Hugging Face's logo

SparseCL
/
BGE-SparseCL-msmarco

Transformers
Safetensors
bert
Inference Endpoints
Model card Files Community
xiaoxiaolin commited on
Commit
9560222
·
verified ·
1 Parent(s): 9580bca

Upload folder using huggingface_hub

Browse files
Files changed (40) hide show
  1. checkpoint-1400/config.json +32 -0
  2. checkpoint-1400/model.safetensors +3 -0
  3. checkpoint-1400/optimizer.pt +3 -0
  4. checkpoint-1400/scheduler.pt +3 -0
  5. checkpoint-1400/special_tokens_map.json +37 -0
  6. checkpoint-1400/tokenizer.json +0 -0
  7. checkpoint-1400/tokenizer_config.json +57 -0
  8. checkpoint-1400/trainer_state.json +20 -0
  9. checkpoint-1400/training_args.bin +3 -0
  10. checkpoint-1400/vocab.txt +0 -0
  11. checkpoint-2800/config.json +32 -0
  12. checkpoint-2800/model.safetensors +3 -0
  13. checkpoint-2800/optimizer.pt +3 -0
  14. checkpoint-2800/scheduler.pt +3 -0
  15. checkpoint-2800/special_tokens_map.json +37 -0
  16. checkpoint-2800/tokenizer.json +0 -0
  17. checkpoint-2800/tokenizer_config.json +57 -0
  18. checkpoint-2800/trainer_state.json +20 -0
  19. checkpoint-2800/training_args.bin +3 -0
  20. checkpoint-2800/vocab.txt +0 -0
  21. checkpoint-4200/config.json +32 -0
  22. checkpoint-4200/model.safetensors +3 -0
  23. checkpoint-4200/optimizer.pt +3 -0
  24. checkpoint-4200/scheduler.pt +3 -0
  25. checkpoint-4200/special_tokens_map.json +37 -0
  26. checkpoint-4200/tokenizer.json +0 -0
  27. checkpoint-4200/tokenizer_config.json +57 -0
  28. checkpoint-4200/trainer_state.json +20 -0
  29. checkpoint-4200/training_args.bin +3 -0
  30. checkpoint-4200/vocab.txt +0 -0
  31. config.json +32 -0
  32. custom_info +9 -0
  33. model.safetensors +3 -0
  34. special_tokens_map.json +37 -0
  35. tokenizer.json +0 -0
  36. tokenizer_config.json +57 -0
  37. train_results.txt +3 -0
  38. trainer_state.json +28 -0
  39. training_args.bin +3 -0
  40. vocab.txt +0 -0
checkpoint-1400/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "BAAI/bge-base-en-v1.5",
3
+ "architectures": [
4
+ "our_BertForCL"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "bert",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "pad_token_id": 0,
26
+ "position_embedding_type": "absolute",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.36.2",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 30522
32
+ }
checkpoint-1400/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5edb423b0bf675b3d90e8ca66f9b0171fcb8fa506add72a0bddd1e4a838fee2
3
+ size 435589760
checkpoint-1400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dad1126737e56836711c4ca6fd0ad3268e0f2f8d43d37aec6ed40468d2d0ac1f
3
+ size 871297541
checkpoint-1400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcea1a200517ffc2cf77af3894149058705795c4078294ca6f50ab18ccde5527
3
+ size 627
checkpoint-1400/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-1400/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1400/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
checkpoint-1400/trainer_state.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1400,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 500,
12
+ "max_steps": 4200,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 3,
15
+ "save_steps": 500,
16
+ "total_flos": 0,
17
+ "train_batch_size": null,
18
+ "trial_name": null,
19
+ "trial_params": null
20
+ }
checkpoint-1400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d5cd02d69da61456bbb3466b9b241932382e73d45cf3f527b4681918f8e3883
3
+ size 4091
checkpoint-1400/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2800/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "BAAI/bge-base-en-v1.5",
3
+ "architectures": [
4
+ "our_BertForCL"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "bert",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "pad_token_id": 0,
26
+ "position_embedding_type": "absolute",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.36.2",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 30522
32
+ }
checkpoint-2800/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a04b904c713f4684fb7de2584dfc431c94da07b9d8402ad7f292443309cd0fff
3
+ size 435589760
checkpoint-2800/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6feff0204605f27a2557dffeba8dc04dd072e758c5b3145dfd9fa3e400514d0
3
+ size 871297541
checkpoint-2800/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5353282c47ce7e1629b303c28d290db65d7df0877959e58338a438dcca8d310
3
+ size 627
checkpoint-2800/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-2800/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2800/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
checkpoint-2800/trainer_state.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2800,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 500,
12
+ "max_steps": 4200,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 3,
15
+ "save_steps": 500,
16
+ "total_flos": 0,
17
+ "train_batch_size": null,
18
+ "trial_name": null,
19
+ "trial_params": null
20
+ }
checkpoint-2800/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d5cd02d69da61456bbb3466b9b241932382e73d45cf3f527b4681918f8e3883
3
+ size 4091
checkpoint-2800/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4200/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "BAAI/bge-base-en-v1.5",
3
+ "architectures": [
