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
2bcec21
·
verified ·
1 Parent(s): 6a1f693

Training in progress, epoch 2

Browse files
Files changed (24) hide show
  1. logs/events.out.tfevents.1709823236.013ec1551212.75384.8 +2 -2
  2. model.safetensors +1 -1
  3. run-8/checkpoint-1532/config.json +34 -0
  4. run-8/checkpoint-1532/model.safetensors +3 -0
  5. run-8/checkpoint-1532/optimizer.pt +3 -0
  6. run-8/checkpoint-1532/rng_state.pth +3 -0
  7. run-8/checkpoint-1532/scheduler.pt +3 -0
  8. run-8/checkpoint-1532/special_tokens_map.json +7 -0
  9. run-8/checkpoint-1532/tokenizer.json +0 -0
  10. run-8/checkpoint-1532/tokenizer_config.json +57 -0
  11. run-8/checkpoint-1532/trainer_state.json +64 -0
  12. run-8/checkpoint-1532/training_args.bin +3 -0
  13. run-8/checkpoint-1532/vocab.txt +0 -0
  14. run-8/checkpoint-766/config.json +34 -0
  15. run-8/checkpoint-766/model.safetensors +3 -0
  16. run-8/checkpoint-766/optimizer.pt +3 -0
  17. run-8/checkpoint-766/rng_state.pth +3 -0
  18. run-8/checkpoint-766/scheduler.pt +3 -0
  19. run-8/checkpoint-766/special_tokens_map.json +7 -0
  20. run-8/checkpoint-766/tokenizer.json +0 -0
  21. run-8/checkpoint-766/tokenizer_config.json +57 -0
  22. run-8/checkpoint-766/trainer_state.json +45 -0
  23. run-8/checkpoint-766/training_args.bin +3 -0
  24. run-8/checkpoint-766/vocab.txt +0 -0
logs/events.out.tfevents.1709823236.013ec1551212.75384.8 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:790e9abbd3bc0f5b622a4fbe098eae692eda2ef05750cdf8ec3c3e20652d6586
3
- size 5325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bfd5e533a21835f81a4ad8faacbd7dcb9f4e92743f7c45018a95eca1367024b
3
+ size 6008
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6da86c79d0e17c8581b54995792ebaf999b19b8e3992a475ee89b3daf5831ef3
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:777cfb0d13b626d72e09a0c5baf26802f79c3e6cbc416eae79497bf1f272b7e5
3
  size 17549312
run-8/checkpoint-1532/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-8/checkpoint-1532/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:777cfb0d13b626d72e09a0c5baf26802f79c3e6cbc416eae79497bf1f272b7e5
3
+ size 17549312
run-8/checkpoint-1532/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f092d215b1424bcb2a08e7fa43d81c183340f57c28f4bd863b5df34777bb42b7
3
+ size 35122746
run-8/checkpoint-1532/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16aaf318a00ee2d6780264865ac856fcd3f746d06b5d79fd7d77f53b35786488
3
+ size 14054
run-8/checkpoint-1532/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae833486d27377b041010a76f7b9079d913e0489782228a24827731d88bfd1f3
3
+ size 1064
run-8/checkpoint-1532/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-8/checkpoint-1532/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-1532/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-8/checkpoint-1532/trainer_state.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.687866927592955,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-8/checkpoint-1532",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1532,
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": 1.324540138244629,
14
+ "learning_rate": 5.804695204967391e-05,
15
+ "loss": 0.357,
16
+ "step": 766
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6193737769080235,
21
+ "eval_f1": 0.45133991537376583,
22
+ "eval_loss": 0.33073100447654724,
23
+ "eval_precision": 0.8080808080808081,
24
+ "eval_recall": 0.3131115459882583,
25
+ "eval_runtime": 132.7451,
26
+ "eval_samples_per_second": 7.699,
27
+ "eval_steps_per_second": 1.929,
28
+ "step": 766
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 5.969402313232422,
33
+ "learning_rate": 2.9023476024836956e-05,
34
+ "loss": 0.3322,
35
+ "step": 1532
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.687866927592955,
40
+ "eval_f1": 0.5997490589711417,
41
+ "eval_loss": 0.3239139914512634,
42
+ "eval_precision": 0.8356643356643356,
43
+ "eval_recall": 0.46771037181996084,
44
+ "eval_runtime": 132.1156,
45
+ "eval_samples_per_second": 7.736,
46
+ "eval_steps_per_second": 1.938,
47
+ "step": 1532
48
+ }
49
+ ],
50
+ "logging_steps": 500,
51
+ "max_steps": 2298,
52
+ "num_input_tokens_seen": 0,
53
+ "num_train_epochs": 3,
54
+ "save_steps": 500,
55
+ "total_flos": 471390394560.0,
56
+ "train_batch_size": 4,
57
+ "trial_name": null,
58
+ "trial_params": {
59
+ "alpha": 0.49392332530271654,
60
+ "learning_rate": 8.707042807451088e-05,
61
+ "num_train_epochs": 3,
62
+ "temperature": 24
63
+ }
64
+ }
run-8/checkpoint-1532/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98c5a1f7db5395b0c52d75563916e8ec0ae6c52e905b7e4048dff1722afde33b
3
+ size 4920
run-8/checkpoint-1532/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-766/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-8/checkpoint-766/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6da86c79d0e17c8581b54995792ebaf999b19b8e3992a475ee89b3daf5831ef3
3
+ size 17549312
run-8/checkpoint-766/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c24eb32c736f91f16bb6bb0568f29161e0ed9b463260a5276a0ba23c0473d7dd
3
+ size 35122746
run-8/checkpoint-766/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a29b5a9fab412f426bae759e459d7d9236aab6602ae439ea13f5bd437e1b98a4
3
+ size 14054
run-8/checkpoint-766/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44a8591740621ca723a809b27c5591d6f786750e5e574c19d8516cbc196b40cc
3
+ size 1064
run-8/checkpoint-766/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-8/checkpoint-766/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-766/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-8/checkpoint-766/trainer_state.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6193737769080235,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-8/checkpoint-766",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 766,
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": 1.324540138244629,
14
+ "learning_rate": 5.804695204967391e-05,
15
+ "loss": 0.357,
16
+ "step": 766
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6193737769080235,
21
+ "eval_f1": 0.45133991537376583,
22
+ "eval_loss": 0.33073100447654724,
23
+ "eval_precision": 0.8080808080808081,
24
+ "eval_recall": 0.3131115459882583,
25
+ "eval_runtime": 132.7451,
26
+ "eval_samples_per_second": 7.699,
27
+ "eval_steps_per_second": 1.929,
28
+ "step": 766
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 2298,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 3,
35
+ "save_steps": 500,
36
+ "total_flos": 235695197280.0,
37
+ "train_batch_size": 4,
38
+ "trial_name": null,
39
+ "trial_params": {
40
+ "alpha": 0.49392332530271654,
41
+ "learning_rate": 8.707042807451088e-05,
42
+ "num_train_epochs": 3,
43
+ "temperature": 24
44
+ }
45
+ }
run-8/checkpoint-766/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98c5a1f7db5395b0c52d75563916e8ec0ae6c52e905b7e4048dff1722afde33b
3
+ size 4920
run-8/checkpoint-766/vocab.txt ADDED
The diff for this file is too large to render. See raw diff