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
61de39f
·
verified ·
1 Parent(s): fc62384

Training in progress, epoch 4

Browse files
Files changed (24) hide show
  1. logs/events.out.tfevents.1713589558.1376c752d37a.9760.32 +2 -2
  2. model.safetensors +1 -1
  3. run-32/checkpoint-642/config.json +34 -0
  4. run-32/checkpoint-642/model.safetensors +3 -0
  5. run-32/checkpoint-642/optimizer.pt +3 -0
  6. run-32/checkpoint-642/rng_state.pth +3 -0
  7. run-32/checkpoint-642/scheduler.pt +3 -0
  8. run-32/checkpoint-642/special_tokens_map.json +7 -0
  9. run-32/checkpoint-642/tokenizer.json +0 -0
  10. run-32/checkpoint-642/tokenizer_config.json +57 -0
  11. run-32/checkpoint-642/trainer_state.json +86 -0
  12. run-32/checkpoint-642/training_args.bin +3 -0
  13. run-32/checkpoint-642/vocab.txt +0 -0
  14. run-32/checkpoint-856/config.json +34 -0
  15. run-32/checkpoint-856/model.safetensors +3 -0
  16. run-32/checkpoint-856/optimizer.pt +3 -0
  17. run-32/checkpoint-856/rng_state.pth +3 -0
  18. run-32/checkpoint-856/scheduler.pt +3 -0
  19. run-32/checkpoint-856/special_tokens_map.json +7 -0
  20. run-32/checkpoint-856/tokenizer.json +0 -0
  21. run-32/checkpoint-856/tokenizer_config.json +57 -0
  22. run-32/checkpoint-856/trainer_state.json +106 -0
  23. run-32/checkpoint-856/training_args.bin +3 -0
  24. run-32/checkpoint-856/vocab.txt +0 -0
logs/events.out.tfevents.1713589558.1376c752d37a.9760.32 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a8542f9c9e63305eb1a59007fa97c6e954ba72753d006c02d4d61291ec3d219
3
- size 6213
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d27b9c5c8e727afa4b94fc2d10cdcae8c18602267188ad24050985b2259f92c2
3
+ size 7673
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e90ec32e2a644279816fa686ca7255b2cfae9b04bfb7a46b60506d3e9aac07f
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f2ad175fc036ef461d8be376547158cebf8e1336231653cd0fc155bc7081cf3
3
  size 17549312
run-32/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-32/checkpoint-642/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7545c0ed02786a0c7b0767fe41804bc4b030a04a9d03c2406880bfb763af0fcd
3
+ size 17549312
run-32/checkpoint-642/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fb42d62f50c5867428828ef81248a175987ffe3c3d8ab732d2e8237a86d4161
3
+ size 35123898
run-32/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-32/checkpoint-642/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94c1cd80e7d8a91e8f5dbb565e9e4eed2df3f4d12f891c3376dee5e0d8dbc59c
3
+ size 1064
run-32/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-32/checkpoint-642/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-32/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-32/checkpoint-642/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7574692442882249,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-32/checkpoint-642",
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": 7.148311614990234,
14
+ "learning_rate": 0.00021207436837213607,
15
+ "loss": 0.5606,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7129466900995899,
21
+ "eval_f1": 0.5040485829959513,
22
+ "eval_loss": 0.5154260396957397,
23
+ "eval_mcc": 0.3157140452463625,
24
+ "eval_precision": 0.594272076372315,
25
+ "eval_recall": 0.437609841827768,
26
+ "eval_runtime": 3.126,
27
+ "eval_samples_per_second": 546.06,
28
+ "eval_steps_per_second": 17.274,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.1550638675689697,
34
+ "learning_rate": 0.0001817780300332595,
35
+ "loss": 0.4995,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7393087287639133,
41
+ "eval_f1": 0.5071982281284606,
42
+ "eval_loss": 0.4903852641582489,
43
+ "eval_mcc": 0.36859649869532995,
44
+ "eval_precision": 0.6856287425149701,
45
+ "eval_recall": 0.4024604569420035,
46
+ "eval_runtime": 3.1521,
47
+ "eval_samples_per_second": 541.536,
48
+ "eval_steps_per_second": 17.131,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.5803661346435547,
54
+ "learning_rate": 0.00015148169169438292,
55
+ "loss": 0.479,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7574692442882249,
61
+ "eval_f1": 0.541019955654102,
62
+ "eval_loss": 0.48610907793045044,
63
+ "eval_mcc": 0.41710213681200975,
64
+ "eval_precision": 0.7327327327327328,
65
+ "eval_recall": 0.4288224956063269,
66
+ "eval_runtime": 3.1361,
67
+ "eval_samples_per_second": 544.307,
68
+ "eval_steps_per_second": 17.219,
69
+ "step": 642
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 1712,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 8,
76
+ "save_steps": 500,
77
+ "total_flos": 1574326993320.0,
78
+ "train_batch_size": 32,
79
+ "trial_name": null,
80
+ "trial_params": {
81
+ "alpha": 0.9251938490023766,
82
+ "learning_rate": 0.00024237070671101265,
83
+ "num_train_epochs": 8,
84
+ "temperature": 22
85
+ }
86
+ }
run-32/checkpoint-642/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0211643bf748d7e4241acbd1423a0a1eddceec49ca8d870c57f42d37dfe7bbe8
3
+ size 5048
run-32/checkpoint-642/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-32/checkpoint-856/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-32/checkpoint-856/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f2ad175fc036ef461d8be376547158cebf8e1336231653cd0fc155bc7081cf3
3
+ size 17549312
run-32/checkpoint-856/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:956dff533bd01149235618fda43ecd5c666a83577c61729c466111b1df501647
3
+ size 35123898
run-32/checkpoint-856/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:057111bfbb4d541cc190a3ed4fcfe228e7425a50e4a06afd33224d43272b1a59
3
+ size 14308
run-32/checkpoint-856/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3134b361018ac69b8bcde524f73ff680a566f240c666714423fdda1ae2a72235
3
+ size 1064
run-32/checkpoint-856/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-32/checkpoint-856/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-32/checkpoint-856/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-32/checkpoint-856/trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7574692442882249,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-32/checkpoint-642",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 856,
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": 7.148311614990234,
14
+ "learning_rate": 0.00021207436837213607,
15
+ "loss": 0.5606,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7129466900995899,
21
+ "eval_f1": 0.5040485829959513,
22
+ "eval_loss": 0.5154260396957397,
23
+ "eval_mcc": 0.3157140452463625,
24
+ "eval_precision": 0.594272076372315,
25
+ "eval_recall": 0.437609841827768,
26
+ "eval_runtime": 3.126,
27
+ "eval_samples_per_second": 546.06,
28
+ "eval_steps_per_second": 17.274,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.1550638675689697,
34
+ "learning_rate": 0.0001817780300332595,
35
+ "loss": 0.4995,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7393087287639133,
41
+ "eval_f1": 0.5071982281284606,
42
+ "eval_loss": 0.4903852641582489,
43
+ "eval_mcc": 0.36859649869532995,
44
+ "eval_precision": 0.6856287425149701,
45
+ "eval_recall": 0.4024604569420035,
46
+ "eval_runtime": 3.1521,
47
+ "eval_samples_per_second": 541.536,
48
+ "eval_steps_per_second": 17.131,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.5803661346435547,
54
+ "learning_rate": 0.00015148169169438292,
55
+ "loss": 0.479,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7574692442882249,
61
+ "eval_f1": 0.541019955654102,
62
+ "eval_loss": 0.48610907793045044,
63
+ "eval_mcc": 0.41710213681200975,
64
+ "eval_precision": 0.7327327327327328,
65
+ "eval_recall": 0.4288224956063269,
66
+ "eval_runtime": 3.1361,
67
+ "eval_samples_per_second": 544.307,
68
+ "eval_steps_per_second": 17.219,
69
+ "step": 642
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 2.8908817768096924,
74
+ "learning_rate": 0.00012118535335550633,
75
+ "loss": 0.4702,
76
+ "step": 856
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7527826596367897,
81
+ "eval_f1": 0.5193621867881549,
82
+ "eval_loss": 0.4752483069896698,
83
+ "eval_mcc": 0.4034441704043775,
84
+ "eval_precision": 0.7378640776699029,
85
+ "eval_recall": 0.4007029876977153,
86
+ "eval_runtime": 3.1566,
87
+ "eval_samples_per_second": 540.775,
88
+ "eval_steps_per_second": 17.107,
89
+ "step": 856
90
+ }
91
+ ],
92
+ "logging_steps": 500,
93
+ "max_steps": 1712,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 8,
96
+ "save_steps": 500,
97
+ "total_flos": 2099102657760.0,
98
+ "train_batch_size": 32,
99
+ "trial_name": null,
100
+ "trial_params": {
101
+ "alpha": 0.9251938490023766,
102
+ "learning_rate": 0.00024237070671101265,
103
+ "num_train_epochs": 8,
104
+ "temperature": 22
105
+ }
106
+ }
run-32/checkpoint-856/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0211643bf748d7e4241acbd1423a0a1eddceec49ca8d870c57f42d37dfe7bbe8
3
+ size 5048
run-32/checkpoint-856/vocab.txt ADDED
The diff for this file is too large to render. See raw diff