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
5f4c81b
·
verified ·
1 Parent(s): d1bc674

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. logs/events.out.tfevents.1713589374.1376c752d37a.9760.30 +2 -2
  2. logs/events.out.tfevents.1713589458.1376c752d37a.9760.31 +3 -0
  3. model.safetensors +1 -1
  4. run-30/checkpoint-856/config.json +34 -0
  5. run-30/checkpoint-856/model.safetensors +3 -0
  6. run-30/checkpoint-856/optimizer.pt +3 -0
  7. run-30/checkpoint-856/rng_state.pth +3 -0
  8. run-30/checkpoint-856/scheduler.pt +3 -0
  9. run-30/checkpoint-856/special_tokens_map.json +7 -0
  10. run-30/checkpoint-856/tokenizer.json +0 -0
  11. run-30/checkpoint-856/tokenizer_config.json +57 -0
  12. run-30/checkpoint-856/trainer_state.json +106 -0
  13. run-30/checkpoint-856/training_args.bin +3 -0
  14. run-30/checkpoint-856/vocab.txt +0 -0
  15. run-31/checkpoint-214/config.json +34 -0
  16. run-31/checkpoint-214/model.safetensors +3 -0
  17. run-31/checkpoint-214/optimizer.pt +3 -0
  18. run-31/checkpoint-214/rng_state.pth +3 -0
  19. run-31/checkpoint-214/scheduler.pt +3 -0
  20. run-31/checkpoint-214/special_tokens_map.json +7 -0
  21. run-31/checkpoint-214/tokenizer.json +0 -0
  22. run-31/checkpoint-214/tokenizer_config.json +57 -0
  23. run-31/checkpoint-214/trainer_state.json +46 -0
  24. run-31/checkpoint-214/training_args.bin +3 -0
  25. run-31/checkpoint-214/vocab.txt +0 -0
  26. training_args.bin +1 -1
logs/events.out.tfevents.1713589374.1376c752d37a.9760.30 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4efecce7b3d6f9bfc6bfcc9089464d9913cf23db105c1eafd3ca35621f5e4aa
3
- size 6942
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2c1bcf8feae2c68a121d9234443e5d3dd443266ab8472e02e0b98b0d1f74a61
3
+ size 8402
logs/events.out.tfevents.1713589458.1376c752d37a.9760.31 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef448550b7b9932d4b4d27a4e8bb6ab2b43d1d53f46c6f0af3e321e6be8fbc41
3
+ size 5483
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c8bbe35980c714a3659b7061f45bc2d7622ba2f5885b488333855b742d7a9b9
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71fa654faafcc6507f9f2c4e6a0a2767af4c5e03c943f9bbcb93249c62c1c97f
3
  size 17549312
run-30/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-30/checkpoint-856/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dfd5d1b6b380e0014dd68ce94a828ae06c6a6f5067400f47f843ae693aa6979
3
+ size 17549312
run-30/checkpoint-856/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbd71fff9acc331644412b00c03e34d27d9cf9f14e49b7a5aeeef050696d14a1
3
+ size 35123898
run-30/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-30/checkpoint-856/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9c1c079aafe58c9b40670c633c88d9388d23e608a97990648f67d164425ac86
3
+ size 1064
run-30/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-30/checkpoint-856/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-30/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-30/checkpoint-856/trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7299355594610427,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-30/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": 6.404624938964844,
14
+ "learning_rate": 0.0006827366491550371,
15
+ "loss": 0.5674,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.70298769771529,
21
+ "eval_f1": 0.47461139896373056,
22
+ "eval_loss": 0.5547006130218506,
23
+ "eval_mcc": 0.28558083057134703,
24
+ "eval_precision": 0.5782828282828283,
25
+ "eval_recall": 0.4024604569420035,
26
+ "eval_runtime": 3.121,
27
+ "eval_samples_per_second": 546.936,
28
+ "eval_steps_per_second": 17.302,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.9503083229064941,
34
+ "learning_rate": 0.0005973945680106575,
35
+ "loss": 0.518,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7299355594610427,
41
+ "eval_f1": 0.5252317198764161,
42
+ "eval_loss": 0.5166522860527039,
43
+ "eval_mcc": 0.35438337904683964,
44
+ "eval_precision": 0.6343283582089553,
45
+ "eval_recall": 0.44815465729349735,
46
+ "eval_runtime": 3.144,
47
+ "eval_samples_per_second": 542.932,
48
+ "eval_steps_per_second": 17.175,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.8388092517852783,
54
+ "learning_rate": 0.0005120524868662778,
55
+ "loss": 0.5125,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7076742823667252,
61
+ "eval_f1": 0.30014025245441794,
62
+ "eval_loss": 0.5383661985397339,
63
+ "eval_mcc": 0.2638138145109301,
64
+ "eval_precision": 0.7430555555555556,
65
+ "eval_recall": 0.18804920913884007,
66
+ "eval_runtime": 3.146,
67
+ "eval_samples_per_second": 542.599,
68
+ "eval_steps_per_second": 17.165,
69
+ "step": 642
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 1.7875562906265259,
74
+ "learning_rate": 0.00042671040572189826,
75
+ "loss": 0.5058,
76
+ "step": 856
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7193907439953134,
81
+ "eval_f1": 0.3803363518758086,
82
+ "eval_loss": 0.5227627158164978,
83
+ "eval_mcc": 0.30264867309481763,
84
+ "eval_precision": 0.7205882352941176,
85
+ "eval_recall": 0.2583479789103691,
86
+ "eval_runtime": 3.1421,
87
+ "eval_samples_per_second": 543.264,
88
+ "eval_steps_per_second": 17.186,
89
+ "step": 856
90
+ }
91
+ ],
92
+ "logging_steps": 500,
93
+ "max_steps": 1926,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 9,
96
+ "save_steps": 500,
97
+ "total_flos": 2099102657760.0,
98
+ "train_batch_size": 32,
99
+ "trial_name": null,
100
+ "trial_params": {
101
+ "alpha": 0.9213962687632572,
102
+ "learning_rate": 0.0007680787302994168,
103
+ "num_train_epochs": 9,
104
+ "temperature": 25
105
+ }
106
+ }
run-30/checkpoint-856/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c21d2a5115c4ec711667a681f6c70624e61496610806db95b0db67741a26789
3
+ size 5048
run-30/checkpoint-856/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-31/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-31/checkpoint-214/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71fa654faafcc6507f9f2c4e6a0a2767af4c5e03c943f9bbcb93249c62c1c97f
3
+ size 17549312
run-31/checkpoint-214/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87ea1cf8b7d6d422667fb1b90bda061f63702c33c7b8190ca0c5c0f225117850
3
+ size 35123898
run-31/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-31/checkpoint-214/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3fed4d33b925c4c635049001e3b3fd7c2810b7f85a1a1f90b878a3a22e4bb6b
3
+ size 1064
run-31/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-31/checkpoint-214/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-31/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-31/checkpoint-214/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7106033977738723,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-31/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": 8.190187454223633,
14
+ "learning_rate": 0.00012111783530103911,
15
+ "loss": 0.6036,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7106033977738723,
21
+ "eval_f1": 0.46304347826086956,
22
+ "eval_loss": 0.5476045608520508,
23
+ "eval_mcc": 0.2951848655219638,
24
+ "eval_precision": 0.6068376068376068,
25
+ "eval_recall": 0.37434094903339193,
26
+ "eval_runtime": 3.1382,
27
+ "eval_samples_per_second": 543.94,
28
+ "eval_steps_per_second": 17.207,
29
+ "step": 214
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 1498,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 7,
36
+ "save_steps": 500,
37
+ "total_flos": 524775664440.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.9889630226398882,
42
+ "learning_rate": 0.00014130414118454564,
43
+ "num_train_epochs": 7,
44
+ "temperature": 15
45
+ }
46
+ }
run-31/checkpoint-214/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c981cf0a286d911e6656921fe8054df3cc858ad8c45c649b452912044449904c
3
+ size 5048
run-31/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 sha256:6c21d2a5115c4ec711667a681f6c70624e61496610806db95b0db67741a26789
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c981cf0a286d911e6656921fe8054df3cc858ad8c45c649b452912044449904c
3
  size 5048