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
e13e52e
·
verified ·
1 Parent(s): 66540f1

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1709878343.6c1c016b0e3e.7263.16 +2 -2
  2. logs/events.out.tfevents.1709878899.6c1c016b0e3e.7263.17 +3 -0
  3. model.safetensors +1 -1
  4. run-16/checkpoint-144/config.json +34 -0
  5. run-16/checkpoint-144/model.safetensors +3 -0
  6. run-16/checkpoint-144/optimizer.pt +3 -0
  7. run-16/checkpoint-144/rng_state.pth +3 -0
  8. run-16/checkpoint-144/scheduler.pt +3 -0
  9. run-16/checkpoint-144/special_tokens_map.json +7 -0
  10. run-16/checkpoint-144/tokenizer.json +0 -0
  11. run-16/checkpoint-144/tokenizer_config.json +57 -0
  12. run-16/checkpoint-144/trainer_state.json +83 -0
  13. run-16/checkpoint-144/training_args.bin +3 -0
  14. run-16/checkpoint-144/vocab.txt +0 -0
  15. run-16/checkpoint-192/config.json +34 -0
  16. run-16/checkpoint-192/model.safetensors +3 -0
  17. run-16/checkpoint-192/optimizer.pt +3 -0
  18. run-16/checkpoint-192/rng_state.pth +3 -0
  19. run-16/checkpoint-192/scheduler.pt +3 -0
  20. run-16/checkpoint-192/special_tokens_map.json +7 -0
  21. run-16/checkpoint-192/tokenizer.json +0 -0
  22. run-16/checkpoint-192/tokenizer_config.json +57 -0
  23. run-16/checkpoint-192/trainer_state.json +102 -0
  24. run-16/checkpoint-192/training_args.bin +3 -0
  25. run-16/checkpoint-192/vocab.txt +0 -0
  26. run-17/checkpoint-48/config.json +34 -0
  27. run-17/checkpoint-48/model.safetensors +3 -0
  28. run-17/checkpoint-48/optimizer.pt +3 -0
  29. run-17/checkpoint-48/rng_state.pth +3 -0
  30. run-17/checkpoint-48/scheduler.pt +3 -0
  31. run-17/checkpoint-48/special_tokens_map.json +7 -0
  32. run-17/checkpoint-48/tokenizer.json +0 -0
  33. run-17/checkpoint-48/tokenizer_config.json +57 -0
  34. run-17/checkpoint-48/trainer_state.json +45 -0
  35. run-17/checkpoint-48/training_args.bin +3 -0
  36. run-17/checkpoint-48/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1709878343.6c1c016b0e3e.7263.16 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5208271e97b80f006885f363d4916be48498fa36257caded30d489269c48f7b
3
- size 5985
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff4f91abc3868ac2b50c9717a571d0bf11b4c1927a866f223f2047a0387bb4aa
3
+ size 8034
logs/events.out.tfevents.1709878899.6c1c016b0e3e.7263.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:060319883ae894b501de238797da93ac3d602be081bbcf23b37e510913498ff5
3
+ size 5313
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88bdd4dc338ef9c8a968b0df5b17e6aa84927b6e6c113d0aeb7a52cf148234d0
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2285520545e833dd1f6db920ddc299d3c4889536ba9dba896e63cd5758984caa
3
  size 17549312
run-16/checkpoint-144/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-16/checkpoint-144/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea9c7e0df39360b7eeb37fd20174fcf7d2600f20c8b04c261b154aa6adc28fea
3
+ size 17549312
run-16/checkpoint-144/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b04c1449a50343b120575acb49c4d5eba4bf20a47de1f5702cb2ec112077cbf3
3
+ size 35122746
run-16/checkpoint-144/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:117413c2e4c616775c2a2540a012ac63a1e136326812b679f4206af03d68f7d5
3
+ size 14054
run-16/checkpoint-144/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1b2e77a5d4ee01b1211df881388a88bed490d0b67131b194da9a5abb64a964c
3
+ size 1064
run-16/checkpoint-144/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-16/checkpoint-144/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-16/checkpoint-144/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-16/checkpoint-144/trainer_state.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7671232876712328,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-16/checkpoint-144",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 144,
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": 1.2878928184509277,
14
+ "learning_rate": 0.00013115653902338105,
15
+ "loss": 0.4962,
16
+ "step": 48
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.700587084148728,
21
+ "eval_f1": 0.662251655629139,
22
+ "eval_loss": 0.4426267147064209,
23
+ "eval_precision": 0.759493670886076,
24
+ "eval_recall": 0.5870841487279843,
25
+ "eval_runtime": 27.3,
26
+ "eval_samples_per_second": 37.436,
27
+ "eval_steps_per_second": 0.586,
28
+ "step": 48
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 3.258302688598633,
33
+ "learning_rate": 0.00011241989059146946,
34
+ "loss": 0.4374,
35
+ "step": 96
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.6898238747553816,
40
+ "eval_f1": 0.6248520710059171,
41
+ "eval_loss": 0.41270217299461365,
42
+ "eval_precision": 0.7904191616766467,
43
+ "eval_recall": 0.5166340508806262,
44
+ "eval_runtime": 27.1797,
45
+ "eval_samples_per_second": 37.602,
46
+ "eval_steps_per_second": 0.589,
47
+ "step": 96
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 1.6551486253738403,
52
+ "learning_rate": 9.368324215955789e-05,
53
+ "loss": 0.4148,
54
+ "step": 144
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.7671232876712328,
59
+ "eval_f1": 0.7643564356435644,
60
+ "eval_loss": 0.39426228404045105,
61
+ "eval_precision": 0.7735470941883767,
62
+ "eval_recall": 0.7553816046966731,
63
+ "eval_runtime": 28.5963,
64
+ "eval_samples_per_second": 35.739,
65
+ "eval_steps_per_second": 0.56,
66
+ "step": 144
67
+ }
68
+ ],
69
+ "logging_steps": 500,
70
+ "max_steps": 384,
71
+ "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 8,
73
+ "save_steps": 500,
74
+ "total_flos": 707085591840.0,
75
+ "train_batch_size": 64,
76
+ "trial_name": null,
77
+ "trial_params": {
78
+ "alpha": 0.6758158495370239,
79
+ "learning_rate": 0.00014989318745529262,
80
+ "num_train_epochs": 8,
81
+ "temperature": 20
82
+ }
83
+ }
run-16/checkpoint-144/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63572106dff22a09912a371bd397d01ccf0c92ef49dec03568516e174c66f6b6
3
+ size 4920
run-16/checkpoint-144/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-16/checkpoint-192/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-16/checkpoint-192/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec760fc973fdf4c32272f31ae6b5950e7fb07416a4f3c4279bab3dd3c479d950
3
+ size 17549312
run-16/checkpoint-192/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60f9e8521bca109c76486446052836a08a509529965b7b7554d3f4ea6cda1ad
3
+ size 35122746
run-16/checkpoint-192/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d267b33c0df8c744bb62ca8fc0e243d0ddded8c46ea62639c56f51d1dc7a548
3
+ size 14054
run-16/checkpoint-192/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3249c0fa459fa540a92c593caa847b4dcdeeb1581c5176121df32e726b1e3cc4
3
+ size 1064
run-16/checkpoint-192/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-16/checkpoint-192/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-16/checkpoint-192/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-16/checkpoint-192/trainer_state.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7671232876712328,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-16/checkpoint-144",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 192,
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": 1.2878928184509277,
14
+ "learning_rate": 0.00013115653902338105,
15
+ "loss": 0.4962,
16
+ "step": 48
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.700587084148728,
21
+ "eval_f1": 0.662251655629139,
22
+ "eval_loss": 0.4426267147064209,
23
+ "eval_precision": 0.759493670886076,
24
+ "eval_recall": 0.5870841487279843,
25
+ "eval_runtime": 27.3,
26
+ "eval_samples_per_second": 37.436,
27
+ "eval_steps_per_second": 0.586,
28
+ "step": 48
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 3.258302688598633,
33
+ "learning_rate": 0.00011241989059146946,
34
+ "loss": 0.4374,
35
+ "step": 96
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.6898238747553816,
40
+ "eval_f1": 0.6248520710059171,
41
+ "eval_loss": 0.41270217299461365,
42
+ "eval_precision": 0.7904191616766467,
43
+ "eval_recall": 0.5166340508806262,
44
+ "eval_runtime": 27.1797,
45
+ "eval_samples_per_second": 37.602,
46
+ "eval_steps_per_second": 0.589,
47
+ "step": 96
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 1.6551486253738403,
52
+ "learning_rate": 9.368324215955789e-05,
53
+ "loss": 0.4148,
54
+ "step": 144
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.7671232876712328,
59
+ "eval_f1": 0.7643564356435644,
60
+ "eval_loss": 0.39426228404045105,
61
+ "eval_precision": 0.7735470941883767,
62
+ "eval_recall": 0.7553816046966731,
63
+ "eval_runtime": 28.5963,
64
+ "eval_samples_per_second": 35.739,
65
+ "eval_steps_per_second": 0.56,
66
+ "step": 144
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 1.3516536951065063,
71
+ "learning_rate": 7.494659372764631e-05,
72
+ "loss": 0.4044,
73
+ "step": 192
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.7632093933463796,
78
+ "eval_f1": 0.7535641547861507,
79
+ "eval_loss": 0.3918641209602356,
80
+ "eval_precision": 0.7855626326963907,
81
+ "eval_recall": 0.7240704500978473,
82
+ "eval_runtime": 27.1274,
83
+ "eval_samples_per_second": 37.674,
84
+ "eval_steps_per_second": 0.59,
85
+ "step": 192
86
+ }
87
+ ],
88
+ "logging_steps": 500,
89
+ "max_steps": 384,
90
+ "num_input_tokens_seen": 0,
91
+ "num_train_epochs": 8,
92
+ "save_steps": 500,
93
+ "total_flos": 942780789120.0,
94
+ "train_batch_size": 64,
95
+ "trial_name": null,
96
+ "trial_params": {
97
+ "alpha": 0.6758158495370239,
98
+ "learning_rate": 0.00014989318745529262,
99
+ "num_train_epochs": 8,
100
+ "temperature": 20
101
+ }
102
+ }
run-16/checkpoint-192/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63572106dff22a09912a371bd397d01ccf0c92ef49dec03568516e174c66f6b6
3
+ size 4920
run-16/checkpoint-192/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-17/checkpoint-48/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-17/checkpoint-48/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2285520545e833dd1f6db920ddc299d3c4889536ba9dba896e63cd5758984caa
3
+ size 17549312
run-17/checkpoint-48/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c52e3a976d7e317b248da76042fec2aef41c248793eb32d5a31d04e4028b7d6
3
+ size 35122746
run-17/checkpoint-48/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f731098665929ed6a815501631b54240caaac6508207c5c55cf0fe36ad39b17
3
+ size 14054
run-17/checkpoint-48/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77cd2257ac7028670e5f35cb08677aabe38d4356a6501dac67f38a92b6cc4513
3
+ size 1064
run-17/checkpoint-48/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-17/checkpoint-48/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-17/checkpoint-48/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-17/checkpoint-48/trainer_state.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7397260273972602,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-17/checkpoint-48",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 48,
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": 1.7164396047592163,
14
+ "learning_rate": 0.0007649073963933848,
15
+ "loss": 0.5715,
16
+ "step": 48
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7397260273972602,
21
+ "eval_f1": 0.7861736334405145,
22
+ "eval_loss": 0.5001023411750793,
23
+ "eval_precision": 0.6671214188267395,
24
+ "eval_recall": 0.9569471624266145,
25
+ "eval_runtime": 27.2812,
26
+ "eval_samples_per_second": 37.462,
27
+ "eval_steps_per_second": 0.586,
28
+ "step": 48
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 240,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 5,
35
+ "save_steps": 500,
36
+ "total_flos": 235695197280.0,
37
+ "train_batch_size": 64,
38
+ "trial_name": null,
39
+ "trial_params": {
40
+ "alpha": 0.8956137687880612,
41
+ "learning_rate": 0.000956134245491731,
42
+ "num_train_epochs": 5,
43
+ "temperature": 12
44
+ }
45
+ }
run-17/checkpoint-48/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95d1d9fe6835ec98bd27792504677b7d08fb2449a2b9aaeb293d875e0c380b75
3
+ size 4920
run-17/checkpoint-48/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 sha256:63572106dff22a09912a371bd397d01ccf0c92ef49dec03568516e174c66f6b6
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95d1d9fe6835ec98bd27792504677b7d08fb2449a2b9aaeb293d875e0c380b75
3
  size 4920