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
b237307
·
verified ·
1 Parent(s): 22ac7d0

Training in progress, epoch 3

Browse files
Files changed (50) hide show
  1. logs/events.out.tfevents.1713590077.1376c752d37a.9760.38 +2 -2
  2. logs/events.out.tfevents.1713590161.1376c752d37a.9760.39 +3 -0
  3. logs/events.out.tfevents.1713590178.1376c752d37a.9760.40 +3 -0
  4. logs/events.out.tfevents.1713590195.1376c752d37a.9760.41 +3 -0
  5. model.safetensors +1 -1
  6. run-38/checkpoint-642/config.json +34 -0
  7. run-38/checkpoint-642/model.safetensors +3 -0
  8. run-38/checkpoint-642/optimizer.pt +3 -0
  9. run-38/checkpoint-642/rng_state.pth +3 -0
  10. run-38/checkpoint-642/scheduler.pt +3 -0
  11. run-38/checkpoint-642/special_tokens_map.json +7 -0
  12. run-38/checkpoint-642/tokenizer.json +0 -0
  13. run-38/checkpoint-642/tokenizer_config.json +57 -0
  14. run-38/checkpoint-642/trainer_state.json +86 -0
  15. run-38/checkpoint-642/training_args.bin +3 -0
  16. run-38/checkpoint-642/vocab.txt +0 -0
  17. run-38/checkpoint-856/config.json +34 -0
  18. run-38/checkpoint-856/model.safetensors +3 -0
  19. run-38/checkpoint-856/optimizer.pt +3 -0
  20. run-38/checkpoint-856/rng_state.pth +3 -0
  21. run-38/checkpoint-856/scheduler.pt +3 -0
  22. run-38/checkpoint-856/special_tokens_map.json +7 -0
  23. run-38/checkpoint-856/tokenizer.json +0 -0
  24. run-38/checkpoint-856/tokenizer_config.json +57 -0
  25. run-38/checkpoint-856/trainer_state.json +106 -0
  26. run-38/checkpoint-856/training_args.bin +3 -0
  27. run-38/checkpoint-856/vocab.txt +0 -0
  28. run-41/checkpoint-428/config.json +34 -0
  29. run-41/checkpoint-428/model.safetensors +3 -0
  30. run-41/checkpoint-428/optimizer.pt +3 -0
  31. run-41/checkpoint-428/rng_state.pth +3 -0
  32. run-41/checkpoint-428/scheduler.pt +3 -0
  33. run-41/checkpoint-428/special_tokens_map.json +7 -0
  34. run-41/checkpoint-428/tokenizer.json +0 -0
  35. run-41/checkpoint-428/tokenizer_config.json +57 -0
  36. run-41/checkpoint-428/trainer_state.json +66 -0
  37. run-41/checkpoint-428/training_args.bin +3 -0
  38. run-41/checkpoint-428/vocab.txt +0 -0
  39. run-41/checkpoint-642/config.json +34 -0
  40. run-41/checkpoint-642/model.safetensors +3 -0
  41. run-41/checkpoint-642/optimizer.pt +3 -0
  42. run-41/checkpoint-642/rng_state.pth +3 -0
  43. run-41/checkpoint-642/scheduler.pt +3 -0
  44. run-41/checkpoint-642/special_tokens_map.json +7 -0
  45. run-41/checkpoint-642/tokenizer.json +0 -0
  46. run-41/checkpoint-642/tokenizer_config.json +57 -0
  47. run-41/checkpoint-642/trainer_state.json +86 -0
  48. run-41/checkpoint-642/training_args.bin +3 -0
  49. run-41/checkpoint-642/vocab.txt +0 -0
  50. training_args.bin +1 -1
logs/events.out.tfevents.1713590077.1376c752d37a.9760.38 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ead32b33617a94f134c86bc405b0f3af5e7fdf981645eadc72e9f0b8b9a57404
3
- size 5482
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7094fdb47487cdb39df3ce652ff34ec5bc44fe82cf9dae0f7965032cefba075b
3
+ size 8402
logs/events.out.tfevents.1713590161.1376c752d37a.9760.39 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:267675278ac39f78c59151d7350912e51b0bcca9fefa43f4b51d29ca9c8ea8ca
3
+ size 5481
logs/events.out.tfevents.1713590178.1376c752d37a.9760.40 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f05006eb8e52445d7af986dedf8a360ac59f3d2d977bda5637c1b5cecc4b23a9
3
+ size 5482
logs/events.out.tfevents.1713590195.1376c752d37a.9760.41 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85d4cb31becb05ef8f255a2943c67d78dca67a832d8164e62bff0af69f6a70aa
3
+ size 7297
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7fdbb0fc21112b532657f3749dd9a22feacaf36a3004a713464b9a03a3f297b
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79ba115280a48b09dbfeec3ae3af1a57872dfedbec5868365de4a3998799b79a
3
  size 17549312
run-38/checkpoint-642/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-38/checkpoint-642/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10b528d0e27dc110524b500afadf4243d2cdf31fcad68f5374fbecfcf847fb5f
3
+ size 17549312
run-38/checkpoint-642/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f7aa12647fd28d30bdc3852eda69bb4d92f8ebffb505f4b68d0d5ef586d41eb
3
+ size 35123898
run-38/checkpoint-642/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11b0c3fe82ed8fc0c5e4a46035e8c4191c362f7c18bb672613fb7c69885d7960
3
+ size 14308
run-38/checkpoint-642/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b718c762c82a46c63f88b93fdc81019e851f7de4e986db8a57b4f0bea224f1b1
3
+ size 1064
run-38/checkpoint-642/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-38/checkpoint-642/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-38/checkpoint-642/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-38/checkpoint-642/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7521968365553603,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-38/checkpoint-642",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 642,
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": 5.823625087738037,
14
+ "learning_rate": 0.00022026694526910956,
15
+ "loss": 0.4997,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7129466900995899,
21
+ "eval_f1": 0.40243902439024387,
22
+ "eval_loss": 0.4626123011112213,
23
+ "eval_mcc": 0.2854021761857005,
24
+ "eval_precision": 0.6573705179282868,
25
+ "eval_recall": 0.28998242530755713,
26
+ "eval_runtime": 3.1456,
27
+ "eval_samples_per_second": 542.661,
28
+ "eval_steps_per_second": 17.167,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.7993404865264893,
34
+ "learning_rate": 0.0001888002388020939,
35
+ "loss": 0.4542,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7398945518453427,
41
+ "eval_f1": 0.47641509433962265,
42
+ "eval_loss": 0.4441252648830414,
43
+ "eval_mcc": 0.366324992569054,
44
+ "eval_precision": 0.7240143369175627,
45
+ "eval_recall": 0.35500878734622143,
46
+ "eval_runtime": 3.7126,
47
+ "eval_samples_per_second": 459.782,
48
+ "eval_steps_per_second": 14.545,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.832775354385376,
54
+ "learning_rate": 0.00015733353233507826,
55
+ "loss": 0.4371,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7521968365553603,
61
+ "eval_f1": 0.5052631578947367,
62
+ "eval_loss": 0.44420263171195984,
63
+ "eval_mcc": 0.4015258565021214,
64
+ "eval_precision": 0.7552447552447552,
65
+ "eval_recall": 0.37961335676625657,
66
+ "eval_runtime": 3.1594,
67
+ "eval_samples_per_second": 540.296,
68
+ "eval_steps_per_second": 17.092,
69
+ "step": 642
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 1712,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 8,
76
+ "save_steps": 500,
77
+ "total_flos": 1574326993320.0,
78
+ "train_batch_size": 32,
79
+ "trial_name": null,
80
+ "trial_params": {
81
+ "alpha": 0.806613569484766,
82
+ "learning_rate": 0.0002517336517361252,
83
+ "num_train_epochs": 8,
84
+ "temperature": 7
85
+ }
86
+ }
run-38/checkpoint-642/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7a56f1a08be493488fc73f1cff5a0aca0dbcd6292eef2952623c01722595b1b
3
+ size 5048
run-38/checkpoint-642/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-38/checkpoint-856/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-38/checkpoint-856/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55eb45d9e6b4731a9c309a4475a23416d6050a4cdf9fdb1dd1b8995403d23f66
3
+ size 17549312
run-38/checkpoint-856/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d8d675a2b7368cb923feb16fa0fbe4d2fb6e1c82d92eb405153704599e7e330
3
+ size 35123898
run-38/checkpoint-856/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:057111bfbb4d541cc190a3ed4fcfe228e7425a50e4a06afd33224d43272b1a59
3
+ size 14308
run-38/checkpoint-856/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ecba6475e3a0dcad6f6ffdd56317cded1b9c61a36b60f31a49dab2e35fb52f0
3
+ size 1064
run-38/checkpoint-856/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-38/checkpoint-856/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-38/checkpoint-856/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-38/checkpoint-856/trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7521968365553603,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-38/checkpoint-642",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 856,
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": 5.823625087738037,
14
+ "learning_rate": 0.00022026694526910956,
15
+ "loss": 0.4997,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7129466900995899,
21
+ "eval_f1": 0.40243902439024387,
22
+ "eval_loss": 0.4626123011112213,
23
+ "eval_mcc": 0.2854021761857005,
24
+ "eval_precision": 0.6573705179282868,
25
+ "eval_recall": 0.28998242530755713,
26
+ "eval_runtime": 3.1456,
27
+ "eval_samples_per_second": 542.661,
28
+ "eval_steps_per_second": 17.167,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.7993404865264893,
34
+ "learning_rate": 0.0001888002388020939,
35
+ "loss": 0.4542,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7398945518453427,
41
+ "eval_f1": 0.47641509433962265,
42
+ "eval_loss": 0.4441252648830414,
43
+ "eval_mcc": 0.366324992569054,
44
+ "eval_precision": 0.7240143369175627,
45
+ "eval_recall": 0.35500878734622143,
46
+ "eval_runtime": 3.7126,
47
+ "eval_samples_per_second": 459.782,
48
+ "eval_steps_per_second": 14.545,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.832775354385376,
54
+ "learning_rate": 0.00015733353233507826,
55
+ "loss": 0.4371,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7521968365553603,
61
+ "eval_f1": 0.5052631578947367,
62
+ "eval_loss": 0.44420263171195984,
63
+ "eval_mcc": 0.4015258565021214,
64
+ "eval_precision": 0.7552447552447552,
65
+ "eval_recall": 0.37961335676625657,
66
+ "eval_runtime": 3.1594,
67
+ "eval_samples_per_second": 540.296,
68
+ "eval_steps_per_second": 17.092,
69
+ "step": 642
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 2.8890116214752197,
74
+ "learning_rate": 0.0001258668258680626,
75
+ "loss": 0.4321,
76
+ "step": 856
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7398945518453427,
81
+ "eval_f1": 0.43367346938775514,
82
+ "eval_loss": 0.4393432140350342,
83
+ "eval_mcc": 0.3683014058572899,
84
+ "eval_precision": 0.7906976744186046,
85
+ "eval_recall": 0.29876977152899825,
86
+ "eval_runtime": 3.8868,
87
+ "eval_samples_per_second": 439.178,
88
+ "eval_steps_per_second": 13.893,
89
+ "step": 856
90
+ }
91
+ ],
92
+ "logging_steps": 500,
93
+ "max_steps": 1712,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 8,
96
+ "save_steps": 500,
97
+ "total_flos": 2099102657760.0,
98
+ "train_batch_size": 32,
99
+ "trial_name": null,
100
+ "trial_params": {
101
+ "alpha": 0.806613569484766,
102
+ "learning_rate": 0.0002517336517361252,
103
+ "num_train_epochs": 8,
104
+ "temperature": 7
105
+ }
106
+ }
run-38/checkpoint-856/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7a56f1a08be493488fc73f1cff5a0aca0dbcd6292eef2952623c01722595b1b
3
+ size 5048
run-38/checkpoint-856/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-41/checkpoint-428/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-41/checkpoint-428/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56d9b4bb3e924e7b234718e51b85c7bd1bd91abea09729d86aed8c050e3bc227
3
+ size 17549312
run-41/checkpoint-428/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08fbe4d5156e1b3ed60020bb03f42a356ae955bedf2185140fe2535886dfc461
3
+ size 35123898
run-41/checkpoint-428/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d0c3b463a8fb08b95f5c77916114776bad3339b633df010e4ffd9b5ddabab1e
3
+ size 14308
run-41/checkpoint-428/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a26048bb011ea03c094269287a2a64b775957ca1e548c51ab52b8a7bd58df02
3
+ size 1064
run-41/checkpoint-428/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-41/checkpoint-428/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-41/checkpoint-428/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-41/checkpoint-428/trainer_state.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7381370826010545,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-41/checkpoint-428",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 428,
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": 7.4478278160095215,
14
+ "learning_rate": 0.00011476430024641456,
15
+ "loss": 0.5267,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7094317516110135,
21
+ "eval_f1": 0.487603305785124,
22
+ "eval_loss": 0.4861217737197876,
23
+ "eval_mcc": 0.3024497025688451,
24
+ "eval_precision": 0.5914786967418546,
25
+ "eval_recall": 0.4147627416520211,
26
+ "eval_runtime": 3.1538,
27
+ "eval_samples_per_second": 541.244,
28
+ "eval_steps_per_second": 17.122,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.338618755340576,
34
+ "learning_rate": 5.738215012320728e-05,
35
+ "loss": 0.4743,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7381370826010545,
41
+ "eval_f1": 0.5299684542586751,
42
+ "eval_loss": 0.4651449918746948,
43
+ "eval_mcc": 0.37172090324876994,
44
+ "eval_precision": 0.6596858638743456,
45
+ "eval_recall": 0.4428822495606327,
46
+ "eval_runtime": 3.7183,
47
+ "eval_samples_per_second": 459.08,
48
+ "eval_steps_per_second": 14.523,
49
+ "step": 428
50
+ }
51
+ ],
52
+ "logging_steps": 500,
53
+ "max_steps": 642,
54
+ "num_input_tokens_seen": 0,
55
+ "num_train_epochs": 3,
56
+ "save_steps": 500,
57
+ "total_flos": 1049551328880.0,
58
+ "train_batch_size": 32,
59
+ "trial_name": null,
60
+ "trial_params": {
61
+ "alpha": 0.8513780187435334,
62
+ "learning_rate": 0.00017214645036962186,
63
+ "num_train_epochs": 3,
64
+ "temperature": 16
65
+ }
66
+ }
run-41/checkpoint-428/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de46263d7c08076987d960712223a62e332a7f53f4d847e28a97176e78448aa3
3
+ size 5048
run-41/checkpoint-428/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-41/checkpoint-642/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-41/checkpoint-642/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79ba115280a48b09dbfeec3ae3af1a57872dfedbec5868365de4a3998799b79a
3
+ size 17549312
run-41/checkpoint-642/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8e8b3df3f184e761f895695479a2dff625db53f63a87b7622ffd76846291abe
3
+ size 35123898
run-41/checkpoint-642/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11b0c3fe82ed8fc0c5e4a46035e8c4191c362f7c18bb672613fb7c69885d7960
3
+ size 14308
run-41/checkpoint-642/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58a950dcd1076e4b3bf60e02e264cf4b6f0846ba1f3ec58606dea72b8e97b408
3
+ size 1064
run-41/checkpoint-642/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-41/checkpoint-642/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-41/checkpoint-642/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-41/checkpoint-642/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7428236672524897,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-41/checkpoint-642",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 642,
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": 7.4478278160095215,
14
+ "learning_rate": 0.00011476430024641456,
15
+ "loss": 0.5267,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7094317516110135,
21
+ "eval_f1": 0.487603305785124,
22
+ "eval_loss": 0.4861217737197876,
23
+ "eval_mcc": 0.3024497025688451,
24
+ "eval_precision": 0.5914786967418546,
25
+ "eval_recall": 0.4147627416520211,
26
+ "eval_runtime": 3.1538,
27
+ "eval_samples_per_second": 541.244,
28
+ "eval_steps_per_second": 17.122,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.338618755340576,
34
+ "learning_rate": 5.738215012320728e-05,
35
+ "loss": 0.4743,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7381370826010545,
41
+ "eval_f1": 0.5299684542586751,
42
+ "eval_loss": 0.4651449918746948,
43
+ "eval_mcc": 0.37172090324876994,
44
+ "eval_precision": 0.6596858638743456,
45
+ "eval_recall": 0.4428822495606327,
46
+ "eval_runtime": 3.7183,
47
+ "eval_samples_per_second": 459.08,
48
+ "eval_steps_per_second": 14.523,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.6570167541503906,
54
+ "learning_rate": 0.0,
55
+ "loss": 0.4594,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7428236672524897,
61
+ "eval_f1": 0.5334750265674814,
62
+ "eval_loss": 0.46071532368659973,
63
+ "eval_mcc": 0.3822943460437718,
64
+ "eval_precision": 0.6747311827956989,
65
+ "eval_recall": 0.44112478031634444,
66
+ "eval_runtime": 3.1598,
67
+ "eval_samples_per_second": 540.217,
68
+ "eval_steps_per_second": 17.089,
69
+ "step": 642
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 642,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 3,
76
+ "save_steps": 500,
77
+ "total_flos": 1574326993320.0,
78
+ "train_batch_size": 32,
79
+ "trial_name": null,
80
+ "trial_params": {
81
+ "alpha": 0.8513780187435334,
82
+ "learning_rate": 0.00017214645036962186,
83
+ "num_train_epochs": 3,
84
+ "temperature": 16
85
+ }
86
+ }
run-41/checkpoint-642/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de46263d7c08076987d960712223a62e332a7f53f4d847e28a97176e78448aa3
3
+ size 5048
run-41/checkpoint-642/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:b7a56f1a08be493488fc73f1cff5a0aca0dbcd6292eef2952623c01722595b1b
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de46263d7c08076987d960712223a62e332a7f53f4d847e28a97176e78448aa3
3
  size 5048