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
39c662d
·
verified ·
1 Parent(s): 2e6d212

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. logs/events.out.tfevents.1709460206.49ae8f4e8e7b.1647.25 +2 -2
  2. logs/events.out.tfevents.1709461228.49ae8f4e8e7b.1647.26 +3 -0
  3. model.safetensors +1 -1
  4. run-24/checkpoint-2635/config.json +34 -0
  5. run-24/checkpoint-2635/model.safetensors +3 -0
  6. run-24/checkpoint-2635/optimizer.pt +3 -0
  7. run-24/checkpoint-2635/rng_state.pth +3 -0
  8. run-24/checkpoint-2635/scheduler.pt +3 -0
  9. run-24/checkpoint-2635/special_tokens_map.json +7 -0
  10. run-24/checkpoint-2635/tokenizer.json +0 -0
  11. run-24/checkpoint-2635/tokenizer_config.json +57 -0
  12. run-24/checkpoint-2635/trainer_state.json +106 -0
  13. run-24/checkpoint-2635/training_args.bin +3 -0
  14. run-24/checkpoint-2635/vocab.txt +0 -0
  15. run-25/checkpoint-527/config.json +34 -0
  16. run-25/checkpoint-527/model.safetensors +3 -0
  17. run-25/checkpoint-527/optimizer.pt +3 -0
  18. run-25/checkpoint-527/rng_state.pth +3 -0
  19. run-25/checkpoint-527/scheduler.pt +3 -0
  20. run-25/checkpoint-527/special_tokens_map.json +7 -0
  21. run-25/checkpoint-527/tokenizer.json +0 -0
  22. run-25/checkpoint-527/tokenizer_config.json +57 -0
  23. run-25/checkpoint-527/trainer_state.json +42 -0
  24. run-25/checkpoint-527/training_args.bin +3 -0
  25. run-25/checkpoint-527/vocab.txt +0 -0
  26. training_args.bin +1 -1
logs/events.out.tfevents.1709460206.49ae8f4e8e7b.1647.25 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a56544a23b6494e4ef54a2fe57bf6ba4091e1703bb942a9f19d16677e3eea72
3
- size 5714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc1958d5c0c16ab3ddc588ff7d77eb419348a03b8e1a2416ac8cb8ca95970148
3
+ size 7670
logs/events.out.tfevents.1709461228.49ae8f4e8e7b.1647.26 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:179f21610474a83bae293d527f59fec590bbd0f4a3b692dbb650ac5757fdce05
3
+ size 5179
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67ce49a130b17131a9bcc1cda679c6d84bd259fd1053e2479e0c548721d66eee
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a018c87fb3bde7f7350ff2883de5a902e01b08ff5eedbec633c2d003f0dfa62
3
  size 17549312
run-24/checkpoint-2635/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-24/checkpoint-2635/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed994e55a85db214d64dad1a31546c70ea3bc7ca09ff53e25262ce35fb06d9b5
3
+ size 17549312
run-24/checkpoint-2635/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:212f63ef15fd2efbe2a0559f1f15d0f38b96b938b6e433633775b5ea08c32e8a
3
+ size 35123898
run-24/checkpoint-2635/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bd37da819cfe1c92aea202c8f190c02a65fdc71a17fd2af0ed4760f9222ae02
3
+ size 14308
run-24/checkpoint-2635/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cea736a560f7e0233552cc69ad5023eb7557f7a27018fb7787e4feb012a1c24a
3
+ size 1064
run-24/checkpoint-2635/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-24/checkpoint-2635/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-24/checkpoint-2635/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-24/checkpoint-2635/trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8337155963302753,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-24/checkpoint-527",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2635,
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": 17.628143310546875,
14
+ "learning_rate": 0.00018567149458255904,
15
+ "loss": 1.3968,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8337155963302753,
21
+ "eval_loss": 1.3282397985458374,
22
+ "eval_runtime": 2.8214,
23
+ "eval_samples_per_second": 309.061,
24
+ "eval_steps_per_second": 2.481,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 10.100229263305664,
30
+ "learning_rate": 0.00013925362093691925,
31
+ "loss": 0.6522,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.8291284403669725,
37
+ "eval_loss": 1.401127576828003,
38
+ "eval_runtime": 2.8077,
39
+ "eval_samples_per_second": 310.572,
40
+ "eval_steps_per_second": 2.493,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": NaN,
46
+ "learning_rate": 9.292382674791261e-05,
47
+ "loss": 0.4794,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8325688073394495,
53
+ "eval_loss": 1.4821361303329468,
54
+ "eval_runtime": 2.8127,
55
+ "eval_samples_per_second": 310.028,
56
+ "eval_steps_per_second": 2.489,
57
+ "step": 1581
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 7.141517162322998,
62
+ "learning_rate": 4.650595310227285e-05,
63
+ "loss": 0.3848,
64
+ "step": 2108
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.8291284403669725,
69
+ "eval_loss": 1.4644421339035034,
70
+ "eval_runtime": 2.8155,
71
+ "eval_samples_per_second": 309.71,
72
+ "eval_steps_per_second": 2.486,
73
+ "step": 2108
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 11.939757347106934,
78
+ "learning_rate": 8.80794566330925e-08,
79
+ "loss": 0.3303,
80
+ "step": 2635
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_accuracy": 0.823394495412844,
85
+ "eval_loss": 1.5062029361724854,
86
+ "eval_runtime": 2.8218,
87
+ "eval_samples_per_second": 309.024,
88
+ "eval_steps_per_second": 2.481,
89
+ "step": 2635
90
+ }
91
+ ],
92
+ "logging_steps": 500,
93
+ "max_steps": 2635,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 5,
96
+ "save_steps": 500,
97
+ "total_flos": 40447180739880.0,
98
+ "train_batch_size": 128,
99
+ "trial_name": null,
100
+ "trial_params": {
101
+ "alpha": 0.4205009910693592,
102
+ "learning_rate": 0.00023208936822819877,
103
+ "num_train_epochs": 5,
104
+ "temperature": 21
105
+ }
106
+ }
run-24/checkpoint-2635/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c22b334783d23b2099fc16003e87298409a4c3cae8698d8fc8241196e2543e45
3
+ size 4984
run-24/checkpoint-2635/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-25/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-25/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a018c87fb3bde7f7350ff2883de5a902e01b08ff5eedbec633c2d003f0dfa62
3
+ size 17549312
run-25/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa4458aad7ee3d8ab66f47b4dc7c26ee40f5edde8d21cb03b8484c305ba89fa
3
+ size 35123898
run-25/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-25/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fb237e721e5611db2f73f40569b50512167f30cdcb7aa0d8e54475e257fc3aa
3
+ size 1064
run-25/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-25/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-25/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-25/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8325688073394495,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-25/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": 3.7773447036743164,
14
+ "learning_rate": 0.0004316595412152798,
15
+ "loss": 0.9448,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8325688073394495,
21
+ "eval_loss": 1.1720139980316162,
22
+ "eval_runtime": 2.8085,
23
+ "eval_samples_per_second": 310.481,
24
+ "eval_steps_per_second": 2.492,
25
+ "step": 527
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 4216,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 8,
32
+ "save_steps": 500,
33
+ "total_flos": 8057768762220.0,
34
+ "train_batch_size": 128,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "alpha": 0.595362243351062,
38
+ "learning_rate": 0.0004933251899603198,
39
+ "num_train_epochs": 8,
40
+ "temperature": 26
41
+ }
42
+ }
run-25/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a14fbcfc55085ad9e99ade30c09bc3ab559b9a9b4869034db56a9230ed5a0c40
3
+ size 4984
run-25/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:c22b334783d23b2099fc16003e87298409a4c3cae8698d8fc8241196e2543e45
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a14fbcfc55085ad9e99ade30c09bc3ab559b9a9b4869034db56a9230ed5a0c40
3
  size 4984