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
f34f2c5
·
verified ·
1 Parent(s): c0c1e57

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1709443313.49ae8f4e8e7b.1647.2 +2 -2
  2. logs/events.out.tfevents.1709444330.49ae8f4e8e7b.1647.3 +3 -0
  3. model.safetensors +1 -1
  4. run-1/checkpoint-2108/config.json +34 -0
  5. run-1/checkpoint-2108/model.safetensors +3 -0
  6. run-1/checkpoint-2108/optimizer.pt +3 -0
  7. run-1/checkpoint-2108/rng_state.pth +3 -0
  8. run-1/checkpoint-2108/scheduler.pt +3 -0
  9. run-1/checkpoint-2108/special_tokens_map.json +7 -0
  10. run-1/checkpoint-2108/tokenizer.json +0 -0
  11. run-1/checkpoint-2108/tokenizer_config.json +57 -0
  12. run-1/checkpoint-2108/trainer_state.json +90 -0
  13. run-1/checkpoint-2108/training_args.bin +3 -0
  14. run-1/checkpoint-2108/vocab.txt +0 -0
  15. run-1/checkpoint-2635/config.json +34 -0
  16. run-1/checkpoint-2635/model.safetensors +3 -0
  17. run-1/checkpoint-2635/optimizer.pt +3 -0
  18. run-1/checkpoint-2635/rng_state.pth +3 -0
  19. run-1/checkpoint-2635/scheduler.pt +3 -0
  20. run-1/checkpoint-2635/special_tokens_map.json +7 -0
  21. run-1/checkpoint-2635/tokenizer.json +0 -0
  22. run-1/checkpoint-2635/tokenizer_config.json +57 -0
  23. run-1/checkpoint-2635/trainer_state.json +106 -0
  24. run-1/checkpoint-2635/training_args.bin +3 -0
  25. run-1/checkpoint-2635/vocab.txt +0 -0
  26. run-2/checkpoint-527/config.json +34 -0
  27. run-2/checkpoint-527/model.safetensors +3 -0
  28. run-2/checkpoint-527/optimizer.pt +3 -0
  29. run-2/checkpoint-527/rng_state.pth +3 -0
  30. run-2/checkpoint-527/scheduler.pt +3 -0
  31. run-2/checkpoint-527/special_tokens_map.json +7 -0
  32. run-2/checkpoint-527/tokenizer.json +0 -0
  33. run-2/checkpoint-527/tokenizer_config.json +57 -0
  34. run-2/checkpoint-527/trainer_state.json +42 -0
  35. run-2/checkpoint-527/training_args.bin +3 -0
  36. run-2/checkpoint-527/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1709443313.49ae8f4e8e7b.1647.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e817ce7f8edd91d103c2866f5407caef2a0f256c3d4fb5ea633565deb474f95
3
- size 5713
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b635010c5af84830556132f4ca0da8255e91c6a79a4fe8389e94dd20b2c88852
3
+ size 7669
logs/events.out.tfevents.1709444330.49ae8f4e8e7b.1647.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:820b6d13a66b5cd0711d5678990f4e861e5e871f77ab432c402e13751d27e898
3
+ size 5179
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83d9086c12fcdbed73cbf47e828bfda0720cdd07c40230f496aea6e054e7918c
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c16f8be64c851905d1c987b28e993ea98e296e059b34044bd34f7c1cf3c4baf5
3
  size 17549312
run-1/checkpoint-2108/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-1/checkpoint-2108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d7dab9438450aa4623e3758f88360801b207ec2037783e27d98bcfb5427de3c
3
+ size 17549312
run-1/checkpoint-2108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2b0c0fc84749a2d770a34d952651fcbaac6d2a2ffaaf02b5eb9a73023cf14cd
3
+ size 35123898
run-1/checkpoint-2108/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:156b964b8b8d6a91ffdb147bae8680ec9176dd914174ff8673c354a99142bf22
3
+ size 14308
run-1/checkpoint-2108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cef0c3882ea93d468b2c49a093fc83ecfa5eebf14173d8c7753f1e308e1923a
3
+ size 1064
run-1/checkpoint-2108/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-2108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-2108/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-2108/trainer_state.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8165137614678899,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-2108",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2108,
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": 6.5936455726623535,
14
+ "learning_rate": 3.3598671878261075e-05,
15
+ "loss": 2.2445,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.786697247706422,
21
+ "eval_loss": 1.6360795497894287,
22
+ "eval_runtime": 2.8227,
23
+ "eval_samples_per_second": 308.927,
24
+ "eval_steps_per_second": 2.48,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": Infinity,
30
+ "learning_rate": 2.5230881206493013e-05,
31
+ "loss": 1.3366,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.805045871559633,
37
+ "eval_loss": 1.3841164112091064,
38
+ "eval_runtime": 2.8165,
39
+ "eval_samples_per_second": 309.6,
40
+ "eval_steps_per_second": 2.485,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 35.57567596435547,
46
+ "learning_rate": 1.6831213236927748e-05,
47
+ "loss": 1.0583,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8027522935779816,
53
+ "eval_loss": 1.3448162078857422,
54
+ "eval_runtime": 2.8149,
55
+ "eval_samples_per_second": 309.783,
56
+ "eval_steps_per_second": 2.487,
57
+ "step": 1581
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 18.64527702331543,
62
+ "learning_rate": 8.431545267362479e-06,
63
+ "loss": 0.931,
64
+ "step": 2108
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.8165137614678899,
69
+ "eval_loss": 1.3177071809768677,
70
+ "eval_runtime": 2.8202,
71
+ "eval_samples_per_second": 309.195,
72
+ "eval_steps_per_second": 2.482,
73
+ "step": 2108
74
+ }
75
+ ],
76
+ "logging_steps": 500,
77
+ "max_steps": 2635,
78
+ "num_input_tokens_seen": 0,
79
+ "num_train_epochs": 5,
80
+ "save_steps": 500,
81
+ "total_flos": 32337743850420.0,
82
+ "train_batch_size": 128,
83
+ "trial_name": null,
84
+ "trial_params": {
85
+ "alpha": 0.4702639641604981,
86
+ "learning_rate": 4.199833984782634e-05,
87
+ "num_train_epochs": 5,
88
+ "temperature": 22
89
+ }
90
+ }
run-1/checkpoint-2108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd32930a2d37230c23fea8f6a6d1f43f7d278b48137a4f81b206df516804576a
3
+ size 4984
run-1/checkpoint-2108/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-2635/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-1/checkpoint-2635/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:644d03d726a94062c31ec9c3a5f10ca26e6a5f4304566ab314fae9ea8be6321f
3
+ size 17549312
run-1/checkpoint-2635/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99f1384461821a2303a0bc7fad4cdbd8e3eda7794968678f8cb33a992b3ca072
3
+ size 35123898
run-1/checkpoint-2635/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bd37da819cfe1c92aea202c8f190c02a65fdc71a17fd2af0ed4760f9222ae02
3
+ size 14308
run-1/checkpoint-2635/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c77c8925419589978bf5c58fe7886c3970c1330eaf904ebdcd7a3d1ce24ba170
3
+ size 1064
run-1/checkpoint-2635/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-2635/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-2635/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-2635/trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8165137614678899,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-2108",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2635,
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": 6.5936455726623535,
14
+ "learning_rate": 3.3598671878261075e-05,
15
+ "loss": 2.2445,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.786697247706422,
21
+ "eval_loss": 1.6360795497894287,
22
+ "eval_runtime": 2.8227,
23
+ "eval_samples_per_second": 308.927,
24
+ "eval_steps_per_second": 2.48,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": Infinity,
30
+ "learning_rate": 2.5230881206493013e-05,
31
+ "loss": 1.3366,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.805045871559633,
37
+ "eval_loss": 1.3841164112091064,
38
+ "eval_runtime": 2.8165,
