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
aabc90d
·
1 Parent(s): 37947da

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1700095978.0ef7b67c0c07.8576.1 +2 -2
  2. logs/events.out.tfevents.1700097911.0ef7b67c0c07.8576.2 +3 -0
  3. model.safetensors +1 -1
  4. run-0/checkpoint-4216/config.json +34 -0
  5. run-0/checkpoint-4216/model.safetensors +3 -0
  6. run-0/checkpoint-4216/optimizer.pt +3 -0
  7. run-0/checkpoint-4216/rng_state.pth +3 -0
  8. run-0/checkpoint-4216/scheduler.pt +3 -0
  9. run-0/checkpoint-4216/special_tokens_map.json +7 -0
  10. run-0/checkpoint-4216/tokenizer.json +0 -0
  11. run-0/checkpoint-4216/tokenizer_config.json +57 -0
  12. run-0/checkpoint-4216/trainer_state.json +144 -0
  13. run-0/checkpoint-4216/training_args.bin +3 -0
  14. run-0/checkpoint-4216/vocab.txt +0 -0
  15. run-0/checkpoint-5270/config.json +34 -0
  16. run-0/checkpoint-5270/model.safetensors +3 -0
  17. run-0/checkpoint-5270/optimizer.pt +3 -0
  18. run-0/checkpoint-5270/rng_state.pth +3 -0
  19. run-0/checkpoint-5270/scheduler.pt +3 -0
  20. run-0/checkpoint-5270/special_tokens_map.json +7 -0
  21. run-0/checkpoint-5270/tokenizer.json +0 -0
  22. run-0/checkpoint-5270/tokenizer_config.json +57 -0
  23. run-0/checkpoint-5270/trainer_state.json +174 -0
  24. run-0/checkpoint-5270/training_args.bin +3 -0
  25. run-0/checkpoint-5270/vocab.txt +0 -0
  26. run-1/checkpoint-527/config.json +34 -0
  27. run-1/checkpoint-527/model.safetensors +3 -0
  28. run-1/checkpoint-527/optimizer.pt +3 -0
  29. run-1/checkpoint-527/rng_state.pth +3 -0
  30. run-1/checkpoint-527/scheduler.pt +3 -0
  31. run-1/checkpoint-527/special_tokens_map.json +7 -0
  32. run-1/checkpoint-527/tokenizer.json +0 -0
  33. run-1/checkpoint-527/tokenizer_config.json +57 -0
  34. run-1/checkpoint-527/trainer_state.json +39 -0
  35. run-1/checkpoint-527/training_args.bin +3 -0
  36. run-1/checkpoint-527/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1700095978.0ef7b67c0c07.8576.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b911cbb28d3511ac6711102c19b0e62fd9e9e03a5a4817c20ec00d8d9874ea0d
3
- size 5255
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c970a6228bfe9d38070bb7569e749de044f1626effa1aae54d30da712b4d5b25
3
+ size 9449
logs/events.out.tfevents.1700097911.0ef7b67c0c07.8576.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9ed3bd33dedf54f8dbec4b2811abe79edd0f5585a04168b4c2e841dfbe96b71
3
+ size 4774
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e128015dfbfb176427716c0541dbc468b06e6421a1bf76c0943eb0b50d1f194
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0384a7e788e01cfc1a0a496c74d1a709c2c10fb868d0c3cb533a0156c1c397cc
3
  size 17549312
run-0/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-0/checkpoint-4216/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7c6bb9d17fd7855b804e1d2d68ae07dcddff1812677daf357f09a3ac0b41d5f
3
+ size 17549312
run-0/checkpoint-4216/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:babeaea918d862aa0f50dc8f37d8be15aaae76624f943f23817fe0b63b7b293a
3
+ size 35123898
run-0/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-0/checkpoint-4216/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8c3b2dd81c5253f96ee8e24d0895ad98a7829a63b3f7b64f71c663be805ca01
3
+ size 1064
run-0/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-0/checkpoint-4216/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/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-0/checkpoint-4216/trainer_state.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8291284403669725,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/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": 0.00014790853024760983,
14
+ "loss": 1.5038,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8211009174311926,
20
+ "eval_loss": 1.3256508111953735,
21
+ "eval_runtime": 2.6523,
22
+ "eval_samples_per_second": 328.767,
23
+ "eval_steps_per_second": 2.639,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.0001314742491089865,
29
+ "loss": 0.7133,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8222477064220184,
35
+ "eval_loss": 1.4129838943481445,
36
+ "eval_runtime": 2.6313,
37
+ "eval_samples_per_second": 331.391,
38
+ "eval_steps_per_second": 2.66,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 0.00011507115256455413,
44
+ "loss": 0.5369,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8130733944954128,
50
+ "eval_loss": 1.4813663959503174,
51
+ "eval_runtime": 2.6306,
52
+ "eval_samples_per_second": 331.479,
53