4
+ "our_BertForCL"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "bert",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "pad_token_id": 0,
26
+ "position_embedding_type": "absolute",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.36.2",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 30522
32
+ }
checkpoint-4200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15fcba6c84ea263e4b7e95ef9f06e58661ae7900370df612f8e806c98a342063
3
+ size 435589760
checkpoint-4200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f0c6f24326f4c6ef9d6421defd011378b4a90ac7a6acf9dfc5657820ccecffc
3
+ size 871297541
checkpoint-4200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe4c02de10aa198f8890d58eaff374045cd827a437d97f98892422dbc9358138
3
+ size 627
checkpoint-4200/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-4200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4200/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
checkpoint-4200/trainer_state.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 500,
12
+ "max_steps": 4200,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 3,
15
+ "save_steps": 500,
16
+ "total_flos": 0,
17
+ "train_batch_size": null,
18
+ "trial_name": null,
19
+ "trial_params": null
20
+ }
checkpoint-4200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d5cd02d69da61456bbb3466b9b241932382e73d45cf3f527b4681918f8e3883
3
+ size 4091
checkpoint-4200/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "BAAI/bge-base-en-v1.5",
3
+ "architectures": [
4
+ "our_BertForCL"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "bert",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "pad_token_id": 0,
26
+ "position_embedding_type": "absolute",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.36.2",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 30522
32
+ }
custom_info ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ epoch=0 step=466 progress=0.111 eval info {'sparsity_loss': 0.914, 'l1l2_ratio_z12': 17.357, 'l1l2_ratio_z13': 20.673, 'l1l2_ratio_z13_all': 22.422} train info {'sparsity_loss': 1.998, 'l1l2_ratio_z12': 18.957, 'l1l2_ratio_z13': 21.562, 'l1l2_ratio_z13_all': 22.183}
2
+ epoch=0 step=932 progress=0.222 eval info {'sparsity_loss': 0.675, 'l1l2_ratio_z12': 17.478, 'l1l2_ratio_z13': 20.46, 'l1l2_ratio_z13_all': 22.557} train info {'sparsity_loss': 0.635, 'l1l2_ratio_z12': 17.533, 'l1l2_ratio_z13': 21.092, 'l1l2_ratio_z13_all': 22.535}
3
+ epoch=0 step=1398 progress=0.333 eval info {'sparsity_loss': 0.524, 'l1l2_ratio_z12': 16.323, 'l1l2_ratio_z13': 19.734, 'l1l2_ratio_z13_all': 22.49} train info {'sparsity_loss': 0.358, 'l1l2_ratio_z12': 16.851, 'l1l2_ratio_z13': 20.649, 'l1l2_ratio_z13_all': 22.541}
4
+ epoch=1 step=466 progress=0.444 eval info {'sparsity_loss': 0.498, 'l1l2_ratio_z12': 15.68, 'l1l2_ratio_z13': 19.731, 'l1l2_ratio_z13_all': 22.524} train info {'sparsity_loss': 0.191, 'l1l2_ratio_z12': 15.885, 'l1l2_ratio_z13': 20.378, 'l1l2_ratio_z13_all': 22.55}
5
+ epoch=1 step=932 progress=0.555 eval info {'sparsity_loss': 0.469, 'l1l2_ratio_z12': 15.545, 'l1l2_ratio_z13': 19.838, 'l1l2_ratio_z13_all': 22.539} train info {'sparsity_loss': 0.14, 'l1l2_ratio_z12': 15.373, 'l1l2_ratio_z13': 20.302, 'l1l2_ratio_z13_all': 22.54}
6
+ epoch=1 step=1398 progress=0.666 eval info {'sparsity_loss': 0.459, 'l1l2_ratio_z12': 15.044, 'l1l2_ratio_z13': 19.485, 'l1l2_ratio_z13_all': 22.522} train info {'sparsity_loss': 0.113, 'l1l2_ratio_z12': 15.045, 'l1l2_ratio_z13': 20.25, 'l1l2_ratio_z13_all': 22.528}
7
+ epoch=2 step=466 progress=0.778 eval info {'sparsity_loss': 0.464, 'l1l2_ratio_z12': 14.709, 'l1l2_ratio_z13': 19.538, 'l1l2_ratio_z13_all': 22.489} train info {'sparsity_loss': 0.063, 'l1l2_ratio_z12': 14.519, 'l1l2_ratio_z13': 20.253, 'l1l2_ratio_z13_all': 22.504}
8
+ epoch=2 step=932 progress=0.889 eval info {'sparsity_loss': 0.473, 'l1l2_ratio_z12': 14.397, 'l1l2_ratio_z13': 19.319, 'l1l2_ratio_z13_all': 22.488} train info {'sparsity_loss': 0.055, 'l1l2_ratio_z12': 14.167, 'l1l2_ratio_z13': 20.184, 'l1l2_ratio_z13_all': 22.504}
9
+ epoch=2 step=1398 progress=1.0 eval info {'sparsity_loss': 0.477, 'l1l2_ratio_z12': 14.242, 'l1l2_ratio_z13': 19.301, 'l1l2_ratio_z13_all': 22.471} train info {'sparsity_loss': 0.054, 'l1l2_ratio_z12': 13.983, 'l1l2_ratio_z13': 20.161, 'l1l2_ratio_z13_all': 22.495}
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15fcba6c84ea263e4b7e95ef9f06e58661ae7900370df612f8e806c98a342063
3
+ size 435589760
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
train_results.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ epoch = 3.0
2
+ train_runtime = 4355.7843
3
+ train_samples_per_second = 0.964
trainer_state.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 3.0,
13
+ "step": 4200,
14
+ "total_flos": 0,
15
+ "train_runtime": 4355.7843,
16
+ "train_samples_per_second": 0.964
17
+ }
18
+ ],
19
+ "logging_steps": 500,
20
+ "max_steps": 4200,
21
+ "num_input_tokens_seen": 0,
22
+ "num_train_epochs": 3,
23
+ "save_steps": 500,
24
+ "total_flos": 0,
25
+ "train_batch_size": null,
26
+ "trial_name": null,
27
+ "trial_params": null
28
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d5cd02d69da61456bbb3466b9b241932382e73d45cf3f527b4681918f8e3883
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff