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
ccc2492
·
verified ·
1 Parent(s): f367877

Training in progress, epoch 1

Browse files
Files changed (38) hide show
  1. logs/events.out.tfevents.1713438345.ec9626078864.14834.23 +2 -2
  2. logs/events.out.tfevents.1713438611.ec9626078864.14834.24 +3 -0
  3. logs/events.out.tfevents.1713438663.ec9626078864.14834.25 +3 -0
  4. model.safetensors +1 -1
  5. run-22/checkpoint-2580/config.json +34 -0
  6. run-22/checkpoint-2580/model.safetensors +3 -0
  7. run-22/checkpoint-2580/optimizer.pt +3 -0
  8. run-22/checkpoint-2580/rng_state.pth +3 -0
  9. run-22/checkpoint-2580/scheduler.pt +3 -0
  10. run-22/checkpoint-2580/special_tokens_map.json +7 -0
  11. run-22/checkpoint-2580/tokenizer.json +0 -0
  12. run-22/checkpoint-2580/tokenizer_config.json +57 -0
  13. run-22/checkpoint-2580/trainer_state.json +106 -0
  14. run-22/checkpoint-2580/training_args.bin +3 -0
  15. run-22/checkpoint-2580/vocab.txt +0 -0
  16. run-22/checkpoint-3225/config.json +34 -0
  17. run-22/checkpoint-3225/model.safetensors +3 -0
  18. run-22/checkpoint-3225/optimizer.pt +3 -0
  19. run-22/checkpoint-3225/rng_state.pth +3 -0
  20. run-22/checkpoint-3225/scheduler.pt +3 -0
  21. run-22/checkpoint-3225/special_tokens_map.json +7 -0
  22. run-22/checkpoint-3225/tokenizer.json +0 -0
  23. run-22/checkpoint-3225/tokenizer_config.json +57 -0
  24. run-22/checkpoint-3225/trainer_state.json +126 -0
  25. run-22/checkpoint-3225/training_args.bin +3 -0
  26. run-22/checkpoint-3225/vocab.txt +0 -0
  27. run-24/checkpoint-645/config.json +34 -0
  28. run-24/checkpoint-645/model.safetensors +3 -0
  29. run-24/checkpoint-645/optimizer.pt +3 -0
  30. run-24/checkpoint-645/rng_state.pth +3 -0
  31. run-24/checkpoint-645/scheduler.pt +3 -0
  32. run-24/checkpoint-645/special_tokens_map.json +7 -0
  33. run-24/checkpoint-645/tokenizer.json +0 -0
  34. run-24/checkpoint-645/tokenizer_config.json +57 -0
  35. run-24/checkpoint-645/trainer_state.json +46 -0
  36. run-24/checkpoint-645/training_args.bin +3 -0
  37. run-24/checkpoint-645/vocab.txt +0 -0
  38. training_args.bin +1 -1
logs/events.out.tfevents.1713438345.ec9626078864.14834.23 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e649642e17a78fdac6d5c568dbc2bd3296a4b92d86cee5877d1cbd7bc811b24b
3
- size 6137
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a057af2fc9ab85956ff456027f5f309b20b12ee0c375ea60894b5be8fad8015
3
+ size 8681
logs/events.out.tfevents.1713438611.ec9626078864.14834.24 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aae85f4cb52e41e0b8f78fab529dbed2817b0e09f86b7139cbc22fdc24fd15e8
3
+ size 5407
logs/events.out.tfevents.1713438663.ec9626078864.14834.25 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5164fe9ff1c3479c74443d245857d81a71e234f26d7de5347dae946f3be62c8
3
+ size 5406
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa3fcc93cda8084c0dc3d735fb7d21e507af573161e7b05204f7b8f74510d918
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae878e89ffd1c421171b279fea59f664c2c3fecd5c19cac9c9978ea09dcd292
3
  size 17549312
run-22/checkpoint-2580/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": "4.39.3",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-22/checkpoint-2580/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f978388f98439a4b44ed0f6b3a833bddef9fa6a800e1c4e72cb14146f7f0dd0
3
+ size 17549312
run-22/checkpoint-2580/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7675d8055553d90c88853abb983c365044a7d898236acc2d8be64b35e85e21d6
3
+ size 35123898
run-22/checkpoint-2580/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a023a654d9d331ee734f6327c4a0681d27975c593b68916f513cbf43ea84370
3
+ size 14308
run-22/checkpoint-2580/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50913474c389078540414080506b8046e5d65649fadd8b1474cd0a3839f6d3c5
3
+ size 1064
run-22/checkpoint-2580/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-22/checkpoint-2580/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-22/checkpoint-2580/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-22/checkpoint-2580/trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8997673516867003,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-22/checkpoint-1290",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2580,
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": 2.1603200435638428,
14
+ "learning_rate": 0.00015804016249699036,
15
+ "loss": 0.3253,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8945327646374563,
21
+ "eval_f1": 0.19047619047619047,
22
+ "eval_loss": 0.29357558488845825,
23
+ "eval_mcc": 0.23285387927696083,
24
+ "eval_precision": 0.6213592233009708,
25
+ "eval_recall": 0.11247803163444639,
26
+ "eval_runtime": 9.9704,
27
+ "eval_samples_per_second": 517.33,
