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
d61991d
·
verified ·
1 Parent(s): 59c3b50

Training in progress, epoch 2

Browse files
Files changed (26) hide show
  1. logs/events.out.tfevents.1713612219.a9446dbff3d4.7440.24 +2 -2
  2. logs/events.out.tfevents.1713612239.a9446dbff3d4.7440.25 +3 -0
  3. model.safetensors +1 -1
  4. run-23/checkpoint-160/config.json +34 -0
  5. run-23/checkpoint-160/model.safetensors +3 -0
  6. run-23/checkpoint-160/optimizer.pt +3 -0
  7. run-23/checkpoint-160/rng_state.pth +3 -0
  8. run-23/checkpoint-160/scheduler.pt +3 -0
  9. run-23/checkpoint-160/special_tokens_map.json +7 -0
  10. run-23/checkpoint-160/tokenizer.json +0 -0
  11. run-23/checkpoint-160/tokenizer_config.json +57 -0
  12. run-23/checkpoint-160/trainer_state.json +46 -0
  13. run-23/checkpoint-160/training_args.bin +3 -0
  14. run-23/checkpoint-160/vocab.txt +0 -0
  15. run-23/checkpoint-320/config.json +34 -0
  16. run-23/checkpoint-320/model.safetensors +3 -0
  17. run-23/checkpoint-320/optimizer.pt +3 -0
  18. run-23/checkpoint-320/rng_state.pth +3 -0
  19. run-23/checkpoint-320/scheduler.pt +3 -0
  20. run-23/checkpoint-320/special_tokens_map.json +7 -0
  21. run-23/checkpoint-320/tokenizer.json +0 -0
  22. run-23/checkpoint-320/tokenizer_config.json +57 -0
  23. run-23/checkpoint-320/trainer_state.json +66 -0
  24. run-23/checkpoint-320/training_args.bin +3 -0
  25. run-23/checkpoint-320/vocab.txt +0 -0
  26. training_args.bin +1 -1
logs/events.out.tfevents.1713612219.a9446dbff3d4.7440.24 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:250c291ede785206f3cd69896d7a9bfe0dad1a6cf3f1a8bc299eac804ebaa114
3
- size 5482
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3e4fafcee8a5aac18058f1004eb594ac449de6edc82ea36ddb5e9e293f2501f
3
+ size 6212
logs/events.out.tfevents.1713612239.a9446dbff3d4.7440.25 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73aa3dcc297706238c089e2cb5da06dd7f7baf94b1444577feeed8578801952e
3
+ size 6211
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae51431d9fe3f60e7687652688dd2e8ffafcb9ba817aeb6283a2a7b0f46ccdce
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3378e66fbe74545663b725432bdbb61ac00efdb339b7f128371a6512f0016729
3
  size 17549312
run-23/checkpoint-160/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-23/checkpoint-160/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00be51582ceef996abe5f3c3044e3f6dd202a8cd82515ef37c83a223dce276df
3
+ size 17549312
run-23/checkpoint-160/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b88723ce66ab85c046bd3b709802b5f9be121b70c7f018d4d6f84261eb0b035c
3
+ size 35123898
run-23/checkpoint-160/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0792eaff268dd73c8e104b5060a487f4ef56535ad3b58888006338b8bc298137
3
+ size 14308
run-23/checkpoint-160/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18c6ac3176f628a9ccc9e522ec63927dc92a7502cbed600d5c75d86b52af93e8
3
+ size 1064
run-23/checkpoint-160/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-23/checkpoint-160/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-23/checkpoint-160/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-23/checkpoint-160/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6666666666666666,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-23/checkpoint-160",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 160,
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": 1.446049451828003,
14
+ "learning_rate": 0.0005691296983851737,
15
+ "loss": 0.6049,
16
+ "step": 160
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6666666666666666,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.5720294713973999,
23
+ "eval_mcc": 0.0,
24
+ "eval_precision": 0.0,
25
+ "eval_recall": 0.0,
26
+ "eval_runtime": 1.9517,
27
+ "eval_samples_per_second": 653.261,
28
+ "eval_steps_per_second": 20.494,
29
+ "step": 160
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 1120,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 7,
36
+ "save_steps": 500,
37
+ "total_flos": 291755437920.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.9539104497371855,
42
+ "learning_rate": 0.000663984648116036,
43
+ "num_train_epochs": 7,
44
+ "temperature": 6
45
+ }
46
+ }
run-23/checkpoint-160/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4988591d4f12e20829cf7195f90bcd54ea9f3931c42b14bc9bb00b5f16d01bff
3
+ size 5048
run-23/checkpoint-160/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-23/checkpoint-320/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-23/checkpoint-320/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3378e66fbe74545663b725432bdbb61ac00efdb339b7f128371a6512f0016729
3
+ size 17549312
run-23/checkpoint-320/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0c54e3e8f7fa530594540f10edec47c379b385c6f607e456ad1771b0d6b4660
3
+ size 35123898
run-23/checkpoint-320/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fce5941012578d026c76372190ed75bc3a1c59455c429a4fd246677d1bfc3594
3
+ size 14308
run-23/checkpoint-320/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:986c4a03e31f8f9455ba2b140eda59f448382e422211d208ded7a97e99f7c4ee
3
+ size 1064
run-23/checkpoint-320/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-23/checkpoint-320/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-23/checkpoint-320/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-23/checkpoint-320/trainer_state.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6925490196078431,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-23/checkpoint-320",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 320,
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": 1.446049451828003,
14
+ "learning_rate": 0.0005691296983851737,
15
+ "loss": 0.6049,
16
+ "step": 160
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6666666666666666,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.5720294713973999,
23
+ "eval_mcc": 0.0,
24
+ "eval_precision": 0.0,
25
+ "eval_recall": 0.0,
26
+ "eval_runtime": 1.9517,
27
+ "eval_samples_per_second": 653.261,
28
+ "eval_steps_per_second": 20.494,
29
+ "step": 160
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.206958293914795,
34
+ "learning_rate": 0.00047427474865431146,
35
+ "loss": 0.5748,
36
+ "step": 320
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.6925490196078431,
41
+ "eval_f1": 0.312280701754386,
42
+ "eval_loss": 0.5560094714164734,
43
+ "eval_mcc": 0.21311872533733642,
44
+ "eval_precision": 0.6137931034482759,
45
+ "eval_recall": 0.20941176470588235,
46
+ "eval_runtime": 1.9268,
47
+ "eval_samples_per_second": 661.712,
48
+ "eval_steps_per_second": 20.76,
49
+ "step": 320
50
+ }
51
+ ],
52
+ "logging_steps": 500,
53
+ "max_steps": 1120,
54
+ "num_input_tokens_seen": 0,
55
+ "num_train_epochs": 7,
56
+ "save_steps": 500,
57
+ "total_flos": 583510875840.0,
58
+ "train_batch_size": 32,
59
+ "trial_name": null,
60
+ "trial_params": {
61
+ "alpha": 0.9539104497371855,
62
+ "learning_rate": 0.000663984648116036,
63
+ "num_train_epochs": 7,
64
+ "temperature": 6
65
+ }
66
+ }
run-23/checkpoint-320/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4988591d4f12e20829cf7195f90bcd54ea9f3931c42b14bc9bb00b5f16d01bff
3
+ size 5048
run-23/checkpoint-320/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:d1a8098f7251a2f71a88aa1f7db7427de9a809ac3810e9c0fad6ad2fc80cdcfa
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4988591d4f12e20829cf7195f90bcd54ea9f3931c42b14bc9bb00b5f16d01bff
3
  size 5048