Hugging Face's logo

Kemasu
/
albert_sae

TensorBoard
Model card Files
xet
Metrics Community
Kemasu commited on
Commit
46ad5eb
·
verified ·
1 Parent(s): 4c3450b

Upload 650 files

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. finetune-BERT-squad/checkpoint-1000/config.json +33 -0
  2. finetune-BERT-squad/checkpoint-1000/optimizer.pt +3 -0
  3. finetune-BERT-squad/checkpoint-1000/rng_state.pth +3 -0
  4. finetune-BERT-squad/checkpoint-1000/scheduler.pt +3 -0
  5. finetune-BERT-squad/checkpoint-1000/special_tokens_map.json +15 -0
  6. finetune-BERT-squad/checkpoint-1000/spiece.model +3 -0
  7. finetune-BERT-squad/checkpoint-1000/tokenizer.json +0 -0
  8. finetune-BERT-squad/checkpoint-1000/tokenizer_config.json +22 -0
  9. finetune-BERT-squad/checkpoint-1000/trainer_state.json +28 -0
  10. finetune-BERT-squad/checkpoint-1000/training_args.bin +3 -0
  11. finetune-BERT-squad/checkpoint-10000/config.json +33 -0
  12. finetune-BERT-squad/checkpoint-10000/optimizer.pt +3 -0
  13. finetune-BERT-squad/checkpoint-10000/rng_state.pth +3 -0
  14. finetune-BERT-squad/checkpoint-10000/scheduler.pt +3 -0
  15. finetune-BERT-squad/checkpoint-10000/special_tokens_map.json +15 -0
  16. finetune-BERT-squad/checkpoint-10000/tokenizer_config.json +22 -0
  17. finetune-BERT-squad/checkpoint-10000/trainer_state.json +136 -0
  18. finetune-BERT-squad/checkpoint-10000/training_args.bin +3 -0
  19. finetune-BERT-squad/checkpoint-10500/config.json +33 -0
  20. finetune-BERT-squad/checkpoint-10500/rng_state.pth +3 -0
  21. finetune-BERT-squad/checkpoint-10500/scheduler.pt +3 -0
  22. finetune-BERT-squad/checkpoint-10500/special_tokens_map.json +15 -0
  23. finetune-BERT-squad/checkpoint-10500/spiece.model +3 -0
  24. finetune-BERT-squad/checkpoint-10500/tokenizer_config.json +22 -0
  25. finetune-BERT-squad/checkpoint-10500/trainer_state.json +142 -0
  26. finetune-BERT-squad/checkpoint-10500/training_args.bin +3 -0
  27. finetune-BERT-squad/checkpoint-11000/config.json +33 -0
  28. finetune-BERT-squad/checkpoint-11000/optimizer.pt +3 -0
  29. finetune-BERT-squad/checkpoint-11000/pytorch_model.bin +3 -0
  30. finetune-BERT-squad/checkpoint-11000/rng_state.pth +3 -0
  31. finetune-BERT-squad/checkpoint-11000/scheduler.pt +3 -0
  32. finetune-BERT-squad/checkpoint-11000/special_tokens_map.json +15 -0
  33. finetune-BERT-squad/checkpoint-11000/spiece.model +3 -0
  34. finetune-BERT-squad/checkpoint-11000/tokenizer.json +0 -0
  35. finetune-BERT-squad/checkpoint-11000/tokenizer_config.json +22 -0
  36. finetune-BERT-squad/checkpoint-11000/trainer_state.json +148 -0
  37. finetune-BERT-squad/checkpoint-11000/training_args.bin +3 -0
  38. finetune-BERT-squad/checkpoint-11500/config.json +33 -0
  39. finetune-BERT-squad/checkpoint-11500/rng_state.pth +3 -0
  40. finetune-BERT-squad/checkpoint-11500/scheduler.pt +3 -0
  41. finetune-BERT-squad/checkpoint-11500/special_tokens_map.json +15 -0
  42. finetune-BERT-squad/checkpoint-11500/spiece.model +3 -0
  43. finetune-BERT-squad/checkpoint-11500/tokenizer.json +0 -0
  44. finetune-BERT-squad/checkpoint-11500/tokenizer_config.json +22 -0
  45. finetune-BERT-squad/checkpoint-11500/trainer_state.json +162 -0
  46. finetune-BERT-squad/checkpoint-11500/training_args.bin +3 -0
  47. finetune-BERT-squad/checkpoint-12000/config.json +33 -0
  48. finetune-BERT-squad/checkpoint-12000/pytorch_model.bin +3 -0
  49. finetune-BERT-squad/checkpoint-12000/rng_state.pth +3 -0
  50. finetune-BERT-squad/checkpoint-12000/scheduler.pt +3 -0
finetune-BERT-squad/checkpoint-1000/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "albert/albert-base-v2",
3
+ "architectures": [
4
+ "AlbertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "down_scale_factor": 1,
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "gap_size": 0,
13
+ "hidden_act": "gelu_new",
14
+ "hidden_dropout_prob": 0,
15
+ "hidden_size": 768,
16
+ "initializer_range": 0.02,
17
+ "inner_group_num": 1,
18
+ "intermediate_size": 3072,
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "albert",