28
+ "eval_steps_per_second": 16.248,
29
+ "step": 645
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.3251060247421265,
34
+ "learning_rate": 0.00011853012187274275,
35
+ "loss": 0.2915,
36
+ "step": 1290
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.8997673516867003,
41
+ "eval_f1": 0.2385861561119293,
42
+ "eval_loss": 0.2915143072605133,
43
+ "eval_mcc": 0.2949928981799802,
44
+ "eval_precision": 0.7363636363636363,
45
+ "eval_recall": 0.14235500878734622,
46
+ "eval_runtime": 9.9347,
47
+ "eval_samples_per_second": 519.192,
48
+ "eval_steps_per_second": 16.307,
49
+ "step": 1290
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.1212515830993652,
54
+ "learning_rate": 7.902008124849518e-05,
55
+ "loss": 0.278,
56
+ "step": 1935
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.8993796044978674,
61
+ "eval_f1": 0.23111111111111113,
62
+ "eval_loss": 0.27244821190834045,
63
+ "eval_mcc": 0.28922713720674353,
64
+ "eval_precision": 0.7358490566037735,
65
+ "eval_recall": 0.13708260105448156,
66
+ "eval_runtime": 9.947,
67
+ "eval_samples_per_second": 518.549,
68
+ "eval_steps_per_second": 16.286,
69
+ "step": 1935
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 2.8891263008117676,
74
+ "learning_rate": 3.951004062424759e-05,
75
+ "loss": 0.2694,
76
+ "step": 2580
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.8984102365257852,
81
+ "eval_f1": 0.34825870646766166,
82
+ "eval_loss": 0.26875007152557373,
83
+ "eval_mcc": 0.338541834655946,
84
+ "eval_precision": 0.5957446808510638,
85
+ "eval_recall": 0.2460456942003515,
86
+ "eval_runtime": 9.9622,
87
+ "eval_samples_per_second": 517.756,
88
+ "eval_steps_per_second": 16.261,
89
+ "step": 2580
90
+ }
91
+ ],
92
+ "logging_steps": 500,
93
+ "max_steps": 3225,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 5,
96
+ "save_steps": 500,
97
+ "total_flos": 6347770130400.0,
98
+ "train_batch_size": 32,
99
+ "trial_name": null,
100
+ "trial_params": {
101
+ "alpha": 0.9879592289455201,
102
+ "learning_rate": 0.00019755020312123793,
103
+ "num_train_epochs": 5,
104
+ "temperature": 26
105
+ }
106
+ }
run-22/checkpoint-2580/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:463d23df8f476e3af460c3bc4425d71e9123ebed51ff3120d6a6683ba8684432
3
+ size 4984
run-22/checkpoint-2580/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-22/checkpoint-3225/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": "4.39.3",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-22/checkpoint-3225/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbd445fc9b95f724be40179971176cf23d19a5b3ae00fba5dc3022a95d6e8841
3
+ size 17549312
run-22/checkpoint-3225/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c17e4e867b821818079629cb702b3a148b5c130b43eec3e7bc9ad029270a03f3
3
+ size 35123898
run-22/checkpoint-3225/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6303d047155f3543a5a16a3524b9e783dc242e14523f52e867381087cb66480
3
+ size 14308
run-22/checkpoint-3225/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7500b3d2e1d5fcb03227a89693b178e40e0c137c27d6d3362185c7743d08fb8
3
+ size 1064
run-22/checkpoint-3225/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-22/checkpoint-3225/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-22/checkpoint-3225/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-22/checkpoint-3225/trainer_state.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9001550988755331,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-22/checkpoint-3225",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3225,
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": 2.1603200435638428,
14
+ "learning_rate": 0.00015804016249699036,
15
+ "loss": 0.3253,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8945327646374563,
21
+ "eval_f1": 0.19047619047619047,
22
+ "eval_loss": 0.29357558488845825,
23
+ "eval_mcc": 0.23285387927696083,
24
+ "eval_precision": 0.6213592233009708,
25
+ "eval_recall": 0.11247803163444639,
26
+ "eval_runtime": 9.9704,
27
+ "eval_samples_per_second": 517.33,
28
+ "eval_steps_per_second": 16.248,
29
+ "step": 645
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.3251060247421265,
34
+ "learning_rate": 0.00011853012187274275,
35
+ "loss": 0.2915,
36
+ "step": 1290
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.8997673516867003,
41
+ "eval_f1": 0.2385861561119293,
42
+ "eval_loss": 0.2915143072605133,
43
+ "eval_mcc": 0.2949928981799802,
44
+ "eval_precision": 0.7363636363636363,
45
+ "eval_recall": 0.14235500878734622,
46
+ "eval_runtime": 9.9347,
47
+ "eval_samples_per_second": 519.192,
48
+ "eval_steps_per_second": 16.307,
49
+ "step": 1290
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.1212515830993652,
54
+ "learning_rate": 7.902008124849518e-05,
55
+ "loss": 0.278,
56
+ "step": 1935
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.8993796044978674,
61
+ "eval_f1": 0.23111111111111113,
62
+ "eval_loss": 0.27244821190834045,
63
+ "eval_mcc": 0.28922713720674353,
64
+ "eval_precision": 0.7358490566037735,
65
+ "eval_recall": 0.13708260105448156,
66
+ "eval_runtime": 9.947,
67
+ "eval_samples_per_second": 518.549,
68
+ "eval_steps_per_second": 16.286,
69
+ "step": 1935
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 2.8891263008117676,
74
+ "learning_rate": 3.951004062424759e-05,
75
+ "loss": 0.2694,
76
+ "step": 2580
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.8984102365257852,
81
+ "eval_f1": 0.34825870646766166,
82
+ "eval_loss": 0.26875007152557373,
83
+ "eval_mcc": 0.338541834655946,
84
+ "eval_precision": 0.5957446808510638,
85
+ "eval_recall": 0.2460456942003515,
86
+ "eval_runtime": 9.9622,
87
+ "eval_samples_per_second": 517.756,
88
+ "eval_steps_per_second": 16.261,
89
+ "step": 2580
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 1.3928107023239136,
94
+ "learning_rate": 0.0,
95
+ "loss": 0.2634,
96
+ "step": 3225
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.9001550988755331,
101
+ "eval_f1": 0.3160690571049136,
102
+ "eval_loss": 0.2647700905799866,
103
+ "eval_mcc": 0.32932996755742344,
104
+ "eval_precision": 0.6467391304347826,
105
+ "eval_recall": 0.20913884007029876,
106
+ "eval_runtime": 9.9395,
107
+ "eval_samples_per_second": 518.939,
108
+ "eval_steps_per_second": 16.299,
109
+ "step": 3225
110
+ }
111
+ ],
112
+ "logging_steps": 500,
113
+ "max_steps": 3225,
114
+ "num_input_tokens_seen": 0,
115
+ "num_train_epochs": 5,
116
+ "save_steps": 500,
117
+ "total_flos": 7934712663000.0,
118
+ "train_batch_size": 32,
119
+ "trial_name": null,
120
+ "trial_params": {
121
+ "alpha": 0.9879592289455201,
122
+ "learning_rate": 0.00019755020312123793,
123
+ "num_train_epochs": 5,
124
+ "temperature": 26
125
+ }
126
+ }
run-22/checkpoint-3225/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:463d23df8f476e3af460c3bc4425d71e9123ebed51ff3120d6a6683ba8684432
3
+ size 4984
run-22/checkpoint-3225/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-24/checkpoint-645/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": "4.39.3",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-24/checkpoint-645/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae878e89ffd1c421171b279fea59f664c2c3fecd5c19cac9c9978ea09dcd292
3
+ size 17549312
run-24/checkpoint-645/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3eaf09c0f5bb64b5471ec3ab967af3fbf67b3dc8dc30a5490d600ffd2ab41c8
3
+ size 35123898
run-24/checkpoint-645/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f64cda8af0c2d214cf65bdf171fde38f18025a5a08f9a451c61fdf726867d7c2
3
+ size 14308
run-24/checkpoint-645/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60217fe2e4ca30b94e2652e28897b62a92eb49ee501ae2760898ff5e28a70bdf
3
+ size 1064
run-24/checkpoint-645/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-24/checkpoint-645/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-24/checkpoint-645/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-24/checkpoint-645/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8937572702597906,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-24/checkpoint-645",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 645,
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": 1.1594387292861938,
14
+ "learning_rate": 0.0003669096859466192,
15
+ "loss": 0.3104,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8937572702597906,
21
+ "eval_f1": 0.17717717717717715,
22
+ "eval_loss": 0.29782024025917053,
23
+ "eval_mcc": 0.22004174832122259,
24
+ "eval_precision": 0.6082474226804123,
25
+ "eval_recall": 0.10369068541300527,
26
+ "eval_runtime": 9.922,
27
+ "eval_samples_per_second": 519.854,
28
+ "eval_steps_per_second": 16.327,
29
+ "step": 645
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 5805,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 9,
36
+ "save_steps": 500,
37
+ "total_flos": 1586942532600.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.8984215980104533,
42
+ "learning_rate": 0.0004127733966899466,
43
+ "num_train_epochs": 9,
44
+ "temperature": 29
45
+ }
46
+ }
run-24/checkpoint-645/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:456127f7769e7956edafc511b28db8949081a7bcc64e2dae6a89559f359d58a4
3
+ size 4984
run-24/checkpoint-645/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 sha256:463d23df8f476e3af460c3bc4425d71e9123ebed51ff3120d6a6683ba8684432
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:456127f7769e7956edafc511b28db8949081a7bcc64e2dae6a89559f359d58a4
3
  size 4984