Hugging Face's logo

DuongTrongChi
/
tiny-bert-sst2-distilled

TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
DuongTrongChi commited on
Commit
8cfa748
·
verified ·
1 Parent(s): fb06dea

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1723124675.621b935b3e3f.593.1 +2 -2
  2. logs/events.out.tfevents.1723126015.621b935b3e3f.593.2 +3 -0
  3. model.safetensors +1 -1
  4. run-0/checkpoint-3162/config.json +34 -0
  5. run-0/checkpoint-3162/model.safetensors +3 -0
  6. run-0/checkpoint-3162/optimizer.pt +3 -0
  7. run-0/checkpoint-3162/rng_state.pth +3 -0
  8. run-0/checkpoint-3162/scheduler.pt +3 -0
  9. run-0/checkpoint-3162/special_tokens_map.json +7 -0
  10. run-0/checkpoint-3162/tokenizer.json +0 -0
  11. run-0/checkpoint-3162/tokenizer_config.json +57 -0
  12. run-0/checkpoint-3162/trainer_state.json +134 -0
  13. run-0/checkpoint-3162/training_args.bin +3 -0
  14. run-0/checkpoint-3162/vocab.txt +0 -0
  15. run-0/checkpoint-3689/config.json +34 -0
  16. run-0/checkpoint-3689/model.safetensors +3 -0
  17. run-0/checkpoint-3689/optimizer.pt +3 -0
  18. run-0/checkpoint-3689/rng_state.pth +3 -0
  19. run-0/checkpoint-3689/scheduler.pt +3 -0
  20. run-0/checkpoint-3689/special_tokens_map.json +7 -0
  21. run-0/checkpoint-3689/tokenizer.json +0 -0
  22. run-0/checkpoint-3689/tokenizer_config.json +57 -0
  23. run-0/checkpoint-3689/trainer_state.json +150 -0
  24. run-0/checkpoint-3689/training_args.bin +3 -0
  25. run-0/checkpoint-3689/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 +54 -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.1723124675.621b935b3e3f.593.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:670a4595c9dc6c1969076957abc32c1f3d965a479ee9c57fc800b3ed675abc80
3
- size 5985
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8096bab86a0b24df9a40172a64f561519bd434e0dde8647a6345c21a91c21041
3
+ size 9009
logs/events.out.tfevents.1723126015.621b935b3e3f.593.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e07578c1e86041521a352d05768e8afe39c5458dbc279608ddd5c274d3e2b89
3
+ size 5451
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9eaa527061ffcbbb3ed9ef481b0e44de3ebf4f763a775b7d567c63df7064ebe
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dea88b2517faac1f4711ba1c629d6bd7f6778460e0bf0733e97fb476836f23f
3
  size 17549312
run-0/checkpoint-3162/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": "4.42.4",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-0/checkpoint-3162/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a1c3fc64e736de2e4a891307f4ebcebdc381f97bb11d490283c3f0f99c06ae6
3
+ size 17549312
run-0/checkpoint-3162/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2dcaf6704c310ffa736f832cef5f99b6b312da5edd7f08c930e03f4275309a8
3
+ size 35123898
run-0/checkpoint-3162/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:522b7aebc7f2d792dff3c51eedb9bc3afba88519f25125b03cb3295366cd0853
3
+ size 14308
run-0/checkpoint-3162/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7208789cde7b2feb78bfb3702bdd9fb4dc386769214e546938f457727fcb0b3
3
+ size 1064
run-0/checkpoint-3162/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-3162/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-3162/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-3162/trainer_state.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8256880733944955,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-3162",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3162,
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": 4.095917701721191,
14
+ "learning_rate": 0.0006378820903022044,
15
+ "loss": 1.3367,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8245412844036697,
21
+ "eval_loss": 1.8473267555236816,
22
+ "eval_runtime": 2.651,
23
+ "eval_samples_per_second": 328.932,
24
+ "eval_steps_per_second": 2.641,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 5.007329940795898,
30
+ "learning_rate": 0.0005315684085851703,
31
+ "loss": 0.5859,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.8130733944954128,
37
+ "eval_loss": 1.815151333808899,
38
+ "eval_runtime": 2.5701,
39
+ "eval_samples_per_second": 339.281,
40
+ "eval_steps_per_second": 2.724,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 5.04394006729126,
46
+ "learning_rate": 0.00042525472686813623,
47
+ "loss": 0.379,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8142201834862385,
53
+ "eval_loss": 1.8933576345443726,
54
+ "eval_runtime": 2.5998,
55
+ "eval_samples_per_second": 335.415,
56
+ "eval_steps_per_second": 2.693,
57
+ "step": 1581
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 11.948037147521973,
62
+ "learning_rate": 0.0003189410451511022,
63
+ "loss": 0.2807,
64
+ "step": 2108
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.8130733944954128,
69
+ "eval_loss": 1.9181652069091797,
70
+ "eval_runtime": 2.6566,
71
+ "eval_samples_per_second": 328.243,
72
+ "eval_steps_per_second": 2.635,
73
+ "step": 2108
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 6.663651466369629,
78
+ "learning_rate": 0.0002128290971754667,
79
+ "loss": 0.2134,
80
+ "step": 2635
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_accuracy": 0.8119266055045872,
85
+ "eval_loss": 1.9277732372283936,
86
+ "eval_runtime": 2.6204,
87
+ "eval_samples_per_second": 332.778,
88
+ "eval_steps_per_second": 2.671,
89
+ "step": 2635
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "grad_norm": 2.037877082824707,
94
+ "learning_rate": 0.00010651541545843262,
95
+ "loss": 0.1741,
96
+ "step": 3162
97
+ },
98
+ {
99
+ "epoch": 6.0,
100
+ "eval_accuracy": 0.8256880733944955,
101
+ "eval_loss": 1.8173047304153442,
102
+ "eval_runtime": 2.6704,
103
+ "eval_samples_per_second": 326.541,
104
+ "eval_steps_per_second": 2.621,
105
+ "step": 3162
106
+ }
107
+ ],
108
+ "logging_steps": 500,
109
+ "max_steps": 3689,
110
+ "num_input_tokens_seen": 0,
111
+ "num_train_epochs": 7,
112
+ "save_steps": 500,
113
+ "stateful_callbacks": {
114
+ "TrainerControl": {
115
+ "args": {
116
+ "should_epoch_stop": false,
117
+ "should_evaluate": false,
118
+ "should_log": false,
119
+ "should_save": true,
120
+ "should_training_stop": false
121
+ },
122
+ "attributes": {}
123
+ }
124
+ },
125
+ "total_flos": 48527917525620.0,
126
+ "train_batch_size": 128,
127
+ "trial_name": null,
128
+ "trial_params": {
129
+ "alpha": 0.2549821714207776,
130
+ "learning_rate": 0.0007441957720192385,
131
+ "num_train_epochs": 7,
132
+ "temperature": 19
133
+ }
134
+ }
run-0/checkpoint-3162/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f6cfd8184ff3b8efaf3dfce012fe436aa85c2d1cd095c8e7f46a76b735b8f47
3
+ size 5176
run-0/checkpoint-3162/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-3689/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": "4.42.4",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-0/checkpoint-3689/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:864bae468ee6347d7f86e3de22347af9b827219b03728892d2cb403eb34656fd
3
+ size 17549312
run-0/checkpoint-3689/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74477d24bb2f0d59afc7df590a7b0e98cab3caf3ec057a3cce8e4c367780c8d6
3
+ size 35123898
run-0/checkpoint-3689/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e550a7bb338b84ab374b4609347d77ec664e40f8a6b6837a56e299227ab3fcb7
3
+ size 14308
run-0/checkpoint-3689/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1896406292054e1d527cd4185180426cba9039fddefdb71224ca431ab8d6aad1
3
+ size 1064
run-0/checkpoint-3689/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-3689/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-3689/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-3689/trainer_state.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8256880733944955,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-3162",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3689,
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": 4.095917701721191,
14
+ "learning_rate": 0.0006378820903022044,
15
+ "loss": 1.3367,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8245412844036697,
21
+ "eval_loss": 1.8473267555236816,
22
+ "eval_runtime": 2.651,
23
+ "eval_samples_per_second": 328.932,
24
+ "eval_steps_per_second": 2.641,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 5.007329940795898,
30
+ "learning_rate": 0.0005315684085851703,
31
+ "loss": 0.5859,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.8130733944954128,
37
+ "eval_loss": 1.815151333808899,
38
+ "eval_runtime": 2.5701,
39
+ "eval_samples_per_second": 339.281,
40
+ "eval_steps_per_second": 2.724,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 5.04394006729126,
46
+ "learning_rate": 0.00042525472686813623,
47
+ "loss": 0.379,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8142201834862385,
53
+ "eval_loss": 1.8933576345443726,
54
+ "eval_runtime": 2.5998,
55
+ "eval_samples_per_second": 335.415,
56
+ "eval_steps_per_second": 2.693,
57
+ "step": 1581
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 11.948037147521973,
62
+ "learning_rate": 0.0003189410451511022,
63
+ "loss": 0.2807,
64
+ "step": 2108
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.8130733944954128,
69
+ "eval_loss": 1.9181652069091797,
70
+ "eval_runtime": 2.6566,
71
+ "eval_samples_per_second": 328.243,
72
+ "eval_steps_per_second": 2.635,
73
+ "step": 2108
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 6.663651466369629,
78
+ "learning_rate": 0.0002128290971754667,
79
+ "loss": 0.2134,
80
+ "step": 2635
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_accuracy": 0.8119266055045872,
85
+ "eval_loss": 1.9277732372283936,
86
+ "eval_runtime": 2.6204,
87
+ "eval_samples_per_second": 332.778,
88
+ "eval_steps_per_second": 2.671,
89
+ "step": 2635
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "grad_norm": 2.037877082824707,
94
+ "learning_rate": 0.00010651541545843262,
95
+ "loss": 0.1741,
96
+ "step": 3162
97
+ },
98
+ {
99
+ "epoch": 6.0,
100
+ "eval_accuracy": 0.8256880733944955,
101
+ "eval_loss": 1.8173047304153442,
102
+ "eval_runtime": 2.6704,
103
+ "eval_samples_per_second": 326.541,
104
+ "eval_steps_per_second": 2.621,
105
+ "step": 3162
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "grad_norm": 2.2663307189941406,
110
+ "learning_rate": 2.017337413985466e-07,
111
+ "loss": 0.1397,
112
+ "step": 3689
113
+ },
114
+ {
115
+ "epoch": 7.0,
116
+ "eval_accuracy": 0.8222477064220184,
117
+ "eval_loss": 1.8090132474899292,
118
+ "eval_runtime": 2.6108,
119
+ "eval_samples_per_second": 333.996,
120
+ "eval_steps_per_second": 2.681,
121
+ "step": 3689
122
+ }
123
+ ],
124
+ "logging_steps": 500,
125
+ "max_steps": 3689,
126
+ "num_input_tokens_seen": 0,
127
+ "num_train_epochs": 7,
128
+ "save_steps": 500,
129
+ "stateful_callbacks": {
130
+ "TrainerControl": {
131
+ "args": {
132
+ "should_epoch_stop": false,
133
+ "should_evaluate": false,
134
+ "should_log": false,
135
+ "should_save": true,
136
+ "should_training_stop": true
137
+ },
138
+ "attributes": {}
139
+ }
140
+ },
141
+ "total_flos": 56628612372420.0,
142
+ "train_batch_size": 128,
143
+ "trial_name": null,
144
+ "trial_params": {
145
+ "alpha": 0.2549821714207776,
146
+ "learning_rate": 0.0007441957720192385,
147
+ "num_train_epochs": 7,
148
+ "temperature": 19
149
+ }
150
+ }
run-0/checkpoint-3689/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f6cfd8184ff3b8efaf3dfce012fe436aa85c2d1cd095c8e7f46a76b735b8f47
3
+ size 5176
run-0/checkpoint-3689/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": "4.42.4",
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 sha256:1dea88b2517faac1f4711ba1c629d6bd7f6778460e0bf0733e97fb476836f23f
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 sha256:8a970871838b6fdc7bd70a04e80f13bd77fe95c077bced9faa9217f1220bfdd3
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 sha256:9733f27bb728718f7284348156186daf975855376673d9de7e218a8cff476307
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:fe073bbc22ec8de4d0d4dc3c09eb684b8f1e74e599abe536c9f8c411ac28eb62
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 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "grad_norm": 23.897071838378906,
14
+ "learning_rate": 0.0003846295223553701,
15
+ "loss": 1.6014,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.823394495412844,
21
+ "eval_loss": 1.887431025505066,
22
+ "eval_runtime": 2.6123,
23
+ "eval_samples_per_second": 333.808,
24
+ "eval_steps_per_second": 2.68,
25
+ "step": 527
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 1581,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 3,
32
+ "save_steps": 500,
33
+ "stateful_callbacks": {
34
+ "TrainerControl": {
35
+ "args": {
36
+ "should_epoch_stop": false,
37
+ "should_evaluate": false,
38
+ "should_log": false,
39
+ "should_save": true,
40
+ "should_training_stop": false
41
+ },
42
+ "attributes": {}
43
+ }
44
+ },
45
+ "total_flos": 8057768762220.0,
46
+ "train_batch_size": 128,
47
+ "trial_name": null,
48
+ "trial_params": {
49
+ "alpha": 0.0036479908390928406,
50
+ "learning_rate": 0.0005763974169135925,
51
+ "num_train_epochs": 3,
52
+ "temperature": 8
53
+ }
54
+ }
run-1/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee08b4ebb17c68b776cbd9351f0069da6b90a4711e2c695fadba226d1539ce66
3
+ size 5176
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 sha256:3f6cfd8184ff3b8efaf3dfce012fe436aa85c2d1cd095c8e7f46a76b735b8f47
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee08b4ebb17c68b776cbd9351f0069da6b90a4711e2c695fadba226d1539ce66
3
  size 5176