Hugging Face's logo

Elkelouizajo
/
BERT_mnli_20K

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
Elkelouizajo commited on
Commit
206aaea
·
verified ·
1 Parent(s): 07a3b38

Upload 77 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. checkpoint-10500/config.json +42 -0
  2. checkpoint-10500/model.safetensors +3 -0
  3. checkpoint-10500/optimizer.pt +3 -0
  4. checkpoint-10500/rng_state.pth +3 -0
  5. checkpoint-10500/scheduler.pt +3 -0
  6. checkpoint-10500/special_tokens_map.json +7 -0
  7. checkpoint-10500/tokenizer.json +0 -0
  8. checkpoint-10500/tokenizer_config.json +55 -0
  9. checkpoint-10500/trainer_state.json +168 -0
  10. checkpoint-10500/training_args.bin +3 -0
  11. checkpoint-10500/vocab.txt +0 -0
  12. checkpoint-11000/config.json +42 -0
  13. checkpoint-11000/model.safetensors +3 -0
  14. checkpoint-11000/optimizer.pt +3 -0
  15. checkpoint-11000/rng_state.pth +3 -0
  16. checkpoint-11000/scheduler.pt +3 -0
  17. checkpoint-11000/special_tokens_map.json +7 -0
  18. checkpoint-11000/tokenizer.json +0 -0
  19. checkpoint-11000/tokenizer_config.json +55 -0
  20. checkpoint-11000/trainer_state.json +175 -0
  21. checkpoint-11000/training_args.bin +3 -0
  22. checkpoint-11000/vocab.txt +0 -0
  23. checkpoint-11500/config.json +42 -0
  24. checkpoint-11500/model.safetensors +3 -0
  25. checkpoint-11500/optimizer.pt +3 -0
  26. checkpoint-11500/rng_state.pth +3 -0
  27. checkpoint-11500/scheduler.pt +3 -0
  28. checkpoint-11500/special_tokens_map.json +7 -0
  29. checkpoint-11500/tokenizer.json +0 -0
  30. checkpoint-11500/tokenizer_config.json +55 -0
  31. checkpoint-11500/trainer_state.json +182 -0
  32. checkpoint-11500/training_args.bin +3 -0
  33. checkpoint-11500/vocab.txt +0 -0
  34. checkpoint-12000/checkpoint-500/config.json +42 -0
  35. checkpoint-12000/checkpoint-500/model.safetensors +3 -0
  36. checkpoint-12000/checkpoint-500/optimizer.pt +3 -0
  37. checkpoint-12000/checkpoint-500/rng_state.pth +3 -0
  38. checkpoint-12000/checkpoint-500/scheduler.pt +3 -0
  39. checkpoint-12000/checkpoint-500/special_tokens_map.json +7 -0
  40. checkpoint-12000/checkpoint-500/tokenizer.json +0 -0
  41. checkpoint-12000/checkpoint-500/tokenizer_config.json +55 -0
  42. checkpoint-12000/checkpoint-500/trainer_state.json +28 -0
  43. checkpoint-12000/checkpoint-500/training_args.bin +3 -0
  44. checkpoint-12000/checkpoint-500/vocab.txt +0 -0
  45. checkpoint-12000/config.json +42 -0
  46. checkpoint-12000/model.safetensors +3 -0
  47. checkpoint-12000/optimizer.pt +3 -0
  48. checkpoint-12000/rng_state.pth +3 -0
  49. checkpoint-12000/scheduler.pt +3 -0
  50. checkpoint-12000/special_tokens_map.json +7 -0
checkpoint-10500/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-10500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:196664a749c5fbcf4fa187e5ad841ce5435f63184a73d70208708c3e3ce799de
3
+ size 1334372264
checkpoint-10500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fb520e27f1839a4998e57dd639b22254d5461782ade21da74f95fdf91d6732d
3
+ size 2668979437
checkpoint-10500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e057f999e4875d8cd17c3421beffd3e20e05cd5b2e31f2cfbd5cc362f6796f5
3
+ size 14308
checkpoint-10500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:679ed43d104b583856e488e6b9b1b5f27b2ff42d5fd70dbdb97da614442a4073
3
+ size 1064
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-10500/trainer_state.json ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.25,
5
+ "eval_steps": 500,
6
+ "global_step": 10500,
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": 8.33536148071289,
14
+ "learning_rate": 1.9545454545454546e-05,
15
+ "loss": 0.5027,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "grad_norm": 142.45716857910156,
21
+ "learning_rate": 1.9090909090909094e-05,
22
+ "loss": 0.3982,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.75,
27
+ "grad_norm": 41.095272064208984,
28
+ "learning_rate": 1.8636363636363638e-05,
29
