Hugging Face's logo

jysh1023
/
tiny-bert-sst2-distilled

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
bert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
Metrics Community
jysh1023 commited on
Commit
8740fda
·
1 Parent(s): 7d30645

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1699948806.45c71320b2c6.349.3 +2 -2
  2. logs/events.out.tfevents.1699949278.45c71320b2c6.349.4 +3 -0
  3. model.safetensors +1 -1
  4. run-2/checkpoint-2635/config.json +34 -0
  5. run-2/checkpoint-2635/model.safetensors +3 -0
  6. run-2/checkpoint-2635/optimizer.pt +3 -0
  7. run-2/checkpoint-2635/rng_state.pth +3 -0
  8. run-2/checkpoint-2635/scheduler.pt +3 -0
  9. run-2/checkpoint-2635/special_tokens_map.json +7 -0
  10. run-2/checkpoint-2635/tokenizer.json +0 -0
  11. run-2/checkpoint-2635/tokenizer_config.json +57 -0
  12. run-2/checkpoint-2635/trainer_state.json +99 -0
  13. run-2/checkpoint-2635/training_args.bin +3 -0
  14. run-2/checkpoint-2635/vocab.txt +0 -0
  15. run-2/checkpoint-3689/config.json +34 -0
  16. run-2/checkpoint-3689/model.safetensors +3 -0
  17. run-2/checkpoint-3689/optimizer.pt +3 -0
  18. run-2/checkpoint-3689/rng_state.pth +3 -0
  19. run-2/checkpoint-3689/scheduler.pt +3 -0
  20. run-2/checkpoint-3689/special_tokens_map.json +7 -0
  21. run-2/checkpoint-3689/tokenizer.json +0 -0
  22. run-2/checkpoint-3689/tokenizer_config.json +57 -0
  23. run-2/checkpoint-3689/trainer_state.json +129 -0
  24. run-2/checkpoint-3689/training_args.bin +3 -0
  25. run-2/checkpoint-3689/vocab.txt +0 -0
  26. run-3/checkpoint-527/config.json +34 -0
  27. run-3/checkpoint-527/model.safetensors +3 -0
  28. run-3/checkpoint-527/optimizer.pt +3 -0
  29. run-3/checkpoint-527/rng_state.pth +3 -0
  30. run-3/checkpoint-527/scheduler.pt +3 -0
  31. run-3/checkpoint-527/special_tokens_map.json +7 -0
  32. run-3/checkpoint-527/tokenizer.json +0 -0
  33. run-3/checkpoint-527/tokenizer_config.json +57 -0
  34. run-3/checkpoint-527/trainer_state.json +39 -0
  35. run-3/checkpoint-527/training_args.bin +3 -0
  36. run-3/checkpoint-527/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1699948806.45c71320b2c6.349.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:510845e227fe08162416194e8620b034d757556cb407d3d2690565ac846333ed
3
- size 5254
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9107e43d4f9cfbb0326134c5a07c9c20000bf4bbd55972e99e0542813e15d3a7
3
+ size 8008
logs/events.out.tfevents.1699949278.45c71320b2c6.349.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:847f1d04ff9d6751b4cc718904fea8bd9a143349295cc1ef1268045354792c64
3
+ size 4774
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c78ef9d434689f47921ba58fcde32802a86cf7014ffa966b3904e83dfab64c4
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f48a4fe2b066e76981e1d5f9ab7af321ba55bb288c652cfca991c81ecf3a4ab5
3
  size 17549312
run-2/checkpoint-2635/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": "4.35.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-2/checkpoint-2635/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e2378ff3c9992da76c399a8c9a662aeb266e4f0312ffbf78c3ae6e7af823c35
3
+ size 17549312
run-2/checkpoint-2635/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e15c766bcac788e56a09bbc887c755529e3c533f558c15bbb9862065fcff6a9
3
+ size 35123898
run-2/checkpoint-2635/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6495712c0480e33150a9e840df89cfbd7359c197e00213528d6031351fe6bf56
3
+ size 14308
run-2/checkpoint-2635/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86ffe5c6df60917b47f2c3f7adf4b731132ac33e22e93bc95aea3eb0f319c5a3
3
+ size 1064
run-2/checkpoint-2635/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-2635/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-2635/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-2635/trainer_state.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8314220183486238,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-2635",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2635,
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
+ "learning_rate": 4.79684197496573e-05,
14
+ "loss": 2.3801,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.7889908256880734,
20
+ "eval_loss": 1.741765022277832,
21
+ "eval_runtime": 0.9163,
22
+ "eval_samples_per_second": 951.658,
23
+ "eval_steps_per_second": 7.639,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 3.9976210705057424e-05,
29
+ "loss": 1.2938,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8084862385321101,
35
+ "eval_loss": 1.5267748832702637,
36
+ "eval_runtime": 0.9325,
37
+ "eval_samples_per_second": 935.111,
38
+ "eval_steps_per_second": 7.507,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 3.1984001660457556e-05,
44
+ "loss": 0.9871,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8176605504587156,
50
+ "eval_loss": 1.4704174995422363,
51
+ "eval_runtime": 0.9635,
52
+ "eval_samples_per_second": 904.99,
53
+ "eval_steps_per_second": 7.265,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 2.4006958097915746e-05,
59
+ "loss": 0.8514,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8245412844036697,
65
+ "eval_loss": 1.4894779920578003,
66
+ "eval_runtime": 0.8473,
67
+ "eval_samples_per_second": 1029.094,
68
+ "eval_steps_per_second": 8.261,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 1.6014749053315874e-05,
74
+ "loss": 0.7616,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8314220183486238,
80
+ "eval_loss": 1.4678914546966553,
81
+ "eval_runtime": 0.8263,
82
+ "eval_samples_per_second": 1055.31,
83
+ "eval_steps_per_second": 8.472,
84
+ "step": 2635
85
+ }
86
+ ],
87
+ "logging_steps": 500,
88
+ "max_steps": 3689,
89
+ "num_train_epochs": 7,
90
+ "save_steps": 500,
91
+ "total_flos": 40418309418180.0,
92
+ "trial_name": null,
93
+ "trial_params": {
94
+ "alpha": 0.3320504403521003,
95
+ "learning_rate": 5.5945463312199106e-05,
96
+ "num_train_epochs": 7,
97
+ "temperature": 29
98
+ }
99
+ }
run-2/checkpoint-2635/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b6c306bf1092d3def665e82057eb0e81f459c5275b49cf388f7789d4edf1545
3
+ size 4664
run-2/checkpoint-2635/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-3689/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": "4.35.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-2/checkpoint-3689/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aa30d0e824fa4155bd81e7bf91d94583335bc4edb723b8dfdb0bb445e544d60
3
+ size 17549312
run-2/checkpoint-3689/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c1360c7f36652b5e1dfda3dc91a97fe86e50a3d4c95c4cbafc22590b71fac0c
3
+ size 35123898
run-2/checkpoint-3689/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:959a157c8997a0f50a0954cb609f9428c4084488e4115a67b439b0d218c1fd23
3
+ size 14308
run-2/checkpoint-3689/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bc8e22fb1cf6b3c45cb2ae76638d10d03b146d662f7297544d62ac6b2c2a11a
3
+ size 1064
run-2/checkpoint-3689/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-3689/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-3689/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-3689/trainer_state.json ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8314220183486238,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-2635",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3689,
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
+ "learning_rate": 4.79684197496573e-05,
14
+ "loss": 2.3801,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.7889908256880734,
20
+ "eval_loss": 1.741765022277832,
21
+ "eval_runtime": 0.9163,
22
+ "eval_samples_per_second": 951.658,
23
+ "eval_steps_per_second": 7.639,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 3.9976210705057424e-05,
29
+ "loss": 1.2938,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8084862385321101,
35
+ "eval_loss": 1.5267748832702637,
36
+ "eval_runtime": 0.9325,
37
+ "eval_samples_per_second": 935.111,
38
+ "eval_steps_per_second": 7.507,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 3.1984001660457556e-05,
44
+ "loss": 0.9871,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8176605504587156,
