Hugging Face's logo

joseph10
/
tinybert-TG-HS-HX-parentpretrained

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
joseph10 commited on
Commit
b358227
•
1 Parent(s): ea2066b

Training in progress, epoch 1

Browse files
Files changed (34) hide show
  1. logs/events.out.tfevents.1702283787.joseph_legion.22340.20 +2 -2
  2. logs/events.out.tfevents.1702286155.joseph_legion.22340.21 +3 -0
  3. model.safetensors +1 -1
  4. run-7/checkpoint-788/config.json +34 -0
  5. run-7/checkpoint-788/model.safetensors +3 -0
  6. run-7/checkpoint-788/optimizer.pt +3 -0
  7. run-7/checkpoint-788/rng_state.pth +3 -0
  8. run-7/checkpoint-788/scheduler.pt +3 -0
  9. run-7/checkpoint-788/special_tokens_map.json +7 -0
  10. run-7/checkpoint-788/tokenizer_config.json +57 -0
  11. run-7/checkpoint-788/trainer_state.json +85 -0
  12. run-7/checkpoint-788/training_args.bin +3 -0
  13. run-7/checkpoint-788/vocab.txt +0 -0
  14. run-7/checkpoint-985/config.json +34 -0
  15. run-7/checkpoint-985/model.safetensors +3 -0
  16. run-7/checkpoint-985/optimizer.pt +3 -0
  17. run-7/checkpoint-985/rng_state.pth +3 -0
  18. run-7/checkpoint-985/scheduler.pt +3 -0
  19. run-7/checkpoint-985/special_tokens_map.json +7 -0
  20. run-7/checkpoint-985/tokenizer_config.json +57 -0
  21. run-7/checkpoint-985/trainer_state.json +100 -0
  22. run-7/checkpoint-985/training_args.bin +3 -0
  23. run-7/checkpoint-985/vocab.txt +0 -0
  24. run-8/checkpoint-197/config.json +34 -0
  25. run-8/checkpoint-197/model.safetensors +3 -0
  26. run-8/checkpoint-197/optimizer.pt +3 -0
  27. run-8/checkpoint-197/rng_state.pth +3 -0
  28. run-8/checkpoint-197/scheduler.pt +3 -0
  29. run-8/checkpoint-197/special_tokens_map.json +7 -0
  30. run-8/checkpoint-197/tokenizer_config.json +57 -0
  31. run-8/checkpoint-197/trainer_state.json +40 -0
  32. run-8/checkpoint-197/training_args.bin +3 -0
  33. run-8/checkpoint-197/vocab.txt +0 -0
  34. training_args.bin +1 -1
logs/events.out.tfevents.1702283787.joseph_legion.22340.20 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dfa6df5afaafda18c7fd256d84cdf2cdf007ecb201166a3f74a373193c2f13a6
3
- size 5885
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caf5d9ba87982d8bdcbc2162f58590cc135eeda5502d9e867314a6e679459b5e
3
+ size 7199
logs/events.out.tfevents.1702286155.joseph_legion.22340.21 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4070902433aee0b479fbde5c40548b71b95614797c4568439a1ffb69622b8cb6
3
+ size 4926
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77c1c660e7ae4aa5c50f91c09d5d943ddf9f3a6f469c194fefb036985994b759
3
  size 44692608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78771c8f22d9b40ff96dee24dfd528a3e5dd5ada89bfc44ac09d1b9fb2cfaa20
3
  size 44692608
run-7/checkpoint-788/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
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": 256,
11
+ "id2label": {
12
+ "0": 0,
13
+ "1": 1
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 1024,
17
+ "label2id": {
18
+ "0": 0,
19
+ "1": 1
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 4,
25
+ "num_hidden_layers": 4,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.36.0.dev0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-7/checkpoint-788/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6eedaf21b9cbb1103045ea5bb80d104d0191e2f485d7c72ac6200fb6cb75d0e
3
+ size 44692608
run-7/checkpoint-788/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1022d7f7ec1574526f26df046fade379355e7d43304821fcb4d2e3a1bb1af85
3
+ size 89430010
run-7/checkpoint-788/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e39bb59d0602913d0446fb1b887e3bef027f47ac31f57a5e1aad549eeef7f347
3
+ size 14308
run-7/checkpoint-788/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:250926c2ddd6c4d6edb1eaaabbb7777d7b92e57f878775f2ad0d73d5893d9790
3
+ size 1064
run-7/checkpoint-788/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-7/checkpoint-788/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-7/checkpoint-788/trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7907170650361312,
3
+ "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-7\\checkpoint-788",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 788,
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": 9.391769458408264e-06,
14
+ "loss": 0.4715,
15
+ "step": 197
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.7722345747637577,
20
+ "eval_loss": 0.4253861606121063,
21
+ "eval_runtime": 125.844,
22
+ "eval_samples_per_second": 57.182,
23
+ "eval_steps_per_second": 0.453,
24
+ "step": 197
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 7.043827093806198e-06,
29
+ "loss": 0.4326,
30
+ "step": 394
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.7833518621456365,
35
+ "eval_loss": 0.4118412137031555,
36
+ "eval_runtime": 125.7992,
37
+ "eval_samples_per_second": 57.202,
38
+ "eval_steps_per_second": 0.453,
39
+ "step": 394
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 4.695884729204132e-06,
44
+ "loss": 0.4188,
45
+ "step": 591
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.7887715397443024,
50
+ "eval_loss": 0.40638259053230286,
51
+ "eval_runtime": 125.6755,
52
+ "eval_samples_per_second": 57.259,
53
+ "eval_steps_per_second": 0.454,
54
+ "step": 591
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 2.347942364602066e-06,
59
+ "loss": 0.4135,
60
+ "step": 788
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.7907170650361312,
65
+ "eval_loss": 0.40277761220932007,
66
+ "eval_runtime": 125.8816,
67
+ "eval_samples_per_second": 57.165,
68
+ "eval_steps_per_second": 0.453,
69
+ "step": 788
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 985,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 5,
76
+ "save_steps": 500,
77
+ "total_flos": 177030409545900.0,
78
+ "trial_name": null,
79
+ "trial_params": {
80
+ "alpha": 0.8077469751146494,
81
+ "learning_rate": 1.173971182301033e-05,
82
+ "num_train_epochs": 5,
83
+ "temperature": 8
84
+ }
85
+ }
run-7/checkpoint-788/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70db95c03b5ec61903552b23f87fba482526d5ac793db9a315d0e5c1b37e6b11
3
+ size 4792
run-7/checkpoint-788/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-985/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
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": 256,
11
+ "id2label": {
12
+ "0": 0,
13
+ "1": 1
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 1024,
17
+ "label2id": {
18
+ "0": 0,
19
+ "1": 1
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 4,
25
+ "num_hidden_layers": 4,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.36.0.dev0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-7/checkpoint-985/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a70b09562d0728ff4bbcc19f0906b678be7a0bfcc4bba5dedfc239bea93bb401
3
+ size 44692608
run-7/checkpoint-985/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65844aa2b9b09754c11f38fcaeb647ce8f6899e12b414ea2291cad5bb046f384
3
+ size 89430010
run-7/checkpoint-985/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50a364bebceef36329237a96faee9e2da941c96eff10dae0acfc327c86066983
3
+ size 14308
run-7/checkpoint-985/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7dc32e386b788bbca892f1f1f7a11660278aec81218dc7b9afa1d76520ac698
3
+ size 1064
run-7/checkpoint-985/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-7/checkpoint-985/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-7/checkpoint-985/trainer_state.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.791828793774319,
3
+ "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-7\\checkpoint-985",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 985,
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": 9.391769458408264e-06,
14
+ "loss": 0.4715,
15
+ "step": 197
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.7722345747637577,
20
+ "eval_loss": 0.4253861606121063,
21
+ "eval_runtime": 125.844,
22
+ "eval_samples_per_second": 57.182,
23
+ "eval_steps_per_second": 0.453,
24
+ "step": 197
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 7.043827093806198e-06,
29
+ "loss": 0.4326,
30
+ "step": 394
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.7833518621456365,
35
+ "eval_loss": 0.4118412137031555,
36
+ "eval_runtime": 125.7992,
37
+ "eval_samples_per_second": 57.202,
38
+ "eval_steps_per_second": 0.453,
39
+ "step": 394
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 4.695884729204132e-06,
44
+ "loss": 0.4188,
45
+ "step": 591
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.7887715397443024,
50
+ "eval_loss": 0.40638259053230286,
51
+ "eval_runtime": 125.6755,
52
+ "eval_samples_per_second": 57.259,
53
+ "eval_steps_per_second": 0.454,
54
+ "step": 591
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 2.347942364602066e-06,
59
+ "loss": 0.4135,
60
+ "step": 788
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.7907170650361312,
65
+ "eval_loss": 0.40277761220932007,
66
+ "eval_runtime": 125.8816,
67
+ "eval_samples_per_second": 57.165,
68
+ "eval_steps_per_second": 0.453,
69
+ "step": 788
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 0.0,
74
+ "loss": 0.4098,
75
+ "step": 985
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.791828793774319,
80
+ "eval_loss": 0.40191134810447693,
81
+ "eval_runtime": 125.8875,
82
+ "eval_samples_per_second": 57.162,
83
+ "eval_steps_per_second": 0.453,
84
+ "step": 985
85
+ }
86
+ ],
87
+ "logging_steps": 500,
88
+ "max_steps": 985,
89
+ "num_input_tokens_seen": 0,
90
+ "num_train_epochs": 5,
91
+ "save_steps": 500,
92
+ "total_flos": 221342066021952.0,
93
+ "trial_name": null,
94
+ "trial_params": {
95
+ "alpha": 0.8077469751146494,
96
+ "learning_rate": 1.173971182301033e-05,
97
+ "num_train_epochs": 5,
98
+ "temperature": 8
99
+ }
100
+ }
run-7/checkpoint-985/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70db95c03b5ec61903552b23f87fba482526d5ac793db9a315d0e5c1b37e6b11
3
+ size 4792
run-7/checkpoint-985/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-197/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
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": 256,
11
+ "id2label": {
12
+ "0": 0,
13
+ "1": 1
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 1024,
17
+ "label2id": {
18
+ "0": 0,
19
+ "1": 1
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 4,
25
+ "num_hidden_layers": 4,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.36.0.dev0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-8/checkpoint-197/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78771c8f22d9b40ff96dee24dfd528a3e5dd5ada89bfc44ac09d1b9fb2cfaa20
3
+ size 44692608
run-8/checkpoint-197/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f063850cfa1a385ea59c7835e36cf6d01e18ed850382d8308dcc2e8d5febdb6
3
+ size 89430010
run-8/checkpoint-197/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfce427b13a79881b8dd7c1ca79db1eca136c641f9f35f4f0773c5f01a793672
3
+ size 14308
run-8/checkpoint-197/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f67b1103072609024641bee4e084cb1a2cb15180645efeb0592748b02d263da
3
+ size 1064
run-8/checkpoint-197/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-8/checkpoint-197/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-8/checkpoint-197/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7752918287937743,
3
+ "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-8\\checkpoint-197",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 197,
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": 9.45388964676361e-06,
14
+ "loss": 0.275,
15
+ "step": 197
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.7752918287937743,
20
+ "eval_loss": 0.26254990696907043,
21
+ "eval_runtime": 125.5427,
22
+ "eval_samples_per_second": 57.319,
23
+ "eval_steps_per_second": 0.454,
24
+ "step": 197
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 591,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 3,
31
+ "save_steps": 500,
32
+ "total_flos": 44298765947484.0,
33
+ "trial_name": null,
34
+ "trial_params": {
35
+ "alpha": 0.43662764362367845,
36
+ "learning_rate": 1.4180834470145417e-05,
37
+ "num_train_epochs": 3,
38
+ "temperature": 19
39
+ }
40
+ }
run-8/checkpoint-197/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef3748f4fdacf1ee097e552e18bffbdfb276f83c94eb1a87d1aba98a3482f9c8
3
+ size 4792
run-8/checkpoint-197/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 sha256:70db95c03b5ec61903552b23f87fba482526d5ac793db9a315d0e5c1b37e6b11
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef3748f4fdacf1ee097e552e18bffbdfb276f83c94eb1a87d1aba98a3482f9c8
3
  size 4792