Hugging Face's logo

langmatthias
/
NLP4WEB-exercise06

Question Answering
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
langmatthias commited on
Commit
bd24791
•
1 Parent(s): fc3f641

Upload with huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-1000/config.json +29 -0
  2. checkpoint-1000/optimizer.pt +3 -0
  3. checkpoint-1000/pytorch_model.bin +3 -0
  4. checkpoint-1000/rng_state.pth +3 -0
  5. checkpoint-1000/scheduler.pt +3 -0
  6. checkpoint-1000/special_tokens_map.json +7 -0
  7. checkpoint-1000/tokenizer.json +0 -0
  8. checkpoint-1000/tokenizer_config.json +16 -0
  9. checkpoint-1000/trainer_state.json +28 -0
  10. checkpoint-1000/training_args.bin +3 -0
  11. checkpoint-1000/vocab.txt +0 -0
  12. checkpoint-10000/config.json +29 -0
  13. checkpoint-10000/optimizer.pt +3 -0
  14. checkpoint-10000/pytorch_model.bin +3 -0
  15. checkpoint-10000/rng_state.pth +3 -0
  16. checkpoint-10000/scheduler.pt +3 -0
  17. checkpoint-10000/special_tokens_map.json +7 -0
  18. checkpoint-10000/tokenizer.json +0 -0
  19. checkpoint-10000/tokenizer_config.json +16 -0
  20. checkpoint-10000/trainer_state.json +136 -0
  21. checkpoint-10000/training_args.bin +3 -0
  22. checkpoint-10000/vocab.txt +0 -0
  23. checkpoint-10500/config.json +29 -0
  24. checkpoint-10500/optimizer.pt +3 -0
  25. checkpoint-10500/pytorch_model.bin +3 -0
  26. checkpoint-10500/rng_state.pth +3 -0
  27. checkpoint-10500/scheduler.pt +3 -0
  28. checkpoint-10500/special_tokens_map.json +7 -0
  29. checkpoint-10500/tokenizer.json +0 -0
  30. checkpoint-10500/tokenizer_config.json +16 -0
  31. checkpoint-10500/trainer_state.json +142 -0
  32. checkpoint-10500/training_args.bin +3 -0
  33. checkpoint-10500/vocab.txt +0 -0
  34. checkpoint-11000/config.json +29 -0
  35. checkpoint-11000/optimizer.pt +3 -0
  36. checkpoint-11000/pytorch_model.bin +3 -0
  37. checkpoint-11000/rng_state.pth +3 -0
  38. checkpoint-11000/scheduler.pt +3 -0
  39. checkpoint-11000/special_tokens_map.json +7 -0
  40. checkpoint-11000/tokenizer.json +0 -0
  41. checkpoint-11000/tokenizer_config.json +16 -0
  42. checkpoint-11000/trainer_state.json +148 -0
  43. checkpoint-11000/training_args.bin +3 -0
  44. checkpoint-11000/vocab.txt +0 -0
  45. checkpoint-11500/config.json +29 -0
  46. checkpoint-11500/optimizer.pt +3 -0
  47. checkpoint-11500/pytorch_model.bin +3 -0
  48. checkpoint-11500/rng_state.pth +3 -0
  49. checkpoint-11500/scheduler.pt +3 -0
  50. checkpoint-11500/special_tokens_map.json +7 -0
checkpoint-1000/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
3
+ "architectures": [
4
+ "BertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "cell": {},
8
+ "classifier_dropout": null,
9
+ "emb_size": 312,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 1200,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 4,
20
+ "pad_token_id": 0,
21
+ "position_embedding_type": "absolute",
22
+ "pre_trained": "",
23
+ "structure": [],
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.27.0.dev0",
26
+ "type_vocab_size": 2,
27
+ "use_cache": true,
28
+ "vocab_size": 30522
29
+ }
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b17b14ad6fcd0a1156e4dc7b5edad92db5183ba0c70add762133bbd81b6e0c
3
+ size 114064901
checkpoint-1000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e98838f455e90fc23867a8f1287208c5874137cba848ee11a35ecf736f447969
3
+ size 57039945
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40c5deaaa4906a6cc3a121941ffd0a024396a5630d7af8fc4515c1dd2841ff10
3
+ size 14575
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eebeab0fa4ccd3d153f3bd0aaf1a39d99e01fb58d321b00ee59cb8efc88cbce
3
+ size 627
checkpoint-1000/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
+ }
checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.13713658804168952,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.07,
12
+ "learning_rate": 2.897147558968733e-05,
13
+ "loss": 3.8538,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.14,
18
+ "learning_rate": 2.794295117937466e-05,
19
+ "loss": 2.9886,
20
+ "step": 1000
21
+ }
22
+ ],
23
+ "max_steps": 14584,
24
+ "num_train_epochs": 2,
25
+ "total_flos": 126350972928000.0,
26
+ "trial_name": null,
27
+ "trial_params": null
28
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f66acec82094efd39d458a8fe525abc7cbca6c8dbd3bc287b3b4a2f983e6fff3
3
+ size 3515
checkpoint-1000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10000/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
3
+ "architectures": [
4
+ "BertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "cell": {},
8
+ "classifier_dropout": null,
9
+ "emb_size": 312,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 1200,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 4,
20
+ "pad_token_id": 0,
21
+ "position_embedding_type": "absolute",
22
+ "pre_trained": "",
23
+ "structure": [],
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.27.0.dev0",
26
+ "type_vocab_size": 2,
27
+ "use_cache": true,
28
+ "vocab_size": 30522
29
+ }
checkpoint-10000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f747b6d7b55c33b45209b88854bca2706886645300e9c69d7e7d4b0d84d4ca0c
3
+ size 114064901
checkpoint-10000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9933636ed2d6c245d145b818df9e101c394b8a6a4bbd85540d8ac21c02919706
3
+ size 57039945
checkpoint-10000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6c1d63ba2e6b207368c62e35db1ae1165ee79da44844bee54e8af97da9ad81c
3
+ size 14575
checkpoint-10000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b04c166fbacbf860bdded5c4cb3abebce049905ce59f2fd58c7cff7b647b71bd
3
+ size 627
checkpoint-10000/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
+ }
checkpoint-10000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10000/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
checkpoint-10000/trainer_state.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.3713658804168953,
5
+ "global_step": 10000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.07,
12
+ "learning_rate": 2.897147558968733e-05,
13
+ "loss": 3.8538,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.14,
18
+ "learning_rate": 2.794295117937466e-05,
19
+ "loss": 2.9886,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.21,
24
+ "learning_rate": 2.6914426769061988e-05,
25
+ "loss": 2.685,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.27,
30
+ "learning_rate": 2.5885902358749317e-05,
31
+ "loss": 2.4911,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.34,
36
+ "learning_rate": 2.4857377948436646e-05,
37
+ "loss": 2.2862,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.41,
42
+ "learning_rate": 2.3828853538123975e-05,
43
+ "loss": 2.14,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.48,
48
+ "learning_rate": 2.28003291278113e-05,
49
+ "loss": 2.122,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.55,
54
+ "learning_rate": 2.177180471749863e-05,
55
+ "loss": 2.0886,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.62,
60
+ "learning_rate": 2.074328030718596e-05,
61
+ "loss": 2.0471,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.69,
66
+ "learning_rate": 1.9714755896873284e-05,
67
+ "loss": 1.9984,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.75,
72
+ "learning_rate": 1.8686231486560613e-05,
73
+ "loss": 2.0018,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.82,
78
+ "learning_rate": 1.7657707076247942e-05,
79
+ "loss": 1.9633,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.89,
84
+ "learning_rate": 1.662918266593527e-05,
85
+ "loss": 1.9129,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.96,
90
+ "learning_rate": 1.56006582556226e-05,
91
+ "loss": 1.9094,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.03,
96
+ "learning_rate": 1.4572133845309929e-05,
97
+ "loss": 1.8448,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.1,
102
+ "learning_rate": 1.3543609434997258e-05,
103
+ "loss": 1.7691,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.17,
108
+ "learning_rate": 1.2515085024684585e-05,
109
+ "loss": 1.7561,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.23,
114
+ "learning_rate": 1.1486560614371914e-05,
115
+ "loss": 1.7437,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 1.3,
120
+ "learning_rate": 1.0458036204059243e-05,
121
+ "loss": 1.7462,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 1.37,
126
+ "learning_rate": 9.429511793746572e-06,
127
+ "loss": 1.6874,
128
+ "step": 10000
129
+ }
130
+ ],
131
+ "max_steps": 14584,
132
+ "num_train_epochs": 2,
133
+ "total_flos": 1263509729280000.0,
134
+ "trial_name": null,
135
+ "trial_params": null
136
+ }
checkpoint-10000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f66acec82094efd39d458a8fe525abc7cbca6c8dbd3bc287b3b4a2f983e6fff3
3
+ size 3515
checkpoint-10000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10500/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
3
+ "architectures": [
4
+ "BertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "cell": {},
8
+ "classifier_dropout": null,
9
+ "emb_size": 312,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 1200,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 4,
20
+ "pad_token_id": 0,
21
+ "position_embedding_type": "absolute",
22
+ "pre_trained": "",
23
+ "structure": [],
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.27.0.dev0",
26
+ "type_vocab_size": 2,
27
+ "use_cache": true,
28
+ "vocab_size": 30522
29
+ }
checkpoint-10500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:709602ebef638c9fd45bdc68f1b1ee9cc81ad6855740f15502d021ea5c0484a8
3
+ size 114064901
checkpoint-10500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88173188429c5cded8cdb7cb3347490024fac652e1d88ec13d8c075d37d63956
3
+ size 57039945
checkpoint-10500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:543d2c8cbe83fa156b68ee82f62e12bf631397d86f4602ca14d395fe88a56003
3
+ size 14575
checkpoint-10500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:220ae99ddf52f42dc878a63cceff78edced869bc7ef25684146225ac65189135
3
+ size 627
checkpoint-10500/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
+ }
checkpoint-10500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10500/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
checkpoint-10500/trainer_state.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.4399341744377399,
5
+ "global_step": 10500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.07,
12
+ "learning_rate": 2.897147558968733e-05,
13
+ "loss": 3.8538,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.14,
18
+ "learning_rate": 2.794295117937466e-05,
19
+ "loss": 2.9886,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.21,
24
+ "learning_rate": 2.6914426769061988e-05,
25
+ "loss": 2.685,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.27,
30
+ "learning_rate": 2.5885902358749317e-05,
31
+ "loss": 2.4911,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.34,
36
+ "learning_rate": 2.4857377948436646e-05,
37
+ "loss": 2.2862,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.41,
42
+ "learning_rate": 2.3828853538123975e-05,
43
+ "loss": 2.14,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.48,
48
+ "learning_rate": 2.28003291278113e-05,
49
+ "loss": 2.122,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.55,
54
+ "learning_rate": 2.177180471749863e-05,
55
+ "loss": 2.0886,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.62,
60
+ "learning_rate": 2.074328030718596e-05,
61
+ "loss": 2.0471,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.69,
66
+ "learning_rate": 1.9714755896873284e-05,
67
+ "loss": 1.9984,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.75,
72
+ "learning_rate": 1.8686231486560613e-05,
73
+ "loss": 2.0018,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.82,
78
+ "learning_rate": 1.7657707076247942e-05,
79
+ "loss": 1.9633,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.89,
84
+ "learning_rate": 1.662918266593527e-05,
85
+ "loss": 1.9129,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.96,
90
+ "learning_rate": 1.56006582556226e-05,
91
+ "loss": 1.9094,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.03,
96
+ "learning_rate": 1.4572133845309929e-05,
97
+ "loss": 1.8448,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.1,
102
+ "learning_rate": 1.3543609434997258e-05,
103
+ "loss": 1.7691,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.17,
108
+ "learning_rate": 1.2515085024684585e-05,
109
+ "loss": 1.7561,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.23,
114
+ "learning_rate": 1.1486560614371914e-05,
115
+ "loss": 1.7437,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 1.3,
120
+ "learning_rate": 1.0458036204059243e-05,
121
+ "loss": 1.7462,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 1.37,
126
+ "learning_rate": 9.429511793746572e-06,
127
+ "loss": 1.6874,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 1.44,
132
+ "learning_rate": 8.400987383433901e-06,
133
+ "loss": 1.7223,
134
+ "step": 10500
135
+ }
136
+ ],
137
+ "max_steps": 14584,
138
+ "num_train_epochs": 2,
139
+ "total_flos": 1326685215744000.0,
140
+ "trial_name": null,
141
+ "trial_params": null
142
+ }
checkpoint-10500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f66acec82094efd39d458a8fe525abc7cbca6c8dbd3bc287b3b4a2f983e6fff3
3
+ size 3515
checkpoint-10500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-11000/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
3
+ "architectures": [
4
+ "BertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "cell": {},
8
+ "classifier_dropout": null,
9
+ "emb_size": 312,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 1200,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 4,
20
+ "pad_token_id": 0,
21
+ "position_embedding_type": "absolute",
22
+ "pre_trained": "",
23
+ "structure": [],
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.27.0.dev0",
26
+ "type_vocab_size": 2,
27
+ "use_cache": true,
28
+ "vocab_size": 30522
29
+ }
checkpoint-11000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cf61a3f31c943d3368bcaca03973504df92e2abeb6c563985d8fb16a8d3bbc6
3
+ size 114064901
checkpoint-11000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cff78f2b6ea9c91e89e16000b02fc76279cdd6cb1e3b0c6216337bf335989351
3
+ size 57039945
checkpoint-11000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31ca4efb7c6a220af89ed080062ff5c4773409690397157ccd6a42156396f4a8
3
+ size 14575
checkpoint-11000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24b38a031160638f7af2dd9144f8ae33ee78212a1d34243d1d4ddb076da336f3
3
+ size 627
checkpoint-11000/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
+ }
checkpoint-11000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-11000/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
checkpoint-11000/trainer_state.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.5085024684585848,
5
+ "global_step": 11000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.07,
12
+ "learning_rate": 2.897147558968733e-05,
13
+ "loss": 3.8538,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.14,
18
+ "learning_rate": 2.794295117937466e-05,
19
+ "loss": 2.9886,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.21,
24
+ "learning_rate": 2.6914426769061988e-05,
25
+ "loss": 2.685,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.27,
30
+ "learning_rate": 2.5885902358749317e-05,
31
+ "loss": 2.4911,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.34,
36
+ "learning_rate": 2.4857377948436646e-05,
37
+ "loss": 2.2862,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.41,
42
+ "learning_rate": 2.3828853538123975e-05,
43
+ "loss": 2.14,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.48,
48
+ "learning_rate": 2.28003291278113e-05,
49
+ "loss": 2.122,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.55,
54
+ "learning_rate": 2.177180471749863e-05,
55
+ "loss": 2.0886,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.62,
60
+ "learning_rate": 2.074328030718596e-05,
61
+ "loss": 2.0471,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.69,
66
+ "learning_rate": 1.9714755896873284e-05,
67
+ "loss": 1.9984,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.75,
72
+ "learning_rate": 1.8686231486560613e-05,
73
+ "loss": 2.0018,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.82,
78
+ "learning_rate": 1.7657707076247942e-05,
79
+ "loss": 1.9633,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.89,
84
+ "learning_rate": 1.662918266593527e-05,
85
+ "loss": 1.9129,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.96,
90
+ "learning_rate": 1.56006582556226e-05,
91
+ "loss": 1.9094,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.03,
96
+ "learning_rate": 1.4572133845309929e-05,
97
+ "loss": 1.8448,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.1,
102
+ "learning_rate": 1.3543609434997258e-05,
103
+ "loss": 1.7691,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.17,
108
+ "learning_rate": 1.2515085024684585e-05,
109
+ "loss": 1.7561,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.23,
114
+ "learning_rate": 1.1486560614371914e-05,
115
+ "loss": 1.7437,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 1.3,
120
+ "learning_rate": 1.0458036204059243e-05,
121
+ "loss": 1.7462,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 1.37,
126
+ "learning_rate": 9.429511793746572e-06,
127
+ "loss": 1.6874,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 1.44,
132
+ "learning_rate": 8.400987383433901e-06,
133
+ "loss": 1.7223,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 1.51,
138
+ "learning_rate": 7.372462973121229e-06,
139
+ "loss": 1.7071,
140
+ "step": 11000
141
+ }
142
+ ],
143
+ "max_steps": 14584,
144
+ "num_train_epochs": 2,
145
+ "total_flos": 1389860702208000.0,
146
+ "trial_name": null,
147
+ "trial_params": null
148
+ }
checkpoint-11000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f66acec82094efd39d458a8fe525abc7cbca6c8dbd3bc287b3b4a2f983e6fff3
3
+ size 3515
checkpoint-11000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-11500/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
3
+ "architectures": [
4
+ "BertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "cell": {},
8
+ "classifier_dropout": null,
9
+ "emb_size": 312,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 1200,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 4,
20
+ "pad_token_id": 0,
21
+ "position_embedding_type": "absolute",
22
+ "pre_trained": "",
23
+ "structure": [],
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.27.0.dev0",
26
+ "type_vocab_size": 2,
27
+ "use_cache": true,
28
+ "vocab_size": 30522
29
+ }
checkpoint-11500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc20867de0204705f87fbe3650685ccb9185cb3d5a43e48ce4381ccefc11d744
3
+ size 114064901
checkpoint-11500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:739f0a30165cdad9d253faefec79d07b0badffb955f3f9f6293e4ce6bffe1fe5
3
+ size 57039945
checkpoint-11500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36461c4a59f4787cbcb5d48376b8b3cb42d3ce8426bfb276e52281d557e1ac2c
3
+ size 14575
checkpoint-11500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30d53639701b91aa54bf77c2bc7d4ad2f6ec8e380fd3da5c15d79021939d1b0c
3
+ size 627
checkpoint-11500/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
+ }