Hugging Face's logo

xuancoblab2023
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
xuancoblab2023 commited on
Commit
59c3b50
·
verified ·
1 Parent(s): 2d9d152

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1713612136.a9446dbff3d4.7440.23 +2 -2
  2. logs/events.out.tfevents.1713612219.a9446dbff3d4.7440.24 +3 -0
  3. model.safetensors +1 -1
  4. run-21/checkpoint-1120/config.json +34 -0
  5. run-21/checkpoint-1120/model.safetensors +3 -0
  6. run-21/checkpoint-1120/optimizer.pt +3 -0
  7. run-21/checkpoint-1120/rng_state.pth +3 -0
  8. run-21/checkpoint-1120/scheduler.pt +3 -0
  9. run-21/checkpoint-1120/special_tokens_map.json +7 -0
  10. run-21/checkpoint-1120/tokenizer.json +0 -0
  11. run-21/checkpoint-1120/tokenizer_config.json +57 -0
  12. run-21/checkpoint-1120/trainer_state.json +166 -0
  13. run-21/checkpoint-1120/training_args.bin +3 -0
  14. run-21/checkpoint-1120/vocab.txt +0 -0
  15. run-21/checkpoint-800/config.json +34 -0
  16. run-21/checkpoint-800/model.safetensors +3 -0
  17. run-21/checkpoint-800/optimizer.pt +3 -0
  18. run-21/checkpoint-800/rng_state.pth +3 -0
  19. run-21/checkpoint-800/scheduler.pt +3 -0
  20. run-21/checkpoint-800/special_tokens_map.json +7 -0
  21. run-21/checkpoint-800/tokenizer.json +0 -0
  22. run-21/checkpoint-800/tokenizer_config.json +57 -0
  23. run-21/checkpoint-800/trainer_state.json +126 -0
  24. run-21/checkpoint-800/training_args.bin +3 -0
  25. run-21/checkpoint-800/vocab.txt +0 -0
  26. run-22/checkpoint-160/config.json +34 -0
  27. run-22/checkpoint-160/model.safetensors +3 -0
  28. run-22/checkpoint-160/optimizer.pt +3 -0
  29. run-22/checkpoint-160/rng_state.pth +3 -0
  30. run-22/checkpoint-160/scheduler.pt +3 -0
  31. run-22/checkpoint-160/special_tokens_map.json +7 -0
  32. run-22/checkpoint-160/tokenizer.json +0 -0
  33. run-22/checkpoint-160/tokenizer_config.json +57 -0
  34. run-22/checkpoint-160/trainer_state.json +46 -0
  35. run-22/checkpoint-160/training_args.bin +3 -0
  36. run-22/checkpoint-160/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1713612136.a9446dbff3d4.7440.23 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da1468622ce88e9c44c7dc803903d84b5e3ce49c60492463e233b3dd106c0156
3
- size 5481
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0073c9fc0a325339312f4245c7383d61ece7d9d1a8f36e40c6921ef36930df0f
3
+ size 10215
logs/events.out.tfevents.1713612219.a9446dbff3d4.7440.24 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:250c291ede785206f3cd69896d7a9bfe0dad1a6cf3f1a8bc299eac804ebaa114
3
+ size 5482
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:609b3ce5938b4f5d307c6e39b424b2063d4ce000c0e097fb91847f5019fa5cb2
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae51431d9fe3f60e7687652688dd2e8ffafcb9ba817aeb6283a2a7b0f46ccdce
3
  size 17549312
run-21/checkpoint-1120/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": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-21/checkpoint-1120/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af30deadcd615c88180f12bd56862fc4ce319a06eb383413091779ee63aa4b1c
3
+ size 17549312
run-21/checkpoint-1120/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19c8b0c115975b3079b2840bf84d17eeeb17e56c444470ddf888d2ef425e178a
3
+ size 35123898
run-21/checkpoint-1120/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dff60335fa5283437e5a2cb72f0621ff75353a3210e4a78bc955f52e428c356c
3
+ size 14308
run-21/checkpoint-1120/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b8a004f910b945f4b7fc43747e8a62e45be45fd7ee6664d12cc870fa67669ef
3
+ size 1064
run-21/checkpoint-1120/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-1120/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-21/checkpoint-1120/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-1120/trainer_state.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7662745098039215,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-800",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1120,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 1.839683175086975,
14
+ "learning_rate": 0.0004864196945990802,
15
+ "loss": 0.5129,
16
+ "step": 160
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6666666666666666,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.5049448609352112,
23
+ "eval_mcc": 0.0,
24
+ "eval_precision": 0.0,
25
+ "eval_recall": 0.0,
26
+ "eval_runtime": 1.8683,
27
+ "eval_samples_per_second": 682.449,
28
+ "eval_steps_per_second": 21.41,
29
+ "step": 160
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.1274871826171875,
34
+ "learning_rate": 0.0004053497454992336,
35
+ "loss": 0.4794,
36
+ "step": 320
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7050980392156863,
41
+ "eval_f1": 0.26848249027237353,
42
+ "eval_loss": 0.45544198155403137,
43
+ "eval_mcc": 0.2568204849073838,
44
+ "eval_precision": 0.7752808988764045,
45
+ "eval_recall": 0.1623529411764706,
46
+ "eval_runtime": 2.1369,
47
+ "eval_samples_per_second": 596.661,
48
+ "eval_steps_per_second": 18.719,
49
+ "step": 320
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.5591638088226318,
54
+ "learning_rate": 0.00032427979639938683,
55
+ "loss": 0.4627,
56
+ "step": 480
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7333333333333333,
61
+ "eval_f1": 0.470404984423676,
62
+ "eval_loss": 0.44455307722091675,
63
+ "eval_mcc": 0.34827660665065835,
64
+ "eval_precision": 0.695852534562212,
65
+ "eval_recall": 0.3552941176470588,
66
+ "eval_runtime": 1.8876,
67
+ "eval_samples_per_second": 675.477,
68
+ "eval_steps_per_second": 21.191,
69
+ "step": 480
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 0.6579329371452332,
74
+ "learning_rate": 0.0002432098472995401,
75
+ "loss": 0.4529,
76
+ "step": 640
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7239215686274509,
81
+ "eval_f1": 0.38461538461538464,
82
+ "eval_loss": 0.4378909468650818,
83
+ "eval_mcc": 0.31777730290612743,
84
+ "eval_precision": 0.7482993197278912,
85
+ "eval_recall": 0.25882352941176473,
86
+ "eval_runtime": 1.8818,
87
+ "eval_samples_per_second": 677.548,
88
+ "eval_steps_per_second": 21.256,
89
+ "step": 640
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 1.6731197834014893,
94
+ "learning_rate": 0.00016213989819969341,
95
+ "loss": 0.4444,
96
+ "step": 800
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.7662745098039215,
101
+ "eval_f1": 0.5906593406593407,
102
+ "eval_loss": 0.4348558187484741,
103
+ "eval_mcc": 0.4456117783291848,
104
+ "eval_precision": 0.7095709570957096,
105
+ "eval_recall": 0.5058823529411764,
106
+ "eval_runtime": 1.8669,
107
+ "eval_samples_per_second": 682.95,
108
+ "eval_steps_per_second": 21.426,
109
+ "step": 800
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 1.8448941707611084,
114
+ "learning_rate": 8.106994909984671e-05,
115
+ "loss": 0.4415,
116
+ "step": 960
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.7623529411764706,
121
+ "eval_f1": 0.5738396624472574,
122
+ "eval_loss": 0.4331771433353424,
123
+ "eval_mcc": 0.4334324670996623,
124
+ "eval_precision": 0.7132867132867133,
125
+ "eval_recall": 0.48,
126
+ "eval_runtime": 1.8638,
127
+ "eval_samples_per_second": 684.078,
128
+ "eval_steps_per_second": 21.461,
129
+ "step": 960
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 1.8716546297073364,
134
+ "learning_rate": 0.0,
135
+ "loss": 0.436,
136
+ "step": 1120
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.7654901960784314,
141
+ "eval_f1": 0.5672937771345876,
142
+ "eval_loss": 0.4309416115283966,
143
+ "eval_mcc": 0.4394955402199731,
144
+ "eval_precision": 0.7368421052631579,
145
+ "eval_recall": 0.4611764705882353,
146
+ "eval_runtime": 1.8706,
147
+ "eval_samples_per_second": 681.61,
148
+ "eval_steps_per_second": 21.384,
149
+ "step": 1120
150
+ }
151
+ ],
152
+ "logging_steps": 500,
153
+ "max_steps": 1120,
154
+ "num_input_tokens_seen": 0,
155
+ "num_train_epochs": 7,
156
+ "save_steps": 500,
157
+ "total_flos": 2042288065440.0,
158
+ "train_batch_size": 32,
159
+ "trial_name": null,
160
+ "trial_params": {
161
+ "alpha": 0.7976867614913634,
162
+ "learning_rate": 0.000567489643698927,
163
+ "num_train_epochs": 7,
164
+ "temperature": 7
165
+ }
166
+ }
run-21/checkpoint-1120/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5a10da45ab9beb7193e8bc6df0a14cafbfd391046ad158e32733c8d41e28621
3
+ size 5048
run-21/checkpoint-1120/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-21/checkpoint-800/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": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-21/checkpoint-800/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de8dd056692469eb3db48a8ddae7419c9930067e596f28a0a89e285d3198160b
3
+ size 17549312
run-21/checkpoint-800/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d032f7055818af670df61de9e8f8f381c5a1beaff16e83e7447cba782ec7fda8
3
+ size 35123898
run-21/checkpoint-800/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ace9fbf746198b511b010eea6f5f472699d26cf6b3b3dc0129b41ac522dca49
3
+ size 14308
run-21/checkpoint-800/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c68ba0550c463dbfd55f2de2cc02d95f96ee8b5aaea1e194b9287e19f4e94f5
3
+ size 1064
run-21/checkpoint-800/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-800/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-21/checkpoint-800/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-800/trainer_state.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7662745098039215,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-800",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 800,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 1.839683175086975,
14
+ "learning_rate": 0.0004864196945990802,
15
+ "loss": 0.5129,
16
+ "step": 160
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6666666666666666,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.5049448609352112,
23
+ "eval_mcc": 0.0,
24
+ "eval_precision": 0.0,
25
+ "eval_recall": 0.0,
26
+ "eval_runtime": 1.8683,
27
+ "eval_samples_per_second": 682.449,
28
+ "eval_steps_per_second": 21.41,
29
+ "step": 160
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.1274871826171875,
34
+ "learning_rate": 0.0004053497454992336,
35
+ "loss": 0.4794,
36
+ "step": 320
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7050980392156863,
41
+ "eval_f1": 0.26848249027237353,
42
+ "eval_loss": 0.45544198155403137,
43
+ "eval_mcc": 0.2568204849073838,
44
+ "eval_precision": 0.7752808988764045,
45
+ "eval_recall": 0.1623529411764706,
46
+ "eval_runtime": 2.1369,
47
+ "eval_samples_per_second": 596.661,
48
+ "eval_steps_per_second": 18.719,
49
+ "step": 320
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.5591638088226318,
54
+ "learning_rate": 0.00032427979639938683,
55
+ "loss": 0.4627,
56
+ "step": 480
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7333333333333333,
61
+ "eval_f1": 0.470404984423676,
62
+ "eval_loss": 0.44455307722091675,
63
+ "eval_mcc": 0.34827660665065835,
64
+ "eval_precision": 0.695852534562212,
65
+ "eval_recall": 0.3552941176470588,
66
+ "eval_runtime": 1.8876,
67
+ "eval_samples_per_second": 675.477,
68
+ "eval_steps_per_second": 21.191,
69
+ "step": 480
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 0.6579329371452332,
74
+ "learning_rate": 0.0002432098472995401,
75
+ "loss": 0.4529,
76
+ "step": 640
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7239215686274509,
81
+ "eval_f1": 0.38461538461538464,
82
+ "eval_loss": 0.4378909468650818,
83
+ "eval_mcc": 0.31777730290612743,
84
