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
13ad255
·
verified ·
1 Parent(s): 32407c5

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1709750166.d65e8524b0f6.5185.26 +2 -2
  2. logs/events.out.tfevents.1709750832.d65e8524b0f6.5185.27 +3 -0
  3. model.safetensors +1 -1
  4. run-26/checkpoint-260/config.json +34 -0
  5. run-26/checkpoint-260/model.safetensors +3 -0
  6. run-26/checkpoint-260/optimizer.pt +3 -0
  7. run-26/checkpoint-260/rng_state.pth +3 -0
  8. run-26/checkpoint-260/scheduler.pt +3 -0
  9. run-26/checkpoint-260/special_tokens_map.json +7 -0
  10. run-26/checkpoint-260/tokenizer.json +0 -0
  11. run-26/checkpoint-260/tokenizer_config.json +57 -0
  12. run-26/checkpoint-260/trainer_state.json +122 -0
  13. run-26/checkpoint-260/training_args.bin +3 -0
  14. run-26/checkpoint-260/vocab.txt +0 -0
  15. run-26/checkpoint-312/config.json +34 -0
  16. run-26/checkpoint-312/model.safetensors +3 -0
  17. run-26/checkpoint-312/optimizer.pt +3 -0
  18. run-26/checkpoint-312/rng_state.pth +3 -0
  19. run-26/checkpoint-312/scheduler.pt +3 -0
  20. run-26/checkpoint-312/special_tokens_map.json +7 -0
  21. run-26/checkpoint-312/tokenizer.json +0 -0
  22. run-26/checkpoint-312/tokenizer_config.json +57 -0
  23. run-26/checkpoint-312/trainer_state.json +141 -0
  24. run-26/checkpoint-312/training_args.bin +3 -0
  25. run-26/checkpoint-312/vocab.txt +0 -0
  26. run-27/checkpoint-52/config.json +34 -0
  27. run-27/checkpoint-52/model.safetensors +3 -0
  28. run-27/checkpoint-52/optimizer.pt +3 -0
  29. run-27/checkpoint-52/rng_state.pth +3 -0
  30. run-27/checkpoint-52/scheduler.pt +3 -0
  31. run-27/checkpoint-52/special_tokens_map.json +7 -0
  32. run-27/checkpoint-52/tokenizer.json +0 -0
  33. run-27/checkpoint-52/tokenizer_config.json +57 -0
  34. run-27/checkpoint-52/trainer_state.json +46 -0
  35. run-27/checkpoint-52/training_args.bin +3 -0
  36. run-27/checkpoint-52/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1709750166.d65e8524b0f6.5185.26 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb7bf23a7bb5f42892898ac977cdeacfc419b41eb8ccb2ef5e74c568c8dc5572
3
- size 5984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6e7a2312f84f04faa116eec2e3a77d37f4b89e8cdae6b2d32478a3386c77d7a
3
+ size 9070
logs/events.out.tfevents.1709750832.d65e8524b0f6.5185.27 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e45cb18a11b839821678f0b663560aa833d3c472000fce9ec5cc04246b1c0730
3
+ size 5312
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bb00e455b644f9e5927df934270917d43a35fc1f5aaebf45803100174efdd07
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcb574f6de4a4ed24dac1305ffcd6e58eb8fa27ddb364bc6eeccd0e850c31aec
3
  size 17549312
run-26/checkpoint-260/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": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-26/checkpoint-260/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6484c48086839dc2a8825c9bc66c20058fe4f2c1bc8c7ceef6c4b0ca44bf9b5
3
+ size 17549312
run-26/checkpoint-260/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16c8da2943bb0941268e6708fca596b1c5a0769abbe440f57a73a707682c8c20
3
+ size 35122746
run-26/checkpoint-260/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a181b1b8071dd5d3e2a0831d4e696afe5f95f0349fc567304bc4728b75f66fb
3
+ size 14054
run-26/checkpoint-260/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c25b42a960e2ba87c4f2c1a72a2edc7df05fd4f466b57b863e7d01ac71e2d069
3
+ size 1064
run-26/checkpoint-260/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-26/checkpoint-260/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-26/checkpoint-260/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-26/checkpoint-260/trainer_state.json ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8258317025440313,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-26/checkpoint-260",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 260,
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": 4.020422458648682,
14
+ "learning_rate": 0.00036726045612177425,
15
+ "loss": 0.5512,
16
+ "step": 52
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7397260273972602,
21
+ "eval_f1": 0.7823240589198035,
22
+ "eval_loss": 0.4979219436645508,
23
+ "eval_precision": 0.6722925457102672,
24
+ "eval_recall": 0.9354207436399217,
25
+ "eval_runtime": 28.449,
26
+ "eval_samples_per_second": 35.924,
27
+ "eval_steps_per_second": 1.125,
28
+ "step": 52
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 2.4581830501556396,
33
+ "learning_rate": 0.00029380836489741936,
34
+ "loss": 0.4888,
35
+ "step": 104
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.7788649706457925,
40
+ "eval_f1": 0.8061749571183533,
41
+ "eval_loss": 0.45355936884880066,
42
+ "eval_precision": 0.7175572519083969,
43
+ "eval_recall": 0.9197651663405088,
44
+ "eval_runtime": 28.5368,
45
+ "eval_samples_per_second": 35.813,
46
+ "eval_steps_per_second": 1.121,
47
+ "step": 104
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 2.563227415084839,
52
+ "learning_rate": 0.00022035627367306455,
53
+ "loss": 0.4608,
54
+ "step": 156
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.7759295499021527,
59
+ "eval_f1": 0.8109000825763832,
60
+ "eval_loss": 0.45456382632255554,
61
+ "eval_precision": 0.7014285714285714,
62
+ "eval_recall": 0.9608610567514677,
63
+ "eval_runtime": 27.7846,
64
+ "eval_samples_per_second": 36.783,
65
+ "eval_steps_per_second": 1.152,
66
+ "step": 156
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 1.4997444152832031,
71
+ "learning_rate": 0.00014690418244870968,
72
+ "loss": 0.4436,
73
+ "step": 208
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.8062622309197651,
78
+ "eval_f1": 0.8176795580110496,
79
+ "eval_loss": 0.4241831302642822,
80
+ "eval_precision": 0.7721739130434783,
81
+ "eval_recall": 0.8688845401174168,
82
+ "eval_runtime": 28.0956,
83
+ "eval_samples_per_second": 36.376,
84
+ "eval_steps_per_second": 1.139,
85
+ "step": 208
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 1.6734051704406738,
90
+ "learning_rate": 7.345209122435484e-05,
91
+ "loss": 0.4276,
92
+ "step": 260
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.8258317025440313,
97
+ "eval_f1": 0.8405017921146953,
98
+ "eval_loss": 0.41184401512145996,
99
+ "eval_precision": 0.775206611570248,
100
+ "eval_recall": 0.9178082191780822,
101
+ "eval_runtime": 28.1973,
102
+ "eval_samples_per_second": 36.245,
103
+ "eval_steps_per_second": 1.135,
104
+ "step": 260
105
+ }
106
+ ],
107
+ "logging_steps": 500,
108
+ "max_steps": 312,
109
+ "num_input_tokens_seen": 0,
110
+ "num_train_epochs": 6,
111
+ "save_steps": 500,
112
+ "total_flos": 1178475986400.0,
113
+ "train_batch_size": 59,
114
+ "trial_name": null,
115
+ "trial_params": {
116
+ "alpha": 0.834805680054491,
117
+ "learning_rate": 0.0004407125473461291,
118
+ "num_train_epochs": 6,
119
+ "per_device_train_batch_size": 59,
120
+ "temperature": 21
121
+ }
122
+ }
run-26/checkpoint-260/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:933b126144a66dbb7b9e564c26759f0fa2a3d3f6cf93d2826c06f906a025640e
3
+ size 4920
run-26/checkpoint-260/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-26/checkpoint-312/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": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-26/checkpoint-312/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a89a3446915571f16cc7f145bf513191bfb06f99c3348f8db57a2aa4b5883d27
3
+ size 17549312
run-26/checkpoint-312/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9187ccd642e3186b0fe27c3061e17a6d15ac5aa9a68108253d1f57a207053e6
3
+ size 35122746
run-26/checkpoint-312/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fd83b6e7701fea2c6d1e6ecd87402243a5ae02d8b291ea889b42273837365ad
3
+ size 14054
run-26/checkpoint-312/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f8e9d6b0efcd4ccdc22fb37a5935f933073da782facff23ce40e66512c03519
3
+ size 1064
run-26/checkpoint-312/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-26/checkpoint-312/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-26/checkpoint-312/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-26/checkpoint-312/trainer_state.json ADDED
@@ -0,0 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8258317025440313,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-26/checkpoint-260",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 312,
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": 4.020422458648682,
14
+ "learning_rate": 0.00036726045612177425,
15
+ "loss": 0.5512,
16
+ "step": 52
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7397260273972602,
21
+ "eval_f1": 0.7823240589198035,
22
+ "eval_loss": 0.4979219436645508,
23
+ "eval_precision": 0.6722925457102672,
24
+ "eval_recall": 0.9354207436399217,
25
+ "eval_runtime": 28.449,
26
+ "eval_samples_per_second": 35.924,
27
+ "eval_steps_per_second": 1.125,
28
+ "step": 52
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 2.4581830501556396,
33
+ "learning_rate": 0.00029380836489741936,
34
+ "loss": 0.4888,
35
+ "step": 104
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.7788649706457925,
40
+ "eval_f1": 0.8061749571183533,
41
+ "eval_loss": 0.45355936884880066,
42
+ "eval_precision": 0.7175572519083969,
43
+ "eval_recall": 0.9197651663405088,
44
+ "eval_runtime": 28.5368,
45
+ "eval_samples_per_second": 35.813,
46
+ "eval_steps_per_second": 1.121,
47
+ "step": 104
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 2.563227415084839,
52
+ "learning_rate": 0.00022035627367306455,
53
+ "loss": 0.4608,
54
+ "step": 156
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.7759295499021527,
59
+ "eval_f1": 0.8109000825763832,
60
+ "eval_loss": 0.45456382632255554,
61
+ "eval_precision": 0.7014285714285714,
62
+ "eval_recall": 0.9608610567514677,
63
+ "eval_runtime": 27.7846,
64
+ "eval_samples_per_second": 36.783,
65
+ "eval_steps_per_second": 1.152,
66
+ "step": 156
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 1.4997444152832031,
71
+ "learning_rate": 0.00014690418244870968,
72
+ "loss": 0.4436,
73
+ "step": 208
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.8062622309197651,
78
+ "eval_f1": 0.8176795580110496,
79
+ "eval_loss": 0.4241831302642822,
80
+ "eval_precision": 0.7721739130434783,
81
+ "eval_recall": 0.8688845401174168,
82
+ "eval_runtime": 28.0956,
83
+ "eval_samples_per_second": 36.376,
84
+ "eval_steps_per_second": 1.139,
85
+ "step": 208
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 1.6734051704406738,
90
+ "learning_rate": 7.345209122435484e-05,
91
+ "loss": 0.4276,
92
+ "step": 260
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.8258317025440313,
97
+ "eval_f1": 0.8405017921146953,
98
+ "eval_loss": 0.41184401512145996,
99
+ "eval_precision": 0.775206611570248,
100
+ "eval_recall": 0.9178082191780822,
101
+ "eval_runtime": 28.1973,
102
+ "eval_samples_per_second": 36.245,
103
+ "eval_steps_per_second": 1.135,
104
+ "step": 260
105
+ },
106
+ {
107
+ "epoch": 6.0,
108
+ "grad_norm": 2.4996392726898193,
109
+ "learning_rate": 0.0,
110
+ "loss": 0.4179,
111
+ "step": 312
112
+ },
113
+ {
114
+ "epoch": 6.0,
115
+ "eval_accuracy": 0.8238747553816047,
116
+ "eval_f1": 0.84070796460177,
117
+ "eval_loss": 0.4115830659866333,
118
+ "eval_precision": 0.7673667205169629,
119
+ "eval_recall": 0.9295499021526419,
120
+ "eval_runtime": 28.7278,
121
+ "eval_samples_per_second": 35.575,
122
+ "eval_steps_per_second": 1.114,
123
+ "step": 312
124
+ }
125
+ ],
126
+ "logging_steps": 500,
127
+ "max_steps": 312,
128
+ "num_input_tokens_seen": 0,
129
+ "num_train_epochs": 6,
130
+ "save_steps": 500,
131
+ "total_flos": 1414171183680.0,
132
+ "train_batch_size": 59,
133
+ "trial_name": null,
134
+ "trial_params": {
135
+ "alpha": 0.834805680054491,
136
+ "learning_rate": 0.0004407125473461291,
137
+ "num_train_epochs": 6,
138
+ "per_device_train_batch_size": 59,
139
+ "temperature": 21
140
+ }
141
+ }
run-26/checkpoint-312/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:933b126144a66dbb7b9e564c26759f0fa2a3d3f6cf93d2826c06f906a025640e
3
+ size 4920
run-26/checkpoint-312/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-27/checkpoint-52/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": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-27/checkpoint-52/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcb574f6de4a4ed24dac1305ffcd6e58eb8fa27ddb364bc6eeccd0e850c31aec
3
+ size 17549312
run-27/checkpoint-52/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4538b89e4f0650b62cf8e09fcf0bfec85af79ca789ee31cf055fd77062ed28d2
3
+ size 35122746
run-27/checkpoint-52/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57a5c50aa7f2ed0b1dcc4148c857bfb22e50d115c1400b6f3fa81740c830107f
3
+ size 14054
run-27/checkpoint-52/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44e4d6cc026852b6f98a538b21016b2a5d9127c9dde873beb6f0a6205ac8f77b
3
+ size 1064
run-27/checkpoint-52/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-27/checkpoint-52/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-27/checkpoint-52/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-27/checkpoint-52/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7397260273972602,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-27/checkpoint-52",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 52,
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": 3.795090675354004,
14
+ "learning_rate": 0.0004299539034695828,
15
+ "loss": 0.5539,
16
+ "step": 52
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7397260273972602,
21
+ "eval_f1": 0.7779632721202002,
22
+ "eval_loss": 0.49282991886138916,
23
+ "eval_precision": 0.6783114992721979,
24
+ "eval_recall": 0.9119373776908023,
25
+ "eval_runtime": 28.2474,
26
+ "eval_samples_per_second": 36.18,
27
+ "eval_steps_per_second": 1.133,
28
+ "step": 52
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 364,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 7,
35
+ "save_steps": 500,
36
+ "total_flos": 235695197280.0,
37
+ "train_batch_size": 59,
38
+ "trial_name": null,
39
+ "trial_params": {
40
+ "alpha": 0.845201757467621,
41
+ "learning_rate": 0.00050161288738118,
42
+ "num_train_epochs": 7,
43
+ "per_device_train_batch_size": 59,
44
+ "temperature": 21
45
+ }
46
+ }
run-27/checkpoint-52/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3427d367c6681566932cafa2f6b6a62ba9e8ebfdfa8d9ebafbc1230e1c415890
3
+ size 4920
run-27/checkpoint-52/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 sha256:83d69afa7ea349d5580248b9721c10f3b2232803e6d1d873807217055f137bde
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3427d367c6681566932cafa2f6b6a62ba9e8ebfdfa8d9ebafbc1230e1c415890
3
  size 4920