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
631d470
·
verified ·
1 Parent(s): a624889

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1713611453.a9446dbff3d4.7440.12 +2 -2
  2. logs/events.out.tfevents.1713611523.a9446dbff3d4.7440.13 +3 -0
  3. model.safetensors +1 -1
  4. run-10/checkpoint-800/config.json +34 -0
  5. run-10/checkpoint-800/model.safetensors +3 -0
  6. run-10/checkpoint-800/optimizer.pt +3 -0
  7. run-10/checkpoint-800/rng_state.pth +3 -0
  8. run-10/checkpoint-800/scheduler.pt +3 -0
  9. run-10/checkpoint-800/special_tokens_map.json +7 -0
  10. run-10/checkpoint-800/tokenizer.json +0 -0
  11. run-10/checkpoint-800/tokenizer_config.json +57 -0
  12. run-10/checkpoint-800/trainer_state.json +126 -0
  13. run-10/checkpoint-800/training_args.bin +3 -0
  14. run-10/checkpoint-800/vocab.txt +0 -0
  15. run-10/checkpoint-960/config.json +34 -0
  16. run-10/checkpoint-960/model.safetensors +3 -0
  17. run-10/checkpoint-960/optimizer.pt +3 -0
  18. run-10/checkpoint-960/rng_state.pth +3 -0
  19. run-10/checkpoint-960/scheduler.pt +3 -0
  20. run-10/checkpoint-960/special_tokens_map.json +7 -0
  21. run-10/checkpoint-960/tokenizer.json +0 -0
  22. run-10/checkpoint-960/tokenizer_config.json +57 -0
  23. run-10/checkpoint-960/trainer_state.json +146 -0
  24. run-10/checkpoint-960/training_args.bin +3 -0
  25. run-10/checkpoint-960/vocab.txt +0 -0
  26. run-11/checkpoint-160/config.json +34 -0
  27. run-11/checkpoint-160/model.safetensors +3 -0
  28. run-11/checkpoint-160/optimizer.pt +3 -0
  29. run-11/checkpoint-160/rng_state.pth +3 -0
  30. run-11/checkpoint-160/scheduler.pt +3 -0
  31. run-11/checkpoint-160/special_tokens_map.json +7 -0
  32. run-11/checkpoint-160/tokenizer.json +0 -0
  33. run-11/checkpoint-160/tokenizer_config.json +57 -0
  34. run-11/checkpoint-160/trainer_state.json +46 -0
  35. run-11/checkpoint-160/training_args.bin +3 -0
  36. run-11/checkpoint-160/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1713611453.a9446dbff3d4.7440.12 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:077e622b1ef7a9f904e281c3128cf550a8d692a3b2093bb1b70ac0a5e022354b
3
- size 6212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:412285beccbfea2188cc08e4868178fd8262a8eee5a0b1c1908618b664d02288
3
+ size 9862
logs/events.out.tfevents.1713611523.a9446dbff3d4.7440.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61adc76c615590e29064e0e9141b6e11b054b70bc929f1821d383504302a8a24
3
+ size 5483
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03dfe0952f0a6030e34124601ff79f276e2ceb48a63399634f680d64e7b92c8a
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32926685d21f549f57d363821973e2f801a85e48500642723d244e67b93d8faa
3
  size 17549312
run-10/checkpoint-800/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-10/checkpoint-800/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:442c7792459a5d6d1ca580493df77192d27154d24844fda019c92a1a2c4d3d6b
3
+ size 17549312
run-10/checkpoint-800/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:913ba612823504d3c2680168a7310c6ecdcc268f45746aeb39d45148f05694e3
3
+ size 35123898
run-10/checkpoint-800/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ace9fbf746198b511b010eea6f5f472699d26cf6b3b3dc0129b41ac522dca49
3
+ size 14308
run-10/checkpoint-800/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0c76362307ad13296aa8e59bc95fed85b0e611763f49dc91837a93b4279649f
3
+ size 1064
run-10/checkpoint-800/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-10/checkpoint-800/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-10/checkpoint-800/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-10/checkpoint-800/trainer_state.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7301960784313726,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-10/checkpoint-800",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 800,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 2.012742280960083,
14
+ "learning_rate": 0.0007591954920690624,
15
+ "loss": 0.5869,
16
+ "step": 160
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6666666666666666,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.5785399675369263,
23
+ "eval_mcc": 0.0,
24
+ "eval_precision": 0.0,
25
+ "eval_recall": 0.0,
26
+ "eval_runtime": 1.8697,
27
+ "eval_samples_per_second": 681.924,
28
+ "eval_steps_per_second": 21.394,
29
+ "step": 160
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.057482957839966,
34
+ "learning_rate": 0.0006642960555604296,
35
+ "loss": 0.5715,
36
+ "step": 320
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.676078431372549,
41
+ "eval_f1": 0.4411366711772666,
42
+ "eval_loss": 0.5550761222839355,
43
+ "eval_mcc": 0.22526645932553852,
44
+ "eval_precision": 0.5191082802547771,
45
+ "eval_recall": 0.3835294117647059,
46
+ "eval_runtime": 1.8672,
47
+ "eval_samples_per_second": 682.827,
48
+ "eval_steps_per_second": 21.422,
49
+ "step": 320
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.645397663116455,
54
+ "learning_rate": 0.0005693966190517968,
55
+ "loss": 0.5736,
56
+ "step": 480
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7043137254901961,
61
+ "eval_f1": 0.28733459357277885,
62
+ "eval_loss": 0.5566152334213257,
63
+ "eval_mcc": 0.25125318174069416,
64
+ "eval_precision": 0.7307692307692307,
65
+ "eval_recall": 0.17882352941176471,
66
+ "eval_runtime": 1.8663,
67
+ "eval_samples_per_second": 683.154,
68
+ "eval_steps_per_second": 21.432,
69
+ "step": 480
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 1.3315376043319702,
74
+ "learning_rate": 0.000474497182543164,
75
+ "loss": 0.5569,
76
+ "step": 640
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7113725490196079,
81
+ "eval_f1": 0.4121405750798722,
82
+ "eval_loss": 0.5367588400840759,
83
+ "eval_mcc": 0.2830725629191131,
84
+ "eval_precision": 0.6417910447761194,
85
+ "eval_recall": 0.3035294117647059,
86
+ "eval_runtime": 1.8722,
87
+ "eval_samples_per_second": 681.014,
88
+ "eval_steps_per_second": 21.365,
89
+ "step": 640
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 1.5584187507629395,
94
+ "learning_rate": 0.0003795977460345312,
95
+ "loss": 0.5469,
96
+ "step": 800
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.7301960784313726,
101
+ "eval_f1": 0.50997150997151,
102
+ "eval_loss": 0.5246202945709229,
103
+ "eval_mcc": 0.3496658305237892,
104
+ "eval_precision": 0.6462093862815884,
105
+ "eval_recall": 0.4211764705882353,
106
+ "eval_runtime": 1.8851,
107
+ "eval_samples_per_second": 676.35,
108
+ "eval_steps_per_second": 21.219,
109
+ "step": 800
110
+ }
111
+ ],
112
+ "logging_steps": 500,
113
+ "max_steps": 1440,
114
+ "num_input_tokens_seen": 0,
115
+ "num_train_epochs": 9,
116
+ "save_steps": 500,
117
+ "total_flos": 1458777189600.0,
118
+ "train_batch_size": 32,
119
+ "trial_name": null,
120
+ "trial_params": {
121
+ "alpha": 0.9116955099903541,
122
+ "learning_rate": 0.0008540949285776952,
123
+ "num_train_epochs": 9,
124
+ "temperature": 21
125
+ }
126
+ }
run-10/checkpoint-800/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34acf28a009a32e591bbfa0e1392d8f5ce60c738ac5de3b2d0a889c73580dc19
3
+ size 5048
run-10/checkpoint-800/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-10/checkpoint-960/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-10/checkpoint-960/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66f73965da9d37cb87fb28260d07b1861ad6dc8f1f68f4df0681fda5ec30a1e6
3
+ size 17549312
run-10/checkpoint-960/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee88a9602fa9870a896c72e0093fea956191d279be0245f994f701f908147b24
3
+ size 35123898
run-10/checkpoint-960/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04833703a2abb12fa47ad4211546498a7ae2dcd9a28a03549753cff4beb5c8aa
3
+ size 14308
run-10/checkpoint-960/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b287167c5ed0ac61b129f7451c1d02b70ff2ea1e90c4038c6878ce104ddfe8f9
3
+ size 1064
run-10/checkpoint-960/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-10/checkpoint-960/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-10/checkpoint-960/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-10/checkpoint-960/trainer_state.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7301960784313726,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-10/checkpoint-800",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 960,
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": 2.012742280960083,
14
+ "learning_rate": 0.0007591954920690624,
15
+ "loss": 0.5869,
16
+ "step": 160
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6666666666666666,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.5785399675369263,
23
+ "eval_mcc": 0.0,
24
+ "eval_precision": 0.0,
25
+ "eval_recall": 0.0,
26
+ "eval_runtime": 1.8697,
27
+ "eval_samples_per_second": 681.924,
28
+ "eval_steps_per_second": 21.394,
29
+ "step": 160
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.057482957839966,
34
+ "learning_rate": 0.0006642960555604296,
35
+ "loss": 0.5715,
36
+ "step": 320
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.676078431372549,
41
+ "eval_f1": 0.4411366711772666,
42
+ "eval_loss": 0.5550761222839355,
43
+ "eval_mcc": 0.22526645932553852,
44
+ "eval_precision": 0.5191082802547771,
45
+ "eval_recall": 0.3835294117647059,
46
+ "eval_runtime": 1.8672,
47
+ "eval_samples_per_second": 682.827,
48
+ "eval_steps_per_second": 21.422,
49
+ "step": 320
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.645397663116455,
54
+ "learning_rate": 0.0005693966190517968,
55
+ "loss": 0.5736,
56
+ "step": 480
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7043137254901961,
61
+ "eval_f1": 0.28733459357277885,
62
+ "eval_loss": 0.5566152334213257,
63
+ "eval_mcc": 0.25125318174069416,
64
+ "eval_precision": 0.7307692307692307,
65
+ "eval_recall": 0.17882352941176471,
66
+ "eval_runtime": 1.8663,
67
+ "eval_samples_per_second": 683.154,
68
+ "eval_steps_per_second": 21.432,
69
+ "step": 480
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 1.3315376043319702,
74
+ "learning_rate": 0.000474497182543164,
75
+ "loss": 0.5569,
76
+ "step": 640
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7113725490196079,
81
+ "eval_f1": 0.4121405750798722,
82
+ "eval_loss": 0.5367588400840759,
83
+ "eval_mcc": 0.2830725629191131,
84
+ "eval_precision": 0.6417910447761194,
85
+ "eval_recall": 0.3035294117647059,
86
+ "eval_runtime": 1.8722,
87
+ "eval_samples_per_second": 681.014,
88
+ "eval_steps_per_second": 21.365,
89
+ "step": 640
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 1.5584187507629395,
94
+ "learning_rate": 0.0003795977460345312,
95
+ "loss": 0.5469,
96
+ "step": 800
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.7301960784313726,
101
+ "eval_f1": 0.50997150997151,
102
+ "eval_loss": 0.5246202945709229,
103
+ "eval_mcc": 0.3496658305237892,
104
+ "eval_precision": 0.6462093862815884,
105
+ "eval_recall": 0.4211764705882353,
106
+ "eval_runtime": 1.8851,
107
+ "eval_samples_per_second": 676.35,
108
+ "eval_steps_per_second": 21.219,
109
+ "step": 800
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 3.2840497493743896,
114
+ "learning_rate": 0.0002846983095258984,
115
+ "loss": 0.5382,
116
+ "step": 960
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.7168627450980393,
121
+ "eval_f1": 0.5305591677503251,
122
+ "eval_loss": 0.5253874659538269,
123
+ "eval_mcc": 0.3348618979447744,
124
+ "eval_precision": 0.5930232558139535,
125
+ "eval_recall": 0.48,
126
+ "eval_runtime": 1.8686,
127
+ "eval_samples_per_second": 682.333,
128
+ "eval_steps_per_second": 21.407,
129
+ "step": 960
130
+ }
131
+ ],
132
+ "logging_steps": 500,
133
+ "max_steps": 1440,
134
+ "num_input_tokens_seen": 0,
135
+ "num_train_epochs": 9,
136
+ "save_steps": 500,
137
+ "total_flos": 1750532627520.0,
138
+ "train_batch_size": 32,
139
+ "trial_name": null,
140
+ "trial_params": {
141
+ "alpha": 0.9116955099903541,
142
+ "learning_rate": 0.0008540949285776952,
143
+ "num_train_epochs": 9,
144
+ "temperature": 21
145
+ }
146
+ }
run-10/checkpoint-960/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34acf28a009a32e591bbfa0e1392d8f5ce60c738ac5de3b2d0a889c73580dc19
3
+ size 5048
run-10/checkpoint-960/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-11/checkpoint-160/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-11/checkpoint-160/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32926685d21f549f57d363821973e2f801a85e48500642723d244e67b93d8faa
3
+ size 17549312
run-11/checkpoint-160/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32f0f04e4cab582205aab80c9983f31ca39914e90cc4f3740bdb71db100869de
3
+ size 35123898
run-11/checkpoint-160/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0792eaff268dd73c8e104b5060a487f4ef56535ad3b58888006338b8bc298137
3
+ size 14308
run-11/checkpoint-160/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aee908b8d53c9a8b49b6b40cf931ea7418b1faf606083db5859b8874ee658031
3
+ size 1064
run-11/checkpoint-160/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-11/checkpoint-160/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-11/checkpoint-160/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-11/checkpoint-160/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6666666666666666,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/checkpoint-160",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 160,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 1.6721558570861816,
14
+ "learning_rate": 0.00018503019081556044,
15
+ "loss": 0.4415,
16
+ "step": 160
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6666666666666666,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.4279707670211792,
23
+ "eval_mcc": 0.0,
24
+ "eval_precision": 0.0,
25
+ "eval_recall": 0.0,
26
+ "eval_runtime": 1.867,
27
+ "eval_samples_per_second": 682.915,
28
+ "eval_steps_per_second": 21.425,
29
+ "step": 160
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 1280,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 8,
36
+ "save_steps": 500,
37
+ "total_flos": 291755437920.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.6824602518835456,
42
+ "learning_rate": 0.00021146307521778334,
43
+ "num_train_epochs": 8,
44
+ "temperature": 21
45
+ }
46
+ }
run-11/checkpoint-160/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60cdc985018d73f19e5030e2edd86f80eaf7431ba2a593bc8e0e861bb44a658c
3
+ size 5048
run-11/checkpoint-160/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34acf28a009a32e591bbfa0e1392d8f5ce60c738ac5de3b2d0a889c73580dc19
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60cdc985018d73f19e5030e2edd86f80eaf7431ba2a593bc8e0e861bb44a658c
3
  size 5048