22
+ "net_structure_type": 0,
23
+ "num_attention_heads": 12,
24
+ "num_hidden_groups": 1,
25
+ "num_hidden_layers": 12,
26
+ "num_memory_blocks": 0,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "torch_dtype": "float16",
30
+ "transformers_version": "4.30.0",
31
+ "type_vocab_size": 2,
32
+ "vocab_size": 30000
33
+ }
finetune-BERT-squad/checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:809c2300017333353f4771d6011698b91fc8650f5e073af7a22a75c1affd6902
3
+ size 44393260
finetune-BERT-squad/checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
3
+ size 14244
finetune-BERT-squad/checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3eee95df3e65efb62f6a4b5a743e7b350af221c418b8b46f67d3de7aeff4e43
3
+ size 1064
finetune-BERT-squad/checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": {
6
+ "content": "[MASK]",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "[SEP]",
14
+ "unk_token": "<unk>"
15
+ }
finetune-BERT-squad/checkpoint-1000/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
3
+ size 760289
finetune-BERT-squad/checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
finetune-BERT-squad/checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": true,
6
+ "eos_token": "[SEP]",
7
+ "keep_accents": false,
8
+ "mask_token": {
9
+ "__type": "AddedToken",
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "model_max_length": 512,
17
+ "pad_token": "<pad>",
18
+ "remove_space": true,
19
+ "sep_token": "[SEP]",
20
+ "tokenizer_class": "AlbertTokenizer",
21
+ "unk_token": "<unk>"
22
+ }
finetune-BERT-squad/checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.09025270758122744,
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": 0.05,
12
+ "learning_rate": 1.969915764139591e-05,
13
+ "loss": 3.07,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.09,
18
+ "learning_rate": 1.939831528279182e-05,
19
+ "loss": 0.0,
20
+ "step": 1000
21
+ }
22
+ ],
23
+ "max_steps": 33240,
24
+ "num_train_epochs": 3,
25
+ "total_flos": 132502818816000.0,
26
+ "trial_name": null,
27
+ "trial_params": null
28
+ }
finetune-BERT-squad/checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f25d45105510bc009d36d968cf2b27158670787ad134758fabe6d424d332bdeb
3
+ size 4408
finetune-BERT-squad/checkpoint-10000/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "albert/albert-base-v2",
3
+ "architectures": [
4
+ "AlbertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "down_scale_factor": 1,
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "gap_size": 0,
13
+ "hidden_act": "gelu_new",
14
+ "hidden_dropout_prob": 0,
15
+ "hidden_size": 768,
16
+ "initializer_range": 0.02,
17
+ "inner_group_num": 1,
18
+ "intermediate_size": 3072,
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "albert",
22
+ "net_structure_type": 0,
23
+ "num_attention_heads": 12,
24
+ "num_hidden_groups": 1,
25
+ "num_hidden_layers": 12,
26
+ "num_memory_blocks": 0,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "torch_dtype": "float16",
30
+ "transformers_version": "4.30.0",
31
+ "type_vocab_size": 2,
32
+ "vocab_size": 30000
33
+ }
finetune-BERT-squad/checkpoint-10000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88b318d5156bdbc1b37a723ad2822e674cc2800b75e9942509242e4f46a46615
3
+ size 44393260
finetune-BERT-squad/checkpoint-10000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
3
+ size 14244
finetune-BERT-squad/checkpoint-10000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1e4ea67dd73b588394e562b7cf55b6510d5763995895f48736a57f04ff2f22e
3
+ size 1064
finetune-BERT-squad/checkpoint-10000/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": {
6
+ "content": "[MASK]",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "[SEP]",
14
+ "unk_token": "<unk>"
15
+ }
finetune-BERT-squad/checkpoint-10000/tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": true,
6
+ "eos_token": "[SEP]",
7
+ "keep_accents": false,
8
+ "mask_token": {
9
+ "__type": "AddedToken",
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "model_max_length": 512,
17
+ "pad_token": "<pad>",
18
+ "remove_space": true,
19
+ "sep_token": "[SEP]",
20
+ "tokenizer_class": "AlbertTokenizer",
21
+ "unk_token": "<unk>"
22
+ }
finetune-BERT-squad/checkpoint-10000/trainer_state.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9025270758122743,
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": 0.05,
12
+ "learning_rate": 1.969915764139591e-05,
13
+ "loss": 3.07,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.09,
18
+ "learning_rate": 1.939831528279182e-05,
19
+ "loss": 0.0,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.14,
24
+ "learning_rate": 1.9097472924187726e-05,
25
+ "loss": 0.0,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.18,
30
+ "learning_rate": 1.8796630565583636e-05,
31
+ "loss": 0.0,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.23,
36
+ "learning_rate": 1.8495788206979545e-05,
37
+ "loss": 0.0,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.27,
42
+ "learning_rate": 1.8194945848375454e-05,
43
+ "loss": 0.0,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.32,
48
+ "learning_rate": 1.789410348977136e-05,
49
+ "loss": 0.0,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.36,
54
+ "learning_rate": 1.759326113116727e-05,
55
+ "loss": 0.0,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.41,
60
+ "learning_rate": 1.729241877256318e-05,
61
+ "loss": 0.0,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.45,
66
+ "learning_rate": 1.699157641395909e-05,
67
+ "loss": 0.0,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.5,
72
+ "learning_rate": 1.6690734055354995e-05,
73
+ "loss": 0.0,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.54,
78
+ "learning_rate": 1.6389891696750904e-05,
79
+ "loss": 0.0,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.59,
84
+ "learning_rate": 1.608904933814681e-05,
85
+ "loss": 0.0,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.63,
90
+ "learning_rate": 1.5788206979542723e-05,
91
+ "loss": 0.0,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.68,
96
+ "learning_rate": 1.548736462093863e-05,
97
+ "loss": 0.0,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.72,
102
+ "learning_rate": 1.5186522262334538e-05,
103
+ "loss": 0.0,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.77,
108
+ "learning_rate": 1.4885679903730446e-05,
109
+ "loss": 0.0,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.81,
114
+ "learning_rate": 1.4584837545126355e-05,
115
+ "loss": 0.0,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.86,
120
+ "learning_rate": 1.4283995186522264e-05,
121
+ "loss": 0.0,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.9,
126
+ "learning_rate": 1.3983152827918172e-05,
127
+ "loss": 0.0,
128
+ "step": 10000
129
+ }
130
+ ],
131
+ "max_steps": 33240,
132
+ "num_train_epochs": 3,
133
+ "total_flos": 1325028188160000.0,
134
+ "trial_name": null,
135
+ "trial_params": null
136
+ }
finetune-BERT-squad/checkpoint-10000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f25d45105510bc009d36d968cf2b27158670787ad134758fabe6d424d332bdeb
3
+ size 4408
finetune-BERT-squad/checkpoint-10500/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "albert/albert-base-v2",
3
+ "architectures": [
4
+ "AlbertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "down_scale_factor": 1,
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "gap_size": 0,
13
+ "hidden_act": "gelu_new",
14
+ "hidden_dropout_prob": 0,
15
+ "hidden_size": 768,
16
+ "initializer_range": 0.02,
17
+ "inner_group_num": 1,
18
+ "intermediate_size": 3072,
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "albert",
22
+ "net_structure_type": 0,
23
+ "num_attention_heads": 12,
24
+ "num_hidden_groups": 1,
25
+ "num_hidden_layers": 12,
26
+ "num_memory_blocks": 0,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "torch_dtype": "float16",
30
+ "transformers_version": "4.30.0",
31
+ "type_vocab_size": 2,
32
+ "vocab_size": 30000
33
+ }
finetune-BERT-squad/checkpoint-10500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
3
+ size 14244
finetune-BERT-squad/checkpoint-10500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b5c676a172f39a05d18e821ef975eb1daba1ccb2ebd04630b26f189f1a127e1
3
+ size 1064
finetune-BERT-squad/checkpoint-10500/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": {
6
+ "content": "[MASK]",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "[SEP]",
14
+ "unk_token": "<unk>"
15
+ }
finetune-BERT-squad/checkpoint-10500/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
3
+ size 760289
finetune-BERT-squad/checkpoint-10500/tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": true,
6
+ "eos_token": "[SEP]",
7
+ "keep_accents": false,
8
+ "mask_token": {
9
+ "__type": "AddedToken",
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "model_max_length": 512,
17
+ "pad_token": "<pad>",
18
+ "remove_space": true,
19
+ "sep_token": "[SEP]",
20
+ "tokenizer_class": "AlbertTokenizer",
21
+ "unk_token": "<unk>"
22
+ }
finetune-BERT-squad/checkpoint-10500/trainer_state.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9476534296028881,
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": 0.05,
12
+ "learning_rate": 1.969915764139591e-05,
13
+ "loss": 3.07,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.09,
18
+ "learning_rate": 1.939831528279182e-05,
19
+ "loss": 0.0,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.14,
24
+ "learning_rate": 1.9097472924187726e-05,
25
+ "loss": 0.0,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.18,
30
+ "learning_rate": 1.8796630565583636e-05,
31
+ "loss": 0.0,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.23,
36
+ "learning_rate": 1.8495788206979545e-05,
37
+ "loss": 0.0,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.27,
42
+ "learning_rate": 1.8194945848375454e-05,
43
+ "loss": 0.0,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.32,
48
+ "learning_rate": 1.789410348977136e-05,
49
+ "loss": 0.0,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.36,
54
+ "learning_rate": 1.759326113116727e-05,
55
+ "loss": 0.0,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.41,
60
+ "learning_rate": 1.729241877256318e-05,
61
+ "loss": 0.0,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.45,
66
+ "learning_rate": 1.699157641395909e-05,
67
+ "loss": 0.0,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.5,
72
+ "learning_rate": 1.6690734055354995e-05,
73
+ "loss": 0.0,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.54,
78
+ "learning_rate": 1.6389891696750904e-05,
79
+ "loss": 0.0,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.59,
84
+ "learning_rate": 1.608904933814681e-05,
85
+ "loss": 0.0,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.63,
90
+ "learning_rate": 1.5788206979542723e-05,
91
+ "loss": 0.0,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.68,
96
+ "learning_rate": 1.548736462093863e-05,
97
+ "loss": 0.0,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.72,
102
+ "learning_rate": 1.5186522262334538e-05,
103
+ "loss": 0.0,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.77,
108
+ "learning_rate": 1.4885679903730446e-05,
109
+ "loss": 0.0,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.81,
114
+ "learning_rate": 1.4584837545126355e-05,
115
+ "loss": 0.0,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.86,
120
+ "learning_rate": 1.4283995186522264e-05,
121
+ "loss": 0.0,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.9,
126
+ "learning_rate": 1.3983152827918172e-05,
127
+ "loss": 0.0,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.95,
132
+ "learning_rate": 1.368231046931408e-05,
133
+ "loss": 0.0,
134
+ "step": 10500
135
+ }
136
+ ],
137
+ "max_steps": 33240,
138
+ "num_train_epochs": 3,
139
+ "total_flos": 1391279597568000.0,
140
+ "trial_name": null,
141
+ "trial_params": null
142
+ }
finetune-BERT-squad/checkpoint-10500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f25d45105510bc009d36d968cf2b27158670787ad134758fabe6d424d332bdeb
3
+ size 4408
finetune-BERT-squad/checkpoint-11000/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "albert/albert-base-v2",
3
+ "architectures": [
4
+ "AlbertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "down_scale_factor": 1,
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "gap_size": 0,
13
+ "hidden_act": "gelu_new",
14
+ "hidden_dropout_prob": 0,
15
+ "hidden_size": 768,
16
+ "initializer_range": 0.02,
17
+ "inner_group_num": 1,
18
+ "intermediate_size": 3072,
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "albert",
22
+ "net_structure_type": 0,
23
+ "num_attention_heads": 12,
24
+ "num_hidden_groups": 1,
25
+ "num_hidden_layers": 12,
26
+ "num_memory_blocks": 0,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "torch_dtype": "float16",
30
+ "transformers_version": "4.30.0",
31
+ "type_vocab_size": 2,
32
+ "vocab_size": 30000
33
+ }
finetune-BERT-squad/checkpoint-11000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95f732e997fb579186b4c45fe3cff07396aa34e0b07425bfd2a6d41bf032526d
3
+ size 44393260
finetune-BERT-squad/checkpoint-11000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fdeb97697ca1d02eb5794ce1a4ad2faf59cddb49d858fa318fbec73b089248e
3
+ size 22202620
finetune-BERT-squad/checkpoint-11000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
3
+ size 14244
finetune-BERT-squad/checkpoint-11000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68ab103c661e8bcc74840891359532ada0dc95aaad4e01ed2d723d41bd7f5170
3
+ size 1064
finetune-BERT-squad/checkpoint-11000/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": {
6
+ "content": "[MASK]",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "[SEP]",
14
+ "unk_token": "<unk>"
15
+ }
finetune-BERT-squad/checkpoint-11000/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
3
+ size 760289
finetune-BERT-squad/checkpoint-11000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
finetune-BERT-squad/checkpoint-11000/tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": true,
6
+ "eos_token": "[SEP]",
7
+ "keep_accents": false,
8
+ "mask_token": {
9
+ "__type": "AddedToken",
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "model_max_length": 512,
17
+ "pad_token": "<pad>",
18
+ "remove_space": true,
19
+ "sep_token": "[SEP]",
20
+ "tokenizer_class": "AlbertTokenizer",
21
+ "unk_token": "<unk>"
22
+ }
finetune-BERT-squad/checkpoint-11000/trainer_state.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9927797833935018,
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": 0.05,
12
+ "learning_rate": 1.969915764139591e-05,
13
+ "loss": 3.07,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.09,
18
+ "learning_rate": 1.939831528279182e-05,
19
+ "loss": 0.0,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.14,
24
+ "learning_rate": 1.9097472924187726e-05,
25
+ "loss": 0.0,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.18,
30
+ "learning_rate": 1.8796630565583636e-05,
31
+ "loss": 0.0,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.23,
36
+ "learning_rate": 1.8495788206979545e-05,
37
+ "loss": 0.0,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.27,
42
+ "learning_rate": 1.8194945848375454e-05,
43
+ "loss": 0.0,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.32,
48
+ "learning_rate": 1.789410348977136e-05,
49
+ "loss": 0.0,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.36,
54
+ "learning_rate": 1.759326113116727e-05,
55
+ "loss": 0.0,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.41,
60
+ "learning_rate": 1.729241877256318e-05,
61
+ "loss": 0.0,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.45,
66
+ "learning_rate": 1.699157641395909e-05,
67
+ "loss": 0.0,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.5,
72
+ "learning_rate": 1.6690734055354995e-05,
73
+ "loss": 0.0,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.54,
78
+ "learning_rate": 1.6389891696750904e-05,
79
+ "loss": 0.0,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.59,
84
+ "learning_rate": 1.608904933814681e-05,
85
+ "loss": 0.0,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.63,
90
+ "learning_rate": 1.5788206979542723e-05,
91
