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
d6258f8
·
verified ·
1 Parent(s): 88e5875

Training in progress, epoch 9

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. logs/events.out.tfevents.1713590338.1376c752d37a.9760.43 +3 -0
  2. logs/events.out.tfevents.1713590355.1376c752d37a.9760.44 +3 -0
  3. logs/events.out.tfevents.1713590372.1376c752d37a.9760.45 +3 -0
  4. logs/events.out.tfevents.1713590456.1376c752d37a.9760.46 +3 -0
  5. logs/events.out.tfevents.1713590540.1376c752d37a.9760.47 +3 -0
  6. logs/events.out.tfevents.1713590556.1376c752d37a.9760.48 +3 -0
  7. logs/events.out.tfevents.1713590657.1376c752d37a.9760.49 +3 -0
  8. logs/events.out.tfevents.1713590674.1376c752d37a.9760.50 +3 -0
  9. logs/events.out.tfevents.1713592348.1376c752d37a.9760.51 +3 -0
  10. model.safetensors +1 -1
  11. run-45/checkpoint-642/config.json +34 -0
  12. run-45/checkpoint-642/model.safetensors +3 -0
  13. run-45/checkpoint-642/optimizer.pt +3 -0
  14. run-45/checkpoint-642/rng_state.pth +3 -0
  15. run-45/checkpoint-642/scheduler.pt +3 -0
  16. run-45/checkpoint-642/special_tokens_map.json +7 -0
  17. run-45/checkpoint-642/tokenizer.json +0 -0
  18. run-45/checkpoint-642/tokenizer_config.json +57 -0
  19. run-45/checkpoint-642/trainer_state.json +86 -0
  20. run-45/checkpoint-642/training_args.bin +3 -0
  21. run-45/checkpoint-642/vocab.txt +0 -0
  22. run-45/checkpoint-856/config.json +34 -0
  23. run-45/checkpoint-856/model.safetensors +3 -0
  24. run-45/checkpoint-856/optimizer.pt +3 -0
  25. run-45/checkpoint-856/rng_state.pth +3 -0
  26. run-45/checkpoint-856/scheduler.pt +3 -0
  27. run-45/checkpoint-856/special_tokens_map.json +7 -0
  28. run-45/checkpoint-856/tokenizer.json +0 -0
  29. run-45/checkpoint-856/tokenizer_config.json +57 -0
  30. run-45/checkpoint-856/trainer_state.json +106 -0
  31. run-45/checkpoint-856/training_args.bin +3 -0
  32. run-45/checkpoint-856/vocab.txt +0 -0
  33. run-46/checkpoint-642/config.json +34 -0
  34. run-46/checkpoint-642/model.safetensors +3 -0
  35. run-46/checkpoint-642/optimizer.pt +3 -0
  36. run-46/checkpoint-642/rng_state.pth +3 -0
  37. run-46/checkpoint-642/scheduler.pt +3 -0
  38. run-46/checkpoint-642/special_tokens_map.json +7 -0
  39. run-46/checkpoint-642/tokenizer.json +0 -0
  40. run-46/checkpoint-642/tokenizer_config.json +57 -0
  41. run-46/checkpoint-642/trainer_state.json +86 -0
  42. run-46/checkpoint-642/training_args.bin +3 -0
  43. run-46/checkpoint-642/vocab.txt +0 -0
  44. run-46/checkpoint-856/config.json +34 -0
  45. run-46/checkpoint-856/model.safetensors +3 -0
  46. run-46/checkpoint-856/optimizer.pt +3 -0
  47. run-46/checkpoint-856/rng_state.pth +3 -0
  48. run-46/checkpoint-856/scheduler.pt +3 -0
  49. run-46/checkpoint-856/special_tokens_map.json +7 -0
  50. run-46/checkpoint-856/tokenizer.json +0 -0
logs/events.out.tfevents.1713590338.1376c752d37a.9760.43 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:057f8cd3fd66ef949a5f2fc13b4fdde82dd775c6f2465335854d666e9a132cc1
3
+ size 5482
logs/events.out.tfevents.1713590355.1376c752d37a.9760.44 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3077d5410349e5b673cc0c7700014dd97351e7827e9a7ae42f77a6bf73661098
3
+ size 5482
logs/events.out.tfevents.1713590372.1376c752d37a.9760.45 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:338497cf36e781e944f5273a09d83f5c4901fbf8f4db03c63289a63117ce2c7f
3
+ size 8403
logs/events.out.tfevents.1713590456.1376c752d37a.9760.46 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36c5e9fc4aad1c657b6a91139dc30d0322f2b9f9851956303304c922e41d4219
3
+ size 8403
logs/events.out.tfevents.1713590540.1376c752d37a.9760.47 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc87e10271dcc0dc94764cdd509c75ba4ec9944a2bff3a551de103915a252a3b
3
+ size 5482
