Hugging Face's logo

Elkelouizajo
/
bert_mixed

Safetensors
bert
Generated from Trainer
Model card Files Community
Elkelouizajo commited on
Commit
7237c8e
•
1 Parent(s): 8273043

Upload 33 files

Browse files
Files changed (33) hide show
  1. checkpoint-8000/config.json +42 -0
  2. checkpoint-8000/model.safetensors +3 -0
  3. checkpoint-8000/optimizer.pt +3 -0
  4. checkpoint-8000/rng_state.pth +3 -0
  5. checkpoint-8000/scheduler.pt +3 -0
  6. checkpoint-8000/special_tokens_map.json +7 -0
  7. checkpoint-8000/tokenizer.json +0 -0
  8. checkpoint-8000/tokenizer_config.json +55 -0
  9. checkpoint-8000/trainer_state.json +133 -0
  10. checkpoint-8000/training_args.bin +3 -0
  11. checkpoint-8000/vocab.txt +0 -0
  12. checkpoint-8500/config.json +42 -0
  13. checkpoint-8500/model.safetensors +3 -0
  14. checkpoint-8500/optimizer.pt +3 -0
  15. checkpoint-8500/rng_state.pth +3 -0
  16. checkpoint-8500/scheduler.pt +3 -0
  17. checkpoint-8500/special_tokens_map.json +7 -0
  18. checkpoint-8500/tokenizer.json +0 -0
  19. checkpoint-8500/tokenizer_config.json +55 -0
  20. checkpoint-8500/trainer_state.json +140 -0
  21. checkpoint-8500/training_args.bin +3 -0
  22. checkpoint-8500/vocab.txt +0 -0
  23. checkpoint-9000/config.json +42 -0
  24. checkpoint-9000/model.safetensors +3 -0
  25. checkpoint-9000/optimizer.pt +3 -0
  26. checkpoint-9000/rng_state.pth +3 -0
  27. checkpoint-9000/scheduler.pt +3 -0
  28. checkpoint-9000/special_tokens_map.json +7 -0
  29. checkpoint-9000/tokenizer.json +0 -0
  30. checkpoint-9000/tokenizer_config.json +55 -0
  31. checkpoint-9000/trainer_state.json +147 -0
  32. checkpoint-9000/training_args.bin +3 -0
  33. checkpoint-9000/vocab.txt +0 -0
checkpoint-8000/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-large-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "finetuning_task": "text-classification",
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "0",
16
+ "1": "1"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "0": 0,
22
+ "1": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 16,
28
+ "num_hidden_layers": 24,
29
+ "pad_token_id": 0,
30
+ "pooler_fc_size": 768,
31
+ "pooler_num_attention_heads": 12,
32
+ "pooler_num_fc_layers": 3,
33
+ "pooler_size_per_head": 128,
34
+ "pooler_type": "first_token_transform",
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.39.0.dev0",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 28996
42
+ }
checkpoint-8000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:154e0b4b0a8e2e84997a967b8d6fb5bd637c9f5fdc58a5f5cb5e0969e0a8a7c4
3
+ size 1334372264
checkpoint-8000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdf7e6e295fd1ed8b7d77eabc7ca43e16523878ff9af933785179a0bb5c0805c
3
+ size 2668968429
checkpoint-8000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afb92490982966c7e7b0789a8bc82bf6f25ae8d471d5b63ed860553eb0abf7a3
3
+ size 13990
checkpoint-8000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d02757c53939130582876d4b5cc049eaf9e6ff4f7a7ba81366771bb4dad1a581
3
+ size 1064
checkpoint-8000/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-8000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8000/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
checkpoint-8000/trainer_state.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.00200100050025,
5
+ "eval_steps": 500,
6
+ "global_step": 8000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.25,
13
+ "grad_norm": 40.72060012817383,
14
+ "learning_rate": 1.8999499749874938e-05,
15
+ "loss": 0.416,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "grad_norm": 0.45640167593955994,
21
+ "learning_rate": 1.7998999499749875e-05,
22
+ "loss": 0.259,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.75,
27
+ "grad_norm": 24.118961334228516,
28
+ "learning_rate": 1.6998499249624815e-05,
29
+ "loss": 0.2726,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 43.76200485229492,
35
+ "learning_rate": 1.599799899949975e-05,
36
+ "loss": 0.2471,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.25,
41
+ "grad_norm": 31.93831443786621,
42
+ "learning_rate": 1.4997498749374688e-05,
43
