Hugging Face's logo

jysh1023
/
tiny-bert-sst2-distilled_original

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
jysh1023 commited on
Commit
0c767e8
·
1 Parent(s): 1a9c15d

Training in progress, epoch 1

Browse files
Files changed (39) hide show
  1. logs/events.out.tfevents.1700277380.bdba95a6283e.570.1 +2 -2
  2. logs/events.out.tfevents.1700279347.bdba95a6283e.570.2 +3 -0
  3. logs/events.out.tfevents.1700279568.bdba95a6283e.570.3 +3 -0
  4. logs/events.out.tfevents.1700280752.bdba95a6283e.570.4 +3 -0
  5. model.safetensors +1 -1
  6. run-0/checkpoint-2635/config.json +34 -0
  7. run-0/checkpoint-2635/model.safetensors +3 -0
  8. run-0/checkpoint-2635/optimizer.pt +3 -0
  9. run-0/checkpoint-2635/rng_state.pth +3 -0
  10. run-0/checkpoint-2635/scheduler.pt +3 -0
  11. run-0/checkpoint-2635/special_tokens_map.json +7 -0
  12. run-0/checkpoint-2635/tokenizer.json +0 -0
  13. run-0/checkpoint-2635/tokenizer_config.json +57 -0
  14. run-0/checkpoint-2635/trainer_state.json +99 -0
  15. run-0/checkpoint-2635/training_args.bin +3 -0
  16. run-0/checkpoint-2635/vocab.txt +0 -0
  17. run-0/checkpoint-3162/config.json +34 -0
  18. run-0/checkpoint-3162/model.safetensors +3 -0
  19. run-0/checkpoint-3162/optimizer.pt +3 -0
  20. run-0/checkpoint-3162/rng_state.pth +3 -0
  21. run-0/checkpoint-3162/scheduler.pt +3 -0
  22. run-0/checkpoint-3162/special_tokens_map.json +7 -0
  23. run-0/checkpoint-3162/tokenizer.json +0 -0
  24. run-0/checkpoint-3162/tokenizer_config.json +57 -0
  25. run-0/checkpoint-3162/trainer_state.json +114 -0
  26. run-0/checkpoint-3162/training_args.bin +3 -0
  27. run-0/checkpoint-3162/vocab.txt +0 -0
  28. run-1/checkpoint-527/config.json +34 -0
  29. run-1/checkpoint-527/model.safetensors +3 -0
  30. run-1/checkpoint-527/optimizer.pt +3 -0
  31. run-1/checkpoint-527/rng_state.pth +3 -0
  32. run-1/checkpoint-527/scheduler.pt +3 -0
  33. run-1/checkpoint-527/special_tokens_map.json +7 -0
  34. run-1/checkpoint-527/tokenizer.json +0 -0
  35. run-1/checkpoint-527/tokenizer_config.json +57 -0
  36. run-1/checkpoint-527/trainer_state.json +39 -0
  37. run-1/checkpoint-527/training_args.bin +3 -0
  38. run-1/checkpoint-527/vocab.txt +0 -0
  39. training_args.bin +1 -1
logs/events.out.tfevents.1700277380.bdba95a6283e.570.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eea2eec68e345246381dde09c7ba565af62a4fb8248efbfcd3466f230ec2d8c9
3
- size 5290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fe50c5bb3f4f082521809283d79d9e231cadffaac4aa39b5fa1892dd41345e4
3
+ size 9484
logs/events.out.tfevents.1700279347.bdba95a6283e.570.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:724b85666020db8657d64dd3a06c2fb45b9769bda1bd2952e4c6ea90d99f8cd1
3
+ size 4486
logs/events.out.tfevents.1700279568.bdba95a6283e.570.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67261f04a61d1a0e198cf6808262bf2b9f962e7b31dab51b00c253ab04d858e0
3
+ size 7563
logs/events.out.tfevents.1700280752.bdba95a6283e.570.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c6acf30581f1d726996d4a9e7c3d293133f761650d6d4f3e5650733801b557a
3
+ size 4809
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3264bc282a0bd9ea3c4406744922b86f17e910a4a6e088156f381d50dfad434
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7b2edadbb47dbfe2b9b7e951a75fd023a50107da47fdbc1afa1e594510f6b78
3
  size 17549312
run-0/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": "4.35.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-0/checkpoint-2635/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9be9f815e9e7e62d52b210f5ad6716083357ccbcddd1b031bb8bae5c441ef5ee
3
+ size 17549312
run-0/checkpoint-2635/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12a1f7bd452917a9ca3b504a0d6b5eb3fd4f358bd7b297039a60f0f53d576571
3
+ size 35123898
run-0/checkpoint-2635/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f498ecc7f86f66da16efa58519f2ba6628266b779089c9aa7803bfb118cc80d
3
+ size 14308
run-0/checkpoint-2635/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbfd2f83ccca96bc82339b227636a5c6a75c86aec01d22305ced66a6187fa28a
3
+ size 1064
run-0/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-0/checkpoint-2635/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/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-0/checkpoint-2635/trainer_state.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8096330275229358,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled_original/run-0/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": 0.0007669546339026458,
14
+ "loss": 1.5056,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8027522935779816,
20
+ "eval_loss": 2.2895803451538086,
21
+ "eval_runtime": 2.7231,
22
+ "eval_samples_per_second": 320.221,
23
+ "eval_steps_per_second": 2.571,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.0006136218979137633,
29
+ "loss": 0.6598,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8004587155963303,
35
+ "eval_loss": 2.373020648956299,
36
+ "eval_runtime": 2.6823,
37
+ "eval_samples_per_second": 325.095,
38
+ "eval_steps_per_second": 2.61,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 0.0004602891619248808,
44
+ "loss": 0.4295,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.7958715596330275,
50
+ "eval_loss": 2.5759832859039307,
51
+ "eval_runtime": 2.7199,
52
+ "eval_samples_per_second": 320.597,
53
+ "eval_steps_per_second": 2.574,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 0.00030695642593599827,
59
+ "loss": 0.3048,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.801605504587156,
65
+ "eval_loss": 2.317852735519409,
66
+ "eval_runtime": 2.6842,
67
+ "eval_samples_per_second": 324.862,
68
+ "eval_steps_per_second": 2.608,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 0.00015362368994711572,
74
+ "loss": 0.2265,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8096330275229358,
80
+ "eval_loss": 2.3232898712158203,
81
+ "eval_runtime": 2.7359,
82
+ "eval_samples_per_second": 318.727,
83
+ "eval_steps_per_second": 2.559,
84
+ "step": 2635
85
+ }
86
+ ],
87
+ "logging_steps": 500,
88
+ "max_steps": 3162,
89
+ "num_train_epochs": 6,
90
+ "save_steps": 500,
91
+ "total_flos": 40418309418180.0,
92
+ "trial_name": null,
93
+ "trial_params": {
94
+ "alpha": 0.05745854764135261,
95
+ "learning_rate": 0.0009199964159332951,
96
+ "num_train_epochs": 6,
97
+ "temperature": 15
98
+ }
99
+ }
run-0/checkpoint-2635/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:831ef973d106cfc0f3031935f697f253e1d3cb341bbce79015a39bb7cda6edfe
3
+ size 4664
run-0/checkpoint-2635/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-3162/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": "4.35.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-0/checkpoint-3162/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b91cd8c8c4cd84479a98293ef0913e27535643691c5a88c858a9d5c99cc207f
3
+ size 17549312
run-0/checkpoint-3162/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b9d37c8c458a6695985ac6b8fb5cbfef1f603100545b28e83dfd24788b3744e
3
+ size 35123898
run-0/checkpoint-3162/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5be763af592ca53ad617ee7b4ba39713316b3262a7224bf7a03a3657280ab1a
3
+ size 14308
run-0/checkpoint-3162/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05f1ec317423eb245df7b637e901af816ecf9d5420e4467d8bbffd3391841440
3
+ size 1064
run-0/checkpoint-3162/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-3162/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-3162/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-3162/trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8096330275229358,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled_original/run-0/checkpoint-2635",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3162,
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": 0.0007669546339026458,
14
+ "loss": 1.5056,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8027522935779816,
20
+ "eval_loss": 2.2895803451538086,
21
+ "eval_runtime": 2.7231,
22
+ "eval_samples_per_second": 320.221,
23
+ "eval_steps_per_second": 2.571,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.0006136218979137633,
29
+ "loss": 0.6598,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8004587155963303,
35
+ "eval_loss": 2.373020648956299,
36
+ "eval_runtime": 2.6823,
37
+ "eval_samples_per_second": 325.095,
38
+ "eval_steps_per_second": 2.61,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 0.0004602891619248808,
44
+ "loss": 0.4295,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.7958715596330275,
50
+ "eval_loss": 2.5759832859039307,
51
+ "eval_runtime": 2.7199,
52
+ "eval_samples_per_second": 320.597,
53
+ "eval_steps_per_second": 2.574,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 0.00030695642593599827,
59
+ "loss": 0.3048,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.801605504587156,
65
+ "eval_loss": 2.317852735519409,
66
+ "eval_runtime": 2.6842,
67
+ "eval_samples_per_second": 324.862,
68
+ "eval_steps_per_second": 2.608,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 0.00015362368994711572,
74
+ "loss": 0.2265,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8096330275229358,
80
+ "eval_loss": 2.3232898712158203,
81
+ "eval_runtime": 2.7359,
82
+ "eval_samples_per_second": 318.727,
83
+ "eval_steps_per_second": 2.559,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 5.819079164663473e-07,
89
+ "loss": 0.1775,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8038990825688074,
95
+ "eval_loss": 2.2668466567993164,
96
+ "eval_runtime": 2.6922,
97
+ "eval_samples_per_second": 323.897,
98
+ "eval_steps_per_second": 2.6,
99
+ "step": 3162
100
+ }
101
+ ],
102
+ "logging_steps": 500,
103
+ "max_steps": 3162,
104
+ "num_train_epochs": 6,
105
+ "save_steps": 500,
106
+ "total_flos": 48509902416420.0,
107
+ "trial_name": null,
108
+ "trial_params": {
109
+ "alpha": 0.05745854764135261,
110
+ "learning_rate": 0.0009199964159332951,
111
+ "num_train_epochs": 6,
112
+ "temperature": 15
113
+ }
114
+ }
run-0/checkpoint-3162/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:831ef973d106cfc0f3031935f697f253e1d3cb341bbce79015a39bb7cda6edfe
3
+ size 4664
run-0/checkpoint-3162/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": "4.35.2",
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:c7b2edadbb47dbfe2b9b7e951a75fd023a50107da47fdbc1afa1e594510f6b78
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:a05d1a99ab48819dbaaf9208877e21242db6a5c51889253342dc02cc030dd3bb
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:df95bce5c5c16e60e49eb22753b34dbfa7966d22f239bd4ae61a5f9a0e6ccf0d
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 sha256:8d4e8dde8c3cc1393310cd2808b9c2e6ed44519b68fc6e83d50ef369fdebd93b
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 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8084862385321101,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled_original/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
+ "learning_rate": 0.0007547350931851784,
14
+ "loss": 0.9577,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8084862385321101,
20
+ "eval_loss": 1.4108219146728516,
21
+ "eval_runtime": 2.7423,
22
+ "eval_samples_per_second": 317.978,
23
+ "eval_steps_per_second": 2.553,
24
+ "step": 527
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 4743,
29
+ "num_train_epochs": 9,
30
+ "save_steps": 500,
31
+ "total_flos": 8117476690260.0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "alpha": 0.5406219777379293,
35
+ "learning_rate": 0.0008488756336204177,
36
+ "num_train_epochs": 9,
37
+ "temperature": 24
38
+ }
39
+ }
run-1/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32fee1b02c10753a236e23df3915f51d15a4d89231b69375404c9fbf68c5317b
3
+ size 4664
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:a06c756d83766d60898dbd6b64258881676eb1e1cacf0b74abb02e375d50aecd
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32fee1b02c10753a236e23df3915f51d15a4d89231b69375404c9fbf68c5317b
3
  size 4664