logs/events.out.tfevents.1713590556.1376c752d37a.9760.48 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aff308d4e43379f1633d05ea8ff18a8dea7aa6ef074fc09aecd7a1916d17d7d
3
+ size 9133
logs/events.out.tfevents.1713590657.1376c752d37a.9760.49 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6632282bf849b09e374d6f0e9b218fbc18550bb7da8c100dd56491c4ee7ad14
3
+ size 5482
logs/events.out.tfevents.1713590674.1376c752d37a.9760.50 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2686c61648382b043a4b34871a39659eece08fe5f804809edd52c46ab05696af
3
+ size 11666
logs/events.out.tfevents.1713592348.1376c752d37a.9760.51 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10a5fa8ba09896d1558dd6a6dc6ab7c485d0c25a1182959cb98cbc48e6d7ecb4
3
+ size 11814
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c0570cc9ad85fd4717e31c7c987df9400861cba344a9450aa5af96d110d78da
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d0924e41d634a5f289f8b8853c0ab4ce9cc00008d07775515ebe7b5b2b52bf0
3
  size 17549312
run-45/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-45/checkpoint-642/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:060a6070a639045409ab3e2f7733eb18de1139e5cd451ebb8ea9b420f7c32c37
3
+ size 17549312
run-45/checkpoint-642/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bdb4ad6d59ab3a2dceaa74bbfca8f7e99bd4632a4e18c2a554900a51c3916e6
3
+ size 35123898
run-45/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-45/checkpoint-642/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ca11405629071bc6d3f2ce84df07ec2a5d19826b9ea417fafebd05f422417b
3
+ size 1064
run-45/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-45/checkpoint-642/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-45/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-45/checkpoint-642/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7217340363210311,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-45/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": 8.950324058532715,
14
+ "learning_rate": 0.00010478179948708485,
15
+ "loss": 0.5816,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7041593438781488,
21
+ "eval_f1": 0.5063538611925709,
22
+ "eval_loss": 0.5396628975868225,
23
+ "eval_mcc": 0.30281965656473075,
24
+ "eval_precision": 0.5704845814977973,
25
+ "eval_recall": 0.45518453427065025,
26
+ "eval_runtime": 3.1674,
27
+ "eval_samples_per_second": 538.919,
28
+ "eval_steps_per_second": 17.048,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.071056604385376,
34
+ "learning_rate": 9.168407455119925e-05,
35
+ "loss": 0.5316,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.705916813122437,
41
+ "eval_f1": 0.4434589800443459,
42
+ "eval_loss": 0.5229035019874573,
43
+ "eval_mcc": 0.27911345997194636,
44
+ "eval_precision": 0.6006006006006006,
45
+ "eval_recall": 0.351493848857645,
46
+ "eval_runtime": 3.1873,
47
+ "eval_samples_per_second": 535.562,
48
+ "eval_steps_per_second": 16.942,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 3.054250478744507,
54
+ "learning_rate": 7.858634961531364e-05,
55
+ "loss": 0.509,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7217340363210311,
61
+ "eval_f1": 0.43384982121573307,
62
+ "eval_loss": 0.509781539440155,
63
+ "eval_mcc": 0.31331689795359174,
64
+ "eval_precision": 0.674074074074074,
65
+ "eval_recall": 0.31985940246045697,
66
+ "eval_runtime": 3.1209,
67
+ "eval_samples_per_second": 546.962,
68
+ "eval_steps_per_second": 17.303,
69
+ "step": 642
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 1926,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 9,
76
+ "save_steps": 500,
77
+ "total_flos": 1574326993320.0,
78
+ "train_batch_size": 32,
79
+ "trial_name": null,
80
+ "trial_params": {
81
+ "alpha": 0.9457260837583084,
82
+ "learning_rate": 0.00011787952442297046,
83
+ "num_train_epochs": 9,
84
+ "temperature": 19
85
+ }
86
+ }
