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
75e8dbd
·
verified ·
1 Parent(s): 5cf7d98

Training in progress, epoch 1

Browse files
Files changed (27) hide show
  1. logs/events.out.tfevents.1709469575.49ae8f4e8e7b.1647.43 +2 -2
  2. logs/events.out.tfevents.1709470190.49ae8f4e8e7b.1647.44 +3 -0
  3. logs/events.out.tfevents.1709470393.49ae8f4e8e7b.1647.45 +3 -0
  4. model.safetensors +1 -1
  5. run-42/checkpoint-1581/config.json +34 -0
  6. run-42/checkpoint-1581/model.safetensors +3 -0
  7. run-42/checkpoint-1581/optimizer.pt +3 -0
  8. run-42/checkpoint-1581/rng_state.pth +3 -0
  9. run-42/checkpoint-1581/scheduler.pt +3 -0
  10. run-42/checkpoint-1581/special_tokens_map.json +7 -0
  11. run-42/checkpoint-1581/tokenizer.json +0 -0
  12. run-42/checkpoint-1581/tokenizer_config.json +57 -0
  13. run-42/checkpoint-1581/trainer_state.json +74 -0
  14. run-42/checkpoint-1581/training_args.bin +3 -0
  15. run-42/checkpoint-1581/vocab.txt +0 -0
  16. run-44/checkpoint-527/config.json +34 -0
  17. run-44/checkpoint-527/model.safetensors +3 -0
  18. run-44/checkpoint-527/optimizer.pt +3 -0
  19. run-44/checkpoint-527/rng_state.pth +3 -0
  20. run-44/checkpoint-527/scheduler.pt +3 -0
  21. run-44/checkpoint-527/special_tokens_map.json +7 -0
  22. run-44/checkpoint-527/tokenizer.json +0 -0
  23. run-44/checkpoint-527/tokenizer_config.json +57 -0
  24. run-44/checkpoint-527/trainer_state.json +42 -0
  25. run-44/checkpoint-527/training_args.bin +3 -0
  26. run-44/checkpoint-527/vocab.txt +0 -0
  27. training_args.bin +1 -1
logs/events.out.tfevents.1709469575.49ae8f4e8e7b.1647.43 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a40a554ad2f2a814a7ccdf822f8be4281477a5375abfb1ccf9fe4d9d7d70585
3
- size 5714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d3ef41a27e7e22165c38b90beda688bc6277f601f4926859965455079946e7a
3
+ size 6602
logs/events.out.tfevents.1709470190.49ae8f4e8e7b.1647.44 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5d3ff1120a464fec2123b2e296f64f226a515b182473888cdc986e38dce241a
3
+ size 5180
logs/events.out.tfevents.1709470393.49ae8f4e8e7b.1647.45 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b839ca66a2bc530be1402a93d5d7caf995899081b74019385ec5745d613d92
3
+ size 5180
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47d82556b71ec7ba2d233600e54bda5a8ce8b5a526201d2c16fd00fdf0367f05
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d889f0a9958d2222a94c1f593a25f0c74e27e6d39e53dbd6df08f7c4d1b933
3
  size 17549312
run-42/checkpoint-1581/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-42/checkpoint-1581/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb1b9f1ab8e5ad093c63e748e53852b739c329d8f97c125b4654c2267b38ee52
3
+ size 17549312
run-42/checkpoint-1581/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d83cdc98130c769c33c5e1fb072888528a168ee1748c05b784d3f8d9d9f0399
3
+ size 35123898
run-42/checkpoint-1581/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46669ed40c03155d5eb7492631b00659805dbfc29b49abcca7edef225d9a6aae
3
+ size 14308
run-42/checkpoint-1581/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5145effbaf6d585934880de23e63dc39469f49bddb6795d2bedb06c0d10f088
3
+ size 1064
run-42/checkpoint-1581/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-42/checkpoint-1581/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-42/checkpoint-1581/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-42/checkpoint-1581/trainer_state.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8405963302752294,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-42/checkpoint-527",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1581,
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": 12.218423843383789,
14
+ "learning_rate": 0.0002468577923854863,
15
+ "loss": 1.1492,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8405963302752294,
21
+ "eval_loss": 1.2373847961425781,
22
+ "eval_runtime": 2.8121,
23
+ "eval_samples_per_second": 310.092,
24
+ "eval_steps_per_second": 2.489,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 7.051322937011719,
30
+ "learning_rate": 0.00012342889619274314,
31
+ "loss": 0.5283,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.8302752293577982,
37
+ "eval_loss": 1.383708119392395,
38
+ "eval_runtime": 2.8134,
39
+ "eval_samples_per_second": 309.949,
40
+ "eval_steps_per_second": 2.488,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": NaN,
46
+ "learning_rate": 2.3421042920824125e-07,
47
+ "loss": 0.3751,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8188073394495413,
53
+ "eval_loss": 1.4459969997406006,
54
+ "eval_runtime": 2.8106,
55
+ "eval_samples_per_second": 310.249,
56
+ "eval_steps_per_second": 2.491,
57
+ "step": 1581
58
+ }
59
+ ],
60
+ "logging_steps": 500,
61
+ "max_steps": 1581,
62
+ "num_input_tokens_seen": 0,
63
+ "num_train_epochs": 3,
64
+ "save_steps": 500,
65
+ "total_flos": 24228458327580.0,
66
+ "train_batch_size": 128,
67
+ "trial_name": null,
68
+ "trial_params": {
69
+ "alpha": 0.47037947579293116,
70
+ "learning_rate": 0.00037028668857822943,
71
+ "num_train_epochs": 3,
72
+ "temperature": 12
73
+ }
74
+ }
run-42/checkpoint-1581/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aca7b7635b8eb9b501fdbcecf7f1e78fe055dc3cb1c47b3d7908aee85b5e4ec
3
+ size 4984
run-42/checkpoint-1581/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-44/checkpoint-527/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-44/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d889f0a9958d2222a94c1f593a25f0c74e27e6d39e53dbd6df08f7c4d1b933
3
+ size 17549312
run-44/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45cc74922e82209980cc9f8f306176861d3f6faf12f5b79c78ff32a572f98dbe
3
+ size 35123898
run-44/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a32291cb0c1329fbb9596dcc47c5d9b0d1f71ecc09dad1791e0b193314659e4
3
+ size 14308
run-44/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dcdcaa2bb0fba7d565c4327853fd6f3ec145e8c25ce2673391a30656f911ecf
3
+ size 1064
run-44/checkpoint-527/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-44/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-44/checkpoint-527/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-44/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8291284403669725,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-44/checkpoint-527",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 527,
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": 15.370396614074707,
14
+ "learning_rate": 0.000199328116615274,
15
+ "loss": 0.9859,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8291284403669725,
21
+ "eval_loss": 1.0127737522125244,
22
+ "eval_runtime": 2.815,
23
+ "eval_samples_per_second": 309.77,
24
+ "eval_steps_per_second": 2.487,
25
+ "step": 527
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 2108,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 4,
32
+ "save_steps": 500,
33
+ "total_flos": 8057768762220.0,
34
+ "train_batch_size": 128,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "alpha": 0.6434351873812945,
38
+ "learning_rate": 0.00026577082215369866,
39
+ "num_train_epochs": 4,
40
+ "temperature": 15
41
+ }
42
+ }
run-44/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d991bc95836a675aff1d1def1fe88079b9249a92348211dab61394ffdea3d5a1
3
+ size 4984
run-44/checkpoint-527/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 sha256:3aca7b7635b8eb9b501fdbcecf7f1e78fe055dc3cb1c47b3d7908aee85b5e4ec
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d991bc95836a675aff1d1def1fe88079b9249a92348211dab61394ffdea3d5a1
3
  size 4984