) hide show
  1. logs/events.out.tfevents.1709750832.d65e8524b0f6.5185.27 +2 -2
  2. logs/events.out.tfevents.1709751390.d65e8524b0f6.5185.28 +3 -0
  3. logs/events.out.tfevents.1709751499.d65e8524b0f6.5185.29 +3 -0
  4. logs/events.out.tfevents.1709751609.d65e8524b0f6.5185.30 +3 -0
  5. model.safetensors +1 -1
  6. run-27/checkpoint-156/config.json +34 -0
  7. run-27/checkpoint-156/model.safetensors +3 -0
  8. run-27/checkpoint-156/optimizer.pt +3 -0
  9. run-27/checkpoint-156/rng_state.pth +3 -0
  10. run-27/checkpoint-156/scheduler.pt +3 -0
  11. run-27/checkpoint-156/special_tokens_map.json +7 -0
  12. run-27/checkpoint-156/tokenizer.json +0 -0
  13. run-27/checkpoint-156/tokenizer_config.json +57 -0
  14. run-27/checkpoint-156/trainer_state.json +84 -0
  15. run-27/checkpoint-156/training_args.bin +3 -0
  16. run-27/checkpoint-156/vocab.txt +0 -0
  17. run-27/checkpoint-208/config.json +34 -0
  18. run-27/checkpoint-208/model.safetensors +3 -0
  19. run-27/checkpoint-208/optimizer.pt +3 -0
  20. run-27/checkpoint-208/rng_state.pth +3 -0
  21. run-27/checkpoint-208/scheduler.pt +3 -0
  22. run-27/checkpoint-208/special_tokens_map.json +7 -0
  23. run-27/checkpoint-208/tokenizer.json +0 -0
  24. run-27/checkpoint-208/tokenizer_config.json +57 -0
  25. run-27/checkpoint-208/trainer_state.json +103 -0
  26. run-27/checkpoint-208/training_args.bin +3 -0
  27. run-27/checkpoint-208/vocab.txt +0 -0
  28. run-30/checkpoint-56/config.json +34 -0
  29. run-30/checkpoint-56/model.safetensors +3 -0
  30. run-30/checkpoint-56/optimizer.pt +3 -0
  31. run-30/checkpoint-56/rng_state.pth +3 -0
  32. run-30/checkpoint-56/scheduler.pt +3 -0
  33. run-30/checkpoint-56/special_tokens_map.json +7 -0
  34. run-30/checkpoint-56/tokenizer.json +0 -0
  35. run-30/checkpoint-56/tokenizer_config.json +57 -0
  36. run-30/checkpoint-56/trainer_state.json +46 -0
  37. run-30/checkpoint-56/training_args.bin +3 -0
  38. run-30/checkpoint-56/vocab.txt +0 -0
  39. training_args.bin +1 -1
logs/events.out.tfevents.1709750832.d65e8524b0f6.5185.27 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:083be76c70a17fd379b3ce494ebd39d8cf4cbb942a1375fa5c4f168d28f5c002
3
- size 5982
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8ff4792f18318ccd15976635badc18ae9adf91ff674607257b4fa8122f488f3
3
+ size 8031
logs/events.out.tfevents.1709751390.d65e8524b0f6.5185.28 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d948c512dcb0bd5524dfc50430f0c128b4412f47a9bcb9eafcf1895530e17a94
3
+ size 5314
logs/events.out.tfevents.1709751499.d65e8524b0f6.5185.29 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:027fb39f30a4a59f0dc4446944d32fdfa1869302c10b4e6d3f9640c1252f1eff
3
+ size 5315
logs/events.out.tfevents.1709751609.d65e8524b0f6.5185.30 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cdde1c4d226c4bafe0b0d770467c5b0030d944445a11713ebfc832a77fbffa3
3
+ size 5313
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c238afc7fd292738acca3d6e49d99d43d1ff9517fa1b5901ab675d443f382623
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a5c00c89f0bb46b19d00bad6f9ed991aca6501b6a0a0e554e5e51f028f745e7
3
  size 17549312
run-27/checkpoint-156/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-27/checkpoint-156/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbaee8679ae68df8313d4988417e064084361e2903d1e8ad11f53a3e39585dc0
3
+ size 17549312
run-27/checkpoint-156/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99b354246d6913eba323884b4bcaa147118974bffb2b424433ce595924e03558
3
+ size 35122746
run-27/checkpoint-156/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f3f2bf3b854c592a6f1e0e90f14af49f8d742650373f022831e4b62d27ad7a2
3
+ size 14054
run-27/checkpoint-156/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3dc3c1c4292c0f67e651d61d07521cfb24eb08f79f962e161113c4869da5ddc
3
+ size 1064
run-27/checkpoint-156/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-27/checkpoint-156/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-27/checkpoint-156/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-27/checkpoint-156/trainer_state.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7778864970645792,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-27/checkpoint-156",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 156,