+ "eval_precision": 0.7482993197278912,
85
+ "eval_recall": 0.25882352941176473,
86
+ "eval_runtime": 1.8818,
87
+ "eval_samples_per_second": 677.548,
88
+ "eval_steps_per_second": 21.256,
89
+ "step": 640
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 1.6731197834014893,
94
+ "learning_rate": 0.00016213989819969341,
95
+ "loss": 0.4444,
96
+ "step": 800
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.7662745098039215,
101
+ "eval_f1": 0.5906593406593407,
102
+ "eval_loss": 0.4348558187484741,
103
+ "eval_mcc": 0.4456117783291848,
104
+ "eval_precision": 0.7095709570957096,
105
+ "eval_recall": 0.5058823529411764,
106
+ "eval_runtime": 1.8669,
107
+ "eval_samples_per_second": 682.95,
108
+ "eval_steps_per_second": 21.426,
109
+ "step": 800
110
+ }
111
+ ],
112
+ "logging_steps": 500,
113
+ "max_steps": 1120,
114
+ "num_input_tokens_seen": 0,
115
+ "num_train_epochs": 7,
116
+ "save_steps": 500,
117
+ "total_flos": 1458777189600.0,
118
+ "train_batch_size": 32,
119
+ "trial_name": null,
120
+ "trial_params": {
121
+ "alpha": 0.7976867614913634,
122
+ "learning_rate": 0.000567489643698927,
123
+ "num_train_epochs": 7,
124
+ "temperature": 7
125
+ }
126
+ }
run-21/checkpoint-800/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5a10da45ab9beb7193e8bc6df0a14cafbfd391046ad158e32733c8d41e28621
3
+ size 5048
run-21/checkpoint-800/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-22/checkpoint-160/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": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-22/checkpoint-160/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae51431d9fe3f60e7687652688dd2e8ffafcb9ba817aeb6283a2a7b0f46ccdce
3
+ size 17549312
run-22/checkpoint-160/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21059efa12fd5452d1641984e8c5f0e2c02ad2d2ce70fd245aba343f550f7030
3
+ size 35123898
run-22/checkpoint-160/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0792eaff268dd73c8e104b5060a487f4ef56535ad3b58888006338b8bc298137
3
+ size 14308
run-22/checkpoint-160/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e959888f6382fd85276cb490b45b912edfa7ca59fcdea440300b4cf19e2b69e3
3
+ size 1064
run-22/checkpoint-160/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-160/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-22/checkpoint-160/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-160/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6666666666666666,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-22/checkpoint-160",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 160,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 1.2584645748138428,
14
+ "learning_rate": 0.0005238544684591053,
15
+ "loss": 0.523,
16
+ "step": 160
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6666666666666666,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.5000438690185547,
23
+ "eval_mcc": 0.0,
24
+ "eval_precision": 0.0,
25
+ "eval_recall": 0.0,
26
+ "eval_runtime": 1.8508,
27
+ "eval_samples_per_second": 688.899,
28
+ "eval_steps_per_second": 21.613,
29
+ "step": 160
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 1120,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 7,
36
+ "save_steps": 500,
37
+ "total_flos": 291755437920.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.8090051353443698,
42
+ "learning_rate": 0.0006111635465356229,
43
+ "num_train_epochs": 7,
44
+ "temperature": 8
45
+ }
46
+ }
run-22/checkpoint-160/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1a8098f7251a2f71a88aa1f7db7427de9a809ac3810e9c0fad6ad2fc80cdcfa
3
+ size 5048
run-22/checkpoint-160/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:e5a10da45ab9beb7193e8bc6df0a14cafbfd391046ad158e32733c8d41e28621
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1a8098f7251a2f71a88aa1f7db7427de9a809ac3810e9c0fad6ad2fc80cdcfa
3
  size 5048