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
5ec4a27
·
verified ·
1 Parent(s): 48ee99c

Training in progress, epoch 1

Browse files
Files changed (18) hide show
  1. logs/events.out.tfevents.1709710093.a2333cf40ebd.21010.49 +2 -2
  2. logs/events.out.tfevents.1709710676.a2333cf40ebd.21010.50 +3 -0
  3. logs/events.out.tfevents.1709712361.a2333cf40ebd.21010.51 +3 -0
  4. logs/events.out.tfevents.1709712555.a2333cf40ebd.21010.52 +3 -0
  5. model.safetensors +1 -1
  6. run-49/checkpoint-384/config.json +34 -0
  7. run-49/checkpoint-384/model.safetensors +3 -0
  8. run-49/checkpoint-384/optimizer.pt +3 -0
  9. run-49/checkpoint-384/rng_state.pth +3 -0
  10. run-49/checkpoint-384/scheduler.pt +3 -0
  11. run-49/checkpoint-384/special_tokens_map.json +7 -0
  12. run-49/checkpoint-384/tokenizer.json +0 -0
  13. run-49/checkpoint-384/tokenizer_config.json +57 -0
  14. run-49/checkpoint-384/trainer_state.json +102 -0
  15. run-49/checkpoint-384/training_args.bin +3 -0
  16. run-49/checkpoint-384/vocab.txt +0 -0
  17. tokenizer.json +1 -1
  18. training_args.bin +2 -2
logs/events.out.tfevents.1709710093.a2333cf40ebd.21010.49 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32de2aa170ca59757c59908d7c300e6f79034a256b171e72049fa8b8d3953f7a
3
- size 5998
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b75f7bc51d48284d72823d0612af0f7e3166231da19baeb010c50de182c3fa9d
3
+ size 8047
logs/events.out.tfevents.1709710676.a2333cf40ebd.21010.50 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7757e302384e168472b889811042dc4e303cee736f4f7b0f6ba12a0c88dac69
3
+ size 11123
logs/events.out.tfevents.1709712361.a2333cf40ebd.21010.51 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b88d72fd27b97dc961e242c944b5571398ee6bd2a4d68a7c9b7572ec4da51ada
3
+ size 4645
logs/events.out.tfevents.1709712555.a2333cf40ebd.21010.52 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ed4f745403d66ce9a273f8b7b1dc86b6b12b5e08f547c158b5adaf992e5da7f
3
+ size 5300
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ee526bf0cc31b3e382181fe8a83975197ed304533b5365d38a036d1565c18a7
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53b0addb5ec649f58fbe410fdbee2f70214bba4ef8370dcc9a0aa30b67a2690c
3
  size 17549312
run-49/checkpoint-384/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-49/checkpoint-384/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffa5b8b77e6837f5f21a5342144b3930fae95780389ffe4d3efce2973e87942e
3
+ size 17549312
run-49/checkpoint-384/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5110266644371292d54f8f2e1694b87c5d54112025c0bd1d5f3bb47f694fa43e
3
+ size 35122746
run-49/checkpoint-384/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45b1fc07ed8b121716021ec87c686f1cd9c3b89c82ea08a6a0792d47a39077c9
3
+ size 14054
run-49/checkpoint-384/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11aa33c2cdd3f8977d5c56d8dfa3fd9e83192a01ee73932f247056818bc65ae9
3
+ size 1064
run-49/checkpoint-384/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-49/checkpoint-384/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-49/checkpoint-384/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-49/checkpoint-384/trainer_state.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.824853228962818,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-49/checkpoint-192",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 384,
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": 2.0952401161193848,
14
+ "learning_rate": 0.000329696350517435,
15
+ "loss": 0.5506,
16
+ "step": 96
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7788649706457925,
21
+ "eval_f1": 0.8055077452667815,
22
+ "eval_loss": 0.46728333830833435,
23
+ "eval_precision": 0.7188940092165899,
24
+ "eval_recall": 0.9158512720156555,
25
+ "eval_runtime": 28.1443,
26
+ "eval_samples_per_second": 36.313,
27
+ "eval_steps_per_second": 1.137,
28
+ "step": 96
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 5.149355888366699,
33
+ "learning_rate": 0.0002884843067027556,
34
+ "loss": 0.4507,
35
+ "step": 192
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.824853228962818,
40
+ "eval_f1": 0.8328664799253034,
41
+ "eval_loss": 0.411376416683197,
42
+ "eval_precision": 0.7964285714285714,
43
+ "eval_recall": 0.87279843444227,
44
+ "eval_runtime": 28.7591,
45
+ "eval_samples_per_second": 35.537,
46
+ "eval_steps_per_second": 1.113,
47
+ "step": 192
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 4.500710487365723,
52
+ "learning_rate": 0.0002472722628880762,
53
+ "loss": 0.4184,
54
+ "step": 288
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8189823874755382,
59
+ "eval_f1": 0.8313582497721058,
60
+ "eval_loss": 0.43684908747673035,
61
+ "eval_precision": 0.7781569965870307,
62
+ "eval_recall": 0.8923679060665362,
63
+ "eval_runtime": 28.8386,
64
+ "eval_samples_per_second": 35.439,
65
+ "eval_steps_per_second": 1.11,
66
+ "step": 288
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 4.119166374206543,
71
+ "learning_rate": 0.00020606021907339686,
72
+ "loss": 0.4097,
73
+ "step": 384
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.8189823874755382,
78
+ "eval_f1": 0.8177339901477833,
79
+ "eval_loss": 0.4454614818096161,
80
+ "eval_precision": 0.8234126984126984,
81
+ "eval_recall": 0.812133072407045,
82
+ "eval_runtime": 28.4183,
83
+ "eval_samples_per_second": 35.963,
84
+ "eval_steps_per_second": 1.126,
85
+ "step": 384
86
+ }
87
+ ],
88
+ "logging_steps": 500,
89
+ "max_steps": 864,
90
+ "num_input_tokens_seen": 0,
91
+ "num_train_epochs": 9,
92
+ "save_steps": 500,
93
+ "total_flos": 942780789120.0,
94
+ "train_batch_size": 32,
95
+ "trial_name": null,
96
+ "trial_params": {
97
+ "alpha": 0.8860751863253173,
98
+ "learning_rate": 0.00037090839433211436,
99
+ "num_train_epochs": 9,
100
+ "temperature": 11
101
+ }
102
+ }
run-49/checkpoint-384/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b6b50bcc2ab6010c774b0d1c8ec4ee0f11fad66a52dd2fe9b32590c7fc389af
3
+ size 4920
run-49/checkpoint-384/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": 29,
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 sha256:73f9e2ac3be6b7c9021ef3ce058ae0e8295e2af415d7d3b6194204458bbf0e58
3
- size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:019a0c30743454578a20e039f50246add333dec6abb36273bd6bc2339b797b34
3
+ size 4920