Hugging Face's logo

Elkelouizajo
/
bert_mnli_16000

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Model card Files Community
Elkelouizajo commited on
Commit
908736a
·
verified ·
1 Parent(s): 5dd6b13

Upload 44 files

Browse files
Files changed (44) hide show
  1. checkpoint-6500/config.json +42 -0
  2. checkpoint-6500/model.safetensors +3 -0
  3. checkpoint-6500/optimizer.pt +3 -0
  4. checkpoint-6500/rng_state.pth +3 -0
  5. checkpoint-6500/scheduler.pt +3 -0
  6. checkpoint-6500/special_tokens_map.json +7 -0
  7. checkpoint-6500/tokenizer.json +0 -0
  8. checkpoint-6500/tokenizer_config.json +55 -0
  9. checkpoint-6500/trainer_state.json +112 -0
  10. checkpoint-6500/training_args.bin +3 -0
  11. checkpoint-6500/vocab.txt +0 -0
  12. checkpoint-7000/config.json +42 -0
  13. checkpoint-7000/model.safetensors +3 -0
  14. checkpoint-7000/optimizer.pt +3 -0
  15. checkpoint-7000/rng_state.pth +3 -0
  16. checkpoint-7000/scheduler.pt +3 -0
  17. checkpoint-7000/special_tokens_map.json +7 -0
  18. checkpoint-7000/tokenizer.json +0 -0
  19. checkpoint-7000/tokenizer_config.json +55 -0
  20. checkpoint-7000/trainer_state.json +119 -0
  21. checkpoint-7000/training_args.bin +3 -0
  22. checkpoint-7000/vocab.txt +0 -0
  23. checkpoint-7500/config.json +42 -0
  24. checkpoint-7500/model.safetensors +3 -0
  25. checkpoint-7500/optimizer.pt +3 -0
  26. checkpoint-7500/rng_state.pth +3 -0
  27. checkpoint-7500/scheduler.pt +3 -0
  28. checkpoint-7500/special_tokens_map.json +7 -0
  29. checkpoint-7500/tokenizer.json +0 -0
  30. checkpoint-7500/tokenizer_config.json +55 -0
  31. checkpoint-7500/trainer_state.json +126 -0
  32. checkpoint-7500/training_args.bin +3 -0
  33. checkpoint-7500/vocab.txt +0 -0
  34. checkpoint-8000/config.json +42 -0
  35. checkpoint-8000/model.safetensors +3 -0
  36. checkpoint-8000/optimizer.pt +3 -0
  37. checkpoint-8000/rng_state.pth +3 -0
  38. checkpoint-8000/scheduler.pt +3 -0
  39. checkpoint-8000/special_tokens_map.json +7 -0
  40. checkpoint-8000/tokenizer.json +0 -0
  41. checkpoint-8000/tokenizer_config.json +55 -0
  42. checkpoint-8000/trainer_state.json +133 -0
  43. checkpoint-8000/training_args.bin +3 -0
  44. checkpoint-8000/vocab.txt +0 -0
checkpoint-6500/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-6500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe9381b24d543696c4a11d7143a8d8ae68467417618e006aa078afd1cd3dd703
3
+ size 1334372264
checkpoint-6500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c1cd2d5c0b323070cd85ec421b91fcf0975817523eb708b0f89a82243683ae1
3
+ size 2668968429
checkpoint-6500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2349598297f3d5d73da41d93042eb9effb689fcf508061b856207681383ff320
3
+ size 13990
checkpoint-6500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed612511e64a411b4f219a1dbbb99a172cb37a5d69b1f12f84cb3c0cd4390ff6
3
+ size 1064
checkpoint-6500/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-6500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-6500/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-6500/trainer_state.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.25,
5
+ "eval_steps": 500,
6
+ "global_step": 6500,
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": 9.530180931091309,
14
+ "learning_rate": 1.9e-05,
15
+ "loss": 0.7046,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "grad_norm": 11.739270210266113,
21
+ "learning_rate": 1.8e-05,
22
+ "loss": 0.574,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.75,
27
+ "grad_norm": 21.960508346557617,
28
+ "learning_rate": 1.7e-05,
29
+ "loss": 0.4031,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 1.2487173080444336,
35
+ "learning_rate": 1.6000000000000003e-05,
36
+ "loss": 0.38,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.25,
41
+ "grad_norm": 11.083433151245117,
42
+ "learning_rate": 1.5000000000000002e-05,
43
+ "loss": 0.2964,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 1.5,
48
+ "grad_norm": 0.22524116933345795,
49
+ "learning_rate": 1.4e-05,
50
+ "loss": 0.3073,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 1.75,
55
+ "grad_norm": 1.0325411558151245,
56
+ "learning_rate": 1.3000000000000001e-05,
57
+ "loss": 0.3027,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 2.0,
62
+ "grad_norm": 10.020037651062012,
63
+ "learning_rate": 1.2e-05,
64
+ "loss": 0.3056,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 2.25,
69
+ "grad_norm": 0.0707927793264389,
70
+ "learning_rate": 1.1000000000000001e-05,
71
+ "loss": 0.1681,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 2.5,
76
+ "grad_norm": 54.09671401977539,
77
+ "learning_rate": 1e-05,
78
+ "loss": 0.1322,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 2.75,
83
+ "grad_norm": 0.42837992310523987,
84
+ "learning_rate": 9e-06,
85
+ "loss": 0.1669,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 3.0,
90
+ "grad_norm": 0.044212982058525085,
91
+ "learning_rate": 8.000000000000001e-06,
92
+ "loss": 0.1565,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 3.25,
97
+ "grad_norm": 0.036281220614910126,
98
+ "learning_rate": 7e-06,
99
+ "loss": 0.0684,
100
+ "step": 6500
101
+ }
102
+ ],
103
+ "logging_steps": 500,
104
+ "max_steps": 10000,
105
+ "num_input_tokens_seen": 0,
106
+ "num_train_epochs": 5,
107
+ "save_steps": 500,
108
+ "total_flos": 1.2110215083606528e+16,
109
+ "train_batch_size": 8,
110
+ "trial_name": null,
111
+ "trial_params": null
112
+ }
checkpoint-6500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c723a0cd71eedc1750912629ef866d84ce379f07f7fbfd5f98bcb6058f7ae473
3
+ size 4920
checkpoint-6500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-7000/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-7000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99b6a627f4965fa5428684537bc20a2883432b9dbe62f1f05071d8c364adc625
3
+ size 1334372264
checkpoint-7000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc2b7de3de75f1a04fcf86b2eb17055df1f802b77d3853a64141c04b78aaeae0
3
+ size 2668968429
checkpoint-7000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e8288967decac787e018817c7c931ed282f15b6bd6c72bddb24d4ee4e068fc0
3
+ size 13990
checkpoint-7000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb18a42f29217f3b1b3c50001b428dacfa5f9ce8ca678597cee0eed3bbf2ccb
3
+ size 1064
checkpoint-7000/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-7000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-7000/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-7000/trainer_state.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.5,
5
+ "eval_steps": 500,
6
+ "global_step": 7000,
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": 9.530180931091309,
14
+ "learning_rate": 1.9e-05,
15
+ "loss": 0.7046,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "grad_norm": 11.739270210266113,
21
+ "learning_rate": 1.8e-05,
22
+ "loss": 0.574,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.75,
27
+ "grad_norm": 21.960508346557617,
28
+ "learning_rate": 1.7e-05,
29
+ "loss": 0.4031,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 1.2487173080444336,
35
+ "learning_rate": 1.6000000000000003e-05,
36
+ "loss": 0.38,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.25,
41
+ "grad_norm": 11.083433151245117,
42
+ "learning_rate": 1.5000000000000002e-05,
43
+ "loss": 0.2964,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 1.5,
48
+ "grad_norm": 0.22524116933345795,
49
+ "learning_rate": 1.4e-05,
50
+ "loss": 0.3073,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 1.75,
55
+ "grad_norm": 1.0325411558151245,
56
+ "learning_rate": 1.3000000000000001e-05,
57
+ "loss": 0.3027,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 2.0,
62
+ "grad_norm": 10.020037651062012,
63
+ "learning_rate": 1.2e-05,
64
+ "loss": 0.3056,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 2.25,
69
+ "grad_norm": 0.0707927793264389,
70
+ "learning_rate": 1.1000000000000001e-05,
71
+ "loss": 0.1681,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 2.5,
76
+ "grad_norm": 54.09671401977539,
77
+ "learning_rate": 1e-05,
78
+ "loss": 0.1322,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 2.75,
83
+ "grad_norm": 0.42837992310523987,
84
+ "learning_rate": 9e-06,
85
+ "loss": 0.1669,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 3.0,
90
+ "grad_norm": 0.044212982058525085,
91
+ "learning_rate": 8.000000000000001e-06,
92
+ "loss": 0.1565,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 3.25,
97
+ "grad_norm": 0.036281220614910126,
98
+ "learning_rate": 7e-06,
99
+ "loss": 0.0684,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 3.5,
104
+ "grad_norm": 0.03776327893137932,
105
+ "learning_rate": 6e-06,
106
+ "loss": 0.0579,
107
+ "step": 7000
108
+ }
109
+ ],
110
+ "logging_steps": 500,
111
+ "max_steps": 10000,
112
+ "num_input_tokens_seen": 0,
113
+ "num_train_epochs": 5,
114
+ "save_steps": 500,
115
+ "total_flos": 1.3042146446934528e+16,
116
+ "train_batch_size": 8,
117
+ "trial_name": null,
118
+ "trial_params": null
119
+ }
checkpoint-7000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c723a0cd71eedc1750912629ef866d84ce379f07f7fbfd5f98bcb6058f7ae473
3
+ size 4920
checkpoint-7000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-7500/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-7500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6469916f0ee3b595dc7e8412feb8051c2e3036160538403be9fbc8d54625fb18
3
+ size 1334372264
checkpoint-7500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7953c38913e4985aeccac2422493226009b28a2716b250516ac86ea4e002080
3
+ size 2668968429
checkpoint-7500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a8e8adc667ca8142c7dba535dc785bfedadb33f1a77d8534b127e2a6c735d85
3
+ size 13990
checkpoint-7500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1394208d445d13f137b75258186988f1f5134e05bce482f7397b51fdb614b3d5
3
+ size 1064
checkpoint-7500/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-7500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-7500/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-7500/trainer_state.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.75,
5
+ "eval_steps": 500,
6
+ "global_step": 7500,
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": 9.530180931091309,
14
+ "learning_rate": 1.9e-05,
15
+ "loss": 0.7046,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "grad_norm": 11.739270210266113,
21
+ "learning_rate": 1.8e-05,
22
+ "loss": 0.574,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.75,
27
+ "grad_norm": 21.960508346557617,
28
+ "learning_rate": 1.7e-05,
29
+ "loss": 0.4031,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 1.2487173080444336,
35
+ "learning_rate": 1.6000000000000003e-05,
36
+ "loss": 0.38,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.25,
41
+ "grad_norm": 11.083433151245117,
42
+ "learning_rate": 1.5000000000000002e-05,
43
+ "loss": 0.2964,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 1.5,
48
+ "grad_norm": 0.22524116933345795,
49
+ "learning_rate": 1.4e-05,
50
+ "loss": 0.3073,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 1.75,
55
+ "grad_norm": 1.0325411558151245,
56
+ "learning_rate": 1.3000000000000001e-05,
57
+ "loss": 0.3027,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 2.0,
62
+ "grad_norm": 10.020037651062012,
63
+ "learning_rate": 1.2e-05,
64
+ "loss": 0.3056,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 2.25,
69
+ "grad_norm": 0.0707927793264389,
70
+ "learning_rate": 1.1000000000000001e-05,
71
+ "loss": 0.1681,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 2.5,
76
+ "grad_norm": 54.09671401977539,
77
+ "learning_rate": 1e-05,
78
+ "loss": 0.1322,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 2.75,
83
+ "grad_norm": 0.42837992310523987,
84
+ "learning_rate": 9e-06,
85
+ "loss": 0.1669,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 3.0,
90
+ "grad_norm": 0.044212982058525085,
91
+ "learning_rate": 8.000000000000001e-06,
92
+ "loss": 0.1565,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 3.25,
97
+ "grad_norm": 0.036281220614910126,
98
+ "learning_rate": 7e-06,
99
+ "loss": 0.0684,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 3.5,
104
+ "grad_norm": 0.03776327893137932,
105
+ "learning_rate": 6e-06,
106
+ "loss": 0.0579,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 3.75,
111
+ "grad_norm": 0.04667246341705322,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.0633,
114
+ "step": 7500
115
+ }
116
+ ],
117
+ "logging_steps": 500,
118
+ "max_steps": 10000,
119
+ "num_input_tokens_seen": 0,
120
+ "num_train_epochs": 5,
121
+ "save_steps": 500,
122
+ "total_flos": 1.3974077810262528e+16,
123
+ "train_batch_size": 8,
124
+ "trial_name": null,
125
+ "trial_params": null
126
+ }
checkpoint-7500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c723a0cd71eedc1750912629ef866d84ce379f07f7fbfd5f98bcb6058f7ae473
3
+ size 4920
checkpoint-7500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
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 sha256:03f85903f34fd172bee97926080315bcf3d485d6c4db1f5ae35e625622b98516
3
+ size 1334372264
checkpoint-8000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d85d8e45e1b282279414f590cfb04ba35485d99aa520aac42e327a2988776996
3
+ size 2668968429
checkpoint-8000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32b69deff9a6c5b0f0245ab655c5b3883527671d649e63077661419d064ab09c
3
+ size 13990
checkpoint-8000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e18997dbe2f5f297675999594e1e89aea466d7c365f00061b7dd98c72ff8a537
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": 4.0,
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": 9.530180931091309,
14
+ "learning_rate": 1.9e-05,
15
+ "loss": 0.7046,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "grad_norm": 11.739270210266113,
21
+ "learning_rate": 1.8e-05,
22
+ "loss": 0.574,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.75,
27
+ "grad_norm": 21.960508346557617,
28
+ "learning_rate": 1.7e-05,
29
+ "loss": 0.4031,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 1.2487173080444336,
35
+ "learning_rate": 1.6000000000000003e-05,
36
+ "loss": 0.38,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.25,
41
+ "grad_norm": 11.083433151245117,
42
+ "learning_rate": 1.5000000000000002e-05,
43
+ "loss": 0.2964,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 1.5,
48
+ "grad_norm": 0.22524116933345795,
49
+ "learning_rate": 1.4e-05,
50
+ "loss": 0.3073,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 1.75,
55
+ "grad_norm": 1.0325411558151245,
56
+ "learning_rate": 1.3000000000000001e-05,
57
+ "loss": 0.3027,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 2.0,
62
+ "grad_norm": 10.020037651062012,
63
+ "learning_rate": 1.2e-05,
64
+ "loss": 0.3056,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 2.25,
69
+ "grad_norm": 0.0707927793264389,
70
+ "learning_rate": 1.1000000000000001e-05,
71
+ "loss": 0.1681,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 2.5,
76
+ "grad_norm": 54.09671401977539,
77
+ "learning_rate": 1e-05,
78
+ "loss": 0.1322,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 2.75,
83
+ "grad_norm": 0.42837992310523987,
84
+ "learning_rate": 9e-06,
85
+ "loss": 0.1669,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 3.0,
90
+ "grad_norm": 0.044212982058525085,
91
+ "learning_rate": 8.000000000000001e-06,
92
+ "loss": 0.1565,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 3.25,
97
+ "grad_norm": 0.036281220614910126,
98
+ "learning_rate": 7e-06,
99
+ "loss": 0.0684,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 3.5,
104
+ "grad_norm": 0.03776327893137932,
105
+ "learning_rate": 6e-06,
106
+ "loss": 0.0579,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 3.75,
111
+ "grad_norm": 0.04667246341705322,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.0633,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 4.0,
118
+ "grad_norm": 0.03510823845863342,
119
+ "learning_rate": 4.000000000000001e-06,
120
+ "loss": 0.0725,
121
+ "step": 8000
122
+ }
123
+ ],
124
+ "logging_steps": 500,
125
+ "max_steps": 10000,
126
+ "num_input_tokens_seen": 0,
127
+ "num_train_epochs": 5,
128
+ "save_steps": 500,
129
+ "total_flos": 1.4904378293704704e+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:c723a0cd71eedc1750912629ef866d84ce379f07f7fbfd5f98bcb6058f7ae473
3
+ size 4920
checkpoint-8000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff