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
4994314
·
verified ·
1 Parent(s): 92b0bf9

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1709617962.404ecd1cf399.26000.7 +2 -2
  2. logs/events.out.tfevents.1709618554.404ecd1cf399.26000.8 +3 -0
  3. model.safetensors +1 -1
  4. run-1/checkpoint-384/config.json +34 -0
  5. run-1/checkpoint-384/model.safetensors +3 -0
  6. run-1/checkpoint-384/optimizer.pt +3 -0
  7. run-1/checkpoint-384/rng_state.pth +3 -0
  8. run-1/checkpoint-384/scheduler.pt +3 -0
  9. run-1/checkpoint-384/special_tokens_map.json +7 -0
  10. run-1/checkpoint-384/tokenizer.json +0 -0
  11. run-1/checkpoint-384/tokenizer_config.json +57 -0
  12. run-1/checkpoint-384/trainer_state.json +102 -0
  13. run-1/checkpoint-384/training_args.bin +3 -0
  14. run-1/checkpoint-384/vocab.txt +0 -0
  15. run-1/checkpoint-480/config.json +34 -0
  16. run-1/checkpoint-480/model.safetensors +3 -0
  17. run-1/checkpoint-480/optimizer.pt +3 -0
  18. run-1/checkpoint-480/rng_state.pth +3 -0
  19. run-1/checkpoint-480/scheduler.pt +3 -0
  20. run-1/checkpoint-480/special_tokens_map.json +7 -0
  21. run-1/checkpoint-480/tokenizer.json +0 -0
  22. run-1/checkpoint-480/tokenizer_config.json +57 -0
  23. run-1/checkpoint-480/trainer_state.json +121 -0
  24. run-1/checkpoint-480/training_args.bin +3 -0
  25. run-1/checkpoint-480/vocab.txt +0 -0
  26. run-2/checkpoint-96/config.json +34 -0
  27. run-2/checkpoint-96/model.safetensors +3 -0
  28. run-2/checkpoint-96/optimizer.pt +3 -0
  29. run-2/checkpoint-96/rng_state.pth +3 -0
  30. run-2/checkpoint-96/scheduler.pt +3 -0
  31. run-2/checkpoint-96/special_tokens_map.json +7 -0
  32. run-2/checkpoint-96/tokenizer.json +0 -0
  33. run-2/checkpoint-96/tokenizer_config.json +57 -0
  34. run-2/checkpoint-96/trainer_state.json +45 -0
  35. run-2/checkpoint-96/training_args.bin +3 -0
  36. run-2/checkpoint-96/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1709617962.404ecd1cf399.26000.7 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83c010591937d098f05e0b1960add24e8e6df5d090fc6659f34e6895e011bb7c
3
- size 5998
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63a1eab9e4171fae7b27211f8b79337498355e38ea8c2576d80c4e1c93098eab
3
+ size 8401
logs/events.out.tfevents.1709618554.404ecd1cf399.26000.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ed1240ba3a3fa092df3a66529d65df5df5563475335a76c17c7c70e2ab80207
3
+ size 5315
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8190e7a62027cce295082d46e30653021a51c5c5bb818e91fd983f5e1473ef8d
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13d9e3c5574fdd7a017d1ca3a56705f207b41a4f67b51080f14f316154309de5
3
  size 17549312
run-1/checkpoint-384/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-1/checkpoint-384/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:599ce20d16ae858c6ea5c4c6394afae3c6a54d089921643934771b92efef5da9
3
+ size 17549312
run-1/checkpoint-384/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff83fffdf6e9eb36130cc77fe371a04494d2b7aa5a6970c1d7d60ca3edded5c6
3
+ size 35122746
run-1/checkpoint-384/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45b1fc07ed8b121716021ec87c686f1cd9c3b89c82ea08a6a0792d47a39077c9
3
+ size 14054
run-1/checkpoint-384/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec21489740ab058e708d6188bdd979b6f04f1e5c8145a4c2c7342f35397725ee
3
+ size 1064
run-1/checkpoint-384/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-384/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-384/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-384/trainer_state.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8199608610567515,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-288",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 384,
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": 1.4932310581207275,
14
+ "learning_rate": 0.00022974033046670533,
15
+ "loss": 0.4667,
16
+ "step": 96
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7651663405088063,
21
+ "eval_f1": 0.7701149425287357,
22
+ "eval_loss": 0.4088786244392395,
23
+ "eval_precision": 0.7542213883677298,
24
+ "eval_recall": 0.786692759295499,
25
+ "eval_runtime": 30.971,
26
+ "eval_samples_per_second": 32.999,
27
+ "eval_steps_per_second": 1.033,
28
+ "step": 96
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 2.3421308994293213,
33
+ "learning_rate": 0.00017230524785002898,
34
+ "loss": 0.4108,
35
+ "step": 192
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.8052837573385518,
40
+ "eval_f1": 0.8202348690153567,
41
+ "eval_loss": 0.39227691292762756,
42
+ "eval_precision": 0.761744966442953,
43
+ "eval_recall": 0.8884540117416829,
44
+ "eval_runtime": 30.7242,
45
+ "eval_samples_per_second": 33.264,
46
+ "eval_steps_per_second": 1.042,
47
+ "step": 192
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 2.60581374168396,
52
+ "learning_rate": 0.00011487016523335267,
53
+ "loss": 0.3914,
54
+ "step": 288
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8199608610567515,
59
+ "eval_f1": 0.8318098720292504,
60
+ "eval_loss": 0.38357415795326233,
61
+ "eval_precision": 0.7804459691252144,
62
+ "eval_recall": 0.8904109589041096,
63
+ "eval_runtime": 32.3837,
64
+ "eval_samples_per_second": 31.559,
65
+ "eval_steps_per_second": 0.988,
66
+ "step": 288
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 3.155740737915039,
71
+ "learning_rate": 5.743508261667633e-05,
72
+ "loss": 0.3802,
73
+ "step": 384
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.8160469667318982,
78
+ "eval_f1": 0.8160469667318982,
79
+ "eval_loss": 0.37758293747901917,
80
+ "eval_precision": 0.8160469667318982,
81
+ "eval_recall": 0.8160469667318982,
82
+ "eval_runtime": 30.8515,
83
+ "eval_samples_per_second": 33.126,
84
+ "eval_steps_per_second": 1.037,
85
+ "step": 384
86
+ }
87
+ ],
88
+ "logging_steps": 500,
89
+ "max_steps": 480,
90
+ "num_input_tokens_seen": 0,
91
+ "num_train_epochs": 5,
92
+ "save_steps": 500,
93
+ "total_flos": 942780789120.0,
94
+ "train_batch_size": 32,
95
+ "trial_name": null,
96
+ "trial_params": {
97
+ "alpha": 0.6818846524061118,
98
+ "learning_rate": 0.00028717541308338166,
99
+ "num_train_epochs": 5,
100
+ "temperature": 29
101
+ }
102
+ }
run-1/checkpoint-384/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:793b34e056c09ac6895e4854810a5a38ad5f7e4ea7bfcdaf2571ad59272936ff
3
+ size 4920
run-1/checkpoint-384/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-480/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-1/checkpoint-480/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:847df229a7ca0cb4095cbd280d7c3c672c7e4ee9114fc1bc359491abd2ab3ffb
3
+ size 17549312
run-1/checkpoint-480/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f70ab8c31ca18dfb957c1ba52f19a90faf43d594db85a5dde58bb6f884e93a5
3
+ size 35122746
run-1/checkpoint-480/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d93f4cfe67413cd27374342b3b9f13806d5fb593a9dc59106a8b24dedb590a8
3
+ size 14054
run-1/checkpoint-480/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9df0e59ca0915eb128e8de1597a625689a2ef7a8993192bedb8693c0c8a3fdb2
3
+ size 1064
run-1/checkpoint-480/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-480/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-480/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-480/trainer_state.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8277886497064579,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-480",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 480,
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": 1.4932310581207275,
14
+ "learning_rate": 0.00022974033046670533,
15
+ "loss": 0.4667,
16
+ "step": 96
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7651663405088063,
21
+ "eval_f1": 0.7701149425287357,
22
+ "eval_loss": 0.4088786244392395,
23
+ "eval_precision": 0.7542213883677298,
24
+ "eval_recall": 0.786692759295499,
25
+ "eval_runtime": 30.971,
26
+ "eval_samples_per_second": 32.999,
27
+ "eval_steps_per_second": 1.033,
28
+ "step": 96
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 2.3421308994293213,
33
+ "learning_rate": 0.00017230524785002898,
34
+ "loss": 0.4108,
35
+ "step": 192
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.8052837573385518,
40
+ "eval_f1": 0.8202348690153567,
41
+ "eval_loss": 0.39227691292762756,
42
+ "eval_precision": 0.761744966442953,
43
+ "eval_recall": 0.8884540117416829,
44
+ "eval_runtime": 30.7242,
45
+ "eval_samples_per_second": 33.264,
46
+ "eval_steps_per_second": 1.042,
47
+ "step": 192
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 2.60581374168396,
52
+ "learning_rate": 0.00011487016523335267,
53
+ "loss": 0.3914,
54
+ "step": 288
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8199608610567515,
59
+ "eval_f1": 0.8318098720292504,
60
+ "eval_loss": 0.38357415795326233,
61
+ "eval_precision": 0.7804459691252144,
62
+ "eval_recall": 0.8904109589041096,
63
+ "eval_runtime": 32.3837,
64
+ "eval_samples_per_second": 31.559,
65
+ "eval_steps_per_second": 0.988,
66
+ "step": 288
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 3.155740737915039,
71
+ "learning_rate": 5.743508261667633e-05,
72
+ "loss": 0.3802,
73
+ "step": 384
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.8160469667318982,
78
+ "eval_f1": 0.8160469667318982,
79
+ "eval_loss": 0.37758293747901917,
80
+ "eval_precision": 0.8160469667318982,
81
+ "eval_recall": 0.8160469667318982,
82
+ "eval_runtime": 30.8515,
83
+ "eval_samples_per_second": 33.126,
84
+ "eval_steps_per_second": 1.037,
85
+ "step": 384
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 0.9643956422805786,
90
+ "learning_rate": 0.0,
91
+ "loss": 0.3716,
92
+ "step": 480
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.8277886497064579,
97
+ "eval_f1": 0.8367346938775511,
98
+ "eval_loss": 0.37470024824142456,
99
+ "eval_precision": 0.7954144620811288,
100
+ "eval_recall": 0.8825831702544031,
101
+ "eval_runtime": 31.628,
102
+ "eval_samples_per_second": 32.313,
103
+ "eval_steps_per_second": 1.012,
104
+ "step": 480
105
+ }
106
+ ],
107
+ "logging_steps": 500,
108
+ "max_steps": 480,
109
+ "num_input_tokens_seen": 0,
110
+ "num_train_epochs": 5,
111
+ "save_steps": 500,
112
+ "total_flos": 1178475986400.0,
113
+ "train_batch_size": 32,
114
+ "trial_name": null,
115
+ "trial_params": {
116
+ "alpha": 0.6818846524061118,
117
+ "learning_rate": 0.00028717541308338166,
118
+ "num_train_epochs": 5,
119
+ "temperature": 29
120
+ }
121
+ }
run-1/checkpoint-480/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:793b34e056c09ac6895e4854810a5a38ad5f7e4ea7bfcdaf2571ad59272936ff
3
+ size 4920
run-1/checkpoint-480/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-96/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-2/checkpoint-96/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13d9e3c5574fdd7a017d1ca3a56705f207b41a4f67b51080f14f316154309de5
3
+ size 17549312
run-2/checkpoint-96/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a252a632d5c67eb44cc758aec3453239907af0eb9827c9db8997964e99a1497e
3
+ size 35122746
run-2/checkpoint-96/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24aa86019b8aea1c551cc1adaf38c4db2fc01de75a22af312230f6b592e0fd81
3
+ size 14054
run-2/checkpoint-96/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e39e4e51c9494499a8a1409f7d0ed6917d746011c4d044f5d8241946c2a360ac
3
+ size 1064
run-2/checkpoint-96/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-2/checkpoint-96/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-96/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-2/checkpoint-96/trainer_state.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7837573385518591,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-96",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 96,
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": 1.613167643547058,
14
+ "learning_rate": 0.00027081825418014463,
15
+ "loss": 0.516,
16
+ "step": 96
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7837573385518591,
21
+ "eval_f1": 0.8073234524847429,
22
+ "eval_loss": 0.44109782576560974,
23
+ "eval_precision": 0.7279874213836478,
24
+ "eval_recall": 0.9060665362035225,
25
+ "eval_runtime": 31.7637,
26
+ "eval_samples_per_second": 32.175,
27
+ "eval_steps_per_second": 1.007,
28
+ "step": 96
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 288,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 3,
35
+ "save_steps": 500,
36
+ "total_flos": 235695197280.0,
37
+ "train_batch_size": 32,
38
+ "trial_name": null,
39
+ "trial_params": {
40
+ "alpha": 0.7853139256228429,
41
+ "learning_rate": 0.00040622738127021695,
42
+ "num_train_epochs": 3,
43
+ "temperature": 5
44
+ }
45
+ }
run-2/checkpoint-96/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0762669f3cc0b738504b8520ffeb23dad59a4047901db16223a1552e162134
3
+ size 4920
run-2/checkpoint-96/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 sha256:793b34e056c09ac6895e4854810a5a38ad5f7e4ea7bfcdaf2571ad59272936ff
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0762669f3cc0b738504b8520ffeb23dad59a4047901db16223a1552e162134
3
  size 4920