Hugging Face's logo

SparseCL
/
BGE-SparseCL-arguana

Transformers
Safetensors
bert
Inference Endpoints
Model card Files Community
xiaoxiaolin commited on
Commit
b2b9d89
•
1 Parent(s): 7b6bf63

Upload folder using huggingface_hub

Browse files
Files changed (40) hide show
  1. checkpoint-223/config.json +32 -0
  2. checkpoint-223/model.safetensors +3 -0
  3. checkpoint-223/optimizer.pt +3 -0
  4. checkpoint-223/scheduler.pt +3 -0
  5. checkpoint-223/special_tokens_map.json +37 -0
  6. checkpoint-223/tokenizer.json +0 -0
  7. checkpoint-223/tokenizer_config.json +57 -0
  8. checkpoint-223/trainer_state.json +20 -0
  9. checkpoint-223/training_args.bin +3 -0
  10. checkpoint-223/vocab.txt +0 -0
  11. checkpoint-446/config.json +32 -0
  12. checkpoint-446/model.safetensors +3 -0
  13. checkpoint-446/optimizer.pt +3 -0
  14. checkpoint-446/scheduler.pt +3 -0
  15. checkpoint-446/special_tokens_map.json +37 -0
  16. checkpoint-446/tokenizer.json +0 -0
  17. checkpoint-446/tokenizer_config.json +57 -0
  18. checkpoint-446/trainer_state.json +20 -0
  19. checkpoint-446/training_args.bin +3 -0
  20. checkpoint-446/vocab.txt +0 -0
  21. checkpoint-669/config.json +32 -0
  22. checkpoint-669/model.safetensors +3 -0
  23. checkpoint-669/optimizer.pt +3 -0
  24. checkpoint-669/scheduler.pt +3 -0
  25. checkpoint-669/special_tokens_map.json +37 -0
  26. checkpoint-669/tokenizer.json +0 -0
  27. checkpoint-669/tokenizer_config.json +57 -0
  28. checkpoint-669/trainer_state.json +20 -0
  29. checkpoint-669/training_args.bin +3 -0
  30. checkpoint-669/vocab.txt +0 -0
  31. config.json +32 -0
  32. custom_info +18 -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-223/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-223/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f0911c8a1bf3e509e80fb14baae8f2df0cc91d6a0a9b9a580c307c498cf26b4
3
+ size 435589760
checkpoint-223/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7782f42b576e4b1e317b646a6694d733a78ee643c0cca836100a3edd75aa7ddb
3
+ size 871297541
checkpoint-223/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd7676efe65de30b30a67819d0925e6bca6c49f4e24571d28991416144f3b378
3
+ size 627
checkpoint-223/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-223/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-223/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-223/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": 223,
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": 669,
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-223/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9de40a7aef8bfe75b782cb7fd1e4244b76ed6f0b70ef2c290ed413203bee48ad
3
+ size 4091
checkpoint-223/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-446/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-446/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d18785f0f7b8244557560734dce91aaf21b53fbe5815a829cfb730b56f7aad1
3
+ size 435589760
checkpoint-446/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79221aab5de71b632a066a0a3b30101f57c410defa493d51072d4b7806598bf9
3
+ size 871297541
checkpoint-446/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e87a0295a20de0a7d18f617b38f6653507c08e0fc8b2cb6049c2a7531faba1f3
3
+ size 627
checkpoint-446/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-446/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-446/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-446/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": 446,
