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
22ac7d0
·
verified ·
1 Parent(s): 937b765

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. logs/events.out.tfevents.1713589993.1376c752d37a.9760.37 +2 -2
  2. logs/events.out.tfevents.1713590077.1376c752d37a.9760.38 +3 -0
  3. model.safetensors +1 -1
  4. run-37/checkpoint-856/config.json +34 -0
  5. run-37/checkpoint-856/model.safetensors +3 -0
  6. run-37/checkpoint-856/optimizer.pt +3 -0
  7. run-37/checkpoint-856/rng_state.pth +3 -0
  8. run-37/checkpoint-856/scheduler.pt +3 -0
  9. run-37/checkpoint-856/special_tokens_map.json +7 -0
  10. run-37/checkpoint-856/tokenizer.json +0 -0
  11. run-37/checkpoint-856/tokenizer_config.json +57 -0
  12. run-37/checkpoint-856/trainer_state.json +106 -0
  13. run-37/checkpoint-856/training_args.bin +3 -0
  14. run-37/checkpoint-856/vocab.txt +0 -0
  15. run-38/checkpoint-214/config.json +34 -0
  16. run-38/checkpoint-214/model.safetensors +3 -0
  17. run-38/checkpoint-214/optimizer.pt +3 -0
  18. run-38/checkpoint-214/rng_state.pth +3 -0
  19. run-38/checkpoint-214/scheduler.pt +3 -0
  20. run-38/checkpoint-214/special_tokens_map.json +7 -0
  21. run-38/checkpoint-214/tokenizer.json +0 -0
  22. run-38/checkpoint-214/tokenizer_config.json +57 -0
  23. run-38/checkpoint-214/trainer_state.json +46 -0
  24. run-38/checkpoint-214/training_args.bin +3 -0
  25. run-38/checkpoint-214/vocab.txt +0 -0
  26. training_args.bin +1 -1
logs/events.out.tfevents.1713589993.1376c752d37a.9760.37 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2c87df54970850a7de0907f9e131c768dd8648b12c3042d49fe5783610b3fd7
3
- size 6942
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad4140853b70db8e22fffde01764936f4514e9dfb8a02c620bba970fde163300
3
+ size 8402
logs/events.out.tfevents.1713590077.1376c752d37a.9760.38 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ead32b33617a94f134c86bc405b0f3af5e7fdf981645eadc72e9f0b8b9a57404
3
+ size 5482
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab59aa5a270b0431e0338fde0ae9b47db938899f8e8941067329f6a3b6977467
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7fdbb0fc21112b532657f3749dd9a22feacaf36a3004a713464b9a03a3f297b
3
  size 17549312
run-37/checkpoint-856/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-37/checkpoint-856/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db4abdf7237519f936d04072c27947a4545953a02c58812bb0d42954d46ab1ff
3
+ size 17549312
run-37/checkpoint-856/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7727cab1445af067b9a73f58b6e0a9ce874d54cab98de175382b3b8be3dacf8a
3
+ size 35123898
run-37/checkpoint-856/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:057111bfbb4d541cc190a3ed4fcfe228e7425a50e4a06afd33224d43272b1a59
3
+ size 14308
run-37/checkpoint-856/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ad298d886586d8a5419b06c81d3294b20bd6a3b8fb6b10464509e873b4fc994
3
+ size 1064
run-37/checkpoint-856/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-37/checkpoint-856/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-37/checkpoint-856/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-37/checkpoint-856/trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7305213825424721,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-37/checkpoint-428",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 856,
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": 2.5660171508789062,
14
+ "learning_rate": 0.0005426960660121868,
15
+ "loss": 0.3936,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7065026362038664,
21
+ "eval_f1": 0.3275167785234899,
22
+ "eval_loss": 0.3753478229045868,
23
+ "eval_mcc": 0.2588181173815382,
24
+ "eval_precision": 0.6931818181818182,
25
+ "eval_recall": 0.21441124780316345,
26
+ "eval_runtime": 3.1566,
27
+ "eval_samples_per_second": 540.772,
28
+ "eval_steps_per_second": 17.107,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.099513530731201,
34
+ "learning_rate": 0.00040702204950914005,
35
+ "loss": 0.372,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7305213825424721,
41
+ "eval_f1": 0.3994778067885118,
42
+ "eval_loss": 0.366894006729126,
43
+ "eval_mcc": 0.33967587808797833,
44
+ "eval_precision": 0.7766497461928934,
45
+ "eval_recall": 0.2688927943760984,
46
+ "eval_runtime": 3.769,
47
+ "eval_samples_per_second": 452.906,
48
+ "eval_steps_per_second": 14.327,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.2766120433807373,
54
+ "learning_rate": 0.0002713480330060934,
55
+ "loss": 0.3619,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7024018746338606,
61
+ "eval_f1": 0.21604938271604937,
62
+ "eval_loss": 0.3670775592327118,
63
+ "eval_mcc": 0.258294733907354,
64
+ "eval_precision": 0.8860759493670886,
65
+ "eval_recall": 0.12302284710017575,
66
+ "eval_runtime": 3.1357,
67
+ "eval_samples_per_second": 544.372,
68
+ "eval_steps_per_second": 17.221,
69
+ "step": 642
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 1.1301072835922241,
74
+ "learning_rate": 0.0001356740165030467,
75
+ "loss": 0.3544,
76
+ "step": 856
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7106033977738723,
81
+ "eval_f1": 0.26268656716417904,
82
+ "eval_loss": 0.3585212826728821,
83
+ "eval_mcc": 0.2861799142479944,
84
+ "eval_precision": 0.8712871287128713,
85
+ "eval_recall": 0.1546572934973638,
86
+ "eval_runtime": 3.7136,
87
+ "eval_samples_per_second": 459.665,
88
+ "eval_steps_per_second": 14.541,
89
+ "step": 856
90
+ }
91
+ ],
92
+ "logging_steps": 500,
93
+ "max_steps": 1070,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 5,
96
+ "save_steps": 500,
97
+ "total_flos": 2099102657760.0,
98
+ "train_batch_size": 32,
99
+ "trial_name": null,
100
+ "trial_params": {
101
+ "alpha": 0.6249127121707758,
102
+ "learning_rate": 0.0006783700825152334,
103
+ "num_train_epochs": 5,
104
+ "temperature": 13
105
+ }
106
+ }
run-37/checkpoint-856/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f01f7cb1930ef4d58db7e82c9c5d393875a675c9066fdbc6e65a97862326c7e8
3
+ size 5048
run-37/checkpoint-856/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-38/checkpoint-214/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-38/checkpoint-214/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7fdbb0fc21112b532657f3749dd9a22feacaf36a3004a713464b9a03a3f297b
3
+ size 17549312
run-38/checkpoint-214/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1b222297111d99a2abdbf07ad025e531b63a271dc3a66bcfbdde37ce9f53272
3
+ size 35123898
run-38/checkpoint-214/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc7e492e6768bc7c3c01ac823da5a8177cf34fc1b175dd727fa3be969661a151
3
+ size 14308
run-38/checkpoint-214/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1826c8cea0c40ded72a475d51b6c931d64b2819e1bcf37efcef92b2b650ece72
3
+ size 1064
run-38/checkpoint-214/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-38/checkpoint-214/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-38/checkpoint-214/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-38/checkpoint-214/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7129466900995899,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-38/checkpoint-214",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 214,
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": 5.823625087738037,
14
+ "learning_rate": 0.00022026694526910956,
15
+ "loss": 0.4997,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7129466900995899,
21
+ "eval_f1": 0.40243902439024387,
22
+ "eval_loss": 0.4626123011112213,
23
+ "eval_mcc": 0.2854021761857005,
24
+ "eval_precision": 0.6573705179282868,
25
+ "eval_recall": 0.28998242530755713,
26
+ "eval_runtime": 3.1456,
27
+ "eval_samples_per_second": 542.661,
28
+ "eval_steps_per_second": 17.167,
29
+ "step": 214
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 1712,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 8,
36
+ "save_steps": 500,
37
+ "total_flos": 524775664440.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.806613569484766,
42
+ "learning_rate": 0.0002517336517361252,
43
+ "num_train_epochs": 8,
44
+ "temperature": 7
45
+ }
46
+ }
run-38/checkpoint-214/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7a56f1a08be493488fc73f1cff5a0aca0dbcd6292eef2952623c01722595b1b
3
+ size 5048
run-38/checkpoint-214/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:f01f7cb1930ef4d58db7e82c9c5d393875a675c9066fdbc6e65a97862326c7e8
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7a56f1a08be493488fc73f1cff5a0aca0dbcd6292eef2952623c01722595b1b
3
  size 5048