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
cef539e
·
verified ·
1 Parent(s): c42a07b

Training in progress, epoch 3

Browse files
Files changed (24) hide show
  1. logs/events.out.tfevents.1713589826.1376c752d37a.9760.35 +2 -2
  2. model.safetensors +1 -1
  3. run-35/checkpoint-428/config.json +34 -0
  4. run-35/checkpoint-428/model.safetensors +3 -0
  5. run-35/checkpoint-428/optimizer.pt +3 -0
  6. run-35/checkpoint-428/rng_state.pth +3 -0
  7. run-35/checkpoint-428/scheduler.pt +3 -0
  8. run-35/checkpoint-428/special_tokens_map.json +7 -0
  9. run-35/checkpoint-428/tokenizer.json +0 -0
  10. run-35/checkpoint-428/tokenizer_config.json +57 -0
  11. run-35/checkpoint-428/trainer_state.json +66 -0
  12. run-35/checkpoint-428/training_args.bin +3 -0
  13. run-35/checkpoint-428/vocab.txt +0 -0
  14. run-35/checkpoint-642/config.json +34 -0
  15. run-35/checkpoint-642/model.safetensors +3 -0
  16. run-35/checkpoint-642/optimizer.pt +3 -0
  17. run-35/checkpoint-642/rng_state.pth +3 -0
  18. run-35/checkpoint-642/scheduler.pt +3 -0
  19. run-35/checkpoint-642/special_tokens_map.json +7 -0
  20. run-35/checkpoint-642/tokenizer.json +0 -0
  21. run-35/checkpoint-642/tokenizer_config.json +57 -0
  22. run-35/checkpoint-642/trainer_state.json +86 -0
  23. run-35/checkpoint-642/training_args.bin +3 -0
  24. run-35/checkpoint-642/vocab.txt +0 -0
logs/events.out.tfevents.1713589826.1376c752d37a.9760.35 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:756b72028d18b1bfceefb0f06026fe869bd79ebb2760e9a8f9ed73d4e44b6598
3
- size 5483
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b3fb01a902a45d0a3de62c370749ba796e520a45aff5046c8d39d37b139d88e
3
+ size 6943
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dc2d648fc55094124d4764c47413294acab41353e2f467f943e98fcc2ffb79e
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e2ef883b224c1ecf6addd276ce6220c763b0ca905cc9802f6404990939965c5
3
  size 17549312
run-35/checkpoint-428/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-35/checkpoint-428/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25f8c06189e55b5e74f9327d5bc7f3931d7dcd74b0f2059789c22c643128dfcb
3
+ size 17549312
run-35/checkpoint-428/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d43ccd2a7229feb4aa27488239fbf699271db18c69ce3d0338b48758d14dae73
3
+ size 35123898
run-35/checkpoint-428/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d0c3b463a8fb08b95f5c77916114776bad3339b633df010e4ffd9b5ddabab1e
3
+ size 14308
run-35/checkpoint-428/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8e50e77ad555607646f9f00edf8d1ccf716ccba4d7bcb72cbcb27264ce70efe
3
+ size 1064
run-35/checkpoint-428/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-35/checkpoint-428/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-35/checkpoint-428/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-35/checkpoint-428/trainer_state.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7047451669595782,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-35/checkpoint-214",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 428,
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": 9.204007148742676,
14
+ "learning_rate": 0.00010073134118996591,
15
+ "loss": 0.5694,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7047451669595782,
21
+ "eval_f1": 0.514450867052023,
22
+ "eval_loss": 0.5304614901542664,
23
+ "eval_mcc": 0.30808910613726637,
24
+ "eval_precision": 0.5692963752665245,
25
+ "eval_recall": 0.46924428822495606,
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": 2.162537097930908,
34
+ "learning_rate": 8.39427843249716e-05,
35
+ "loss": 0.5228,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7041593438781488,
41
+ "eval_f1": 0.45168295331161784,
42
+ "eval_loss": 0.5144214034080505,
43
+ "eval_mcc": 0.27849213002840095,
44
+ "eval_precision": 0.5909090909090909,
45
+ "eval_recall": 0.3655536028119508,
46
+ "eval_runtime": 3.6842,
47
+ "eval_samples_per_second": 463.333,
48
+ "eval_steps_per_second": 14.657,
49
+ "step": 428
50
+ }
51
+ ],
52
+ "logging_steps": 500,
53
+ "max_steps": 1498,
54
+ "num_input_tokens_seen": 0,
55
+ "num_train_epochs": 7,
56
+ "save_steps": 500,
57
+ "total_flos": 1049551328880.0,
58
+ "train_batch_size": 32,
59
+ "trial_name": null,
60
+ "trial_params": {
61
+ "alpha": 0.9231832458790068,
62
+ "learning_rate": 0.00011751989805496024,
63
+ "num_train_epochs": 7,
64
+ "temperature": 10
65
+ }
66
+ }
run-35/checkpoint-428/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:900171b85ecd44d34036a14f92291fe4a63ad82facf0081f97b5e4401cf8a786
3
+ size 5048
run-35/checkpoint-428/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-35/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-35/checkpoint-642/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e2ef883b224c1ecf6addd276ce6220c763b0ca905cc9802f6404990939965c5
3
+ size 17549312
run-35/checkpoint-642/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1669efd35a939b8f8b350584f4e40953198ce8bdd99ea65e07dd0e6ce31f5a9b
3
+ size 35123898
run-35/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-35/checkpoint-642/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a086e2474db32c8616872365790ad4c6d2ca9a6425cd3a2c43808dde280c60eb
3
+ size 1064
run-35/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-35/checkpoint-642/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-35/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-35/checkpoint-642/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7170474516695958,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-35/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": 9.204007148742676,
14
+ "learning_rate": 0.00010073134118996591,
15
+ "loss": 0.5694,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7047451669595782,
21
+ "eval_f1": 0.514450867052023,
22
+ "eval_loss": 0.5304614901542664,
23
+ "eval_mcc": 0.30808910613726637,
24
+ "eval_precision": 0.5692963752665245,
25
+ "eval_recall": 0.46924428822495606,
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": 2.162537097930908,
34
+ "learning_rate": 8.39427843249716e-05,
35
+ "loss": 0.5228,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7041593438781488,
41
+ "eval_f1": 0.45168295331161784,
42
+ "eval_loss": 0.5144214034080505,
43
+ "eval_mcc": 0.27849213002840095,
44
+ "eval_precision": 0.5909090909090909,
45
+ "eval_recall": 0.3655536028119508,
46
+ "eval_runtime": 3.6842,
47
+ "eval_samples_per_second": 463.333,
48
+ "eval_steps_per_second": 14.657,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 3.3931689262390137,
54
+ "learning_rate": 6.715422745997727e-05,
55
+ "loss": 0.5045,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7170474516695958,
61
+ "eval_f1": 0.455467869222097,
62
+ "eval_loss": 0.5072826743125916,
63
+ "eval_mcc": 0.3064169652874968,
64
+ "eval_precision": 0.6352201257861635,
65
+ "eval_recall": 0.35500878734622143,
66
+ "eval_runtime": 3.1368,
67
+ "eval_samples_per_second": 544.189,
68
+ "eval_steps_per_second": 17.215,
69
+ "step": 642
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 1498,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 7,
76
+ "save_steps": 500,
77
+ "total_flos": 1574326993320.0,
78
+ "train_batch_size": 32,
79
+ "trial_name": null,
80
+ "trial_params": {
81
+ "alpha": 0.9231832458790068,
82
+ "learning_rate": 0.00011751989805496024,
83
+ "num_train_epochs": 7,
84
+ "temperature": 10
85
+ }
86
+ }
run-35/checkpoint-642/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:900171b85ecd44d34036a14f92291fe4a63ad82facf0081f97b5e4401cf8a786
3
+ size 5048
run-35/checkpoint-642/vocab.txt ADDED
The diff for this file is too large to render. See raw diff