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
8af7fe8
·
verified ·
1 Parent(s): 4a131b6

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. logs/events.out.tfevents.1713587822.1376c752d37a.9760.10 +2 -2
  2. logs/events.out.tfevents.1713587889.1376c752d37a.9760.11 +3 -0
  3. model.safetensors +1 -1
  4. run-10/checkpoint-642/config.json +34 -0
  5. run-10/checkpoint-642/model.safetensors +3 -0
  6. run-10/checkpoint-642/optimizer.pt +3 -0
  7. run-10/checkpoint-642/rng_state.pth +3 -0
  8. run-10/checkpoint-642/scheduler.pt +3 -0
  9. run-10/checkpoint-642/special_tokens_map.json +7 -0
  10. run-10/checkpoint-642/tokenizer.json +0 -0
  11. run-10/checkpoint-642/tokenizer_config.json +57 -0
  12. run-10/checkpoint-642/trainer_state.json +86 -0
  13. run-10/checkpoint-642/training_args.bin +3 -0
  14. run-10/checkpoint-642/vocab.txt +0 -0
  15. run-11/checkpoint-214/config.json +34 -0
  16. run-11/checkpoint-214/model.safetensors +3 -0
  17. run-11/checkpoint-214/optimizer.pt +3 -0
  18. run-11/checkpoint-214/rng_state.pth +3 -0
  19. run-11/checkpoint-214/scheduler.pt +3 -0
  20. run-11/checkpoint-214/special_tokens_map.json +7 -0
  21. run-11/checkpoint-214/tokenizer.json +0 -0
  22. run-11/checkpoint-214/tokenizer_config.json +57 -0
  23. run-11/checkpoint-214/trainer_state.json +46 -0
  24. run-11/checkpoint-214/training_args.bin +3 -0
  25. run-11/checkpoint-214/vocab.txt +0 -0
  26. training_args.bin +1 -1
logs/events.out.tfevents.1713587822.1376c752d37a.9760.10 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:795a130cbadd3bcc7d565ceeeb014e9f3eae94394c9f0b1d691c7d846be31c16
3
- size 6213
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e805263988fd2d0d370dc0f88d401d4d338bfd926d36e0eadc9f660f7de8f49f
3
+ size 7673
logs/events.out.tfevents.1713587889.1376c752d37a.9760.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abe6176881c666021d81515c11f3e5c55bbe3b52cf87fb25c9bc285453aaa6be
3
+ size 5482
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f22e5f9985c8d5aac29e35557c4e14733afb354f88cf2ea82b1ccaf68d14c1b
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bf217176616957db81afaa727013dd843ec597db5ad1173a132bcd96a179788
3
  size 17549312
run-10/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-10/checkpoint-642/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b07f79bc07be050416282e55c83b0e2d1f0a6038bac55928d6c4f3ab1fd45b5
3
+ size 17549312
run-10/checkpoint-642/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c24e9f7022557fbb3f5d01bdbf5ba8211d73179d8bd7abb5004db92365b3a5a4
3
+ size 35123898
run-10/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-10/checkpoint-642/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3a2b132724a126572ef11fce9a6c8e4157983c9dcf22c57ee45715b270db39d
3
+ size 1064
run-10/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-10/checkpoint-642/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-10/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-10/checkpoint-642/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6690099589923842,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-10/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": 1.0974807739257812,
14
+ "learning_rate": 0.0004326089412215258,
15
+ "loss": 0.1568,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6654950205038078,
21
+ "eval_f1": 0.02393162393162393,
22
+ "eval_loss": 0.14753811061382294,
23
+ "eval_mcc": 0.021494295311278402,
24
+ "eval_precision": 0.4375,
25
+ "eval_recall": 0.012302284710017574,
26
+ "eval_runtime": 3.1372,
27
+ "eval_samples_per_second": 544.118,
28
+ "eval_steps_per_second": 17.213,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 0.3948715031147003,
34
+ "learning_rate": 0.00038454128108580076,
35
+ "loss": 0.1489,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.6690099589923842,
41
+ "eval_f1": 0.053601340033500824,
42
+ "eval_loss": 0.14619438350200653,
43
+ "eval_mcc": 0.06522448130722841,
44
+ "eval_precision": 0.5714285714285714,
45
+ "eval_recall": 0.028119507908611598,
46
+ "eval_runtime": 3.1687,
47
+ "eval_samples_per_second": 538.707,
48
+ "eval_steps_per_second": 17.042,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 0.6567928791046143,
54
+ "learning_rate": 0.00033647362095007565,
55
+ "loss": 0.1472,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.667252489748096,
61
+ "eval_f1": 0.030716723549488054,
62
+ "eval_loss": 0.1447131335735321,
63
+ "eval_mcc": 0.04171739573435696,
64
+ "eval_precision": 0.5294117647058824,
65
+ "eval_recall": 0.015817223198594025,
66
+ "eval_runtime": 3.1648,
67
+ "eval_samples_per_second": 539.364,
68
+ "eval_steps_per_second": 17.062,
69
+ "step": 642
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 2140,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 10,
76
+ "save_steps": 500,
77
+ "total_flos": 1574326993320.0,
78
+ "train_batch_size": 32,
79
+ "trial_name": null,
80
+ "trial_params": {
81
+ "alpha": 0.22222976837593644,
82
+ "learning_rate": 0.0004806766013572509,
83
+ "num_train_epochs": 10,
84
+ "temperature": 30
85
+ }
86
+ }
run-10/checkpoint-642/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce1e2c15e1a8520a4fcd42f95a999b7b5dccad7eb96455bf4a3b6fdb073ddf90
3
+ size 5048
run-10/checkpoint-642/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-11/checkpoint-214/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-11/checkpoint-214/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bf217176616957db81afaa727013dd843ec597db5ad1173a132bcd96a179788
3
+ size 17549312
run-11/checkpoint-214/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:551f5af553e47d2b59fffb9babaf7e804f509bf1ab7ab28a0d13ce21c84e2b4d
3
+ size 35123898
run-11/checkpoint-214/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc7e492e6768bc7c3c01ac823da5a8177cf34fc1b175dd727fa3be969661a151
3
+ size 14308
run-11/checkpoint-214/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:facdfe60b79ca80358caca4987af2fb2766d0f80ca3c8f2b33f5c18ec69a81f0
3
+ size 1064
run-11/checkpoint-214/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-11/checkpoint-214/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-11/checkpoint-214/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-11/checkpoint-214/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7082601054481547,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/checkpoint-214",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 214,
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": 7.572170734405518,
14
+ "learning_rate": 0.00012123385931636098,
15
+ "loss": 0.5934,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7082601054481547,
21
+ "eval_f1": 0.435374149659864,
22
+ "eval_loss": 0.5416340827941895,
23
+ "eval_mcc": 0.28153811271695595,
24
+ "eval_precision": 0.6134185303514377,
25
+ "eval_recall": 0.3374340949033392,
26
+ "eval_runtime": 3.1348,
27
+ "eval_samples_per_second": 544.534,
28
+ "eval_steps_per_second": 17.226,
29
+ "step": 214
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 1926,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 9,
36
+ "save_steps": 500,
37
+ "total_flos": 524775664440.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.9696180923551023,
42
+ "learning_rate": 0.0001363880917309061,
43
+ "num_train_epochs": 9,
44
+ "temperature": 20
45
+ }
46
+ }
run-11/checkpoint-214/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf09225d27944ca78423d64d6c64a16677c929bc8b03065b895767c7cb1b599b
3
+ size 5048
run-11/checkpoint-214/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:ce1e2c15e1a8520a4fcd42f95a999b7b5dccad7eb96455bf4a3b6fdb073ddf90
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf09225d27944ca78423d64d6c64a16677c929bc8b03065b895767c7cb1b599b
3
  size 5048