39
+ "eval_samples_per_second": 309.6,
40
+ "eval_steps_per_second": 2.485,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 35.57567596435547,
46
+ "learning_rate": 1.6831213236927748e-05,
47
+ "loss": 1.0583,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8027522935779816,
53
+ "eval_loss": 1.3448162078857422,
54
+ "eval_runtime": 2.8149,
55
+ "eval_samples_per_second": 309.783,
56
+ "eval_steps_per_second": 2.487,
57
+ "step": 1581
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 18.64527702331543,
62
+ "learning_rate": 8.431545267362479e-06,
63
+ "loss": 0.931,
64
+ "step": 2108
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.8165137614678899,
69
+ "eval_loss": 1.3177071809768677,
70
+ "eval_runtime": 2.8202,
71
+ "eval_samples_per_second": 309.195,
72
+ "eval_steps_per_second": 2.482,
73
+ "step": 2108
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 16.987468719482422,
78
+ "learning_rate": 3.187729779721164e-08,
79
+ "loss": 0.8787,
80
+ "step": 2635
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_accuracy": 0.8153669724770642,
85
+ "eval_loss": 1.315588116645813,
86
+ "eval_runtime": 2.8163,
87
+ "eval_samples_per_second": 309.628,
88
+ "eval_steps_per_second": 2.486,
89
+ "step": 2635
90
+ }
91
+ ],
92
+ "logging_steps": 500,
93
+ "max_steps": 2635,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 5,
96
+ "save_steps": 500,
97
+ "total_flos": 40447180739880.0,
98
+ "train_batch_size": 128,
99
+ "trial_name": null,
100
+ "trial_params": {
101
+ "alpha": 0.4702639641604981,
102
+ "learning_rate": 4.199833984782634e-05,
103
+ "num_train_epochs": 5,
104
+ "temperature": 22
105
+ }
106
+ }
run-1/checkpoint-2635/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd32930a2d37230c23fea8f6a6d1f43f7d278b48137a4f81b206df516804576a
3
+ size 4984
run-1/checkpoint-2635/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-2/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c16f8be64c851905d1c987b28e993ea98e296e059b34044bd34f7c1cf3c4baf5
3
+ size 17549312
run-2/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d80f51b3929f25709e999b1291195aa5857976026ef5cd7e75a9fd81c1829bc1
3
+ size 35123898
run-2/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a32291cb0c1329fbb9596dcc47c5d9b0d1f71ecc09dad1791e0b193314659e4
3
+ size 14308
run-2/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d921b7eca97b1be9265517642faaa27bdc0af595c79b7b40f85c493534f65969
3
+ size 1064
run-2/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-2/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7763761467889908,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/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": 6.471368312835693,
14
+ "learning_rate": 2.8549539646703335e-05,
15
+ "loss": 2.1389,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7763761467889908,
21
+ "eval_loss": 1.5801109075546265,
22
+ "eval_runtime": 2.8093,
23
+ "eval_samples_per_second": 310.393,
24
+ "eval_steps_per_second": 2.492,
25
+ "step": 527
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 2108,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 4,
32
+ "save_steps": 500,
33
+ "total_flos": 8057768762220.0,
34
+ "train_batch_size": 128,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "alpha": 0.5278139834631775,
38
+ "learning_rate": 3.806605286227111e-05,
39
+ "num_train_epochs": 4,
40
+ "temperature": 30
41
+ }
42
+ }
run-2/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e0c2a26f7d6dc63b27272b7c42729d66852eba78b186883669f5422e9f41d72
3
+ size 4984
run-2/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:cd32930a2d37230c23fea8f6a6d1f43f7d278b48137a4f81b206df516804576a
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e0c2a26f7d6dc63b27272b7c42729d66852eba78b186883669f5422e9f41d72
3
  size 4984