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": 669,
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-446/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9de40a7aef8bfe75b782cb7fd1e4244b76ed6f0b70ef2c290ed413203bee48ad
3
+ size 4091
checkpoint-446/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-669/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-669/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bfc8399b76b6709e43654298a116c963952ab3651c25e7c8d11a6cda7e7aebb
3
+ size 435589760
checkpoint-669/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d444b25fa6162e97022ad0dbc0e4fae80be2f1175feb12e606ca70a74555fb9b
3
+ size 871297541
checkpoint-669/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82ec17673b3e7963e0c4f1af2ebfb57b440f40ce01f43680698e3b11a75f0f99
3
+ size 627
checkpoint-669/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-669/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-669/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-669/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": 669,
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": 669,
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-669/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9de40a7aef8bfe75b782cb7fd1e4244b76ed6f0b70ef2c290ed413203bee48ad
3
+ size 4091
checkpoint-669/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 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ epoch=0 step=74 progress=0.111 eval info {'sparsity_loss': 4.853, 'l1l2_ratio_z12': 22.048, 'l1l2_ratio_z13': 22.067, 'l1l2_ratio_z13_all': 22.094} train info {'sparsity_loss': 4.738, 'l1l2_ratio_z12': 21.977, 'l1l2_ratio_z13': 22.069, 'l1l2_ratio_z13_all': 22.081}
2
+ epoch=0 step=148 progress=0.221 eval info {'sparsity_loss': 3.817, 'l1l2_ratio_z12': 20.865, 'l1l2_ratio_z13': 21.497, 'l1l2_ratio_z13_all': 21.807} train info {'sparsity_loss': 4.166, 'l1l2_ratio_z12': 21.612, 'l1l2_ratio_z13': 21.949, 'l1l2_ratio_z13_all': 22.072}
3
+ epoch=0 step=222 progress=0.332 eval info {'sparsity_loss': 2.019, 'l1l2_ratio_z12': 18.063, 'l1l2_ratio_z13': 20.341, 'l1l2_ratio_z13_all': 21.472} train info {'sparsity_loss': 2.016, 'l1l2_ratio_z12': 18.956, 'l1l2_ratio_z13': 20.793, 'l1l2_ratio_z13_all': 21.643}
4
+ epoch=1 step=74 progress=0.444 eval info {'sparsity_loss': 1.931, 'l1l2_ratio_z12': 17.818, 'l1l2_ratio_z13': 20.208, 'l1l2_ratio_z13_all': 21.486} train info {'sparsity_loss': 1.048, 'l1l2_ratio_z12': 17.301, 'l1l2_ratio_z13': 20.246, 'l1l2_ratio_z13_all': 21.508}
5
+ epoch=1 step=148 progress=0.555 eval info {'sparsity_loss': 1.837, 'l1l2_ratio_z12': 17.526, 'l1l2_ratio_z13': 20.168, 'l1l2_ratio_z13_all': 21.485} train info {'sparsity_loss': 0.777, 'l1l2_ratio_z12': 16.856, 'l1l2_ratio_z13': 20.127, 'l1l2_ratio_z13_all': 21.501}
6
+ epoch=1 step=222 progress=0.665 eval info {'sparsity_loss': 1.897, 'l1l2_ratio_z12': 17.559, 'l1l2_ratio_z13': 20.121, 'l1l2_ratio_z13_all': 21.476} train info {'sparsity_loss': 0.64, 'l1l2_ratio_z12': 16.471, 'l1l2_ratio_z13': 20.028, 'l1l2_ratio_z13_all': 21.478}
7
+ epoch=2 step=74 progress=0.777 eval info {'sparsity_loss': 1.787, 'l1l2_ratio_z12': 17.187, 'l1l2_ratio_z13': 20.038, 'l1l2_ratio_z13_all': 21.438} train info {'sparsity_loss': 0.448, 'l1l2_ratio_z12': 15.951, 'l1l2_ratio_z13': 19.908, 'l1l2_ratio_z13_all': 21.416}
8
+ epoch=2 step=148 progress=0.888 eval info {'sparsity_loss': 1.762, 'l1l2_ratio_z12': 16.979, 'l1l2_ratio_z13': 19.961, 'l1l2_ratio_z13_all': 21.39} train info {'sparsity_loss': 0.411, 'l1l2_ratio_z12': 15.817, 'l1l2_ratio_z13': 19.835, 'l1l2_ratio_z13_all': 21.364}
9
+ epoch=2 step=222 progress=0.999 eval info {'sparsity_loss': 1.799, 'l1l2_ratio_z12': 17.175, 'l1l2_ratio_z13': 20.007, 'l1l2_ratio_z13_all': 21.423} train info {'sparsity_loss': 0.407, 'l1l2_ratio_z12': 15.763, 'l1l2_ratio_z13': 19.842, 'l1l2_ratio_z13_all': 21.377}
10
+ epoch=0 step=74 progress=0.111 eval info {'sparsity_loss': 4.885, 'l1l2_ratio_z12': 22.056, 'l1l2_ratio_z13': 22.061, 'l1l2_ratio_z13_all': 22.085} train info {'sparsity_loss': 4.742, 'l1l2_ratio_z12': 21.978, 'l1l2_ratio_z13': 22.07, 'l1l2_ratio_z13_all': 22.08}
11
+ epoch=0 step=148 progress=0.221 eval info {'sparsity_loss': 2.345, 'l1l2_ratio_z12': 19.058, 'l1l2_ratio_z13': 20.721, 'l1l2_ratio_z13_all': 21.525} train info {'sparsity_loss': 3.53, 'l1l2_ratio_z12': 20.752, 'l1l2_ratio_z13': 21.529, 'l1l2_ratio_z13_all': 21.849}
12
+ epoch=0 step=222 progress=0.332 eval info {'sparsity_loss': 1.784, 'l1l2_ratio_z12': 17.413, 'l1l2_ratio_z13': 20.03, 'l1l2_ratio_z13_all': 21.309} train info {'sparsity_loss': 1.392, 'l1l2_ratio_z12': 17.868, 'l1l2_ratio_z13': 20.384, 'l1l2_ratio_z13_all': 21.498}
13
+ epoch=1 step=74 progress=0.444 eval info {'sparsity_loss': 1.757, 'l1l2_ratio_z12': 17.377, 'l1l2_ratio_z13': 20.077, 'l1l2_ratio_z13_all': 21.394} train info {'sparsity_loss': 0.809, 'l1l2_ratio_z12': 16.659, 'l1l2_ratio_z13': 19.988, 'l1l2_ratio_z13_all': 21.365}
14
+ epoch=1 step=148 progress=0.555 eval info {'sparsity_loss': 1.824, 'l1l2_ratio_z12': 16.717, 'l1l2_ratio_z13': 19.728, 'l1l2_ratio_z13_all': 21.187} train info {'sparsity_loss': 0.602, 'l1l2_ratio_z12': 16.155, 'l1l2_ratio_z13': 19.859, 'l1l2_ratio_z13_all': 21.313}
15
+ epoch=1 step=222 progress=0.665 eval info {'sparsity_loss': 1.768, 'l1l2_ratio_z12': 16.853, 'l1l2_ratio_z13': 19.839, 'l1l2_ratio_z13_all': 21.263} train info {'sparsity_loss': 0.529, 'l1l2_ratio_z12': 15.902, 'l1l2_ratio_z13': 19.765, 'l1l2_ratio_z13_all': 21.294}
16
+ epoch=2 step=74 progress=0.777 eval info {'sparsity_loss': 1.826, 'l1l2_ratio_z12': 16.565, 'l1l2_ratio_z13': 19.745, 'l1l2_ratio_z13_all': 21.22} train info {'sparsity_loss': 0.337, 'l1l2_ratio_z12': 15.245, 'l1l2_ratio_z13': 19.61, 'l1l2_ratio_z13_all': 21.196}
17
+ epoch=2 step=148 progress=0.888 eval info {'sparsity_loss': 1.816, 'l1l2_ratio_z12': 16.56, 'l1l2_ratio_z13': 19.741, 'l1l2_ratio_z13_all': 21.223} train info {'sparsity_loss': 0.337, 'l1l2_ratio_z12': 15.237, 'l1l2_ratio_z13': 19.583, 'l1l2_ratio_z13_all': 21.191}
18
+ epoch=2 step=222 progress=0.999 eval info {'sparsity_loss': 1.817, 'l1l2_ratio_z12': 16.539, 'l1l2_ratio_z13': 19.719, 'l1l2_ratio_z13_all': 21.212} train info {'sparsity_loss': 0.308, 'l1l2_ratio_z12': 15.175, 'l1l2_ratio_z13': 19.615, 'l1l2_ratio_z13_all': 21.215}
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bfc8399b76b6709e43654298a116c963952ab3651c25e7c8d11a6cda7e7aebb
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 = 1724.6458
3
+ train_samples_per_second = 0.388
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": 669,
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": 669,
14
+ "total_flos": 0,
15
+ "train_runtime": 1724.6458,
16
+ "train_samples_per_second": 0.388
17
+ }
18
+ ],
19
+ "logging_steps": 500,
20
+ "max_steps": 669,
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 sha256:9de40a7aef8bfe75b782cb7fd1e4244b76ed6f0b70ef2c290ed413203bee48ad
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff