Hugging Face's logo

jysh1023
/
tiny-bert-sst2-distilled_original

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
jysh1023 commited on
Commit
8da49b7
·
1 Parent(s): 103f308

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1700282528.bdba95a6283e.570.5 +2 -2
  2. logs/events.out.tfevents.1700284300.bdba95a6283e.570.6 +3 -0
  3. model.safetensors +1 -1
  4. run-2/checkpoint-4216/config.json +34 -0
  5. run-2/checkpoint-4216/model.safetensors +3 -0
  6. run-2/checkpoint-4216/optimizer.pt +3 -0
  7. run-2/checkpoint-4216/rng_state.pth +3 -0
  8. run-2/checkpoint-4216/scheduler.pt +3 -0
  9. run-2/checkpoint-4216/special_tokens_map.json +7 -0
  10. run-2/checkpoint-4216/tokenizer.json +0 -0
  11. run-2/checkpoint-4216/tokenizer_config.json +57 -0
  12. run-2/checkpoint-4216/trainer_state.json +144 -0
  13. run-2/checkpoint-4216/training_args.bin +3 -0
  14. run-2/checkpoint-4216/vocab.txt +0 -0
  15. run-2/checkpoint-4743/config.json +34 -0
  16. run-2/checkpoint-4743/model.safetensors +3 -0
  17. run-2/checkpoint-4743/optimizer.pt +3 -0
  18. run-2/checkpoint-4743/rng_state.pth +3 -0
  19. run-2/checkpoint-4743/scheduler.pt +3 -0
  20. run-2/checkpoint-4743/special_tokens_map.json +7 -0
  21. run-2/checkpoint-4743/tokenizer.json +0 -0
  22. run-2/checkpoint-4743/tokenizer_config.json +57 -0
  23. run-2/checkpoint-4743/trainer_state.json +159 -0
  24. run-2/checkpoint-4743/training_args.bin +3 -0
  25. run-2/checkpoint-4743/vocab.txt +0 -0
  26. run-3/checkpoint-527/config.json +34 -0
  27. run-3/checkpoint-527/model.safetensors +3 -0
  28. run-3/checkpoint-527/optimizer.pt +3 -0
  29. run-3/checkpoint-527/rng_state.pth +3 -0
  30. run-3/checkpoint-527/scheduler.pt +3 -0
  31. run-3/checkpoint-527/special_tokens_map.json +7 -0
  32. run-3/checkpoint-527/tokenizer.json +0 -0
  33. run-3/checkpoint-527/tokenizer_config.json +57 -0
  34. run-3/checkpoint-527/trainer_state.json +39 -0
  35. run-3/checkpoint-527/training_args.bin +3 -0
  36. run-3/checkpoint-527/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1700282528.bdba95a6283e.570.5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6fe4c4097f8e6f73131e4da901997e51a77bc967a4b73af6cb09758fb57bac6
3
- size 5289
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a047329a624f2ab75fb2e36488b806e01c6a63c90633f10fd0785e178ac6d27b
3
+ size 9003
logs/events.out.tfevents.1700284300.bdba95a6283e.570.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ab7a1c81614d3f2a9c26261dd20dc889145308adf06620b3f9953d3c5e5ed68
3
+ size 4809
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f12bdd95ed0bac7d9f9938b7d13dd201c9413ef634c33f5026259d6184662f20
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd4179ffda3d0d979a96ef2f1ec97eb5b11debae9610d1ee38c1e4eb18502b1a
3
  size 17549312
run-2/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-2/checkpoint-4216/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2a82ef7da6224840fe4e4f173608915620b1116e2ef5a4fcd38f976c739f66f
3
+ size 17549312
run-2/checkpoint-4216/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ccbad440944092e79ad17072c64d562cbab968d4f42ec61f01c45dd2c849298
3
+ size 35123898
run-2/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-2/checkpoint-4216/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7896d30db304dfc17cd7bce03b643dfac978231fb254393e1b59b0d5839cc1b3
3
+ size 1064
run-2/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-2/checkpoint-4216/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-4216/trainer_state.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8038990825688074,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled_original/run-2/checkpoint-3689",
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": 1.7859230398937433e-05,
14
+ "loss": 3.7946,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.7626146788990825,
20
+ "eval_loss": 2.703794479370117,
21
+ "eval_runtime": 2.6906,
22
+ "eval_samples_per_second": 324.093,
23
+ "eval_steps_per_second": 2.602,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 1.562735598104793e-05,
29
+ "loss": 2.4437,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.783256880733945,
35
+ "eval_loss": 2.1900758743286133,
36
+ "eval_runtime": 2.727,
37