50
+ "eval_loss": 1.4704174995422363,
51
+ "eval_runtime": 0.9635,
52
+ "eval_samples_per_second": 904.99,
53
+ "eval_steps_per_second": 7.265,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 2.4006958097915746e-05,
59
+ "loss": 0.8514,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8245412844036697,
65
+ "eval_loss": 1.4894779920578003,
66
+ "eval_runtime": 0.8473,
67
+ "eval_samples_per_second": 1029.094,
68
+ "eval_steps_per_second": 8.261,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 1.6014749053315874e-05,
74
+ "loss": 0.7616,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8314220183486238,
80
+ "eval_loss": 1.4678914546966553,
81
+ "eval_runtime": 0.8263,
82
+ "eval_samples_per_second": 1055.31,
83
+ "eval_steps_per_second": 8.472,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 8.022540008716e-06,
89
+ "loss": 0.7166,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.823394495412844,
95
+ "eval_loss": 1.4865918159484863,
96
+ "eval_runtime": 0.8315,
97
+ "eval_samples_per_second": 1048.752,
98
+ "eval_steps_per_second": 8.419,
99
+ "step": 3162
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "learning_rate": 3.0330964116128545e-08,
104
+ "loss": 0.687,
105
+ "step": 3689
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "eval_accuracy": 0.8256880733944955,
110
+ "eval_loss": 1.492751955986023,
111
+ "eval_runtime": 0.8403,
112
+ "eval_samples_per_second": 1037.675,
113
+ "eval_steps_per_second": 8.33,
114
+ "step": 3689
115
+ }
116
+ ],
117
+ "logging_steps": 500,
118
+ "max_steps": 3689,
119
+ "num_train_epochs": 7,
120
+ "save_steps": 500,
121
+ "total_flos": 56612034005400.0,
122
+ "trial_name": null,
123
+ "trial_params": {
124
+ "alpha": 0.3320504403521003,
125
+ "learning_rate": 5.5945463312199106e-05,
126
+ "num_train_epochs": 7,
127
+ "temperature": 29
128
+ }
129
+ }
run-2/checkpoint-3689/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b6c306bf1092d3def665e82057eb0e81f459c5275b49cf388f7789d4edf1545
3
+ size 4664
run-2/checkpoint-3689/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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": "4.35.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-3/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f48a4fe2b066e76981e1d5f9ab7af321ba55bb288c652cfca991c81ecf3a4ab5
3
+ size 17549312
run-3/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:550a498edd1bcf532dd3a3b2e6cde5eae6907363de42bd0d245ec526416630e3
3
+ size 35123898
run-3/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ababcbf30496eb4976cce44a5faf0cf605467f452ba655745eb60d884a0042d8
3
+ size 14308
run-3/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a50a14139c803589db76c9095f71e2bcbd2e698c9aaf39a5371aa801aff1c42
3
+ size 1064
run-3/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-3/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7878440366972477,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/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
+ "learning_rate": 5.221248060148077e-05,
14
+ "loss": 3.1126,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.7878440366972477,
20
+ "eval_loss": 2.2062058448791504,
21
+ "eval_runtime": 0.8309,
22
+ "eval_samples_per_second": 1049.417,
23
+ "eval_steps_per_second": 8.424,
24
+ "step": 527
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 4216,
29
+ "num_train_epochs": 8,
30
+ "save_steps": 500,
31
+ "total_flos": 8117476690260.0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "alpha": 0.005810782253789393,
35
+ "learning_rate": 5.9655235288846326e-05,
36
+ "num_train_epochs": 8,
37
+ "temperature": 15
38
+ }
39
+ }
run-3/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b90fe7ad519b6df3d25521c0d14f4888a6afdddcf10996424b3e41b8b6d2140e
3
+ size 4664
run-3/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 sha256:0b6c306bf1092d3def665e82057eb0e81f459c5275b49cf388f7789d4edf1545
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b90fe7ad519b6df3d25521c0d14f4888a6afdddcf10996424b3e41b8b6d2140e
3
  size 4664