+ "loss": 0.0,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.68,
96
+ "learning_rate": 1.548736462093863e-05,
97
+ "loss": 0.0,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.72,
102
+ "learning_rate": 1.5186522262334538e-05,
103
+ "loss": 0.0,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.77,
108
+ "learning_rate": 1.4885679903730446e-05,
109
+ "loss": 0.0,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.81,
114
+ "learning_rate": 1.4584837545126355e-05,
115
+ "loss": 0.0,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.86,
120
+ "learning_rate": 1.4283995186522264e-05,
121
+ "loss": 0.0,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.9,
126
+ "learning_rate": 1.3983152827918172e-05,
127
+ "loss": 0.0,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.95,
132
+ "learning_rate": 1.368231046931408e-05,
133
+ "loss": 0.0,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.99,
138
+ "learning_rate": 1.338146811070999e-05,
139
+ "loss": 0.0,
140
+ "step": 11000
141
+ }
142
+ ],
143
+ "max_steps": 33240,
144
+ "num_train_epochs": 3,
145
+ "total_flos": 1457531006976000.0,
146
+ "trial_name": null,
147
+ "trial_params": null
148
+ }
finetune-BERT-squad/checkpoint-11000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f25d45105510bc009d36d968cf2b27158670787ad134758fabe6d424d332bdeb
3
+ size 4408
finetune-BERT-squad/checkpoint-11500/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "albert/albert-base-v2",
3
+ "architectures": [
4
+ "AlbertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "down_scale_factor": 1,
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "gap_size": 0,
13
+ "hidden_act": "gelu_new",
14
+ "hidden_dropout_prob": 0,
15
+ "hidden_size": 768,
16
+ "initializer_range": 0.02,
17
+ "inner_group_num": 1,
18
+ "intermediate_size": 3072,
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "albert",
22
+ "net_structure_type": 0,
23
+ "num_attention_heads": 12,
24
+ "num_hidden_groups": 1,
25
+ "num_hidden_layers": 12,
26
+ "num_memory_blocks": 0,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "torch_dtype": "float16",
30
+ "transformers_version": "4.30.0",
31
+ "type_vocab_size": 2,
32
+ "vocab_size": 30000
33
+ }
finetune-BERT-squad/checkpoint-11500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
3
+ size 14244
finetune-BERT-squad/checkpoint-11500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f6340d550096bab4c7e42fa613a759acb67c9e7ee9c0812ab10acee70c81ff
3
+ size 1064
finetune-BERT-squad/checkpoint-11500/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": {
6
+ "content": "[MASK]",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "[SEP]",
14
+ "unk_token": "<unk>"
15
+ }
finetune-BERT-squad/checkpoint-11500/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
3
+ size 760289
finetune-BERT-squad/checkpoint-11500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
finetune-BERT-squad/checkpoint-11500/tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": true,
6
+ "eos_token": "[SEP]",
7
+ "keep_accents": false,
8
+ "mask_token": {
9
+ "__type": "AddedToken",
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "model_max_length": 512,
17
+ "pad_token": "<pad>",
18
+ "remove_space": true,
19
+ "sep_token": "[SEP]",
20
+ "tokenizer_class": "AlbertTokenizer",
21
+ "unk_token": "<unk>"
22
+ }
finetune-BERT-squad/checkpoint-11500/trainer_state.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0379061371841156,
5
+ "global_step": 11500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "learning_rate": 1.969915764139591e-05,
13
+ "loss": 3.07,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.09,
18
+ "learning_rate": 1.939831528279182e-05,
19
+ "loss": 0.0,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.14,
24
+ "learning_rate": 1.9097472924187726e-05,
25
+ "loss": 0.0,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.18,
30
+ "learning_rate": 1.8796630565583636e-05,
31
+ "loss": 0.0,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.23,
36
+ "learning_rate": 1.8495788206979545e-05,
37
+ "loss": 0.0,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.27,
42
+ "learning_rate": 1.8194945848375454e-05,
43
+ "loss": 0.0,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.32,
48
+ "learning_rate": 1.789410348977136e-05,
49
+ "loss": 0.0,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.36,
54
+ "learning_rate": 1.759326113116727e-05,
55
+ "loss": 0.0,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.41,
60
+ "learning_rate": 1.729241877256318e-05,
61
+ "loss": 0.0,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.45,
66
+ "learning_rate": 1.699157641395909e-05,
67
+ "loss": 0.0,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.5,
72
+ "learning_rate": 1.6690734055354995e-05,
73
+ "loss": 0.0,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.54,
78
+ "learning_rate": 1.6389891696750904e-05,
79
+ "loss": 0.0,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.59,
84
+ "learning_rate": 1.608904933814681e-05,
85
+ "loss": 0.0,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.63,
90
+ "learning_rate": 1.5788206979542723e-05,
91
+ "loss": 0.0,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.68,
96
+ "learning_rate": 1.548736462093863e-05,
97
+ "loss": 0.0,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.72,
102
+ "learning_rate": 1.5186522262334538e-05,
103
+ "loss": 0.0,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.77,
108
+ "learning_rate": 1.4885679903730446e-05,
109
+ "loss": 0.0,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.81,
114
+ "learning_rate": 1.4584837545126355e-05,
115
+ "loss": 0.0,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.86,
120
+ "learning_rate": 1.4283995186522264e-05,
121
+ "loss": 0.0,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.9,
126
+ "learning_rate": 1.3983152827918172e-05,
127
+ "loss": 0.0,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.95,
132
+ "learning_rate": 1.368231046931408e-05,
133
+ "loss": 0.0,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.99,
138
+ "learning_rate": 1.338146811070999e-05,
139
+ "loss": 0.0,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 1.0,
144
+ "eval_loss": NaN,
145
+ "eval_runtime": 72.3735,
146
+ "eval_samples_per_second": 149.336,
147
+ "eval_steps_per_second": 18.667,
148
+ "step": 11080
149
+ },
150
+ {
151
+ "epoch": 1.04,
152
+ "learning_rate": 1.3080625752105897e-05,
153
+ "loss": 0.0,
154
+ "step": 11500
155
+ }
156
+ ],
157
+ "max_steps": 33240,
158
+ "num_train_epochs": 3,
159
+ "total_flos": 1523749290679296.0,
160
+ "trial_name": null,
161
+ "trial_params": null
162
+ }
finetune-BERT-squad/checkpoint-11500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f25d45105510bc009d36d968cf2b27158670787ad134758fabe6d424d332bdeb
3
+ size 4408
finetune-BERT-squad/checkpoint-12000/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "albert/albert-base-v2",
3
+ "architectures": [
4
+ "AlbertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "down_scale_factor": 1,
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "gap_size": 0,
13
+ "hidden_act": "gelu_new",
14
+ "hidden_dropout_prob": 0,
15
+ "hidden_size": 768,
16
+ "initializer_range": 0.02,
17
+ "inner_group_num": 1,
18
+ "intermediate_size": 3072,
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "albert",
22
+ "net_structure_type": 0,
23
+ "num_attention_heads": 12,
24
+ "num_hidden_groups": 1,
25
+ "num_hidden_layers": 12,
26
+ "num_memory_blocks": 0,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "torch_dtype": "float16",
30
+ "transformers_version": "4.30.0",
31
+ "type_vocab_size": 2,
32
+ "vocab_size": 30000
33
+ }
finetune-BERT-squad/checkpoint-12000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fdeb97697ca1d02eb5794ce1a4ad2faf59cddb49d858fa318fbec73b089248e
3
+ size 22202620
finetune-BERT-squad/checkpoint-12000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
3
+ size 14244
finetune-BERT-squad/checkpoint-12000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2831058d573ecbab962cf6c1524191f511f2039da31145974b7a419a34df0d74
3
+ size 1064