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
d819b41
·
verified ·
1 Parent(s): d24a2a9

Training in progress, epoch 2

Browse files
Files changed (26) hide show
  1. logs/events.out.tfevents.1709742338.fcc57e6e3903.3035.3 +2 -2
  2. model.safetensors +1 -1
  3. run-3/checkpoint-176/config.json +34 -0
  4. run-3/checkpoint-176/model.safetensors +3 -0
  5. run-3/checkpoint-176/optimizer.pt +3 -0
  6. run-3/checkpoint-176/rng_state.pth +3 -0
  7. run-3/checkpoint-176/scheduler.pt +3 -0
  8. run-3/checkpoint-176/special_tokens_map.json +7 -0
  9. run-3/checkpoint-176/tokenizer.json +0 -0
  10. run-3/checkpoint-176/tokenizer_config.json +57 -0
  11. run-3/checkpoint-176/trainer_state.json +46 -0
  12. run-3/checkpoint-176/training_args.bin +3 -0
  13. run-3/checkpoint-176/vocab.txt +0 -0
  14. run-3/checkpoint-352/config.json +34 -0
  15. run-3/checkpoint-352/model.safetensors +3 -0
  16. run-3/checkpoint-352/optimizer.pt +3 -0
  17. run-3/checkpoint-352/rng_state.pth +3 -0
  18. run-3/checkpoint-352/scheduler.pt +3 -0
  19. run-3/checkpoint-352/special_tokens_map.json +7 -0
  20. run-3/checkpoint-352/tokenizer.json +0 -0
  21. run-3/checkpoint-352/tokenizer_config.json +57 -0
  22. run-3/checkpoint-352/trainer_state.json +65 -0
  23. run-3/checkpoint-352/training_args.bin +3 -0
  24. run-3/checkpoint-352/vocab.txt +0 -0
  25. tokenizer.json +1 -1
  26. training_args.bin +1 -1
logs/events.out.tfevents.1709742338.fcc57e6e3903.3035.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fc37f035c54ce47187cd97c64bdefab842600ca13b7b3b129c51201bf249d29
3
- size 5328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e93aadbbfe3ced2c9914b0a9803b303f44e2911fe4db39dda063742b8c9f4b7e
3
+ size 6011
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b72faf6103e6a3c3d6bdafbff0cbeaac121ce7de8cb2bb06a35f4382a46810f7
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1974eec902e3411aa7bdd0f55ac57f6756f178ad876646ecf017e352ad9e898e
3
  size 17549312
run-3/checkpoint-176/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-3/checkpoint-176/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97780c69f05de76f9d89d5b245a3979297519b2bb08ee6e324817933a1e9732d
3
+ size 17549312
run-3/checkpoint-176/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f8e333d05e84d805f18a38e78ce9501048bf03a54bec47e756aa8091e56d87d
3
+ size 35122746
run-3/checkpoint-176/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb717feef51d4e88669e8d1d471d0d708609e7a7f8d567ec759694a724e3fc78
3
+ size 14054
run-3/checkpoint-176/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4df630553ac056afaca829e09299470a446e3edfbcc58c6ef47d35774499ff5a
3
+ size 1064
run-3/checkpoint-176/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-3/checkpoint-176/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-176/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-3/checkpoint-176/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5148514851485149,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-176",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 176,
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": 0.5431386232376099,
14
+ "learning_rate": 0.00012088388613301416,
15
+ "loss": 0.2133,
16
+ "step": 176
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5148514851485149,
21
+ "eval_f1": 0.14035087719298245,
22
+ "eval_loss": 0.20053359866142273,
23
+ "eval_precision": 0.6060606060606061,
24
+ "eval_recall": 0.07936507936507936,
25
+ "eval_runtime": 15.0376,
26
+ "eval_samples_per_second": 33.582,
27
+ "eval_steps_per_second": 1.064,
28
+ "step": 176
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 1760,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 10,
35
+ "save_steps": 500,
36
+ "total_flos": 777843283140.0,
37
+ "train_batch_size": 54,
38
+ "trial_name": null,
39
+ "trial_params": {
40
+ "alpha": 0.239256796645401,
41
+ "learning_rate": 0.0001343154290366824,
42
+ "num_train_epochs": 10,
43
+ "per_device_train_batch_size": 54,
44
+ "temperature": 13
45
+ }
46
+ }
run-3/checkpoint-176/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e3fa9f35ba1a109d4dbcaa99a0da7b79ffac3932fc22f17787de76b9701cac
3
+ size 4920
run-3/checkpoint-176/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-352/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-3/checkpoint-352/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1974eec902e3411aa7bdd0f55ac57f6756f178ad876646ecf017e352ad9e898e
3
+ size 17549312
run-3/checkpoint-352/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fe56813aec20e9c530c799541711276e4122a893f587c682768f294add19ae8
3
+ size 35122746
run-3/checkpoint-352/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a77ce242917a7974aafb79775c4d65cace9e5b2e8fa33c1e308b9820377f088
3
+ size 14054
run-3/checkpoint-352/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:002fe54a80031d1f95e02e2eee1d855cb07114f7aafaa809fb60363c389c81c4
3
+ size 1064
run-3/checkpoint-352/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-3/checkpoint-352/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-352/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-3/checkpoint-352/trainer_state.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5148514851485149,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-176",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 352,
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": 0.5431386232376099,
14
+ "learning_rate": 0.00012088388613301416,
15
+ "loss": 0.2133,
16
+ "step": 176
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5148514851485149,
21
+ "eval_f1": 0.14035087719298245,
22
+ "eval_loss": 0.20053359866142273,
23
+ "eval_precision": 0.6060606060606061,
24
+ "eval_recall": 0.07936507936507936,
25
+ "eval_runtime": 15.0376,
26
+ "eval_samples_per_second": 33.582,
27
+ "eval_steps_per_second": 1.064,
28
+ "step": 176
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 0.2198910117149353,
33
+ "learning_rate": 0.00010745234322934593,
34
+ "loss": 0.2028,
35
+ "step": 352
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.5069306930693069,
40
+ "eval_f1": 0.1263157894736842,
41
+ "eval_loss": 0.20091117918491364,
42
+ "eval_precision": 0.5454545454545454,
43
+ "eval_recall": 0.07142857142857142,
44
+ "eval_runtime": 14.9354,
45
+ "eval_samples_per_second": 33.812,
46
+ "eval_steps_per_second": 1.071,
47
+ "step": 352
48
+ }
49
+ ],
50
+ "logging_steps": 500,
51
+ "max_steps": 1760,
52
+ "num_input_tokens_seen": 0,
53
+ "num_train_epochs": 10,
54
+ "save_steps": 500,
55
+ "total_flos": 1555686566280.0,
56
+ "train_batch_size": 54,
57
+ "trial_name": null,
58
+ "trial_params": {
59
+ "alpha": 0.239256796645401,
60
+ "learning_rate": 0.0001343154290366824,
61
+ "num_train_epochs": 10,
62
+ "per_device_train_batch_size": 54,
63
+ "temperature": 13
64
+ }
65
+ }
run-3/checkpoint-352/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e3fa9f35ba1a109d4dbcaa99a0da7b79ffac3932fc22f17787de76b9701cac
3
+ size 4920
run-3/checkpoint-352/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json CHANGED
@@ -2,7 +2,7 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 31,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 33,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28fccab1cf160e9a976a6e2833e6b2e52a870fecc8101aaab94f3f44ebbc487e
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e3fa9f35ba1a109d4dbcaa99a0da7b79ffac3932fc22f17787de76b9701cac
3
  size 4920