+ "loss": 0.3902,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 1.3833879232406616,
35
+ "learning_rate": 1.8181818181818182e-05,
36
+ "loss": 0.3792,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.25,
41
+ "grad_norm": 22.25682258605957,
42
+ "learning_rate": 1.772727272727273e-05,
43
+ "loss": 0.2412,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 1.5,
48
+ "grad_norm": 0.08785621076822281,
49
+ "learning_rate": 1.7272727272727274e-05,
50
+ "loss": 0.2646,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 1.75,
55
+ "grad_norm": 0.1938224732875824,
56
+ "learning_rate": 1.681818181818182e-05,
57
+ "loss": 0.2591,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 2.0,
62
+ "grad_norm": 0.19619984924793243,
63
+ "learning_rate": 1.6363636363636366e-05,
64
+ "loss": 0.2579,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 2.25,
69
+ "grad_norm": 0.052116330713033676,
70
+ "learning_rate": 1.590909090909091e-05,
71
+ "loss": 0.1256,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 2.5,
76
+ "grad_norm": 19.55641746520996,
77
+ "learning_rate": 1.5454545454545454e-05,
78
+ "loss": 0.1313,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 2.75,
83
+ "grad_norm": 0.09100260585546494,
84
+ "learning_rate": 1.5000000000000002e-05,
85
+ "loss": 0.1431,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 3.0,
90
+ "grad_norm": 0.006416453048586845,
91
+ "learning_rate": 1.4545454545454546e-05,
92
+ "loss": 0.1158,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 3.25,
97
+ "grad_norm": 0.9075784087181091,
98
+ "learning_rate": 1.4090909090909092e-05,
99
+ "loss": 0.0716,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 3.5,
104
+ "grad_norm": 0.0059479945339262486,
105
+ "learning_rate": 1.3636363636363637e-05,
106
+ "loss": 0.0638,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 3.75,
111
+ "grad_norm": 0.03586824983358383,
112
+ "learning_rate": 1.3181818181818183e-05,
113
+ "loss": 0.0713,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 4.0,
118
+ "grad_norm": 0.029572978615760803,
119
+ "learning_rate": 1.2727272727272728e-05,
120
+ "loss": 0.0798,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 4.25,
125
+ "grad_norm": 0.029360467568039894,
126
+ "learning_rate": 1.2272727272727274e-05,
127
+ "loss": 0.0432,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 4.5,
132
+ "grad_norm": 1.2467519044876099,
133
+ "learning_rate": 1.181818181818182e-05,
134
+ "loss": 0.0563,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 4.75,
139
+ "grad_norm": 0.03312988951802254,
140
+ "learning_rate": 1.1363636363636366e-05,
141
+ "loss": 0.05,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 5.0,
146
+ "grad_norm": 0.034050144255161285,
147
+ "learning_rate": 1.0909090909090909e-05,
148
+ "loss": 0.0727,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 5.25,
153
+ "grad_norm": 0.012058685533702374,
154
+ "learning_rate": 1.0454545454545455e-05,
155
+ "loss": 0.0158,
156
+ "step": 10500
157
+ }
158
+ ],
159
+ "logging_steps": 500,
160
+ "max_steps": 22000,
161
+ "num_input_tokens_seen": 0,
162
+ "num_train_epochs": 11,
163
+ "save_steps": 500,
164
+ "total_flos": 7.824961692183552e+16,
165
+ "train_batch_size": 8,
166
+ "trial_name": null,
167
+ "trial_params": null
168
+ }
checkpoint-10500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:841cca5ca8f442bb498a1e599a68b8668b20af506517904fc9f8db7b28756855
3
+ size 4920
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-11000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:923e6e1b8d4919190033edb281c8d5da056a767bdcbfaf2eac15bafc973bf882
3
+ size 1334372264
checkpoint-11000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f377f19b22c86138a2bd7639bade6cf72f2d7ab14da0aa2b185ac1128b78c0d5
3
+ size 2668979437
checkpoint-11000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:006019ee8ce34698c0b65011b5cdf78774617eb586cc83a471b768336f4c2d77
3
+ size 14308
checkpoint-11000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66c075c789dc17366be3c4e1d6d7e47717822d39ad8032727eb39784b7f62f40
3
+ size 1064
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-11000/trainer_state.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.5,
5
+ "eval_steps": 500,
6
+ "global_step": 11000,
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": 8.33536148071289,
14
+ "learning_rate": 1.9545454545454546e-05,
15
+ "loss": 0.5027,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "grad_norm": 142.45716857910156,
21
+ "learning_rate": 1.9090909090909094e-05,
22
+ "loss": 0.3982,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.75,
27
+ "grad_norm": 41.095272064208984,
28
+ "learning_rate": 1.8636363636363638e-05,
29
+ "loss": 0.3902,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 1.3833879232406616,
35
+ "learning_rate": 1.8181818181818182e-05,
36
+ "loss": 0.3792,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.25,
41
+ "grad_norm": 22.25682258605957,
42
+ "learning_rate": 1.772727272727273e-05,
43
+ "loss": 0.2412,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 1.5,
48
+ "grad_norm": 0.08785621076822281,
49
+ "learning_rate": 1.7272727272727274e-05,
50
+ "loss": 0.2646,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 1.75,
55
+ "grad_norm": 0.1938224732875824,
56
+ "learning_rate": 1.681818181818182e-05,
57
+ "loss": 0.2591,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 2.0,
62
+ "grad_norm": 0.19619984924793243,
63
+ "learning_rate": 1.6363636363636366e-05,
64
+ "loss": 0.2579,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 2.25,
69
+ "grad_norm": 0.052116330713033676,
70
+ "learning_rate": 1.590909090909091e-05,
71
+ "loss": 0.1256,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 2.5,
76
+ "grad_norm": 19.55641746520996,
77
+ "learning_rate": 1.5454545454545454e-05,
78
+ "loss": 0.1313,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 2.75,
83
+ "grad_norm": 0.09100260585546494,
84
+ "learning_rate": 1.5000000000000002e-05,
85
+ "loss": 0.1431,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 3.0,
90
+ "grad_norm": 0.006416453048586845,
91
+ "learning_rate": 1.4545454545454546e-05,
92
+ "loss": 0.1158,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 3.25,
97
+ "grad_norm": 0.9075784087181091,
98
+ "learning_rate": 1.4090909090909092e-05,
99
+ "loss": 0.0716,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 3.5,
104
+ "grad_norm": 0.0059479945339262486,
105
+ "learning_rate": 1.3636363636363637e-05,
106
+ "loss": 0.0638,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 3.75,
111
+ "grad_norm": 0.03586824983358383,
112
+ "learning_rate": 1.3181818181818183e-05,
113
+ "loss": 0.0713,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 4.0,
118
+ "grad_norm": 0.029572978615760803,
119
+ "learning_rate": 1.2727272727272728e-05,
120
+ "loss": 0.0798,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 4.25,
125
+ "grad_norm": 0.029360467568039894,
126
+ "learning_rate": 1.2272727272727274e-05,
127
+ "loss": 0.0432,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 4.5,
132
+ "grad_norm": 1.2467519044876099,
133
+ "learning_rate": 1.181818181818182e-05,
134
+ "loss": 0.0563,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 4.75,
139
+ "grad_norm": 0.03312988951802254,
140
+ "learning_rate": 1.1363636363636366e-05,
141
+ "loss": 0.05,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 5.0,
146
+ "grad_norm": 0.034050144255161285,
147
+ "learning_rate": 1.0909090909090909e-05,
148
+ "loss": 0.0727,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 5.25,
153
+ "grad_norm": 0.012058685533702374,
154
+ "learning_rate": 1.0454545454545455e-05,
155
+ "loss": 0.0158,
156
+ "step": 10500
157
+ },
158
+ {
159
+ "epoch": 5.5,
160
+ "grad_norm": 0.004920224193483591,
161
+ "learning_rate": 1e-05,
162
+ "loss": 0.0524,
163
+ "step": 11000
164
+ }
165
+ ],
166
+ "logging_steps": 500,
167
+ "max_steps": 22000,
168
+ "num_input_tokens_seen": 0,
169
+ "num_train_epochs": 11,
170
+ "save_steps": 500,
171
+ "total_flos": 8.197734237514752e+16,
172
+ "train_batch_size": 8,
173
+ "trial_name": null,
174
+ "trial_params": null
175
+ }
checkpoint-11000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:841cca5ca8f442bb498a1e599a68b8668b20af506517904fc9f8db7b28756855
3
+ size 4920
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-11500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16235cf1357b317cf073726b4364cf841241907372098f98bce6ea8f674d2ff4
3
+ size 1334372264
checkpoint-11500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d10ba58c6944563264ba8ea29dd6a8c23366826a08158f5c060ed2b295d0a133
3
+ size 2668979437
checkpoint-11500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d77445233a6e1b17d15185431e0d4bb75965fd5d1e4d21aec91ae3b6f340995c
3
+ size 14308
checkpoint-11500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c57583dd7694b44fbeafcc3c449590b9fb95ad9526a3da346a5fba38775e7c5f
3
+ size 1064
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
+ }
checkpoint-11500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-11500/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-11500/trainer_state.json ADDED
@@ -0,0 +1,182 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.75,
5
+ "eval_steps": 500,
6
+ "global_step": 11500,
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": 8.33536148071289,
14
+ "learning_rate": 1.9545454545454546e-05,
15
+ "loss": 0.5027,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "grad_norm": 142.45716857910156,
21
+ "learning_rate": 1.9090909090909094e-05,
22
+ "loss": 0.3982,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.75,
27
+ "grad_norm": 41.095272064208984,
28
+ "learning_rate": 1.8636363636363638e-05,
29
+ "loss": 0.3902,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 1.3833879232406616,
35
+ "learning_rate": 1.8181818181818182e-05,
36
+ "loss": 0.3792,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.25,
41
+ "grad_norm": 22.25682258605957,
42
+ "learning_rate": 1.772727272727273e-05,
43
+ "loss": 0.2412,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 1.5,
48
+ "grad_norm": 0.08785621076822281,
49
+ "learning_rate": 1.7272727272727274e-05,
50
+ "loss": 0.2646,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 1.75,
55
+ "grad_norm": 0.1938224732875824,
56
+ "learning_rate": 1.681818181818182e-05,
57
+ "loss": 0.2591,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 2.0,
62
+ "grad_norm": 0.19619984924793243,
63
+ "learning_rate": 1.6363636363636366e-05,
64
+ "loss": 0.2579,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 2.25,
69
+ "grad_norm": 0.052116330713033676,
70
+ "learning_rate": 1.590909090909091e-05,
71
+ "loss": 0.1256,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 2.5,
76
+ "grad_norm": 19.55641746520996,
77
+ "learning_rate": 1.5454545454545454e-05,
78
+ "loss": 0.1313,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 2.75,
83
+ "grad_norm": 0.09100260585546494,
84
+ "learning_rate": 1.5000000000000002e-05,
85
+ "loss": 0.1431,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 3.0,
90
+ "grad_norm": 0.006416453048586845,
91
+ "learning_rate": 1.4545454545454546e-05,
92
+ "loss": 0.1158,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 3.25,
97
+ "grad_norm": 0.9075784087181091,
98
+ "learning_rate": 1.4090909090909092e-05,
99
+ "loss": 0.0716,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 3.5,
104
+ "grad_norm": 0.0059479945339262486,
105
+ "learning_rate": 1.3636363636363637e-05,
106
+ "loss": 0.0638,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 3.75,
111
+ "grad_norm": 0.03586824983358383,
112
+ "learning_rate": 1.3181818181818183e-05,
113
+ "loss": 0.0713,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 4.0,
118
+ "grad_norm": 0.029572978615760803,
119
+ "learning_rate": 1.2727272727272728e-05,
120
+ "loss": 0.0798,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 4.25,
125
+ "grad_norm": 0.029360467568039894,
126
+ "learning_rate": 1.2272727272727274e-05,
127
+ "loss": 0.0432,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 4.5,
132
+ "grad_norm": 1.2467519044876099,
133
+ "learning_rate": 1.181818181818182e-05,
134
+ "loss": 0.0563,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 4.75,
139
+ "grad_norm": 0.03312988951802254,
140
+ "learning_rate": 1.1363636363636366e-05,
141
+ "loss": 0.05,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 5.0,
146
+ "grad_norm": 0.034050144255161285,
147
+ "learning_rate": 1.0909090909090909e-05,
148
+ "loss": 0.0727,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 5.25,
153
+ "grad_norm": 0.012058685533702374,
154
+ "learning_rate": 1.0454545454545455e-05,
155
+ "loss": 0.0158,
156
+ "step": 10500
157
+ },
158
+ {
159
+ "epoch": 5.5,
160
+ "grad_norm": 0.004920224193483591,
161
+ "learning_rate": 1e-05,
162
+ "loss": 0.0524,
163
+ "step": 11000
164
+ },
165
+ {
166
+ "epoch": 5.75,
167
+ "grad_norm": 0.038101330399513245,
168
+ "learning_rate": 9.545454545454547e-06,
169
+ "loss": 0.0604,
170
+ "step": 11500
171
+ }
172
+ ],
173
+ "logging_steps": 500,
174
+ "max_steps": 22000,
175
+ "num_input_tokens_seen": 0,
176
+ "num_train_epochs": 11,
177
+ "save_steps": 500,
178
+ "total_flos": 8.570506782845952e+16,
179
+ "train_batch_size": 8,
180
+ "trial_name": null,
181
+ "trial_params": null
182
+ }
checkpoint-11500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:841cca5ca8f442bb498a1e599a68b8668b20af506517904fc9f8db7b28756855
3
+ size 4920
checkpoint-11500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-12000/checkpoint-500/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-12000/checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:117265976ad903d93b3845eea60fedadcf0cbd177ea4d561d200bf0fbd5c4896
3
+ size 1334372264
checkpoint-12000/checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:885be0d6776128d0c84bbef6870a9f71b2858b3af445f97e9c8dae2eb2cdfdd0
3
+ size 2668979437
checkpoint-12000/checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e2969a142b24ad149c1bd7f78749451eb55fd7eefc4b245c2b819e2886401d3
3
+ size 14308
checkpoint-12000/checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a1c93b84c4d17c9a730b1ac1017523b452bd8ffa6fd0648f36c83b58fb771cf
3
+ size 1064
checkpoint-12000/checkpoint-500/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-12000/checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-12000/checkpoint-500/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-12000/checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.25,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
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": 8.33536148071289,
14
+ "learning_rate": 1.9545454545454546e-05,
15
+ "loss": 0.5027,
16
+ "step": 500
17
+ }
18
+ ],
19
+ "logging_steps": 500,
20
+ "max_steps": 22000,
21
+ "num_input_tokens_seen": 0,
22
+ "num_train_epochs": 11,
23
+ "save_steps": 500,
24
+ "total_flos": 3727725453312000.0,
25
+ "train_batch_size": 8,
26
+ "trial_name": null,
27
+ "trial_params": null
28
+ }
checkpoint-12000/checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:841cca5ca8f442bb498a1e599a68b8668b20af506517904fc9f8db7b28756855
3
+ size 4920
checkpoint-12000/checkpoint-500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-12000/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-12000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be53dc7586e41d64e142af9b130ac134410205df44085a342f2e3945c1bc87bc
3
+ size 1334372264
checkpoint-12000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2261e1ae6ba9f412069c493254780964940d2a44552b873ee1a6a98b04eb3752
3
+ size 2668979437
checkpoint-12000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d712518d87eab24a25fed24bd0cd3b71e5d3269108e4be688ab3a90271f65f4
3
+ size 14308
checkpoint-12000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aacf2eec9fc1964a7a3e30b42ab86aad90b733a050c02af1b703abdbad17d0c5
3
+ size 1064
checkpoint-12000/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
+ }