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
63cd0f7
·
verified ·
1 Parent(s): 309bc6c

Training in progress, epoch 1

Browse files
Files changed (41) hide show
  1. logs/events.out.tfevents.1711298162.8cc2eef2edb7.2942.18 +2 -2
  2. logs/events.out.tfevents.1711298299.8cc2eef2edb7.2942.19 +3 -0
  3. logs/events.out.tfevents.1711298319.8cc2eef2edb7.2942.20 +3 -0
  4. logs/events.out.tfevents.1711298338.8cc2eef2edb7.2942.21 +3 -0
  5. logs/events.out.tfevents.1711298358.8cc2eef2edb7.2942.22 +3 -0
  6. logs/events.out.tfevents.1711298377.8cc2eef2edb7.2942.23 +3 -0
  7. model.safetensors +1 -1
  8. run-18/checkpoint-1782/config.json +34 -0
  9. run-18/checkpoint-1782/model.safetensors +3 -0
  10. run-18/checkpoint-1782/optimizer.pt +3 -0
  11. run-18/checkpoint-1782/rng_state.pth +3 -0
  12. run-18/checkpoint-1782/scheduler.pt +3 -0
  13. run-18/checkpoint-1782/special_tokens_map.json +7 -0
  14. run-18/checkpoint-1782/tokenizer.json +0 -0
  15. run-18/checkpoint-1782/tokenizer_config.json +57 -0
  16. run-18/checkpoint-1782/trainer_state.json +146 -0
  17. run-18/checkpoint-1782/training_args.bin +3 -0
  18. run-18/checkpoint-1782/vocab.txt +0 -0
  19. run-18/checkpoint-2079/config.json +34 -0
  20. run-18/checkpoint-2079/model.safetensors +3 -0
  21. run-18/checkpoint-2079/optimizer.pt +3 -0
  22. run-18/checkpoint-2079/rng_state.pth +3 -0
  23. run-18/checkpoint-2079/scheduler.pt +3 -0
  24. run-18/checkpoint-2079/special_tokens_map.json +7 -0
  25. run-18/checkpoint-2079/tokenizer.json +0 -0
  26. run-18/checkpoint-2079/tokenizer_config.json +57 -0
  27. run-18/checkpoint-2079/trainer_state.json +166 -0
  28. run-18/checkpoint-2079/training_args.bin +3 -0
  29. run-18/checkpoint-2079/vocab.txt +0 -0
  30. run-23/checkpoint-297/config.json +34 -0
  31. run-23/checkpoint-297/model.safetensors +3 -0
  32. run-23/checkpoint-297/optimizer.pt +3 -0
  33. run-23/checkpoint-297/rng_state.pth +3 -0
  34. run-23/checkpoint-297/scheduler.pt +3 -0
  35. run-23/checkpoint-297/special_tokens_map.json +7 -0
  36. run-23/checkpoint-297/tokenizer.json +0 -0
  37. run-23/checkpoint-297/tokenizer_config.json +57 -0
  38. run-23/checkpoint-297/trainer_state.json +46 -0
  39. run-23/checkpoint-297/training_args.bin +3 -0
  40. run-23/checkpoint-297/vocab.txt +0 -0
  41. training_args.bin +1 -1
logs/events.out.tfevents.1711298162.8cc2eef2edb7.2942.18 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04bc6fa3dbe36826d86e8b2b0000f15af0fd6d6f82952a140da66e2bcf06968e
3
- size 6137
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70cb5beabba111bf5106404bd45bcd66db656cedfea4ed343e2ff905efab2287
3
+ size 10141
logs/events.out.tfevents.1711298299.8cc2eef2edb7.2942.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6af27dd191be1975f0b3095aea4b97acf31fede483489305114dbe51cff4a763
3
+ size 5406
logs/events.out.tfevents.1711298319.8cc2eef2edb7.2942.20 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06ab913629627de13e0dc71d81cd6060b195478b26aab3cb23ca5391e7753cd3
3
+ size 5406
logs/events.out.tfevents.1711298338.8cc2eef2edb7.2942.21 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7be6fd9969bf3c1975645f532a0e8bf4860c104243c1f432640e55b048e2a789
3
+ size 5406
logs/events.out.tfevents.1711298358.8cc2eef2edb7.2942.22 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c94d3edd0b6fcf56cf2217e0383e7c49b9ad3289f3e6d3693f9bc416ef92aec0
3
+ size 5406
logs/events.out.tfevents.1711298377.8cc2eef2edb7.2942.23 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebbbc565826ee3bbdb73a6c5ad22421a4f21feaebcbd8a6c344025ea04aa7888
3
+ size 5407
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b233a316669d1986b3815033d2948f4497b62d0c0f045eeb705c1987df77cbb6
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f01780a229ee2eabe716b8cc84e6bb9c22daa03c8cc81186440efc669053d3d
3
  size 17549312
run-18/checkpoint-1782/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": "4.39.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-18/checkpoint-1782/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:880b1f5c6115314c8e81c1c2c4a345ea5ec1c54ce7929b28ea8252f70bb3d4b3
3
+ size 17549312
run-18/checkpoint-1782/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60bcb368009e5bb1a69c56ecb5807843643a9553c27b826c6eca81afbe14f01d
3
+ size 35123898
run-18/checkpoint-1782/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a02d6fe58f222754d8b6c88c72e65619363bb5593417cc44e98640fe115ffbc
3
+ size 14308
run-18/checkpoint-1782/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c591d01eeb1804047560292ea3b4497da9902f2518ecf15aecdf38342bfcbd73
3
+ size 1064
run-18/checkpoint-1782/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-18/checkpoint-1782/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-18/checkpoint-1782/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-18/checkpoint-1782/trainer_state.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6772277227722773,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-18/checkpoint-1782",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1782,
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": 1.6970789432525635,
14
+ "learning_rate": 0.0001678982407816263,
15
+ "loss": 0.6448,
16
+ "step": 297
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5287128712871287,
21
+ "eval_f1": 0.22222222222222224,
22
+ "eval_loss": 0.6524360179901123,
23
+ "eval_mcc": 0.09039579598072835,
24
+ "eval_precision": 0.6296296296296297,
25
+ "eval_recall": 0.1349206349206349,
26
+ "eval_runtime": 0.9373,
27
+ "eval_samples_per_second": 538.78,
28
+ "eval_steps_per_second": 17.07,
29
+ "step": 297
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.302747964859009,
34
+ "learning_rate": 0.0001399152006513553,
35
+ "loss": 0.6287,
36
+ "step": 594
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.6237623762376238,
41
+ "eval_f1": 0.6415094339622641,
42
+ "eval_loss": 0.6215968132019043,
43
+ "eval_mcc": 0.24899823929472167,
44
+ "eval_precision": 0.6115107913669064,
45
+ "eval_recall": 0.6746031746031746,
46
+ "eval_runtime": 0.9284,
47
+ "eval_samples_per_second": 543.954,
48
+ "eval_steps_per_second": 17.234,
49
+ "step": 594
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.1591579914093018,
54
+ "learning_rate": 0.00011193216052108422,
55
+ "loss": 0.5976,
56
+ "step": 891
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.6574257425742575,
61
+ "eval_f1": 0.7205169628432957,
62
+ "eval_loss": 0.610277533531189,
63
+ "eval_mcc": 0.3542682585809925,
64
+ "eval_precision": 0.6076294277929155,
65
+ "eval_recall": 0.8849206349206349,
66
+ "eval_runtime": 0.9295,
67
+ "eval_samples_per_second": 543.279,
68
+ "eval_steps_per_second": 17.213,
69
+ "step": 891
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 2.0118372440338135,
74
+ "learning_rate": 8.394912039081316e-05,
75
+ "loss": 0.5713,
76
+ "step": 1188
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.6534653465346535,
81
+ "eval_f1": 0.7107438016528924,
82
+ "eval_loss": 0.6075993776321411,
83
+ "eval_mcc": 0.33543408373963995,
84
+ "eval_precision": 0.6090651558073654,
85
+ "eval_recall": 0.8531746031746031,
86
+ "eval_runtime": 0.9317,
87
+ "eval_samples_per_second": 542.017,
88
+ "eval_steps_per_second": 17.173,
89
+ "step": 1188
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 4.029730796813965,
94
+ "learning_rate": 5.596608026054211e-05,
95
+ "loss": 0.555,
96
+ "step": 1485
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.6653465346534654,
101
+ "eval_f1": 0.70298769771529,
102
+ "eval_loss": 0.585565984249115,
103
+ "eval_mcc": 0.34256466693603754,
104
+ "eval_precision": 0.6309148264984227,
105
+ "eval_recall": 0.7936507936507936,
106
+ "eval_runtime": 0.9318,
107
+ "eval_samples_per_second": 541.94,
108
+ "eval_steps_per_second": 17.17,
109
+ "step": 1485
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 3.707862138748169,
114
+ "learning_rate": 2.7983040130271054e-05,
115
+ "loss": 0.5461,
116
+ "step": 1782
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.6772277227722773,
121
+ "eval_f1": 0.7104795737122557,
122
+ "eval_loss": 0.58236163854599,
123
+ "eval_mcc": 0.3648417915119883,
124
+ "eval_precision": 0.6430868167202572,
125
+ "eval_recall": 0.7936507936507936,
126
+ "eval_runtime": 0.9341,
127
+ "eval_samples_per_second": 540.611,
128
+ "eval_steps_per_second": 17.128,
129
+ "step": 1782
130
+ }
131
+ ],
132
+ "logging_steps": 500,
133
+ "max_steps": 2079,
134
+ "num_input_tokens_seen": 0,
135
+ "num_train_epochs": 7,
136
+ "save_steps": 500,
137
+ "total_flos": 4384207595880.0,
138
+ "train_batch_size": 32,
139
+ "trial_name": null,
140
+ "trial_params": {
141
+ "alpha": 0.9135980547715112,
142
+ "learning_rate": 0.00019588128091189738,
143
+ "num_train_epochs": 7,
144
+ "temperature": 19
145
+ }
146
+ }
run-18/checkpoint-1782/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0be51b8bea9f36c48824e7746075aabaa63845e60abf2a29043e4a3f5e851715
3
+ size 4920
run-18/checkpoint-1782/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-18/checkpoint-2079/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": "4.39.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-18/checkpoint-2079/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22b6d8e3621e022870cad6402765d4dc8d64244ec863d086ca01735e5b342264
3
+ size 17549312
run-18/checkpoint-2079/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b74fd431bb94b39e2ca9ed19c092fcdc38a6ae20c13127b3f7ef79314d8367f4
3
+ size 35123898
run-18/checkpoint-2079/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cb1e97db59d008285d4798ce62e5afec1cdcb1f6d8dc6abd815daafb111f5ec
3
+ size 14308
run-18/checkpoint-2079/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d46cc236a35f916a9bca12c1fb4dd2d840a851dc24d03210717615cfffa25a3
3
+ size 1064
run-18/checkpoint-2079/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-18/checkpoint-2079/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-18/checkpoint-2079/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-18/checkpoint-2079/trainer_state.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6831683168316832,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-18/checkpoint-2079",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2079,
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": 1.6970789432525635,
14
+ "learning_rate": 0.0001678982407816263,
15
+ "loss": 0.6448,
16
+ "step": 297
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5287128712871287,
21
+ "eval_f1": 0.22222222222222224,
22
+ "eval_loss": 0.6524360179901123,
23
+ "eval_mcc": 0.09039579598072835,
24
+ "eval_precision": 0.6296296296296297,
25
+ "eval_recall": 0.1349206349206349,
26
+ "eval_runtime": 0.9373,
27
+ "eval_samples_per_second": 538.78,
28
+ "eval_steps_per_second": 17.07,
29
+ "step": 297
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.302747964859009,
34
+ "learning_rate": 0.0001399152006513553,
35
+ "loss": 0.6287,
36
+ "step": 594
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.6237623762376238,
41
+ "eval_f1": 0.6415094339622641,
42
+ "eval_loss": 0.6215968132019043,
43
+ "eval_mcc": 0.24899823929472167,
44
+ "eval_precision": 0.6115107913669064,
45
+ "eval_recall": 0.6746031746031746,
46
+ "eval_runtime": 0.9284,
47
+ "eval_samples_per_second": 543.954,
48
+ "eval_steps_per_second": 17.234,
49
+ "step": 594
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.1591579914093018,
54
+ "learning_rate": 0.00011193216052108422,
55
+ "loss": 0.5976,
56
+ "step": 891
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.6574257425742575,
61
+ "eval_f1": 0.7205169628432957,
62
+ "eval_loss": 0.610277533531189,
63
+ "eval_mcc": 0.3542682585809925,
64
+ "eval_precision": 0.6076294277929155,
65
+ "eval_recall": 0.8849206349206349,
66
+ "eval_runtime": 0.9295,
67
+ "eval_samples_per_second": 543.279,
68
+ "eval_steps_per_second": 17.213,
69
+ "step": 891
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 2.0118372440338135,
74
+ "learning_rate": 8.394912039081316e-05,
75
+ "loss": 0.5713,
76
+ "step": 1188
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.6534653465346535,
81
+ "eval_f1": 0.7107438016528924,
82
+ "eval_loss": 0.6075993776321411,
83
+ "eval_mcc": 0.33543408373963995,
84
+ "eval_precision": 0.6090651558073654,
85
+ "eval_recall": 0.8531746031746031,
86
+ "eval_runtime": 0.9317,
87
+ "eval_samples_per_second": 542.017,
88
+ "eval_steps_per_second": 17.173,
89
+ "step": 1188
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 4.029730796813965,
94
+ "learning_rate": 5.596608026054211e-05,
95
+ "loss": 0.555,
96
+ "step": 1485
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.6653465346534654,
101
+ "eval_f1": 0.70298769771529,
102
+ "eval_loss": 0.585565984249115,
103
+ "eval_mcc": 0.34256466693603754,
104
+ "eval_precision": 0.6309148264984227,
105
+ "eval_recall": 0.7936507936507936,
106
+ "eval_runtime": 0.9318,
107
+ "eval_samples_per_second": 541.94,
108
+ "eval_steps_per_second": 17.17,
109
+ "step": 1485
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 3.707862138748169,
114
+ "learning_rate": 2.7983040130271054e-05,
115
+ "loss": 0.5461,
116
+ "step": 1782
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.6772277227722773,
121
+ "eval_f1": 0.7104795737122557,
122
+ "eval_loss": 0.58236163854599,
123
+ "eval_mcc": 0.3648417915119883,
124
+ "eval_precision": 0.6430868167202572,
125
+ "eval_recall": 0.7936507936507936,
126
+ "eval_runtime": 0.9341,
127
+ "eval_samples_per_second": 540.611,
128
+ "eval_steps_per_second": 17.128,
129
+ "step": 1782
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 3.284318447113037,
134
+ "learning_rate": 0.0,
135
+ "loss": 0.5394,
136
+ "step": 2079
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.6831683168316832,
141
+ "eval_f1": 0.7132616487455198,
142
+ "eval_loss": 0.5821448564529419,
143
+ "eval_mcc": 0.37527743125375096,
144
+ "eval_precision": 0.6503267973856209,
145
+ "eval_recall": 0.7896825396825397,
146
+ "eval_runtime": 0.9426,
147
+ "eval_samples_per_second": 535.728,
148
+ "eval_steps_per_second": 16.974,
149
+ "step": 2079
150
+ }
151
+ ],
152
+ "logging_steps": 500,
153
+ "max_steps": 2079,
154
+ "num_input_tokens_seen": 0,
155
+ "num_train_epochs": 7,
156
+ "save_steps": 500,
157
+ "total_flos": 5114908861860.0,
158
+ "train_batch_size": 32,
159
+ "trial_name": null,
160
+ "trial_params": {
161
+ "alpha": 0.9135980547715112,
162
+ "learning_rate": 0.00019588128091189738,
163
+ "num_train_epochs": 7,
164
+ "temperature": 19
165
+ }
166
+ }
run-18/checkpoint-2079/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0be51b8bea9f36c48824e7746075aabaa63845e60abf2a29043e4a3f5e851715
3
+ size 4920
run-18/checkpoint-2079/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-23/checkpoint-297/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": "4.39.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-23/checkpoint-297/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f01780a229ee2eabe716b8cc84e6bb9c22daa03c8cc81186440efc669053d3d
3
+ size 17549312
run-23/checkpoint-297/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0ad3f9bc73770598f1860b730360cd4135c6a451ffe5dfe43d93bc1c927c194
3
+ size 35123898
run-23/checkpoint-297/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f5e396c574b9b2ecc40d3f9e87d628a8f4be69caef81905a47fcf8895067e6
3
+ size 14308
run-23/checkpoint-297/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fce6adcadf307a95e6354ae13cd19de791f29563bca84e5a440fcb1e9d98ebd
3
+ size 1064
run-23/checkpoint-297/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-23/checkpoint-297/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-23/checkpoint-297/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-23/checkpoint-297/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5900990099009901,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-23/checkpoint-297",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 297,
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": 1.666294813156128,
14
+ "learning_rate": 0.00034226276676608983,
15
+ "loss": 0.688,
16
+ "step": 297
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5900990099009901,
21
+ "eval_f1": 0.5389755011135857,
22
+ "eval_loss": 0.6901505589485168,
23
+ "eval_mcc": 0.18426952240167496,
24
+ "eval_precision": 0.6142131979695431,
25
+ "eval_recall": 0.4801587301587302,
26
+ "eval_runtime": 0.9313,
27
+ "eval_samples_per_second": 542.229,
28
+ "eval_steps_per_second": 17.18,
29
+ "step": 297
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 2376,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 8,
36
+ "save_steps": 500,
37
+ "total_flos": 730701265980.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.9955244977733414,
42
+ "learning_rate": 0.00039115744773267407,
43
+ "num_train_epochs": 8,
44
+ "temperature": 44
45
+ }
46
+ }
run-23/checkpoint-297/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ca7c7c08b7a76c03d0e0693b58755b1f2d1740559f1524ae92203199ea260ef
3
+ size 4920
run-23/checkpoint-297/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 sha256:0be51b8bea9f36c48824e7746075aabaa63845e60abf2a29043e4a3f5e851715
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ca7c7c08b7a76c03d0e0693b58755b1f2d1740559f1524ae92203199ea260ef
3
  size 4920