+ "loss": 0.1518,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 1.5,
48
+ "grad_norm": 0.02012985199689865,
49
+ "learning_rate": 1.3996998499249626e-05,
50
+ "loss": 0.1421,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 1.75,
55
+ "grad_norm": 0.22942015528678894,
56
+ "learning_rate": 1.2996498249124563e-05,
57
+ "loss": 0.1463,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 2.0,
62
+ "grad_norm": 0.18562756478786469,
63
+ "learning_rate": 1.19959979989995e-05,
64
+ "loss": 0.1512,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 2.25,
69
+ "grad_norm": 0.14861415326595306,
70
+ "learning_rate": 1.0995497748874438e-05,
71
+ "loss": 0.0811,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 2.5,
76
+ "grad_norm": 0.19507120549678802,
77
+ "learning_rate": 9.994997498749376e-06,
78
+ "loss": 0.0634,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 2.75,
83
+ "grad_norm": 0.011564640328288078,
84
+ "learning_rate": 8.994497248624313e-06,
85
+ "loss": 0.0776,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 3.0,
90
+ "grad_norm": 0.1320619136095047,
91
+ "learning_rate": 7.993996998499251e-06,
92
+ "loss": 0.0583,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 3.25,
97
+ "grad_norm": 0.002501310082152486,
98
+ "learning_rate": 6.9934967483741875e-06,
99
+ "loss": 0.0283,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 3.5,
104
+ "grad_norm": 0.008065233938395977,
105
+ "learning_rate": 5.992996498249125e-06,
106
+ "loss": 0.0245,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 3.75,
111
+ "grad_norm": 0.012150153517723083,
112
+ "learning_rate": 4.992496248124062e-06,
113
+ "loss": 0.0282,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 4.0,
118
+ "grad_norm": 0.0018927728524431586,
119
+ "learning_rate": 3.991995997999e-06,
120
+ "loss": 0.0181,
121
+ "step": 8000
122
+ }
123
+ ],
124
+ "logging_steps": 500,
125
+ "max_steps": 9995,
126
+ "num_input_tokens_seen": 0,
127
+ "num_train_epochs": 5,
128
+ "save_steps": 500,
129
+ "total_flos": 1.4909037950521344e+16,
130
+ "train_batch_size": 8,
131
+ "trial_name": null,
132
+ "trial_params": null
133
+ }
checkpoint-8000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2af8ef0f6a7e09f2ebe39e5b7c56b97bb0da3d67bdca473d4e30026e53d8a99
3
+ size 4920
checkpoint-8000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8500/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-large-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "finetuning_task": "text-classification",
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "0",
16
+ "1": "1"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "0": 0,
22
+ "1": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 16,
28
+ "num_hidden_layers": 24,
29
+ "pad_token_id": 0,
30
+ "pooler_fc_size": 768,
31
+ "pooler_num_attention_heads": 12,
32
+ "pooler_num_fc_layers": 3,
33
+ "pooler_size_per_head": 128,
34
+ "pooler_type": "first_token_transform",
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.39.0.dev0",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 28996
42
+ }
checkpoint-8500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:575a89ec8a94bd4de9161a0d52f2136868f5472043b4747c01fb08d921e1b8c0
3
+ size 1334372264
checkpoint-8500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da1c150043e4fb7e6a20649baf6bcddfaaf778e063711fd34d24760b35b23b43
3
+ size 2668968429
checkpoint-8500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9a715511c204b43c860ba7e3b91437f68ee5c1f37b9efc8f7f51cfcabcf38c5
3
+ size 13990
checkpoint-8500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7084ff96214ff2c9040c391610f97fbfc3440f9dbcd812fff653e0655bcdea93
3
+ size 1064
checkpoint-8500/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-8500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8500/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
checkpoint-8500/trainer_state.json ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.252126063031516,
5
+ "eval_steps": 500,
6
+ "global_step": 8500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.25,
13
+ "grad_norm": 40.72060012817383,
14
+ "learning_rate": 1.8999499749874938e-05,
15
+ "loss": 0.416,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "grad_norm": 0.45640167593955994,
21
+ "learning_rate": 1.7998999499749875e-05,
22
+ "loss": 0.259,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.75,
27
+ "grad_norm": 24.118961334228516,
28
+ "learning_rate": 1.6998499249624815e-05,
29
+ "loss": 0.2726,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 43.76200485229492,
35
+ "learning_rate": 1.599799899949975e-05,
36
+ "loss": 0.2471,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.25,
41
+ "grad_norm": 31.93831443786621,
42
+ "learning_rate": 1.4997498749374688e-05,
43
+ "loss": 0.1518,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 1.5,
48
+ "grad_norm": 0.02012985199689865,
49
+ "learning_rate": 1.3996998499249626e-05,
50
+ "loss": 0.1421,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 1.75,
55
+ "grad_norm": 0.22942015528678894,
56
+ "learning_rate": 1.2996498249124563e-05,
57
+ "loss": 0.1463,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 2.0,
62
+ "grad_norm": 0.18562756478786469,
63
+ "learning_rate": 1.19959979989995e-05,
64
+ "loss": 0.1512,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 2.25,
69
+ "grad_norm": 0.14861415326595306,
70
+ "learning_rate": 1.0995497748874438e-05,
71
+ "loss": 0.0811,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 2.5,
76
+ "grad_norm": 0.19507120549678802,
77
+ "learning_rate": 9.994997498749376e-06,
78
+ "loss": 0.0634,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 2.75,
83
+ "grad_norm": 0.011564640328288078,
84
+ "learning_rate": 8.994497248624313e-06,
85
+ "loss": 0.0776,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 3.0,
90
+ "grad_norm": 0.1320619136095047,
91
+ "learning_rate": 7.993996998499251e-06,
92
+ "loss": 0.0583,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 3.25,
97
+ "grad_norm": 0.002501310082152486,
98
+ "learning_rate": 6.9934967483741875e-06,
99
+ "loss": 0.0283,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 3.5,
104
+ "grad_norm": 0.008065233938395977,
105
+ "learning_rate": 5.992996498249125e-06,
106
+ "loss": 0.0245,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 3.75,
111
+ "grad_norm": 0.012150153517723083,
112
+ "learning_rate": 4.992496248124062e-06,
113
+ "loss": 0.0282,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 4.0,
118
+ "grad_norm": 0.0018927728524431586,
119
+ "learning_rate": 3.991995997999e-06,
120
+ "loss": 0.0181,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 4.25,
125
+ "grad_norm": 0.00044900510692968965,
126
+ "learning_rate": 2.991495747873937e-06,
127
+ "loss": 0.0051,
128
+ "step": 8500
129
+ }
130
+ ],
131
+ "logging_steps": 500,
132
+ "max_steps": 9995,
133
+ "num_input_tokens_seen": 0,
134
+ "num_train_epochs": 5,
135
+ "save_steps": 500,
136
+ "total_flos": 1.5840969313849344e+16,
137
+ "train_batch_size": 8,
138
+ "trial_name": null,
139
+ "trial_params": null
140
+ }
checkpoint-8500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2af8ef0f6a7e09f2ebe39e5b7c56b97bb0da3d67bdca473d4e30026e53d8a99
3
+ size 4920
checkpoint-8500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-9000/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-large-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "finetuning_task": "text-classification",
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "0",
16
+ "1": "1"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "0": 0,
22
+ "1": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 16,
28
+ "num_hidden_layers": 24,
29
+ "pad_token_id": 0,
30
+ "pooler_fc_size": 768,
31
+ "pooler_num_attention_heads": 12,
32
+ "pooler_num_fc_layers": 3,
33
+ "pooler_size_per_head": 128,
34
+ "pooler_type": "first_token_transform",
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.39.0.dev0",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 28996
42
+ }
checkpoint-9000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba8155b1ecc69deaebcf73193a218424c35b2e0f61318ea2bcc07df10b40989d
3
+ size 1334372264
checkpoint-9000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa075b22a65c8ea60ff1a9a9134373d8885887c1c4664b7c5297084d04d0089f
3
+ size 2668968429
checkpoint-9000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24ca7a01cbf3d55837a7b2d127658498bf66f39691d38efe881948c2831f3bd8
3
+ size 13990
checkpoint-9000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56472f9474b6da777d44c5285f2be40ac4dca0945b67e9814473834390db7805
3
+ size 1064
checkpoint-9000/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-9000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-9000/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
checkpoint-9000/trainer_state.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.502251125562782,
5
+ "eval_steps": 500,
6
+ "global_step": 9000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.25,
13
+ "grad_norm": 40.72060012817383,
14
+ "learning_rate": 1.8999499749874938e-05,
15
+ "loss": 0.416,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "grad_norm": 0.45640167593955994,
21
+ "learning_rate": 1.7998999499749875e-05,
22
+ "loss": 0.259,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.75,
27
+ "grad_norm": 24.118961334228516,
28
+ "learning_rate": 1.6998499249624815e-05,
29
+ "loss": 0.2726,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 43.76200485229492,
35
+ "learning_rate": 1.599799899949975e-05,
36
+ "loss": 0.2471,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.25,
41
+ "grad_norm": 31.93831443786621,
42
+ "learning_rate": 1.4997498749374688e-05,
43
+ "loss": 0.1518,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 1.5,
48
+ "grad_norm": 0.02012985199689865,
49
+ "learning_rate": 1.3996998499249626e-05,
50
+ "loss": 0.1421,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 1.75,
55
+ "grad_norm": 0.22942015528678894,
56
+ "learning_rate": 1.2996498249124563e-05,
57
+ "loss": 0.1463,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 2.0,
62
+ "grad_norm": 0.18562756478786469,
63
+ "learning_rate": 1.19959979989995e-05,
64
+ "loss": 0.1512,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 2.25,
69
+ "grad_norm": 0.14861415326595306,
70
+ "learning_rate": 1.0995497748874438e-05,
71
+ "loss": 0.0811,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 2.5,
76
+ "grad_norm": 0.19507120549678802,
77
+ "learning_rate": 9.994997498749376e-06,
78
+ "loss": 0.0634,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 2.75,
83
+ "grad_norm": 0.011564640328288078,
84
+ "learning_rate": 8.994497248624313e-06,
85
+ "loss": 0.0776,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 3.0,
90
+ "grad_norm": 0.1320619136095047,
91
+ "learning_rate": 7.993996998499251e-06,
92
+ "loss": 0.0583,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 3.25,
97
+ "grad_norm": 0.002501310082152486,
98
+ "learning_rate": 6.9934967483741875e-06,
99
+ "loss": 0.0283,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 3.5,
104
+ "grad_norm": 0.008065233938395977,
105
+ "learning_rate": 5.992996498249125e-06,
106
+ "loss": 0.0245,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 3.75,
111
+ "grad_norm": 0.012150153517723083,
112
+ "learning_rate": 4.992496248124062e-06,
113
+ "loss": 0.0282,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 4.0,
118
+ "grad_norm": 0.0018927728524431586,
119
+ "learning_rate": 3.991995997999e-06,
120
+ "loss": 0.0181,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 4.25,
125
+ "grad_norm": 0.00044900510692968965,
126
+ "learning_rate": 2.991495747873937e-06,
127
+ "loss": 0.0051,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 4.5,
132
+ "grad_norm": 0.0030473130755126476,
133
+ "learning_rate": 1.9909954977488747e-06,
134
+ "loss": 0.0097,
135
+ "step": 9000
136
+ }
137
+ ],
138
+ "logging_steps": 500,
139
+ "max_steps": 9995,
140
+ "num_input_tokens_seen": 0,
141
+ "num_train_epochs": 5,
142
+ "save_steps": 500,
143
+ "total_flos": 1.6772900677177344e+16,
144
+ "train_batch_size": 8,
145
+ "trial_name": null,
146
+ "trial_params": null
147
+ }
checkpoint-9000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2af8ef0f6a7e09f2ebe39e5b7c56b97bb0da3d67bdca473d4e30026e53d8a99
3
+ size 4920
checkpoint-9000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff