Hugging Face's logo

Slava
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
Slava commited on
Commit
69cd240
·
verified ·
1 Parent(s): 58de099

Training in progress, epoch 1

Browse files
Files changed (38) hide show
  1. logs/events.out.tfevents.1706196200.A-FVFFG2C4Q05P.18450.5 +2 -2
  2. logs/events.out.tfevents.1706201443.A-FVFFG2C4Q05P.18450.6 +3 -0
  3. logs/events.out.tfevents.1706202000.A-FVFFG2C4Q05P.18450.7 +3 -0
  4. model.safetensors +1 -1
  5. run-4/checkpoint-3689/config.json +34 -0
  6. run-4/checkpoint-3689/model.safetensors +3 -0
  7. run-4/checkpoint-3689/optimizer.pt +3 -0
  8. run-4/checkpoint-3689/rng_state.pth +3 -0
  9. run-4/checkpoint-3689/scheduler.pt +3 -0
  10. run-4/checkpoint-3689/special_tokens_map.json +7 -0
  11. run-4/checkpoint-3689/tokenizer.json +0 -0
  12. run-4/checkpoint-3689/tokenizer_config.json +57 -0
  13. run-4/checkpoint-3689/trainer_state.json +131 -0
  14. run-4/checkpoint-3689/training_args.bin +3 -0
  15. run-4/checkpoint-3689/vocab.txt +0 -0
  16. run-4/checkpoint-4743/config.json +34 -0
  17. run-4/checkpoint-4743/model.safetensors +3 -0
  18. run-4/checkpoint-4743/optimizer.pt +3 -0
  19. run-4/checkpoint-4743/rng_state.pth +3 -0
  20. run-4/checkpoint-4743/scheduler.pt +3 -0
  21. run-4/checkpoint-4743/special_tokens_map.json +7 -0
  22. run-4/checkpoint-4743/tokenizer.json +0 -0
  23. run-4/checkpoint-4743/tokenizer_config.json +57 -0
  24. run-4/checkpoint-4743/trainer_state.json +161 -0
  25. run-4/checkpoint-4743/training_args.bin +3 -0
  26. run-4/checkpoint-4743/vocab.txt +0 -0
  27. run-6/checkpoint-527/config.json +34 -0
  28. run-6/checkpoint-527/model.safetensors +3 -0
  29. run-6/checkpoint-527/optimizer.pt +3 -0
  30. run-6/checkpoint-527/rng_state.pth +3 -0
  31. run-6/checkpoint-527/scheduler.pt +3 -0
  32. run-6/checkpoint-527/special_tokens_map.json +7 -0
  33. run-6/checkpoint-527/tokenizer.json +0 -0
  34. run-6/checkpoint-527/tokenizer_config.json +57 -0
  35. run-6/checkpoint-527/trainer_state.json +41 -0
  36. run-6/checkpoint-527/training_args.bin +3 -0
  37. run-6/checkpoint-527/vocab.txt +0 -0
  38. training_args.bin +1 -1
logs/events.out.tfevents.1706196200.A-FVFFG2C4Q05P.18450.5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00996ac2e26a9ba61d96ffe89b5b8299ebe0f1aae0cd9f3c9859ad31c1005f5e
3
- size 5395
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2150ffc03dbf4295a48bc6fd64640bd58eae624cc8646d0f3835b003cd2d328f
3
+ size 9109
logs/events.out.tfevents.1706201443.A-FVFFG2C4Q05P.18450.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c529fa8a1808bccf7a2337247d8bcaf8fa6e1698aebfe7308bcde00932d9376
3
+ size 4916
logs/events.out.tfevents.1706202000.A-FVFFG2C4Q05P.18450.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d390bf222c5be4a67445955d310953167bb0e9f04db3b85b132e93854825ea39
3
+ size 4916
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20c6f535ff7be2c32349e826fe4e9a8cc287c32c8820afae128deea5181c2150
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5debd9170913b2c53818bce2c3725974be7877da5f24d081bb2eed873630741
3
  size 17549312
run-4/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": "4.37.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-4/checkpoint-3689/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d00187027f9775c06483d1601ef24a7ba4fa21419beae3d7072ed3b571650801
3
+ size 17549312
run-4/checkpoint-3689/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0a1e68985ebfc9bd6ae644b2955346603de7743acac53775cb44ef9ba7f0c73
3
+ size 35122373
run-4/checkpoint-3689/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1944a0f816099340e1dbf1a93e033a5a3a4bb0c92f096d7559d0edb8afc135de
3
+ size 13617
run-4/checkpoint-3689/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:339488adec8778fcd4fdb109a1e35cd4ac784f4f9e846f1af8fb13badd9efd9f
3
+ size 627
run-4/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-4/checkpoint-3689/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-3689/trainer_state.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8302752293577982,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/checkpoint-3689",
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
+ "learning_rate": 8.185589369281136e-05,
14
+ "loss": 1.3236,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8130733944954128,
20
+ "eval_loss": 1.107783555984497,
21
+ "eval_runtime": 7.0372,
22
+ "eval_samples_per_second": 123.913,
23
+ "eval_steps_per_second": 0.995,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 7.162390698120995e-05,
29
+ "loss": 0.686,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8256880733944955,
35
+ "eval_loss": 1.0679908990859985,
36
+ "eval_runtime": 6.9855,
37
+ "eval_samples_per_second": 124.83,
38
+ "eval_steps_per_second": 1.002,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 6.139192026960852e-05,
44
+ "loss": 0.5273,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8211009174311926,
50
+ "eval_loss": 1.0926319360733032,
51
+ "eval_runtime": 7.0896,
52
+ "eval_samples_per_second": 122.996,
53
+ "eval_steps_per_second": 0.987,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 5.1159933558007106e-05,
59
+ "loss": 0.4436,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8279816513761468,
65
+ "eval_loss": 1.1032575368881226,
66
+ "eval_runtime": 8.0424,
67
+ "eval_samples_per_second": 108.425,
68
+ "eval_steps_per_second": 0.87,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 4.092794684640568e-05,
74
+ "loss": 0.3913,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8256880733944955,
80
+ "eval_loss": 1.157786250114441,
81
+ "eval_runtime": 6.8773,
82
+ "eval_samples_per_second": 126.794,
83
+ "eval_steps_per_second": 1.018,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 3.069596013480426e-05,
89
+ "loss": 0.3573,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8222477064220184,
95
+ "eval_loss": 1.1634522676467896,
96
+ "eval_runtime": 6.8898,
97
+ "eval_samples_per_second": 126.564,
98
+ "eval_steps_per_second": 1.016,
99
+ "step": 3162
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "learning_rate": 2.046397342320284e-05,
104
+ "loss": 0.3285,
105
+ "step": 3689
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "eval_accuracy": 0.8302752293577982,
110
+ "eval_loss": 1.1784659624099731,
111
+ "eval_runtime": 6.6314,
112
+ "eval_samples_per_second": 131.496,
113
+ "eval_steps_per_second": 1.056,
114
+ "step": 3689
115
+ }
116
+ ],
117
+ "logging_steps": 500,
118
+ "max_steps": 4743,
119
+ "num_input_tokens_seen": 0,
120
+ "num_train_epochs": 9,
121
+ "save_steps": 500,
122
+ "total_flos": 56642674579560.0,
123
+ "train_batch_size": 128,
124
+ "trial_name": null,
125
+ "trial_params": {
126
+ "alpha": 0.6484108691726712,
127
+ "learning_rate": 9.208788040441279e-05,
128
+ "num_train_epochs": 9,
129
+ "temperature": 16
130
+ }
131
+ }
run-4/checkpoint-3689/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a802a6ef5b6f7d1deb28aafada439e905b1de2242376315c4a5c34f1077a137d
3
+ size 4283
run-4/checkpoint-3689/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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": "4.37.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-4/checkpoint-4743/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33468de4fe9616aa87ba250d43e49969f4ce367e1a4e9aa9af37b945d7437a8f
3
+ size 17549312
run-4/checkpoint-4743/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e8ff402cb0df65d2d2219a417517dd20acfb4ae2e23daf11a8ea19d582a8641
3
+ size 35122373
run-4/checkpoint-4743/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e213b9ff178552aa357195f6c9b9ab9b2dd2939ab6f17cc6cea934aabceeb6f8
3
+ size 13617
run-4/checkpoint-4743/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80609a8e9ea53068973038ef471fe018599ae393b4bab29625ee3fffa5d5a6ea
3
+ size 627
run-4/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-4/checkpoint-4743/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-4743/trainer_state.json ADDED
@@ -0,0 +1,161 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8302752293577982,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/checkpoint-3689",
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": 8.185589369281136e-05,
14
+ "loss": 1.3236,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8130733944954128,
20
+ "eval_loss": 1.107783555984497,
21
+ "eval_runtime": 7.0372,
22
+ "eval_samples_per_second": 123.913,
23
+ "eval_steps_per_second": 0.995,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 7.162390698120995e-05,
29
+ "loss": 0.686,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8256880733944955,
35
+ "eval_loss": 1.0679908990859985,
36
+ "eval_runtime": 6.9855,
37
+ "eval_samples_per_second": 124.83,
38
+ "eval_steps_per_second": 1.002,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 6.139192026960852e-05,
44
+ "loss": 0.5273,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8211009174311926,
50
+ "eval_loss": 1.0926319360733032,
51
+ "eval_runtime": 7.0896,
52
+ "eval_samples_per_second": 122.996,
53
+ "eval_steps_per_second": 0.987,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 5.1159933558007106e-05,
59
+ "loss": 0.4436,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8279816513761468,
65
+ "eval_loss": 1.1032575368881226,
66
+ "eval_runtime": 8.0424,
67
+ "eval_samples_per_second": 108.425,
68
+ "eval_steps_per_second": 0.87,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 4.092794684640568e-05,
74
+ "loss": 0.3913,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8256880733944955,
80
+ "eval_loss": 1.157786250114441,
81
+ "eval_runtime": 6.8773,
82
+ "eval_samples_per_second": 126.794,
83
+ "eval_steps_per_second": 1.018,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 3.069596013480426e-05,
89
+ "loss": 0.3573,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8222477064220184,
95
+ "eval_loss": 1.1634522676467896,
96
+ "eval_runtime": 6.8898,
97
+ "eval_samples_per_second": 126.564,
98
+ "eval_steps_per_second": 1.016,
99
+ "step": 3162
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "learning_rate": 2.046397342320284e-05,
104
+ "loss": 0.3285,
105
+ "step": 3689
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "eval_accuracy": 0.8302752293577982,
110
+ "eval_loss": 1.1784659624099731,
111
+ "eval_runtime": 6.6314,
112
+ "eval_samples_per_second": 131.496,
113
+ "eval_steps_per_second": 1.056,
114
+ "step": 3689
115
+ },
116
+ {
117
+ "epoch": 8.0,
118
+ "learning_rate": 1.023198671160142e-05,
119
+ "loss": 0.3132,
120
+ "step": 4216
121
+ },
122
+ {
123
+ "epoch": 8.0,
124
+ "eval_accuracy": 0.8268348623853211,
125
+ "eval_loss": 1.1929923295974731,
126
+ "eval_runtime": 6.9183,
127
+ "eval_samples_per_second": 126.043,
128
+ "eval_steps_per_second": 1.012,
129
+ "step": 4216
130
+ },
131
+ {
132
+ "epoch": 9.0,
133
+ "learning_rate": 0.0,
134
+ "loss": 0.2988,
135
+ "step": 4743
136
+ },
137
+ {
138
+ "epoch": 9.0,
139
+ "eval_accuracy": 0.823394495412844,
140
+ "eval_loss": 1.2045751810073853,
141
+ "eval_runtime": 6.575,
142
+ "eval_samples_per_second": 132.625,
143
+ "eval_steps_per_second": 1.065,
144
+ "step": 4743
145
+ }
146
+ ],
147
+ "logging_steps": 500,
148
+ "max_steps": 4743,
149
+ "num_input_tokens_seen": 0,
150
+ "num_train_epochs": 9,
151
+ "save_steps": 500,
152
+ "total_flos": 72808011721980.0,
153
+ "train_batch_size": 128,
154
+ "trial_name": null,
155
+ "trial_params": {
156
+ "alpha": 0.6484108691726712,
157
+ "learning_rate": 9.208788040441279e-05,
158
+ "num_train_epochs": 9,
159
+ "temperature": 16
160
+ }
161
+ }
run-4/checkpoint-4743/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a802a6ef5b6f7d1deb28aafada439e905b1de2242376315c4a5c34f1077a137d
3
+ size 4283
run-4/checkpoint-4743/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/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": "4.37.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-6/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5debd9170913b2c53818bce2c3725974be7877da5f24d081bb2eed873630741
3
+ size 17549312
run-6/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd920976fa42f98779e8fce4d8936de4c71d3ab136297f86898d6adcab951d0b
3
+ size 35122373
run-6/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f943a8d8f93fea7f44cad3b9bfb2d2b97d65b141eb704b9cba669cf42e776b14
3
+ size 13617
run-6/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8e3219ab2aa8c4da394f07081ac3a2364e1c06ba10f4737c74b0f9ac0565b57
3
+ size 627
run-6/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-6/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/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-6/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8222477064220184,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-6/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": 0.00047872990969994726,
14
+ "loss": 0.5581,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8222477064220184,
20
+ "eval_loss": 0.6657201051712036,
21
+ "eval_runtime": 6.9991,
22
+ "eval_samples_per_second": 124.587,
23
+ "eval_steps_per_second": 1.0,
24
+ "step": 527
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 5270,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 10,
31
+ "save_steps": 500,
32
+ "total_flos": 8069051778960.0,
33
+ "train_batch_size": 128,
34
+ "trial_name": null,
35
+ "trial_params": {
36
+ "alpha": 0.8719084426456489,
37
+ "learning_rate": 0.0005319221218888303,
38
+ "num_train_epochs": 10,
39
+ "temperature": 25
40
+ }
41
+ }
run-6/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38487dd6445b9a0ec1b811154337420fd97312579fa8d24de47f1c0ea2ebe18c
3
+ size 4283
run-6/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:a802a6ef5b6f7d1deb28aafada439e905b1de2242376315c4a5c34f1077a137d
3
  size 4283
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38487dd6445b9a0ec1b811154337420fd97312579fa8d24de47f1c0ea2ebe18c
3
  size 4283