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": 3.795090675354004,
14
+ "learning_rate": 0.0004299539034695828,
15
+ "loss": 0.5539,
16
+ "step": 52
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7397260273972602,
21
+ "eval_f1": 0.7779632721202002,
22
+ "eval_loss": 0.49282991886138916,
23
+ "eval_precision": 0.6783114992721979,
24
+ "eval_recall": 0.9119373776908023,
25
+ "eval_runtime": 28.2474,
26
+ "eval_samples_per_second": 36.18,
27
+ "eval_steps_per_second": 1.133,
28
+ "step": 52
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 2.3241050243377686,
33
+ "learning_rate": 0.0003582949195579857,
34
+ "loss": 0.4958,
35
+ "step": 104
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.776908023483366,
40
+ "eval_f1": 0.8074324324324325,
41
+ "eval_loss": 0.4643081724643707,
42
+ "eval_precision": 0.7102526002971769,
43
+ "eval_recall": 0.9354207436399217,
44
+ "eval_runtime": 28.4313,
45
+ "eval_samples_per_second": 35.946,
46
+ "eval_steps_per_second": 1.126,
47
+ "step": 104
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 2.4190268516540527,
52
+ "learning_rate": 0.00028663593564638853,
53
+ "loss": 0.4714,
54
+ "step": 156
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.7778864970645792,
59
+ "eval_f1": 0.8090832632464255,
60
+ "eval_loss": 0.4609759449958801,
61
+ "eval_precision": 0.7094395280235988,
62
+ "eval_recall": 0.9412915851272016,
63
+ "eval_runtime": 28.809,
64
+ "eval_samples_per_second": 35.475,
65
+ "eval_steps_per_second": 1.111,
66
+ "step": 156
67
+ }
68
+ ],
69
+ "logging_steps": 500,
70
+ "max_steps": 364,
71
+ "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 7,
73
+ "save_steps": 500,
74
+ "total_flos": 707085591840.0,
75
+ "train_batch_size": 59,
76
+ "trial_name": null,
77
+ "trial_params": {
78
+ "alpha": 0.845201757467621,
79
+ "learning_rate": 0.00050161288738118,
80
+ "num_train_epochs": 7,
81
+ "per_device_train_batch_size": 59,
82
+ "temperature": 21
83
+ }
84
+ }
run-27/checkpoint-156/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3427d367c6681566932cafa2f6b6a62ba9e8ebfdfa8d9ebafbc1230e1c415890
3
+ size 4920
run-27/checkpoint-156/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-27/checkpoint-208/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-27/checkpoint-208/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:102c93b829589eb1cac4ad524d714afd102e305c94b7f8dcd13e732020ab7405
3
+ size 17549312
run-27/checkpoint-208/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:877d549bf031de1088c4cc2b02c3935790c955023333cbb7838afc0cc7f3eee4
3
+ size 35122746
run-27/checkpoint-208/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b6ed2075102dd75f9c18fe89ccd178319808314220b3c31c67cb30308a85909
3
+ size 14054
run-27/checkpoint-208/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcfad319aafebfc536f7ba6caa955cb14f7b60b3df258f75f6a9906cafa524a9
3
+ size 1064
run-27/checkpoint-208/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-27/checkpoint-208/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-27/checkpoint-208/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-27/checkpoint-208/trainer_state.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7945205479452054,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-27/checkpoint-208",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 208,
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": 3.795090675354004,
14
+ "learning_rate": 0.0004299539034695828,
15
+ "loss": 0.5539,
16
+ "step": 52
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7397260273972602,
21
+ "eval_f1": 0.7779632721202002,
22
+ "eval_loss": 0.49282991886138916,
23
+ "eval_precision": 0.6783114992721979,
24
+ "eval_recall": 0.9119373776908023,
25
+ "eval_runtime": 28.2474,
26
+ "eval_samples_per_second": 36.18,
27
+ "eval_steps_per_second": 1.133,
28
+ "step": 52
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 2.3241050243377686,
33
+ "learning_rate": 0.0003582949195579857,
34
+ "loss": 0.4958,
35
+ "step": 104
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.776908023483366,
40
+ "eval_f1": 0.8074324324324325,
41
+ "eval_loss": 0.4643081724643707,
42
+ "eval_precision": 0.7102526002971769,
43
+ "eval_recall": 0.9354207436399217,
44
+ "eval_runtime": 28.4313,
45
+ "eval_samples_per_second": 35.946,
46
+ "eval_steps_per_second": 1.126,
47
+ "step": 104
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 2.4190268516540527,
52
+ "learning_rate": 0.00028663593564638853,
53
+ "loss": 0.4714,
54
+ "step": 156
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.7778864970645792,
59
+ "eval_f1": 0.8090832632464255,
60
+ "eval_loss": 0.4609759449958801,
61
+ "eval_precision": 0.7094395280235988,
62
+ "eval_recall": 0.9412915851272016,
63
+ "eval_runtime": 28.809,
64
+ "eval_samples_per_second": 35.475,
65
+ "eval_steps_per_second": 1.111,
66
+ "step": 156
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 3.24399471282959,
71
+ "learning_rate": 0.0002149769517347914,
72
+ "loss": 0.4531,
73
+ "step": 208
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.7945205479452054,
78
+ "eval_f1": 0.8111510791366907,
79
+ "eval_loss": 0.4340381920337677,
80
+ "eval_precision": 0.7504159733777038,
81
+ "eval_recall": 0.8825831702544031,
82
+ "eval_runtime": 28.4651,
83
+ "eval_samples_per_second": 35.904,
84
+ "eval_steps_per_second": 1.124,
85
+ "step": 208
86
+ }
87
+ ],
88
+ "logging_steps": 500,
89
+ "max_steps": 364,
90
+ "num_input_tokens_seen": 0,
91
+ "num_train_epochs": 7,
92
+ "save_steps": 500,
93
+ "total_flos": 942780789120.0,
94
+ "train_batch_size": 59,
95
+ "trial_name": null,
96
+ "trial_params": {
97
+ "alpha": 0.845201757467621,
98
+ "learning_rate": 0.00050161288738118,
99
+ "num_train_epochs": 7,
100
+ "per_device_train_batch_size": 59,
101
+ "temperature": 21
102
+ }
103
+ }
run-27/checkpoint-208/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3427d367c6681566932cafa2f6b6a62ba9e8ebfdfa8d9ebafbc1230e1c415890
3
+ size 4920
run-27/checkpoint-208/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-30/checkpoint-56/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-30/checkpoint-56/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a5c00c89f0bb46b19d00bad6f9ed991aca6501b6a0a0e554e5e51f028f745e7
3
+ size 17549312
run-30/checkpoint-56/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b38df252558245bda6818cd03784ce17df77370b0a874894f92db1f03eb4980
3
+ size 35122746
run-30/checkpoint-56/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:246901d84b3447ae67c6e9126b5bbf4473c08da78ffc08c216b42ebe7054b997
3
+ size 14054
run-30/checkpoint-56/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4df513a35f06ea0da7e195eadb1eb84530e3e52b103421b6a7f034aaf26c0265
3
+ size 1064
run-30/checkpoint-56/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-30/checkpoint-56/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-30/checkpoint-56/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-30/checkpoint-56/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7847358121330724,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-30/checkpoint-56",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 56,
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": 2.488581895828247,
14
+ "learning_rate": 0.00035374495201026426,
15
+ "loss": 0.5645,
16
+ "step": 56
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7847358121330724,
21
+ "eval_f1": 0.8049645390070922,
22
+ "eval_loss": 0.4679928421974182,
23
+ "eval_precision": 0.7358184764991896,
24
+ "eval_recall": 0.8884540117416829,
25
+ "eval_runtime": 28.8427,
26
+ "eval_samples_per_second": 35.434,
27
+ "eval_steps_per_second": 1.109,
28
+ "step": 56
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 392,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 7,
35
+ "save_steps": 500,
36
+ "total_flos": 235695197280.0,
37
+ "train_batch_size": 55,
38
+ "trial_name": null,
39
+ "trial_params": {
40
+ "alpha": 0.9318712276013821,
41
+ "learning_rate": 0.000412702444011975,
42
+ "num_train_epochs": 7,
43
+ "per_device_train_batch_size": 55,
44
+ "temperature": 27
45
+ }
46
+ }
run-30/checkpoint-56/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87c31c0ff5ab5419b10c4b045c98d73f4009f0b63f2ceac81514144c885ecd65
3
+ size 4920
run-30/checkpoint-56/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 sha256:89efecad9561cc854d69fd70f328f321f6dd5b5b818174094a406c3a368090ff
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87c31c0ff5ab5419b10c4b045c98d73f4009f0b63f2ceac81514144c885ecd65
3
  size 4920