+ "eval_samples_per_second": 319.764,
38
+ "eval_steps_per_second": 2.567,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 1.3395481563158429e-05,
44
+ "loss": 1.9346,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.7947247706422018,
50
+ "eval_loss": 2.0303852558135986,
51
+ "eval_runtime": 2.6751,
52
+ "eval_samples_per_second": 325.965,
53
+ "eval_steps_per_second": 2.617,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 1.1163607145268927e-05,
59
+ "loss": 1.6702,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.7970183486238532,
65
+ "eval_loss": 1.899391531944275,
66
+ "eval_runtime": 2.7138,
67
+ "eval_samples_per_second": 321.32,
68
+ "eval_steps_per_second": 2.579,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 8.93596778320085e-06,
74
+ "loss": 1.4962,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.7970183486238532,
80
+ "eval_loss": 1.8389862775802612,
81
+ "eval_runtime": 2.6971,
82
+ "eval_samples_per_second": 323.307,
83
+ "eval_steps_per_second": 2.595,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 6.7040933653113484e-06,
89
+ "loss": 1.3923,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.7981651376146789,
95
+ "eval_loss": 1.7970421314239502,
96
+ "eval_runtime": 2.7446,
97
+ "eval_samples_per_second": 317.712,
98
+ "eval_steps_per_second": 2.55,
99
+ "step": 3162
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "learning_rate": 4.472218947421847e-06,
104
+ "loss": 1.3181,
105
+ "step": 3689
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "eval_accuracy": 0.8038990825688074,
110
+ "eval_loss": 1.7871743440628052,
111
+ "eval_runtime": 2.6838,
112
+ "eval_samples_per_second": 324.909,
113
+ "eval_steps_per_second": 2.608,
114
+ "step": 3689
115
+ },
116
+ {
117
+ "epoch": 8.0,
118
+ "learning_rate": 2.240344529532346e-06,
119
+ "loss": 1.2822,
120
+ "step": 4216
121
+ },
122
+ {
123
+ "epoch": 8.0,
124
+ "eval_accuracy": 0.8038990825688074,
125
+ "eval_loss": 1.769896388053894,
126
+ "eval_runtime": 2.7534,
127
+ "eval_samples_per_second": 316.705,
128
+ "eval_steps_per_second": 2.542,
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": 0.15431079596404795,
140
+ "learning_rate": 2.008686976100551e-05,
141
+ "num_train_epochs": 9,
142
+ "temperature": 26
143
+ }
144
+ }
run-2/checkpoint-4216/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35fef526ef3e659c6023033ec75dbddda78d254aee60cff3f8cb777637c56032
3
+ size 4664
run-2/checkpoint-4216/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-4743/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:865fe2ca4ef425bff25c38a2f21cb5a47c52ce98f200f1848e8fc9faf65b884e
3
+ size 17549312
run-2/checkpoint-4743/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7496bd463eb0bd587324793b356e0a8e37fb5bcff9e4483c18484fb4321049e6
3
+ size 35123898
run-2/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-2/checkpoint-4743/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bb8cb3bb969c6a3ee90618d44880a8715af90e1dbff3c4712a9735f9317842e
3
+ size 1064
run-2/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-2/checkpoint-4743/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-4743/trainer_state.json ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.805045871559633,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled_original/run-2/checkpoint-4743",
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": 1.7859230398937433e-05,
14
+ "loss": 3.7946,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.7626146788990825,
20
+ "eval_loss": 2.703794479370117,
21
+ "eval_runtime": 2.6906,
22
+ "eval_samples_per_second": 324.093,
23
+ "eval_steps_per_second": 2.602,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 1.562735598104793e-05,
29
+ "loss": 2.4437,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.783256880733945,
35
+ "eval_loss": 2.1900758743286133,
36
+ "eval_runtime": 2.727,
37
+ "eval_samples_per_second": 319.764,
38
+ "eval_steps_per_second": 2.567,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 1.3395481563158429e-05,
44
+ "loss": 1.9346,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.7947247706422018,
50
+ "eval_loss": 2.0303852558135986,
51
+ "eval_runtime": 2.6751,
52
+ "eval_samples_per_second": 325.965,