+ "eval_steps_per_second": 2.661,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 9.863687142593081e-05,
59
+ "loss": 0.4298,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.819954128440367,
65
+ "eval_loss": 1.4730076789855957,
66
+ "eval_runtime": 2.629,
67
+ "eval_samples_per_second": 331.69,
68
+ "eval_steps_per_second": 2.663,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 8.22025902873075e-05,
74
+ "loss": 0.3569,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8165137614678899,
80
+ "eval_loss": 1.6235142946243286,
81
+ "eval_runtime": 2.6181,
82
+ "eval_samples_per_second": 333.07,
83
+ "eval_steps_per_second": 2.674,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 6.576830914868419e-05,
89
+ "loss": 0.3121,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8130733944954128,
95
+ "eval_loss": 1.5953558683395386,
96
+ "eval_runtime": 2.6353,
97
+ "eval_samples_per_second": 330.889,
98
+ "eval_steps_per_second": 2.656,
99
+ "step": 3162
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "learning_rate": 4.933402801006087e-05,
104
+ "loss": 0.2779,
105
+ "step": 3689
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "eval_accuracy": 0.8165137614678899,
110
+ "eval_loss": 1.5940132141113281,
111
+ "eval_runtime": 2.638,
112
+ "eval_samples_per_second": 330.559,
113
+ "eval_steps_per_second": 2.654,
114
+ "step": 3689
115
+ },
116
+ {
117
+ "epoch": 8.0,
118
+ "learning_rate": 3.2899746871437564e-05,
119
+ "loss": 0.253,
120
+ "step": 4216
121
+ },
122
+ {
123
+ "epoch": 8.0,
124
+ "eval_accuracy": 0.8291284403669725,
125
+ "eval_loss": 1.6077648401260376,
126
+ "eval_runtime": 2.6314,
127
+ "eval_samples_per_second": 331.377,
128
+ "eval_steps_per_second": 2.66,
129
+ "step": 4216
130
+ }
131
+ ],
132
+ "logging_steps": 500,
133
+ "max_steps": 5270,
134
+ "num_train_epochs": 10,
135
+ "save_steps": 500,
136
+ "total_flos": 64677008811300.0,
137
+ "trial_name": null,
138
+ "trial_params": {
139
+ "alpha": 0.4020095097837325,
140
+ "learning_rate": 0.00016434281138623312,
141
+ "num_train_epochs": 10,
142
+ "temperature": 12
143
+ }
144
+ }
run-0/checkpoint-4216/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65178f463aeaf39a13d8ba13438e7d131c26a92476a5b5cf1d59944b12ddd026
3
+ size 4664
run-0/checkpoint-4216/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-5270/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-0/checkpoint-5270/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:362ba1d5fb3dd5753aae3b833b01eb29f244220d533a991fafbea8f2c8d307d6
3
+ size 17549312
run-0/checkpoint-5270/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:840fede8a95369198439a91c52759990401c3f9bc57bf94838652ed64f2dab73
3
+ size 35123898
run-0/checkpoint-5270/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a15c2d4c9f13c3c35211dadd11fccb633da2d92ebea0a00cb7665e9b14539805
3
+ size 14308
run-0/checkpoint-5270/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6661d08c5b01f63bc39c438002f5cf968f0bfe50707f943a0aacb0891531bed6
3
+ size 1064
run-0/checkpoint-5270/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-0/checkpoint-5270/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-5270/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-0/checkpoint-5270/trainer_state.json ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8291284403669725,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-4216",
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5270,
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": 0.00014790853024760983,
14
+ "loss": 1.5038,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8211009174311926,
20
+ "eval_loss": 1.3256508111953735,
21
+ "eval_runtime": 2.6523,
22
+ "eval_samples_per_second": 328.767,
23
+ "eval_steps_per_second": 2.639,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.0001314742491089865,
29
+ "loss": 0.7133,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8222477064220184,
35
+ "eval_loss": 1.4129838943481445,
36
+ "eval_runtime": 2.6313,
37
+ "eval_samples_per_second": 331.391,
38
+ "eval_steps_per_second": 2.66,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 0.00011507115256455413,
44
+ "loss": 0.5369,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8130733944954128,
50
+ "eval_loss": 1.4813663959503174,
51
+ "eval_runtime": 2.6306,
52
+ "eval_samples_per_second": 331.479,
53
+ "eval_steps_per_second": 2.661,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 9.863687142593081e-05,
59
+ "loss": 0.4298,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.819954128440367,
