hassanalsawadi commited on
Commit
b72490d
·
verified ·
1 Parent(s): 0216268

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1721411579.f39e781deb18.907.1 +2 -2
  2. logs/events.out.tfevents.1721413326.f39e781deb18.907.2 +3 -0
  3. model.safetensors +1 -1
  4. run-0/checkpoint-1581/config.json +34 -0
  5. run-0/checkpoint-1581/model.safetensors +3 -0
  6. run-0/checkpoint-1581/optimizer.pt +3 -0
  7. run-0/checkpoint-1581/rng_state.pth +3 -0
  8. run-0/checkpoint-1581/scheduler.pt +3 -0
  9. run-0/checkpoint-1581/special_tokens_map.json +7 -0
  10. run-0/checkpoint-1581/tokenizer.json +0 -0
  11. run-0/checkpoint-1581/tokenizer_config.json +57 -0
  12. run-0/checkpoint-1581/trainer_state.json +86 -0
  13. run-0/checkpoint-1581/training_args.bin +3 -0
  14. run-0/checkpoint-1581/vocab.txt +0 -0
  15. run-0/checkpoint-5270/config.json +34 -0
  16. run-0/checkpoint-5270/model.safetensors +3 -0
  17. run-0/checkpoint-5270/optimizer.pt +3 -0
  18. run-0/checkpoint-5270/rng_state.pth +3 -0
  19. run-0/checkpoint-5270/scheduler.pt +3 -0
  20. run-0/checkpoint-5270/special_tokens_map.json +7 -0
  21. run-0/checkpoint-5270/tokenizer.json +0 -0
  22. run-0/checkpoint-5270/tokenizer_config.json +57 -0
  23. run-0/checkpoint-5270/trainer_state.json +198 -0
  24. run-0/checkpoint-5270/training_args.bin +3 -0
  25. run-0/checkpoint-5270/vocab.txt +0 -0
  26. run-1/checkpoint-527/config.json +34 -0
  27. run-1/checkpoint-527/model.safetensors +3 -0
  28. run-1/checkpoint-527/optimizer.pt +3 -0
  29. run-1/checkpoint-527/rng_state.pth +3 -0
  30. run-1/checkpoint-527/scheduler.pt +3 -0
  31. run-1/checkpoint-527/special_tokens_map.json +7 -0
  32. run-1/checkpoint-527/tokenizer.json +0 -0
  33. run-1/checkpoint-527/tokenizer_config.json +57 -0
  34. run-1/checkpoint-527/trainer_state.json +54 -0
  35. run-1/checkpoint-527/training_args.bin +3 -0
  36. run-1/checkpoint-527/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1721411579.f39e781deb18.907.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6fdbeb35295be360ca92ccbaa8e4925754e035beb6a2eb4c7dddbb33433a2af
3
- size 5987
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3618ec319a7e9b908c76a8bcbacfc968e25f455a06b40cdac4ba395b6119527c
3
+ size 10613
logs/events.out.tfevents.1721413326.f39e781deb18.907.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1901e1630ea5ac0582927008e830ca66ce45e78e0259f9a6f127c1e2c37121d0
3
+ size 5452
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d40eeef1c7a0af9f1e3a9cc121a9aec9856da1439dbd464e915aaee3805610d
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c06445438c5fb87316cd2cb4763f63bd612c65ec4ef79cea948ec831a22891e9
3
  size 17549312
run-0/checkpoint-1581/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": "4.42.4",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-0/checkpoint-1581/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:573963d8371d9a18b2dd1a69019285dd1736c54f0024d0703bf73356c8a5b8a1
3
+ size 17549312
run-0/checkpoint-1581/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc9d2a49972b2ce95a2c7d80cbe7ec404d933307d775f56758d73d71a219ab33
3
+ size 35123898
run-0/checkpoint-1581/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a82df51000915659b456ad52af3debde383df68929936f84f551af1b1989186
3
+ size 14308
run-0/checkpoint-1581/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:881e4329df5884153eea52d644b3b95c7200d1970354083cd7a4e411a2ac22bc
3
+ size 1064
run-0/checkpoint-1581/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-0/checkpoint-1581/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-1581/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-0/checkpoint-1581/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8348623853211009,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-1581",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1581,
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": 25.944990158081055,
14
+ "learning_rate": 0.0001902833119739952,
15
+ "loss": 1.3021,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8245412844036697,
21
+ "eval_loss": 1.3208283185958862,
22
+ "eval_runtime": 2.3956,
23
+ "eval_samples_per_second": 363.993,
24
+ "eval_steps_per_second": 2.922,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 19.690343856811523,
30
+ "learning_rate": 0.00016914072175466238,
31
+ "loss": 0.6063,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.823394495412844,
37
+ "eval_loss": 1.3363850116729736,
38
+ "eval_runtime": 2.4029,
39
+ "eval_samples_per_second": 362.895,
40
+ "eval_steps_per_second": 2.913,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 3.532933473587036,
46
+ "learning_rate": 0.00014799813153532957,
47
+ "loss": 0.4408,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8348623853211009,
53
+ "eval_loss": 1.334192156791687,
54
+ "eval_runtime": 2.4015,
55
+ "eval_samples_per_second": 363.104,
56
+ "eval_steps_per_second": 2.915,
57
+ "step": 1581
58
+ }
59
+ ],
60
+ "logging_steps": 500,
61
+ "max_steps": 5270,
62
+ "num_input_tokens_seen": 0,
63
+ "num_train_epochs": 10,
64
+ "save_steps": 500,
65
+ "stateful_callbacks": {
66
+ "TrainerControl": {
67
+ "args": {
68
+ "should_epoch_stop": false,
69
+ "should_evaluate": false,
70
+ "should_log": false,
71
+ "should_save": true,
72
+ "should_training_stop": false
73
+ },
74
+ "attributes": {}
75
+ }
76
+ },
77
+ "total_flos": 24228458327580.0,
78
+ "train_batch_size": 128,
79
+ "trial_name": null,
80
+ "trial_params": {
81
+ "alpha": 0.5044754522393149,
82
+ "learning_rate": 0.00021142590219332797,
83
+ "num_train_epochs": 10,
84
+ "temperature": 21
85
+ }
86
+ }
run-0/checkpoint-1581/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71ee3b8fabdace7b3b360bef47288e304ce46d525841a5824231251db0d68f07
3
+ size 5176
run-0/checkpoint-1581/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-5270/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": "4.42.4",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-0/checkpoint-5270/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff547420487a5a2580027ee6431243bd7ed613317e1edf71adea15813bbb30fc
3
+ size 17549312
run-0/checkpoint-5270/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:737e4e590de66da084187577c68f4f6da500d1ecf60c2b283c8c30e019029636
3
+ size 35123898
run-0/checkpoint-5270/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a825f14b66ba01ee141ce262529689c9881cb7d12dc65b93a897ba115df075eb
3
+ size 14308
run-0/checkpoint-5270/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:232178f1088ae7c50f614816320a83bb61f6c44278ea88c707954078f9d32d79
3
+ size 1064
run-0/checkpoint-5270/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-0/checkpoint-5270/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-5270/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-0/checkpoint-5270/trainer_state.json ADDED
@@ -0,0 +1,198 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8348623853211009,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-1581",
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5270,
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": 25.944990158081055,
14
+ "learning_rate": 0.0001902833119739952,
15
+ "loss": 1.3021,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8245412844036697,
21
+ "eval_loss": 1.3208283185958862,
22
+ "eval_runtime": 2.3956,
23
+ "eval_samples_per_second": 363.993,
24
+ "eval_steps_per_second": 2.922,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 19.690343856811523,
30
+ "learning_rate": 0.00016914072175466238,
31
+ "loss": 0.6063,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.823394495412844,
37
+ "eval_loss": 1.3363850116729736,
38
+ "eval_runtime": 2.4029,
39
+ "eval_samples_per_second": 362.895,
40
+ "eval_steps_per_second": 2.913,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 3.532933473587036,
46
+ "learning_rate": 0.00014799813153532957,
47
+ "loss": 0.4408,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8348623853211009,
53
+ "eval_loss": 1.334192156791687,
54
+ "eval_runtime": 2.4015,
55
+ "eval_samples_per_second": 363.104,
56
+ "eval_steps_per_second": 2.915,
57
+ "step": 1581
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 7.432313919067383,
62
+ "learning_rate": 0.00012685554131599677,
63
+ "loss": 0.3482,
64
+ "step": 2108
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.8268348623853211,
69
+ "eval_loss": 1.40156090259552,
70
+ "eval_runtime": 2.4103,
71
+ "eval_samples_per_second": 361.775,
72
+ "eval_steps_per_second": 2.904,
73
+ "step": 2108
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 6.922064781188965,
78
+ "learning_rate": 0.00010571295109666398,
79
+ "loss": 0.2898,
80
+ "step": 2635
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_accuracy": 0.8222477064220184,
85
+ "eval_loss": 1.4034457206726074,
86
+ "eval_runtime": 2.3977,
87
+ "eval_samples_per_second": 363.677,
88
+ "eval_steps_per_second": 2.919,
89
+ "step": 2635
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "grad_norm": 4.356622219085693,
94
+ "learning_rate": 8.457036087733119e-05,
95
+ "loss": 0.2454,
96
+ "step": 3162
97
+ },
98
+ {
99
+ "epoch": 6.0,
100
+ "eval_accuracy": 0.8153669724770642,
101
+ "eval_loss": 1.4904314279556274,
102
+ "eval_runtime": 2.3935,
103
+ "eval_samples_per_second": 364.316,
104
+ "eval_steps_per_second": 2.925,
105
+ "step": 3162
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "grad_norm": 7.468222141265869,
110
+ "learning_rate": 6.342777065799838e-05,
111
+ "loss": 0.2182,
112
+ "step": 3689
113
+ },
114
+ {
115
+ "epoch": 7.0,
116
+ "eval_accuracy": 0.8268348623853211,
117
+ "eval_loss": 1.485904335975647,
118
+ "eval_runtime": 2.4024,
119
+ "eval_samples_per_second": 362.976,
120
+ "eval_steps_per_second": 2.914,
121
+ "step": 3689
122
+ },
123
+ {
124
+ "epoch": 8.0,
125
+ "grad_norm": 12.38081169128418,
126
+ "learning_rate": 4.2325299205685204e-05,
127
+ "loss": 0.1996,
128
+ "step": 4216
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_accuracy": 0.8222477064220184,
133
+ "eval_loss": 1.467812180519104,
134
+ "eval_runtime": 2.4062,
135
+ "eval_samples_per_second": 362.398,
136
+ "eval_steps_per_second": 2.909,
137
+ "step": 4216
138
+ },
139
+ {
140
+ "epoch": 9.0,
141
+ "grad_norm": 11.503551483154297,
142
+ "learning_rate": 2.1182708986352403e-05,
143
+ "loss": 0.1824,
144
+ "step": 4743
145
+ },
146
+ {
147
+ "epoch": 9.0,
148
+ "eval_accuracy": 0.823394495412844,
149
+ "eval_loss": 1.4659483432769775,
150
+ "eval_runtime": 2.4027,
151
+ "eval_samples_per_second": 362.928,
152
+ "eval_steps_per_second": 2.913,
153
+ "step": 4743
154
+ },
155
+ {
156
+ "epoch": 10.0,
157
+ "grad_norm": 4.441977024078369,
158
+ "learning_rate": 4.0118767019606826e-08,
159
+ "loss": 0.1725,
160
+ "step": 5270
161
+ },
162
+ {
163
+ "epoch": 10.0,
164
+ "eval_accuracy": 0.8222477064220184,
165
+ "eval_loss": 1.4608328342437744,
166
+ "eval_runtime": 2.3933,
167
+ "eval_samples_per_second": 364.358,
168
+ "eval_steps_per_second": 2.925,
169
+ "step": 5270
170
+ }
171
+ ],
172
+ "logging_steps": 500,
173
+ "max_steps": 5270,
174
+ "num_input_tokens_seen": 0,
175
+ "num_train_epochs": 10,
176
+ "save_steps": 500,
177
+ "stateful_callbacks": {
178
+ "TrainerControl": {
179
+ "args": {
180
+ "should_epoch_stop": false,
181
+ "should_evaluate": false,
182
+ "should_log": false,
183
+ "should_save": true,
184
+ "should_training_stop": true
185
+ },
186
+ "attributes": {}
187
+ }
188
+ },
189
+ "total_flos": 80830646058420.0,
190
+ "train_batch_size": 128,
191
+ "trial_name": null,
192
+ "trial_params": {
193
+ "alpha": 0.5044754522393149,
194
+ "learning_rate": 0.00021142590219332797,
195
+ "num_train_epochs": 10,
196
+ "temperature": 21
197
+ }
198
+ }
run-0/checkpoint-5270/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71ee3b8fabdace7b3b360bef47288e304ce46d525841a5824231251db0d68f07
3
+ size 5176
run-0/checkpoint-5270/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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": "4.42.4",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-1/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c06445438c5fb87316cd2cb4763f63bd612c65ec4ef79cea948ec831a22891e9
3
+ size 17549312
run-1/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c1a77daca698f2c632e2ca52934e62f4cc4848a3cc123f5ab228264ffa93d2c
3
+ size 35123898
run-1/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9733f27bb728718f7284348156186daf975855376673d9de7e218a8cff476307
3
+ size 14308
run-1/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52fd14ddaec379b5ff7e150097543d4f2f09f45826937a82c3d6213b76f42511
3
+ size 1064
run-1/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-1/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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-1/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7889908256880734,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/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": 26.40542221069336,
14
+ "learning_rate": 3.516452480363675e-05,
15
+ "loss": 2.3632,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7889908256880734,
21
+ "eval_loss": 1.7152718305587769,
22
+ "eval_runtime": 2.397,
23
+ "eval_samples_per_second": 363.793,
24
+ "eval_steps_per_second": 2.92,
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
+ "stateful_callbacks": {
34
+ "TrainerControl": {
35
+ "args": {
36
+ "should_epoch_stop": false,
37
+ "should_evaluate": false,
38
+ "should_log": false,
39
+ "should_save": true,
40
+ "should_training_stop": false
41
+ },
42
+ "attributes": {}
43
+ }
44
+ },
45
+ "total_flos": 8057768762220.0,
46
+ "train_batch_size": 128,
47
+ "trial_name": null,
48
+ "trial_params": {
49
+ "alpha": 0.33033463277200115,
50
+ "learning_rate": 4.6886033071515664e-05,
51
+ "num_train_epochs": 4,
52
+ "temperature": 7
53
+ }
54
+ }
run-1/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27f7862bbe76809bc2a140ac76310c7af1b9d469f8a70696e0761dae4b091b3b
3
+ size 5176
run-1/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 sha256:71ee3b8fabdace7b3b360bef47288e304ce46d525841a5824231251db0d68f07
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27f7862bbe76809bc2a140ac76310c7af1b9d469f8a70696e0761dae4b091b3b
3
  size 5176