run-45/checkpoint-642/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ee27860bb71df6808d0fe7853aac7d1a7270f4e940f95dd467b73a67fbddc6b
3
+ size 5048
run-45/checkpoint-642/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-45/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-45/checkpoint-856/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6400f61a67fb8239c0ecfcbf3fa5dd9dc88e84d33a33cd1dfd0902ad5a23543a
3
+ size 17549312
run-45/checkpoint-856/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a9c0893994efa929394a589eff562cfe79a592603a74e4cf5dc238d54a55af2
3
+ size 35123898
run-45/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-45/checkpoint-856/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:473149c2ba7bf2bb07a706fd979d8fd682a5f9eca9efe6dea9ec3d4ee082d17c
3
+ size 1064
run-45/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-45/checkpoint-856/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-45/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-45/checkpoint-856/trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7357937902753369,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-45/checkpoint-856",
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": 8.950324058532715,
14
+ "learning_rate": 0.00010478179948708485,
15
+ "loss": 0.5816,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7041593438781488,
21
+ "eval_f1": 0.5063538611925709,
22
+ "eval_loss": 0.5396628975868225,
23
+ "eval_mcc": 0.30281965656473075,
24
+ "eval_precision": 0.5704845814977973,
25
+ "eval_recall": 0.45518453427065025,
26
+ "eval_runtime": 3.1674,
27
+ "eval_samples_per_second": 538.919,
28
+ "eval_steps_per_second": 17.048,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.071056604385376,
34
+ "learning_rate": 9.168407455119925e-05,
35
+ "loss": 0.5316,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.705916813122437,
41
+ "eval_f1": 0.4434589800443459,
42
+ "eval_loss": 0.5229035019874573,
43
+ "eval_mcc": 0.27911345997194636,
44
+ "eval_precision": 0.6006006006006006,
45
+ "eval_recall": 0.351493848857645,
46
+ "eval_runtime": 3.1873,
47
+ "eval_samples_per_second": 535.562,
48
+ "eval_steps_per_second": 16.942,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 3.054250478744507,
54
+ "learning_rate": 7.858634961531364e-05,
55
+ "loss": 0.509,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7217340363210311,
61
+ "eval_f1": 0.43384982121573307,
62
+ "eval_loss": 0.509781539440155,
63
+ "eval_mcc": 0.31331689795359174,
64
+ "eval_precision": 0.674074074074074,
65
+ "eval_recall": 0.31985940246045697,
66
+ "eval_runtime": 3.1209,
67
+ "eval_samples_per_second": 546.962,
68
+ "eval_steps_per_second": 17.303,
69
+ "step": 642
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 5.881683349609375,
74
+ "learning_rate": 6.548862467942804e-05,
75
+ "loss": 0.496,
76
+ "step": 856
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7357937902753369,
81
+ "eval_f1": 0.507103825136612,
82
+ "eval_loss": 0.49531644582748413,
83
+ "eval_mcc": 0.3606499983342828,
84
+ "eval_precision": 0.6705202312138728,
85
+ "eval_recall": 0.4077328646748682,
86
+ "eval_runtime": 3.9891,
87
+ "eval_samples_per_second": 427.912,
88
+ "eval_steps_per_second": 13.537,
89
+ "step": 856
90
+ }
91
+ ],
92
+ "logging_steps": 500,
93
+ "max_steps": 1926,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 9,
96
+ "save_steps": 500,
97
+ "total_flos": 2099102657760.0,
98
+ "train_batch_size": 32,
99
+ "trial_name": null,
100
+ "trial_params": {
101
+ "alpha": 0.9457260837583084,
102
+ "learning_rate": 0.00011787952442297046,
103
+ "num_train_epochs": 9,
104
+ "temperature": 19
105
+ }
106
+ }
run-45/checkpoint-856/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ee27860bb71df6808d0fe7853aac7d1a7270f4e940f95dd467b73a67fbddc6b
3
+ size 5048