65
+ "eval_loss": 1.4730076789855957,
66
+ "eval_runtime": 2.629,
67
+ "eval_samples_per_second": 331.69,
68
+ "eval_steps_per_second": 2.663,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 8.22025902873075e-05,
74
+ "loss": 0.3569,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8165137614678899,
80
+ "eval_loss": 1.6235142946243286,
81
+ "eval_runtime": 2.6181,
82
+ "eval_samples_per_second": 333.07,
83
+ "eval_steps_per_second": 2.674,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 6.576830914868419e-05,
89
+ "loss": 0.3121,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8130733944954128,
95
+ "eval_loss": 1.5953558683395386,
96
+ "eval_runtime": 2.6353,
97
+ "eval_samples_per_second": 330.889,
98
+ "eval_steps_per_second": 2.656,
99
+ "step": 3162
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "learning_rate": 4.933402801006087e-05,
104
+ "loss": 0.2779,
105
+ "step": 3689
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "eval_accuracy": 0.8165137614678899,
110
+ "eval_loss": 1.5940132141113281,
111
+ "eval_runtime": 2.638,
112
+ "eval_samples_per_second": 330.559,
113
+ "eval_steps_per_second": 2.654,
114
+ "step": 3689
115
+ },
116
+ {
117
+ "epoch": 8.0,
118
+ "learning_rate": 3.2899746871437564e-05,
119
+ "loss": 0.253,
120
+ "step": 4216
121
+ },
122
+ {
123
+ "epoch": 8.0,
124
+ "eval_accuracy": 0.8291284403669725,
125
+ "eval_loss": 1.6077648401260376,
126
+ "eval_runtime": 2.6314,
127
+ "eval_samples_per_second": 331.377,
128
+ "eval_steps_per_second": 2.66,
129
+ "step": 4216
130
+ },
131
+ {
132
+ "epoch": 9.0,
133
+ "learning_rate": 1.646546573281425e-05,
134
+ "loss": 0.234,
135
+ "step": 4743
136
+ },
137
+ {
138
+ "epoch": 9.0,
139
+ "eval_accuracy": 0.8268348623853211,
140
+ "eval_loss": 1.603592038154602,
141
+ "eval_runtime": 2.6242,
142
+ "eval_samples_per_second": 332.289,
143
+ "eval_steps_per_second": 2.667,
144
+ "step": 4743
145
+ },
146
+ {
147
+ "epoch": 10.0,
148
+ "learning_rate": 3.1184594190936076e-08,
149
+ "loss": 0.2202,
150
+ "step": 5270
151
+ },
152
+ {
153
+ "epoch": 10.0,
154
+ "eval_accuracy": 0.823394495412844,
155
+ "eval_loss": 1.6026126146316528,
156
+ "eval_runtime": 2.6421,
157
+ "eval_samples_per_second": 330.043,
158
+ "eval_steps_per_second": 2.649,
159
+ "step": 5270
160
+ }
161
+ ],
162
+ "logging_steps": 500,
163
+ "max_steps": 5270,
164
+ "num_train_epochs": 10,
165
+ "save_steps": 500,
166
+ "total_flos": 80852083045800.0,
167
+ "trial_name": null,
168
+ "trial_params": {
169
+ "alpha": 0.4020095097837325,
170
+ "learning_rate": 0.00016434281138623312,
171
+ "num_train_epochs": 10,
172
+ "temperature": 12
173
+ }
174
+ }
run-0/checkpoint-5270/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65178f463aeaf39a13d8ba13438e7d131c26a92476a5b5cf1d59944b12ddd026
3
+ size 4664
run-0/checkpoint-5270/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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-1/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0384a7e788e01cfc1a0a496c74d1a709c2c10fb868d0c3cb533a0156c1c397cc
3
+ size 17549312
run-1/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b7f486a0b5d377c86388bc90ba06218abdb52111e4e68210d0b66e58f9ddf6b
3
+ size 35123898
run-1/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-1/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c1b47cf9888c9e7251f721c3b2a48b4b832972a075e4accd44bfe39a9ede746
3
+ size 1064
run-1/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-1/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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-1/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.823394495412844,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/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": 0.00014946971324611056,
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
+ "logging_steps": 500,
28
+ "max_steps": 4743,
29
+ "num_train_epochs": 9,
30
+ "save_steps": 500,
31
+ "total_flos": 8117476690260.0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "alpha": 0.052937085110831505,
35
+ "learning_rate": 0.00016811355227088032,
36
+ "num_train_epochs": 9,
37
+ "temperature": 28
38
+ }
39
+ }
run-1/checkpoint-527/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-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 sha256:65178f463aeaf39a13d8ba13438e7d131c26a92476a5b5cf1d59944b12ddd026
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9778c4a9b9e0841a37887d1e9944802b8b476bac60a9e2178954f797fa2f6f75
3
  size 4664