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
9aad9d8
·
verified ·
1 Parent(s): 2489bae

Training in progress, epoch 3

Browse files
Files changed (24) hide show
  1. logs/events.out.tfevents.1713589743.1376c752d37a.9760.34 +2 -2
  2. model.safetensors +1 -1
  3. run-34/checkpoint-428/config.json +34 -0
  4. run-34/checkpoint-428/model.safetensors +3 -0
  5. run-34/checkpoint-428/optimizer.pt +3 -0
  6. run-34/checkpoint-428/rng_state.pth +3 -0
  7. run-34/checkpoint-428/scheduler.pt +3 -0
  8. run-34/checkpoint-428/special_tokens_map.json +7 -0
  9. run-34/checkpoint-428/tokenizer.json +0 -0
  10. run-34/checkpoint-428/tokenizer_config.json +57 -0
  11. run-34/checkpoint-428/trainer_state.json +66 -0
  12. run-34/checkpoint-428/training_args.bin +3 -0
  13. run-34/checkpoint-428/vocab.txt +0 -0
  14. run-34/checkpoint-642/config.json +34 -0
  15. run-34/checkpoint-642/model.safetensors +3 -0
  16. run-34/checkpoint-642/optimizer.pt +3 -0
  17. run-34/checkpoint-642/rng_state.pth +3 -0
  18. run-34/checkpoint-642/scheduler.pt +3 -0
  19. run-34/checkpoint-642/special_tokens_map.json +7 -0
  20. run-34/checkpoint-642/tokenizer.json +0 -0
  21. run-34/checkpoint-642/tokenizer_config.json +57 -0
  22. run-34/checkpoint-642/trainer_state.json +86 -0
  23. run-34/checkpoint-642/training_args.bin +3 -0
  24. run-34/checkpoint-642/vocab.txt +0 -0
logs/events.out.tfevents.1713589743.1376c752d37a.9760.34 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d6d56413b88a65d3fe41d53ecf83847cc9fbf5feff41183a207e1d7ef26c8fd
3
- size 5482
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bafebcf56348b29e3bcbc6b2d586d6c04d8fba5dacb044733ff85b6d28efa0c
3
+ size 6942
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c7083431eb6fcd2c2ec7a4ec7a14fc1a11f2f8d6805544e01a2036c2d71a045
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ff2b8ab26cd043a2793efd97ce83ab086254efe8f54208ce8a4b414868070cd
3
  size 17549312
run-34/checkpoint-428/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": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-34/checkpoint-428/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:937acbbdca9ced28fd11ebaeb495b2e9844b73f5e081a9af997605a62fc23d84
3
+ size 17549312
run-34/checkpoint-428/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:559542ccaf874a3ad4346b158586ddfc13577b7d9defd91158bf5ff135ae0502
3
+ size 35123898
run-34/checkpoint-428/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d0c3b463a8fb08b95f5c77916114776bad3339b633df010e4ffd9b5ddabab1e
3
+ size 14308
run-34/checkpoint-428/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afaf32aea229a0bbd18fbeb1ea23205523682ee39b4d03eb011e3593bd77b324
3
+ size 1064
run-34/checkpoint-428/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-34/checkpoint-428/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-34/checkpoint-428/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-34/checkpoint-428/trainer_state.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7334504979496193,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-34/checkpoint-428",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 428,
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": 4.8471832275390625,
14
+ "learning_rate": 0.0003084590636066452,
15
+ "loss": 0.4895,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7041593438781488,
21
+ "eval_f1": 0.3631778058007566,
22
+ "eval_loss": 0.4574507474899292,
23
+ "eval_mcc": 0.25518418317792835,
24
+ "eval_precision": 0.6428571428571429,
25
+ "eval_recall": 0.2530755711775044,
26
+ "eval_runtime": 3.1432,
27
+ "eval_samples_per_second": 543.077,
28
+ "eval_steps_per_second": 17.18,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.93764066696167,
34
+ "learning_rate": 0.0002313442977049839,
35
+ "loss": 0.4474,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7334504979496193,
41
+ "eval_f1": 0.4291091593475534,
42
+ "eval_loss": 0.4426566958427429,
43
+ "eval_mcc": 0.3470390546850216,
44
+ "eval_precision": 0.75,
45
+ "eval_recall": 0.30052724077328646,
46
+ "eval_runtime": 3.675,
47
+ "eval_samples_per_second": 464.485,
48
+ "eval_steps_per_second": 14.694,
49
+ "step": 428
50
+ }
51
+ ],
52
+ "logging_steps": 500,
53
+ "max_steps": 1070,
54
+ "num_input_tokens_seen": 0,
55
+ "num_train_epochs": 5,
56
+ "save_steps": 500,
57
+ "total_flos": 1049551328880.0,
58
+ "train_batch_size": 32,
59
+ "trial_name": null,
60
+ "trial_params": {
61
+ "alpha": 0.7948524745832855,
62
+ "learning_rate": 0.0003855738295083065,
63
+ "num_train_epochs": 5,
64
+ "temperature": 15
65
+ }
66
+ }
run-34/checkpoint-428/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:051fab5723c44be17f791f8c45489e1552a330ef8815754068f2bb19eae15a1c
3
+ size 5048
run-34/checkpoint-428/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-34/checkpoint-642/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": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-34/checkpoint-642/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ff2b8ab26cd043a2793efd97ce83ab086254efe8f54208ce8a4b414868070cd
3
+ size 17549312
run-34/checkpoint-642/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c27526e1c9661e0eaf777dadb4cba4974b7f9624f2b67c3819365cf6bcb42a8
3
+ size 35123898
run-34/checkpoint-642/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11b0c3fe82ed8fc0c5e4a46035e8c4191c362f7c18bb672613fb7c69885d7960
3
+ size 14308
run-34/checkpoint-642/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2be01de77cf01fe0786ced9f3f172f54f417dfb78a2b9d4b7d5306c14a112fa5
3
+ size 1064
run-34/checkpoint-642/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-34/checkpoint-642/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-34/checkpoint-642/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-34/checkpoint-642/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7334504979496193,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-34/checkpoint-428",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 642,
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": 4.8471832275390625,
14
+ "learning_rate": 0.0003084590636066452,
15
+ "loss": 0.4895,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7041593438781488,
21
+ "eval_f1": 0.3631778058007566,
22
+ "eval_loss": 0.4574507474899292,
23
+ "eval_mcc": 0.25518418317792835,
24
+ "eval_precision": 0.6428571428571429,
25
+ "eval_recall": 0.2530755711775044,
26
+ "eval_runtime": 3.1432,
27
+ "eval_samples_per_second": 543.077,
28
+ "eval_steps_per_second": 17.18,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.93764066696167,
34
+ "learning_rate": 0.0002313442977049839,
35
+ "loss": 0.4474,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7334504979496193,
41
+ "eval_f1": 0.4291091593475534,
42
+ "eval_loss": 0.4426566958427429,
43
+ "eval_mcc": 0.3470390546850216,
44
+ "eval_precision": 0.75,
45
+ "eval_recall": 0.30052724077328646,
46
+ "eval_runtime": 3.675,
47
+ "eval_samples_per_second": 464.485,
48
+ "eval_steps_per_second": 14.694,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 3.0922608375549316,
54
+ "learning_rate": 0.0001542295318033226,
55
+ "loss": 0.4323,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7223198594024605,
61
+ "eval_f1": 0.35945945945945945,
62
+ "eval_loss": 0.4437848925590515,
63
+ "eval_mcc": 0.3145764348029479,
64
+ "eval_precision": 0.7777777777777778,
65
+ "eval_recall": 0.23374340949033393,
66
+ "eval_runtime": 3.1441,
67
+ "eval_samples_per_second": 542.917,
68
+ "eval_steps_per_second": 17.175,
69
+ "step": 642
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 1070,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 5,
76
+ "save_steps": 500,
77
+ "total_flos": 1574326993320.0,
78
+ "train_batch_size": 32,
79
+ "trial_name": null,
80
+ "trial_params": {
81
+ "alpha": 0.7948524745832855,
82
+ "learning_rate": 0.0003855738295083065,
83
+ "num_train_epochs": 5,
84
+ "temperature": 15
85
+ }
86
+ }
run-34/checkpoint-642/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:051fab5723c44be17f791f8c45489e1552a330ef8815754068f2bb19eae15a1c
3
+ size 5048
run-34/checkpoint-642/vocab.txt ADDED
The diff for this file is too large to render. See raw diff