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
23d943c
·
verified ·
1 Parent(s): 72a356d

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1713611707.a9446dbff3d4.7440.16 +2 -2
  2. logs/events.out.tfevents.1713611757.a9446dbff3d4.7440.17 +3 -0
  3. model.safetensors +1 -1
  4. run-14/checkpoint-480/config.json +34 -0
  5. run-14/checkpoint-480/model.safetensors +3 -0
  6. run-14/checkpoint-480/optimizer.pt +3 -0
  7. run-14/checkpoint-480/rng_state.pth +3 -0
  8. run-14/checkpoint-480/scheduler.pt +3 -0
  9. run-14/checkpoint-480/special_tokens_map.json +7 -0
  10. run-14/checkpoint-480/tokenizer.json +0 -0
  11. run-14/checkpoint-480/tokenizer_config.json +57 -0
  12. run-14/checkpoint-480/trainer_state.json +86 -0
  13. run-14/checkpoint-480/training_args.bin +3 -0
  14. run-14/checkpoint-480/vocab.txt +0 -0
  15. run-14/checkpoint-640/config.json +34 -0
  16. run-14/checkpoint-640/model.safetensors +3 -0
  17. run-14/checkpoint-640/optimizer.pt +3 -0
  18. run-14/checkpoint-640/rng_state.pth +3 -0
  19. run-14/checkpoint-640/scheduler.pt +3 -0
  20. run-14/checkpoint-640/special_tokens_map.json +7 -0
  21. run-14/checkpoint-640/tokenizer.json +0 -0
  22. run-14/checkpoint-640/tokenizer_config.json +57 -0
  23. run-14/checkpoint-640/trainer_state.json +106 -0
  24. run-14/checkpoint-640/training_args.bin +3 -0
  25. run-14/checkpoint-640/vocab.txt +0 -0
  26. run-15/checkpoint-160/config.json +34 -0
  27. run-15/checkpoint-160/model.safetensors +3 -0
  28. run-15/checkpoint-160/optimizer.pt +3 -0
  29. run-15/checkpoint-160/rng_state.pth +3 -0
  30. run-15/checkpoint-160/scheduler.pt +3 -0
  31. run-15/checkpoint-160/special_tokens_map.json +7 -0
  32. run-15/checkpoint-160/tokenizer.json +0 -0
  33. run-15/checkpoint-160/tokenizer_config.json +57 -0
  34. run-15/checkpoint-160/trainer_state.json +46 -0
  35. run-15/checkpoint-160/training_args.bin +3 -0
  36. run-15/checkpoint-160/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1713611707.a9446dbff3d4.7440.16 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28043178bd882b340f3230feba3deb72bc4e78ca58adc105f0a62124530afefa
3
- size 5483
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b05078d76bbb5d3b42abcd070290a93528e01653efaa183782afc10f5ba23a5
3
+ size 8403
logs/events.out.tfevents.1713611757.a9446dbff3d4.7440.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14dfecc90724fa874c3839cfa6935de1bcc19e6b015286796f7f4a603ccbf47f
3
+ size 5482
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0142724fa20ed611e1b33d0280d454e12ec1c71b9b71578e3db5fc76a38a438
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07333b048aa459db0d0af4961e00c4c7ef225856518bb6c0473bf52db39df13e
3
  size 17549312
run-14/checkpoint-480/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-14/checkpoint-480/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4167856446d0b910371d7785f8690ac7a501d9d769ae9db80fca8f6243fc81c0
3
+ size 17549312
run-14/checkpoint-480/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d202c8c69a33bbdf63949012dfadea81258fbed447bd25b53870f9ec9005a4e8
3
+ size 35123898
run-14/checkpoint-480/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7df88a1682b20a33ad4db7d2033c40d86d4e86ed5570f42d184cc6ff147cd7b4
3
+ size 14308
run-14/checkpoint-480/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4d296d5e6c884c5995753b273e24b8dcaf0f959d7fbd35d07a759eb2dd3d307
3
+ size 1064
run-14/checkpoint-480/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-14/checkpoint-480/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-480/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-14/checkpoint-480/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.687843137254902,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/checkpoint-480",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 480,
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": 1.9069746732711792,
14
+ "learning_rate": 0.0001514416935217273,
15
+ "loss": 0.5085,
16
+ "step": 160
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6666666666666666,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.4942961037158966,
23
+ "eval_mcc": 0.0,
24
+ "eval_precision": 0.0,
25
+ "eval_recall": 0.0,
26
+ "eval_runtime": 1.8701,
27
+ "eval_samples_per_second": 681.789,
28
+ "eval_steps_per_second": 21.389,
29
+ "step": 160
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.130017638206482,
34
+ "learning_rate": 0.00012980716587576626,
35
+ "loss": 0.4801,
36
+ "step": 320
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.6862745098039216,
41
+ "eval_f1": 0.2673992673992674,
42
+ "eval_loss": 0.4666464626789093,
43
+ "eval_mcc": 0.18544515371789866,
44
+ "eval_precision": 0.6033057851239669,
45
+ "eval_recall": 0.17176470588235293,
46
+ "eval_runtime": 1.8689,
47
+ "eval_samples_per_second": 682.229,
48
+ "eval_steps_per_second": 21.403,
49
+ "step": 320
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 3.3810486793518066,
54
+ "learning_rate": 0.00010817263822980523,
55
+ "loss": 0.4677,
56
+ "step": 480
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.687843137254902,
61
+ "eval_f1": 0.45776566757493187,
62
+ "eval_loss": 0.46491068601608276,
63
+ "eval_mcc": 0.25237818375033577,
64
+ "eval_precision": 0.5436893203883495,
65
+ "eval_recall": 0.3952941176470588,
66
+ "eval_runtime": 1.8683,
67
+ "eval_samples_per_second": 682.456,
68
+ "eval_steps_per_second": 21.41,
69
+ "step": 480
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 1280,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 8,
76
+ "save_steps": 500,
77
+ "total_flos": 875266313760.0,
78
+ "train_batch_size": 32,
79
+ "trial_name": null,
80
+ "trial_params": {
81
+ "alpha": 0.7926575748257565,
82
+ "learning_rate": 0.00017307622116768837,
83
+ "num_train_epochs": 8,
84
+ "temperature": 11
85
+ }
86
+ }
run-14/checkpoint-480/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b6b19052d4c806997afdfae7afcfc25427cf0da55d0d521079b159e1e5e6a52
3
+ size 5048
run-14/checkpoint-480/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-640/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-14/checkpoint-640/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efe7968afd477c15d32795f93fa62d4feb23181356efc778f37ba839e9735f5c
3
+ size 17549312
run-14/checkpoint-640/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a86ddaff339fcc9a1ccc1133d057d88973fe55d4c6ab26660f24a6163398ffac
3
+ size 35123898
run-14/checkpoint-640/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fae3cb80286aa140b95db910a9642553ceeaeadd75e7dc192487af85f7f7af75
3
+ size 14308
run-14/checkpoint-640/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6968d514b7d9b5cbc465c1ecae3b038ed67cfcf96079b95f662538ea80d2d64b
3
+ size 1064
run-14/checkpoint-640/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-14/checkpoint-640/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-640/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-14/checkpoint-640/trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6933333333333334,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/checkpoint-640",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 640,
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": 1.9069746732711792,
14
+ "learning_rate": 0.0001514416935217273,
15
+ "loss": 0.5085,
16
+ "step": 160
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6666666666666666,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.4942961037158966,
23
+ "eval_mcc": 0.0,
24
+ "eval_precision": 0.0,
25
+ "eval_recall": 0.0,
26
+ "eval_runtime": 1.8701,
27
+ "eval_samples_per_second": 681.789,
28
+ "eval_steps_per_second": 21.389,
29
+ "step": 160
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.130017638206482,
34
+ "learning_rate": 0.00012980716587576626,
35
+ "loss": 0.4801,
36
+ "step": 320
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.6862745098039216,
41
+ "eval_f1": 0.2673992673992674,
42
+ "eval_loss": 0.4666464626789093,
43
+ "eval_mcc": 0.18544515371789866,
44
+ "eval_precision": 0.6033057851239669,
45
+ "eval_recall": 0.17176470588235293,
46
+ "eval_runtime": 1.8689,
47
+ "eval_samples_per_second": 682.229,
48
+ "eval_steps_per_second": 21.403,
49
+ "step": 320
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 3.3810486793518066,
54
+ "learning_rate": 0.00010817263822980523,
55
+ "loss": 0.4677,
56
+ "step": 480
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.687843137254902,
61
+ "eval_f1": 0.45776566757493187,
62
+ "eval_loss": 0.46491068601608276,
63
+ "eval_mcc": 0.25237818375033577,
64
+ "eval_precision": 0.5436893203883495,
65
+ "eval_recall": 0.3952941176470588,
66
+ "eval_runtime": 1.8683,
67
+ "eval_samples_per_second": 682.456,
68
+ "eval_steps_per_second": 21.41,
69
+ "step": 480
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 1.599716067314148,
74
+ "learning_rate": 8.653811058384418e-05,
75
+ "loss": 0.4606,
76
+ "step": 640
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.6933333333333334,
81
+ "eval_f1": 0.3450586264656616,
82
+ "eval_loss": 0.4478222727775574,
83
+ "eval_mcc": 0.22240963104490394,
84
+ "eval_precision": 0.5988372093023255,
85
+ "eval_recall": 0.24235294117647058,
86
+ "eval_runtime": 1.8717,
87
+ "eval_samples_per_second": 681.198,
88
+ "eval_steps_per_second": 21.371,
89
+ "step": 640
90
+ }
91
+ ],
92
+ "logging_steps": 500,
93
+ "max_steps": 1280,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 8,
96
+ "save_steps": 500,
97
+ "total_flos": 1167021751680.0,
98
+ "train_batch_size": 32,
99
+ "trial_name": null,
100
+ "trial_params": {
101
+ "alpha": 0.7926575748257565,
102
+ "learning_rate": 0.00017307622116768837,
103
+ "num_train_epochs": 8,
104
+ "temperature": 11
105
+ }
106
+ }
run-14/checkpoint-640/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b6b19052d4c806997afdfae7afcfc25427cf0da55d0d521079b159e1e5e6a52
3
+ size 5048
run-14/checkpoint-640/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-15/checkpoint-160/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-15/checkpoint-160/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07333b048aa459db0d0af4961e00c4c7ef225856518bb6c0473bf52db39df13e
3
+ size 17549312
run-15/checkpoint-160/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:548fb4861dfcadc58334d1ac00b74411ea2d38a2fd2f3a2e0b54b894e6f72633
3
+ size 35123898
run-15/checkpoint-160/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0792eaff268dd73c8e104b5060a487f4ef56535ad3b58888006338b8bc298137
3
+ size 14308
run-15/checkpoint-160/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:565150b206a5b8b847cd54989f9be3aefd58d82f9defb18be933ba7e92bb0987
3
+ size 1064
run-15/checkpoint-160/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-15/checkpoint-160/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-15/checkpoint-160/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-15/checkpoint-160/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6666666666666666,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-15/checkpoint-160",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 160,
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": 1.2901545763015747,
14
+ "learning_rate": 0.0008412100077685249,
15
+ "loss": 0.6355,
16
+ "step": 160
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6666666666666666,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.6301137804985046,
23
+ "eval_mcc": 0.0,
24
+ "eval_precision": 0.0,
25
+ "eval_recall": 0.0,
26
+ "eval_runtime": 1.871,
27
+ "eval_samples_per_second": 681.46,
28
+ "eval_steps_per_second": 21.379,
29
+ "step": 160
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 1600,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 10,
36
+ "save_steps": 500,
37
+ "total_flos": 291755437920.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.9881027780146323,
42
+ "learning_rate": 0.000934677786409472,
43
+ "num_train_epochs": 10,
44
+ "temperature": 23
45
+ }
46
+ }
run-15/checkpoint-160/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7013243ea232fbe58d7d060e36eb9837e206b5a39405a889bb222ed574858f48
3
+ size 5048
run-15/checkpoint-160/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 sha256:4b6b19052d4c806997afdfae7afcfc25427cf0da55d0d521079b159e1e5e6a52
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7013243ea232fbe58d7d060e36eb9837e206b5a39405a889bb222ed574858f48
3
  size 5048