53
+ "eval_steps_per_second": 2.617,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 1.1163607145268927e-05,
59
+ "loss": 1.6702,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.7970183486238532,
65
+ "eval_loss": 1.899391531944275,
66
+ "eval_runtime": 2.7138,
67
+ "eval_samples_per_second": 321.32,
68
+ "eval_steps_per_second": 2.579,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 8.93596778320085e-06,
74
+ "loss": 1.4962,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.7970183486238532,
80
+ "eval_loss": 1.8389862775802612,
81
+ "eval_runtime": 2.6971,
82
+ "eval_samples_per_second": 323.307,
83
+ "eval_steps_per_second": 2.595,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 6.7040933653113484e-06,
89
+ "loss": 1.3923,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.7981651376146789,
95
+ "eval_loss": 1.7970421314239502,
96
+ "eval_runtime": 2.7446,
97
+ "eval_samples_per_second": 317.712,
98
+ "eval_steps_per_second": 2.55,
99
+ "step": 3162
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "learning_rate": 4.472218947421847e-06,
104
+ "loss": 1.3181,
105
+ "step": 3689
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "eval_accuracy": 0.8038990825688074,
110
+ "eval_loss": 1.7871743440628052,
111
+ "eval_runtime": 2.6838,
112
+ "eval_samples_per_second": 324.909,
113
+ "eval_steps_per_second": 2.608,
114
+ "step": 3689
115
+ },
116
+ {
117
+ "epoch": 8.0,
118
+ "learning_rate": 2.240344529532346e-06,
119
+ "loss": 1.2822,
120
+ "step": 4216
121
+ },
122
+ {
123
+ "epoch": 8.0,
124
+ "eval_accuracy": 0.8038990825688074,
125
+ "eval_loss": 1.769896388053894,
126
+ "eval_runtime": 2.7534,
127
+ "eval_samples_per_second": 316.705,
128
+ "eval_steps_per_second": 2.542,
129
+ "step": 4216
130
+ },
131
+ {
132
+ "epoch": 9.0,
133
+ "learning_rate": 8.470111642844407e-09,
134
+ "loss": 1.2654,
135
+ "step": 4743
136
+ },
137
+ {
138
+ "epoch": 9.0,
139
+ "eval_accuracy": 0.805045871559633,
140
+ "eval_loss": 1.7723108530044556,
141
+ "eval_runtime": 2.682,
142
+ "eval_samples_per_second": 325.131,
143
+ "eval_steps_per_second": 2.61,
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": 0.15431079596404795,
155
+ "learning_rate": 2.008686976100551e-05,
156
+ "num_train_epochs": 9,
157
+ "temperature": 26
158
+ }
159
+ }
run-2/checkpoint-4743/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35fef526ef3e659c6023033ec75dbddda78d254aee60cff3f8cb777637c56032
3
+ size 4664
run-2/checkpoint-4743/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd4179ffda3d0d979a96ef2f1ec97eb5b11debae9610d1ee38c1e4eb18502b1a
3
+ size 17549312
run-3/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6490fb627c367b480f3da1db6af0af09fe10768ac7337f8a071eb7517f1a8b72
3
+ size 35123898
run-3/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-3/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd3d382c717a8e5af0d4cb78a98155f40a7f71ef8550fc321c1aaa7bec957ee0
3
+ size 1064
run-3/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-3/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.805045871559633,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled_original/run-3/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": 0.00041526386683348685,
14
+ "loss": 0.4613,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.805045871559633,
20
+ "eval_loss": 0.6051546335220337,
21
+ "eval_runtime": 2.7198,
22
+ "eval_samples_per_second": 320.613,
23
+ "eval_steps_per_second": 2.574,
24
+ "step": 527
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 2635,
29
+ "num_train_epochs": 5,
30
+ "save_steps": 500,
31
+ "total_flos": 8117476690260.0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "alpha": 0.9238940809632088,
35
+ "learning_rate": 0.0005190798335418586,
36
+ "num_train_epochs": 5,
37
+ "temperature": 22
38
+ }
39
+ }
run-3/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7347a6a4d2a64a7d635c666aa8a0b2a3bdfe634a3e64aa55460c04f9d49a1f45
3
+ size 4664
run-3/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 sha256:35fef526ef3e659c6023033ec75dbddda78d254aee60cff3f8cb777637c56032
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7347a6a4d2a64a7d635c666aa8a0b2a3bdfe634a3e64aa55460c04f9d49a1f45
3
  size 4664