Hugging Face's logo

JeukHwang
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
Model card Files
xet
Metrics Community
JeukHwang commited on
Commit
85d6146
·
1 Parent(s): 517ff9c

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1699910323.b18f42e49ba4.3021.22 +2 -2
  2. logs/events.out.tfevents.1699910730.b18f42e49ba4.3021.23 +3 -0
  3. model.safetensors +1 -1
  4. run-21/checkpoint-2635/config.json +34 -0
  5. run-21/checkpoint-2635/model.safetensors +3 -0
  6. run-21/checkpoint-2635/optimizer.pt +3 -0
  7. run-21/checkpoint-2635/rng_state.pth +3 -0
  8. run-21/checkpoint-2635/scheduler.pt +3 -0
  9. run-21/checkpoint-2635/special_tokens_map.json +7 -0
  10. run-21/checkpoint-2635/tokenizer.json +0 -0
  11. run-21/checkpoint-2635/tokenizer_config.json +57 -0
  12. run-21/checkpoint-2635/trainer_state.json +99 -0
  13. run-21/checkpoint-2635/training_args.bin +3 -0
  14. run-21/checkpoint-2635/vocab.txt +0 -0
  15. run-21/checkpoint-3162/config.json +34 -0
  16. run-21/checkpoint-3162/model.safetensors +3 -0
  17. run-21/checkpoint-3162/optimizer.pt +3 -0
  18. run-21/checkpoint-3162/rng_state.pth +3 -0
  19. run-21/checkpoint-3162/scheduler.pt +3 -0
  20. run-21/checkpoint-3162/special_tokens_map.json +7 -0
  21. run-21/checkpoint-3162/tokenizer.json +0 -0
  22. run-21/checkpoint-3162/tokenizer_config.json +57 -0
  23. run-21/checkpoint-3162/trainer_state.json +114 -0
  24. run-21/checkpoint-3162/training_args.bin +3 -0
  25. run-21/checkpoint-3162/vocab.txt +0 -0
  26. run-22/checkpoint-527/config.json +34 -0
  27. run-22/checkpoint-527/model.safetensors +3 -0
  28. run-22/checkpoint-527/optimizer.pt +3 -0
  29. run-22/checkpoint-527/rng_state.pth +3 -0
  30. run-22/checkpoint-527/scheduler.pt +3 -0
  31. run-22/checkpoint-527/special_tokens_map.json +7 -0
  32. run-22/checkpoint-527/tokenizer.json +0 -0
  33. run-22/checkpoint-527/tokenizer_config.json +57 -0
  34. run-22/checkpoint-527/trainer_state.json +39 -0
  35. run-22/checkpoint-527/training_args.bin +3 -0
  36. run-22/checkpoint-527/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1699910323.b18f42e49ba4.3021.22 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae0426d3cbdf139ee9ea0a640ebf18ff3961955a3536492336ac759c32c18094
3
- size 5253
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edb2e725cfecbcc021eca7b963b2f3f6c85cebcfa6dca5c50c5991b5e1d2555c
3
+ size 7527
logs/events.out.tfevents.1699910730.b18f42e49ba4.3021.23 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f872239f49b38b53b2064268ae57530ae28763210de7757ebf0e8a2892b5c936
3
+ size 4773
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11ac06fd0758b28a577a25b1f5635d689997ac4ce45727516b156a19b16c5b59
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a8c37522937932027514ae91a3c6ff2f920c52a20a332b9d0885922c97ccac2
3
  size 17549312
run-21/checkpoint-2635/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": "4.35.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-21/checkpoint-2635/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73346ba14bf3fff224e7b607bd87902b8612a452e2a9a1f6a57d7d30826050d1
3
+ size 17549312
run-21/checkpoint-2635/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bef86ce423961093aee285aad4fc3ac3e87c05b020ef5caff8549534f7db2236
3
+ size 35123898
run-21/checkpoint-2635/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6495712c0480e33150a9e840df89cfbd7359c197e00213528d6031351fe6bf56
3
+ size 14308
run-21/checkpoint-2635/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceb92ed1d4d95451eca9381e1828c3aaedde809fd1c835d6f43de70ccfb92bb3
3
+ size 1064
run-21/checkpoint-2635/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-21/checkpoint-2635/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-21/checkpoint-2635/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-21/checkpoint-2635/trainer_state.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8256880733944955,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-2635",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2635,
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
+ "learning_rate": 0.0007813674039938339,
14
+ "loss": 1.4569,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8211009174311926,
20
+ "eval_loss": 1.8369688987731934,
21
+ "eval_runtime": 0.957,
22
+ "eval_samples_per_second": 911.136,
23
+ "eval_steps_per_second": 7.314,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.0006251532075201045,
29
+ "loss": 0.6203,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.819954128440367,
35
+ "eval_loss": 2.187230110168457,
36
+ "eval_runtime": 0.833,
37
+ "eval_samples_per_second": 1046.865,
38
+ "eval_steps_per_second": 8.404,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 0.0004689390110463753,
44
+ "loss": 0.4011,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8222477064220184,
50
+ "eval_loss": 2.2777745723724365,
51
+ "eval_runtime": 0.8303,
52
+ "eval_samples_per_second": 1050.221,
53
+ "eval_steps_per_second": 8.431,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 0.000312724814572646,
59
+ "loss": 0.2824,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8176605504587156,
65
+ "eval_loss": 2.049936294555664,
66
+ "eval_runtime": 0.9199,
67
+ "eval_samples_per_second": 947.944,
68
+ "eval_steps_per_second": 7.61,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 0.00015651061809891667,
74
+ "loss": 0.2061,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8256880733944955,
80
+ "eval_loss": 2.054544687271118,
81
+ "eval_runtime": 0.8429,
82
+ "eval_samples_per_second": 1034.572,
83
+ "eval_steps_per_second": 8.305,
84
+ "step": 2635
85
+ }
86
+ ],
87
+ "logging_steps": 500,
88
+ "max_steps": 3162,
89
+ "num_train_epochs": 6,
90
+ "save_steps": 500,
91
+ "total_flos": 40418309418180.0,
92
+ "trial_name": null,
93
+ "trial_params": {
94
+ "alpha": 0.12545237557795993,
95
+ "learning_rate": 0.0009372851788423759,
96
+ "num_train_epochs": 6,
97
+ "temperature": 30
98
+ }
99
+ }
run-21/checkpoint-2635/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cf4805dbdf09e6f5258853c790c37af35f2cbe2f2d5a284a8389b7ec93b9b40
3
+ size 4600
run-21/checkpoint-2635/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-21/checkpoint-3162/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": "4.35.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-21/checkpoint-3162/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2812cd07cbfaa5e8db36f16ac7a0ab2b1bfbcb4263eb8ad93f16d0cf3ff0647f
3
+ size 17549312
run-21/checkpoint-3162/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7497c1bdf6fd5ca77fb20e3a1b282822486df8940073be7486be110956d73c8a
3
+ size 35123898
run-21/checkpoint-3162/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4a805f5b31aed4614530263d37ef452339ef59079ff627a6dd75bd82ccc8197
3
+ size 14308
run-21/checkpoint-3162/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d072378c1f4a756995d84a0040dbc6a88059769dba98c7be4c5a1377838e17f3
3
+ size 1064
run-21/checkpoint-3162/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-21/checkpoint-3162/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-21/checkpoint-3162/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-21/checkpoint-3162/trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8256880733944955,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-2635",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3162,
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
+ "learning_rate": 0.0007813674039938339,
14
+ "loss": 1.4569,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8211009174311926,
20
+ "eval_loss": 1.8369688987731934,
21
+ "eval_runtime": 0.957,
22
+ "eval_samples_per_second": 911.136,
23
+ "eval_steps_per_second": 7.314,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.0006251532075201045,
29
+ "loss": 0.6203,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.819954128440367,
35
+ "eval_loss": 2.187230110168457,
36
+ "eval_runtime": 0.833,
37
+ "eval_samples_per_second": 1046.865,
38
+ "eval_steps_per_second": 8.404,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 0.0004689390110463753,
44
+ "loss": 0.4011,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8222477064220184,
50
+ "eval_loss": 2.2777745723724365,
51
+ "eval_runtime": 0.8303,
52
+ "eval_samples_per_second": 1050.221,
53
+ "eval_steps_per_second": 8.431,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 0.000312724814572646,
59
+ "loss": 0.2824,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8176605504587156,
65
+ "eval_loss": 2.049936294555664,
66
+ "eval_runtime": 0.9199,
67
+ "eval_samples_per_second": 947.944,
68
+ "eval_steps_per_second": 7.61,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 0.00015651061809891667,
74
+ "loss": 0.2061,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8256880733944955,
80
+ "eval_loss": 2.054544687271118,
81
+ "eval_runtime": 0.8429,
82
+ "eval_samples_per_second": 1034.572,
83
+ "eval_steps_per_second": 8.305,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 2.9642162518734216e-07,
89
+ "loss": 0.1638,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8222477064220184,
95
+ "eval_loss": 2.0563035011291504,
96
+ "eval_runtime": 0.8349,
97
+ "eval_samples_per_second": 1044.492,
98
+ "eval_steps_per_second": 8.385,
99
+ "step": 3162
100
+ }
101
+ ],
102
+ "logging_steps": 500,
103
+ "max_steps": 3162,
104
+ "num_train_epochs": 6,
105
+ "save_steps": 500,
106
+ "total_flos": 48509902416420.0,
107
+ "trial_name": null,
108
+ "trial_params": {
109
+ "alpha": 0.12545237557795993,
110
+ "learning_rate": 0.0009372851788423759,
111
+ "num_train_epochs": 6,
112
+ "temperature": 30
113
+ }
114
+ }
run-21/checkpoint-3162/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cf4805dbdf09e6f5258853c790c37af35f2cbe2f2d5a284a8389b7ec93b9b40
3
+ size 4600
run-21/checkpoint-3162/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-22/checkpoint-527/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": "4.35.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-22/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a8c37522937932027514ae91a3c6ff2f920c52a20a332b9d0885922c97ccac2
3
+ size 17549312
run-22/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8893c54ad888be40b5cc4b2d9092d9757e591e67cb7ad253c8848f5a2638e76
3
+ size 35123898
run-22/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ababcbf30496eb4976cce44a5faf0cf605467f452ba655745eb60d884a0042d8
3
+ size 14308
run-22/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54f6bfb1b936a30a866dbf384a2af80577a833aab50cab40965f98a8da7a1006
3
+ size 1064
run-22/checkpoint-527/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-22/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-22/checkpoint-527/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-22/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8119266055045872,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-22/checkpoint-527",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 527,
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
+ "learning_rate": 0.0002438746383718142,
14
+ "loss": 1.5658,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8119266055045872,
20
+ "eval_loss": 1.591517686843872,
21
+ "eval_runtime": 0.8322,
22
+ "eval_samples_per_second": 1047.812,
23
+ "eval_steps_per_second": 8.411,
24
+ "step": 527
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 3689,
29
+ "num_train_epochs": 7,
30
+ "save_steps": 500,
31
+ "total_flos": 8117476690260.0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "alpha": 0.24619262739255549,
35
+ "learning_rate": 0.0002844304587270384,
36
+ "num_train_epochs": 7,
37
+ "temperature": 30
38
+ }
39
+ }
run-22/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:514dd10b819ed437f80437be6fb00aa001e9247d6260b3e65ea536a793f87a5d
3
+ size 4600
run-22/checkpoint-527/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 sha256:9cf4805dbdf09e6f5258853c790c37af35f2cbe2f2d5a284a8389b7ec93b9b40
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:514dd10b819ed437f80437be6fb00aa001e9247d6260b3e65ea536a793f87a5d
3
  size 4600