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
9b5ce48
·
verified ·
1 Parent(s): 8810d10

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. logs/events.out.tfevents.1713435480.ec9626078864.14834.2 +2 -2
  2. logs/events.out.tfevents.1713435639.ec9626078864.14834.3 +3 -0
  3. model.safetensors +1 -1
  4. run-1/checkpoint-1935/config.json +34 -0
  5. run-1/checkpoint-1935/model.safetensors +3 -0
  6. run-1/checkpoint-1935/optimizer.pt +3 -0
  7. run-1/checkpoint-1935/rng_state.pth +3 -0
  8. run-1/checkpoint-1935/scheduler.pt +3 -0
  9. run-1/checkpoint-1935/special_tokens_map.json +7 -0
  10. run-1/checkpoint-1935/tokenizer.json +0 -0
  11. run-1/checkpoint-1935/tokenizer_config.json +57 -0
  12. run-1/checkpoint-1935/trainer_state.json +86 -0
  13. run-1/checkpoint-1935/training_args.bin +3 -0
  14. run-1/checkpoint-1935/vocab.txt +0 -0
  15. run-2/checkpoint-645/config.json +34 -0
  16. run-2/checkpoint-645/model.safetensors +3 -0
  17. run-2/checkpoint-645/optimizer.pt +3 -0
  18. run-2/checkpoint-645/rng_state.pth +3 -0
  19. run-2/checkpoint-645/scheduler.pt +3 -0
  20. run-2/checkpoint-645/special_tokens_map.json +7 -0
  21. run-2/checkpoint-645/tokenizer.json +0 -0
  22. run-2/checkpoint-645/tokenizer_config.json +57 -0
  23. run-2/checkpoint-645/trainer_state.json +46 -0
  24. run-2/checkpoint-645/training_args.bin +3 -0
  25. run-2/checkpoint-645/vocab.txt +0 -0
  26. training_args.bin +1 -1
logs/events.out.tfevents.1713435480.ec9626078864.14834.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39b5d7c8136b3d7247caaedfd754e1c8464e0ae7a71c9e0f0e7a376c64db7e2c
3
- size 6136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cad290f44091a9549b6143f7dc0b3865de27ce17385c3abf8a5c48d18bcbf53e
3
+ size 7220
logs/events.out.tfevents.1713435639.ec9626078864.14834.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fe45c570d899c054189b24f2d6be611d30b054461f6969bfe05cf186ae610c0
3
+ size 5407
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0496bb45dc5f07ee38fbd5863775af88fc0090e4852724fad0a3585afec47ee1
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb96c5f3357124400483af6b58cd88a83e3a28826a7e18a50b4981577900e23
3
  size 17549312
run-1/checkpoint-1935/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": "4.39.3",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-1/checkpoint-1935/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19469a8626d0c4b67b8f5f0e93f19fcbcad5208f38fd4dd0669fb770c8de517d
3
+ size 17549312
run-1/checkpoint-1935/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40b00e4eba1c521a6e77c326d599081d7b969d3059d4b96e618f2efcc0648de9
3
+ size 35123898
run-1/checkpoint-1935/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52accd942491f2dc7d4a75134a3eb6fb2aad787ad955e2de73fb9398b7a6277c
3
+ size 14308
run-1/checkpoint-1935/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bf9c83183b0e1c51bf77d8928aacb0a36cbe8f82f51a709ec8bc02379ad8521
3
+ size 1064
run-1/checkpoint-1935/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-1/checkpoint-1935/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-1935/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-1/checkpoint-1935/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.898797983714618,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-1935",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1935,
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": 0.8288795948028564,
14
+ "learning_rate": 0.0001908740631878717,
15
+ "loss": 0.3032,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8892981775882125,
21
+ "eval_f1": 0.12557427258805512,
22
+ "eval_loss": 0.29040220379829407,
23
+ "eval_mcc": 0.15515682588139135,
24
+ "eval_precision": 0.4880952380952381,
25
+ "eval_recall": 0.07205623901581722,
26
+ "eval_runtime": 9.95,
27
+ "eval_samples_per_second": 518.391,
28
+ "eval_steps_per_second": 16.281,
29
+ "step": 645
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 0.593945324420929,
34
+ "learning_rate": 9.543703159393586e-05,
35
+ "loss": 0.2874,
36
+ "step": 1290
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.8964715005816207,
41
+ "eval_f1": 0.16300940438871472,
42
+ "eval_loss": 0.2867793142795563,
43
+ "eval_mcc": 0.23910805095304313,
44
+ "eval_precision": 0.7536231884057971,
45
+ "eval_recall": 0.0913884007029877,
46
+ "eval_runtime": 9.9641,
47
+ "eval_samples_per_second": 517.657,
48
+ "eval_steps_per_second": 16.258,
49
+ "step": 1290
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.2576031684875488,
54
+ "learning_rate": 0.0,
55
+ "loss": 0.2765,
56
+ "step": 1935
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.898797983714618,
61
+ "eval_f1": 0.24347826086956523,
62
+ "eval_loss": 0.2753896117210388,
63
+ "eval_mcc": 0.2888763289104669,
64
+ "eval_precision": 0.6942148760330579,
65
+ "eval_recall": 0.14762741652021089,
66
+ "eval_runtime": 9.9488,
67
+ "eval_samples_per_second": 518.456,
68
+ "eval_steps_per_second": 16.283,
69
+ "step": 1935
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 1935,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 3,
76
+ "save_steps": 500,
77
+ "total_flos": 4760827597800.0,
78
+ "train_batch_size": 32,
79
+ "trial_name": null,
80
+ "trial_params": {
81
+ "alpha": 0.8638056037769629,
82
+ "learning_rate": 0.0002863110947818076,
83
+ "num_train_epochs": 3,
84
+ "temperature": 11
85
+ }
86
+ }
run-1/checkpoint-1935/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce98fa442c340f2adff4e1c65554f6839e9ff8c67f1a36d5cc21a06f170066fc
3
+ size 4984
run-1/checkpoint-1935/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-645/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": "4.39.3",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-2/checkpoint-645/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb96c5f3357124400483af6b58cd88a83e3a28826a7e18a50b4981577900e23
3
+ size 17549312
run-2/checkpoint-645/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19fca2b20f370d235bcc36ab2449a3844334e39ddfed8aace6b0046bb32aeee6
3
+ size 35123898
run-2/checkpoint-645/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f64cda8af0c2d214cf65bdf171fde38f18025a5a08f9a451c61fdf726867d7c2
3
+ size 14308
run-2/checkpoint-645/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47e2b777b41012e39fcdb3e09cda1de1cfb09d6bd9f7f7861e1b0afd5113892d
3
+ size 1064
run-2/checkpoint-645/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-2/checkpoint-645/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-645/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-2/checkpoint-645/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8896859247770453,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-645",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 645,
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": 0.19485902786254883,
14
+ "learning_rate": 5.781432585735223e-06,
15
+ "loss": 0.1549,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8896859247770453,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.12795990705490112,
23
+ "eval_mcc": 0.0,
24
+ "eval_precision": 0.0,
25
+ "eval_recall": 0.0,
26
+ "eval_runtime": 9.951,
27
+ "eval_samples_per_second": 518.339,
28
+ "eval_steps_per_second": 16.28,
29
+ "step": 645
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 1290,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 2,
36
+ "save_steps": 500,
37
+ "total_flos": 1586942532600.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.30145127091544865,
42
+ "learning_rate": 1.1562865171470446e-05,
43
+ "num_train_epochs": 2,
44
+ "temperature": 15
45
+ }
46
+ }
run-2/checkpoint-645/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4202a8d7c63a37c290ab4450fff22373975f79b17b204250141802339eb28c5c
3
+ size 4984
run-2/checkpoint-645/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:ce98fa442c340f2adff4e1c65554f6839e9ff8c67f1a36d5cc21a06f170066fc
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4202a8d7c63a37c290ab4450fff22373975f79b17b204250141802339eb28c5c
3
  size 4984