Hugging Face's logo

marlex7
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
marlex7 commited on
Commit
5ef2bdb
·
1 Parent(s): 371faec

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1700097911.0ef7b67c0c07.8576.2 +2 -2
  2. logs/events.out.tfevents.1700099651.0ef7b67c0c07.8576.3 +3 -0
  3. model.safetensors +1 -1
  4. run-1/checkpoint-4216/config.json +34 -0
  5. run-1/checkpoint-4216/model.safetensors +3 -0
  6. run-1/checkpoint-4216/optimizer.pt +3 -0
  7. run-1/checkpoint-4216/rng_state.pth +3 -0
  8. run-1/checkpoint-4216/scheduler.pt +3 -0
  9. run-1/checkpoint-4216/special_tokens_map.json +7 -0
  10. run-1/checkpoint-4216/tokenizer.json +0 -0
  11. run-1/checkpoint-4216/tokenizer_config.json +57 -0
  12. run-1/checkpoint-4216/trainer_state.json +144 -0
  13. run-1/checkpoint-4216/training_args.bin +3 -0
  14. run-1/checkpoint-4216/vocab.txt +0 -0
  15. run-1/checkpoint-4743/config.json +34 -0
  16. run-1/checkpoint-4743/model.safetensors +3 -0
  17. run-1/checkpoint-4743/optimizer.pt +3 -0
  18. run-1/checkpoint-4743/rng_state.pth +3 -0
  19. run-1/checkpoint-4743/scheduler.pt +3 -0
  20. run-1/checkpoint-4743/special_tokens_map.json +7 -0
  21. run-1/checkpoint-4743/tokenizer.json +0 -0
  22. run-1/checkpoint-4743/tokenizer_config.json +57 -0
  23. run-1/checkpoint-4743/trainer_state.json +159 -0
  24. run-1/checkpoint-4743/training_args.bin +3 -0
  25. run-1/checkpoint-4743/vocab.txt +0 -0
  26. run-2/checkpoint-527/config.json +34 -0
  27. run-2/checkpoint-527/model.safetensors +3 -0
  28. run-2/checkpoint-527/optimizer.pt +3 -0
  29. run-2/checkpoint-527/rng_state.pth +3 -0
  30. run-2/checkpoint-527/scheduler.pt +3 -0
  31. run-2/checkpoint-527/special_tokens_map.json +7 -0
  32. run-2/checkpoint-527/tokenizer.json +0 -0
  33. run-2/checkpoint-527/tokenizer_config.json +57 -0
  34. run-2/checkpoint-527/trainer_state.json +39 -0
  35. run-2/checkpoint-527/training_args.bin +3 -0
  36. run-2/checkpoint-527/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1700097911.0ef7b67c0c07.8576.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1dd709c32505d7a7864690ec816eff74d102fb8e2647365c9451d1047ffcff06
3
- size 5254
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09a93ce5586e8a29b0c7956db7583bfcf8a7f1dba6971f700737959ca12e3f35
3
+ size 8968
logs/events.out.tfevents.1700099651.0ef7b67c0c07.8576.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b94d2dbfd93a783cab73f885e5a3bf8c309bd54882436c37819e3fd465e38a7b
3
+ size 4774
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdcb79d03e36e8724a017eb5d8410cd9f760de06381973b7af7eaedc06d351d2
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5684590b773e27e4cabce4f2ece963f65d58fbb57ad79bd41fb186da2df122c
3
  size 17549312
run-1/checkpoint-4216/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": "4.35.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-1/checkpoint-4216/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea9c570e7b5cc08f1e102f3b8f804c03f7d97beba066e80f85a9352fa70a433b
3
+ size 17549312
run-1/checkpoint-4216/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68792d7a51f0ce502656efbfac1b3d64542d1b95878f475af945db8dd12d85eb
3
+ size 35123898
run-1/checkpoint-4216/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:260dd997fbd88fb4f37289d66733a02693a446f3f0745c4f3fa0ba0f46c931e2
3
+ size 14308
run-1/checkpoint-4216/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5392642ae24c7897675480e102f3f48af092cf4437861939fb4a3867b5c2207e
3
+ size 1064
run-1/checkpoint-4216/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-4216/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-4216/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-4216/trainer_state.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8268348623853211,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-4216",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4216,
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": 0.00014946971324611056,
14
+ "loss": 2.145,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.823394495412844,
20
+ "eval_loss": 1.8049757480621338,
21
+ "eval_runtime": 2.6317,
22
+ "eval_samples_per_second": 331.345,
23
+ "eval_steps_per_second": 2.66,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.00013079042966045718,
29
+ "loss": 0.9755,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8188073394495413,
35
+ "eval_loss": 1.9008780717849731,
36
+ "eval_runtime": 2.6239,
37
+ "eval_samples_per_second": 332.334,
38
+ "eval_steps_per_second": 2.668,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 0.00011211114607480381,
44
+ "loss": 0.7327,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8222477064220184,
50
+ "eval_loss": 1.9420150518417358,
51
+ "eval_runtime": 2.6317,
52
+ "eval_samples_per_second": 331.343,
53
+ "eval_steps_per_second": 2.66,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 9.343186248915043e-05,
59
+ "loss": 0.5827,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8153669724770642,
65
+ "eval_loss": 2.017528772354126,
66
+ "eval_runtime": 2.6816,
67
+ "eval_samples_per_second": 325.181,
68
+ "eval_steps_per_second": 2.61,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 7.475257890349707e-05,
74
+ "loss": 0.4851,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8165137614678899,
80
+ "eval_loss": 2.1781740188598633,
81
+ "eval_runtime": 2.6676,
82
+ "eval_samples_per_second": 326.883,
83
+ "eval_steps_per_second": 2.624,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 5.6073295317843696e-05,
89
+ "loss": 0.4204,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8142201834862385,
95
+ "eval_loss": 2.129305601119995,
96
+ "eval_runtime": 2.6508,
97
+ "eval_samples_per_second": 328.958,
98
+ "eval_steps_per_second": 2.641,
99
+ "step": 3162
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "learning_rate": 3.739401173219033e-05,
104
+ "loss": 0.3787,
105
+ "step": 3689
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "eval_accuracy": 0.8096330275229358,
110
+ "eval_loss": 2.1337575912475586,
111
+ "eval_runtime": 2.688,
112
+ "eval_samples_per_second": 324.4,
113
+ "eval_steps_per_second": 2.604,
114
+ "step": 3689
115
+ },
116
+ {
117
+ "epoch": 8.0,
118
+ "learning_rate": 1.8714728146536963e-05,
119
+ "loss": 0.3455,
120
+ "step": 4216
121
+ },
122
+ {
123
+ "epoch": 8.0,
124
+ "eval_accuracy": 0.8268348623853211,
125
+ "eval_loss": 2.115010976791382,
126
+ "eval_runtime": 2.6909,
127
+ "eval_samples_per_second": 324.06,
128
+ "eval_steps_per_second": 2.601,
129
+ "step": 4216
130
+ }
131
+ ],
132
+ "logging_steps": 500,
133
+ "max_steps": 4743,
134
+ "num_train_epochs": 9,
135
+ "save_steps": 500,
136
+ "total_flos": 64677008811300.0,
137
+ "trial_name": null,
138
+ "trial_params": {
139
+ "alpha": 0.052937085110831505,
140
+ "learning_rate": 0.00016811355227088032,
141
+ "num_train_epochs": 9,
142
+ "temperature": 28
143
+ }
144
+ }
run-1/checkpoint-4216/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9778c4a9b9e0841a37887d1e9944802b8b476bac60a9e2178954f797fa2f6f75
3
+ size 4664
run-1/checkpoint-4216/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-4743/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": "4.35.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-1/checkpoint-4743/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c6c48a8065ed05260fd030ac67970d7b0ef0ab2eb89fc8f628f4e8914874337
3
+ size 17549312
run-1/checkpoint-4743/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68c1637f91494d6e17ba12a36d795cd5d0a47c8200c067a9f3b942e52672823
3
+ size 35123898
run-1/checkpoint-4743/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06c57ce5e6b2e9f61341a63c012a7ceeecd2734f8a396f51216cd4c12a9112a1
3
+ size 14308
run-1/checkpoint-4743/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f38a6bcb13bae065f35789dfddcef17c865ca36b2cbf18f310e8678978418394
3
+ size 1064
run-1/checkpoint-4743/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-4743/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-4743/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-4743/trainer_state.json ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8268348623853211,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-4216",
4
+ "epoch": 9.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4743,
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": 0.00014946971324611056,
14
+ "loss": 2.145,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.823394495412844,
20
+ "eval_loss": 1.8049757480621338,
21
+ "eval_runtime": 2.6317,
22
+ "eval_samples_per_second": 331.345,
23
+ "eval_steps_per_second": 2.66,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.00013079042966045718,
29
+ "loss": 0.9755,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8188073394495413,
35
+ "eval_loss": 1.9008780717849731,
36
+ "eval_runtime": 2.6239,
37
+ "eval_samples_per_second": 332.334,
38
+ "eval_steps_per_second": 2.668,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 0.00011211114607480381,
44
+ "loss": 0.7327,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8222477064220184,
50
+ "eval_loss": 1.9420150518417358,
51
+ "eval_runtime": 2.6317,
52
+ "eval_samples_per_second": 331.343,
53
+ "eval_steps_per_second": 2.66,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 9.343186248915043e-05,
59
+ "loss": 0.5827,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8153669724770642,
65
+ "eval_loss": 2.017528772354126,
66
+ "eval_runtime": 2.6816,
67
+ "eval_samples_per_second": 325.181,
68
+ "eval_steps_per_second": 2.61,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 7.475257890349707e-05,
74
+ "loss": 0.4851,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8165137614678899,
80
+ "eval_loss": 2.1781740188598633,
81
+ "eval_runtime": 2.6676,
82
+ "eval_samples_per_second": 326.883,
83
+ "eval_steps_per_second": 2.624,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 5.6073295317843696e-05,
89
+ "loss": 0.4204,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8142201834862385,
95
+ "eval_loss": 2.129305601119995,
96
+ "eval_runtime": 2.6508,
97
+ "eval_samples_per_second": 328.958,
98
+ "eval_steps_per_second": 2.641,
99
+ "step": 3162
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "learning_rate": 3.739401173219033e-05,
104
+ "loss": 0.3787,
105
+ "step": 3689
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "eval_accuracy": 0.8096330275229358,
110
+ "eval_loss": 2.1337575912475586,
111
+ "eval_runtime": 2.688,
112
+ "eval_samples_per_second": 324.4,
113
+ "eval_steps_per_second": 2.604,
114
+ "step": 3689
115
+ },
116
+ {
117
+ "epoch": 8.0,
118
+ "learning_rate": 1.8714728146536963e-05,
119
+ "loss": 0.3455,
120
+ "step": 4216
121
+ },
122
+ {
123
+ "epoch": 8.0,
124
+ "eval_accuracy": 0.8268348623853211,
125
+ "eval_loss": 2.115010976791382,
126
+ "eval_runtime": 2.6909,
127
+ "eval_samples_per_second": 324.06,
128
+ "eval_steps_per_second": 2.601,
129
+ "step": 4216
130
+ },
131
+ {
132
+ "epoch": 9.0,
133
+ "learning_rate": 7.088912176718546e-08,
134
+ "loss": 0.3239,
135
+ "step": 4743
136
+ },
137
+ {
138
+ "epoch": 9.0,
139
+ "eval_accuracy": 0.8165137614678899,
140
+ "eval_loss": 2.101562261581421,
141
+ "eval_runtime": 2.6947,
142
+ "eval_samples_per_second": 323.6,
143
+ "eval_steps_per_second": 2.598,
144
+ "step": 4743
145
+ }
146
+ ],
147
+ "logging_steps": 500,
148
+ "max_steps": 4743,
149
+ "num_train_epochs": 9,
150
+ "save_steps": 500,
151
+ "total_flos": 72756683549280.0,
152
+ "trial_name": null,
153
+ "trial_params": {
154
+ "alpha": 0.052937085110831505,
155
+ "learning_rate": 0.00016811355227088032,
156
+ "num_train_epochs": 9,
157
+ "temperature": 28
158
+ }
159
+ }
run-1/checkpoint-4743/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9778c4a9b9e0841a37887d1e9944802b8b476bac60a9e2178954f797fa2f6f75
3
+ size 4664
run-1/checkpoint-4743/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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": "4.35.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-2/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5684590b773e27e4cabce4f2ece963f65d58fbb57ad79bd41fb186da2df122c
3
+ size 17549312
run-2/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ed2edb72cbf39a8665d7966e8405f9a38df4823dd20ebf0e5820714b075419
3
+ size 35123898
run-2/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df95bce5c5c16e60e49eb22753b34dbfa7966d22f239bd4ae61a5f9a0e6ccf0d
3
+ size 14308
run-2/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7ae23a1da5c731d3a50433b19bb49f3ac0a063b6ca1e9bf0528a711456b5995
3
+ size 1064
run-2/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-2/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7614678899082569,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/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": 1.8491531182399142e-05,
14
+ "loss": 3.8741,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.7614678899082569,
20
+ "eval_loss": 2.7297239303588867,
21
+ "eval_runtime": 2.7029,
22
+ "eval_samples_per_second": 322.618,
23
+ "eval_steps_per_second": 2.59,
24
+ "step": 527
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 4216,
29
+ "num_train_epochs": 8,
30
+ "save_steps": 500,
31
+ "total_flos": 8117476690260.0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "alpha": 0.0989236004227847,
35
+ "learning_rate": 2.1127451345527043e-05,
36
+ "num_train_epochs": 8,
37
+ "temperature": 14
38
+ }
39
+ }
run-2/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c77420f1051747d06d2dbd002693f07d255ca1b62b3d3632b864c5128fdb19
3
+ size 4664
run-2/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 sha256:9778c4a9b9e0841a37887d1e9944802b8b476bac60a9e2178954f797fa2f6f75
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c77420f1051747d06d2dbd002693f07d255ca1b62b3d3632b864c5128fdb19
3
  size 4664