run-45/checkpoint-856/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-46/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-46/checkpoint-642/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c3591bb3055074b6410fb1659f3943c8263e100b5b8397f22ebc454d3607b84
3
+ size 17549312
run-46/checkpoint-642/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:865c528aad337fc9f0201f0c53815b1bb830b9d50e5dec9c7284ed9ec8f61980
3
+ size 35123898
run-46/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-46/checkpoint-642/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b41ab2de1b1ba28cc0790285edbb8eb5351dd4f61c98b3fb0c5215892203add6
3
+ size 1064
run-46/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-46/checkpoint-642/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-46/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-46/checkpoint-642/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7486818980667839,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-46/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": 4.412960052490234,
14
+ "learning_rate": 0.00020694993120331544,
15
+ "loss": 0.4902,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7164616285881664,
21
+ "eval_f1": 0.39800995024875624,
22
+ "eval_loss": 0.4596139192581177,
23
+ "eval_mcc": 0.2945528643838721,
24
+ "eval_precision": 0.6808510638297872,
25
+ "eval_recall": 0.281195079086116,
26
+ "eval_runtime": 3.1802,
27
+ "eval_samples_per_second": 536.76,
28
+ "eval_steps_per_second": 16.98,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.3837729692459106,
34
+ "learning_rate": 0.00018395549440294705,
35
+ "loss": 0.4478,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7387229056824839,
41
+ "eval_f1": 0.4520884520884521,
42
+ "eval_loss": 0.44098830223083496,
43
+ "eval_mcc": 0.3627159463012621,
44
+ "eval_precision": 0.7510204081632653,
45
+ "eval_recall": 0.3233743409490334,
46
+ "eval_runtime": 4.0058,
47
+ "eval_samples_per_second": 426.137,
48
+ "eval_steps_per_second": 13.481,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.0605193376541138,
54
+ "learning_rate": 0.00016096105760257865,
55
+ "loss": 0.4298,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7486818980667839,
61
+ "eval_f1": 0.48,
62
+ "eval_loss": 0.4385921359062195,
63
+ "eval_mcc": 0.39214620237686104,
64
+ "eval_precision": 0.7734375,
65
+ "eval_recall": 0.34797891036906853,
66
+ "eval_runtime": 3.1306,
67
+ "eval_samples_per_second": 545.257,
68
+ "eval_steps_per_second": 17.249,
69
+ "step": 642
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 2140,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 10,
76
+ "save_steps": 500,
77
+ "total_flos": 1574326993320.0,
78
+ "train_batch_size": 32,
79
+ "trial_name": null,
80
+ "trial_params": {
81
+ "alpha": 0.7874456347292355,
82
+ "learning_rate": 0.0002299443680036838,
83
+ "num_train_epochs": 10,
84
+ "temperature": 21
85
+ }
86
+ }
run-46/checkpoint-642/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:307030bbc71a6f7602dc49f4dcc76f8982a5d3ad58f9330b26fd83847b7540d2
3
+ size 5048
run-46/checkpoint-642/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-46/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-46/checkpoint-856/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:059bf2521fa0900ea633225ebdff71ffcde95da746c5ada21b471b55b8fe8492
3
+ size 17549312
run-46/checkpoint-856/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de0d354de1a0bcbaec849fad9494626f6615101ebeec71bd2605ae840b0ad593
3
+ size 35123898
run-46/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-46/checkpoint-856/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:261e13a08de453e753145656cc1f1f0a9948c22a45647683efd11fb5f96517f1
3
+ size 1064
run-46/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-46/checkpoint-856/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff