Hugging Face's logo

SparseCL
/
GTE-SparseCL-arguana

Transformers
Safetensors
new
custom_code
Inference Endpoints
Model card Files Community
xiaoxiaolin commited on
Commit
ee17ccf
•
1 Parent(s): 48c0621

Upload folder using huggingface_hub

Browse files
Files changed (40) hide show
  1. checkpoint-223/config.json +44 -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 +62 -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 +44 -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 +62 -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 +44 -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 +62 -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 +44 -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 +62 -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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Alibaba-NLP/gte-large-en-v1.5",
3
+ "architectures": [
4
+ "NewModelForCL"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
9
+ "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
10
+ "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
11
+ "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
12
+ "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
13
+ "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
14
+ "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
15
+ },
16
+ "classifier_dropout": null,
17
+ "hidden_act": "gelu",
18
+ "hidden_dropout_prob": 0.1,
19
+ "hidden_size": 1024,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 4096,
22
+ "layer_norm_eps": 1e-12,
23
+ "layer_norm_type": "layer_norm",
24
+ "logn_attention_clip1": false,
25
+ "logn_attention_scale": false,
26
+ "max_position_embeddings": 8192,
27
+ "model_type": "new",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 24,
30
+ "pack_qkv": true,
31
+ "pad_token_id": 0,
32
+ "position_embedding_type": "rope",
33
+ "rope_scaling": {
34
+ "factor": 2.0,
35
+ "type": "ntk"
36
+ },
37
+ "rope_theta": 160000,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.36.2",
40
+ "type_vocab_size": 2,
41
+ "unpad_inputs": false,
42
+ "use_memory_efficient_attention": false,
43
+ "vocab_size": 30522
44
+ }
checkpoint-223/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baab41e5dab391c3ab0d26d3f612457810d455020402154e1f5560ea3a739c8d
3
+ size 1736561104
checkpoint-223/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a4fb675937460a9b17ad548dfc828bdbddda985766e4e017278766b511043d1
3
+ size 3473287493
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 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
47
+ "mask_token": "[MASK]",
48
+ "max_length": 8000,
49
+ "model_max_length": 32768,
50
+ "pad_to_multiple_of": null,
51
+ "pad_token": "[PAD]",
52
+ "pad_token_type_id": 0,
53
+ "padding_side": "right",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
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:c9d28c1554748c4e852ecb4292a6890e4f0b1fc576494b1f2b7a646ac50c07a2
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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Alibaba-NLP/gte-large-en-v1.5",
3
+ "architectures": [
4
+ "NewModelForCL"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
9
+ "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
10
+ "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
11
+ "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
12
+ "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
13
+ "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
14
+ "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
15
+ },
16
+ "classifier_dropout": null,
17
+ "hidden_act": "gelu",
18
+ "hidden_dropout_prob": 0.1,
19
+ "hidden_size": 1024,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 4096,
22
+ "layer_norm_eps": 1e-12,
23
+ "layer_norm_type": "layer_norm",
24
+ "logn_attention_clip1": false,
25
+ "logn_attention_scale": false,
26
+ "max_position_embeddings": 8192,
27
+ "model_type": "new",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 24,
30
+ "pack_qkv": true,
31
+ "pad_token_id": 0,
32
+ "position_embedding_type": "rope",
33
+ "rope_scaling": {
34
+ "factor": 2.0,
35
+ "type": "ntk"
36
+ },
37
+ "rope_theta": 160000,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.36.2",
40
+ "type_vocab_size": 2,
41
+ "unpad_inputs": false,
42
+ "use_memory_efficient_attention": false,
43
+ "vocab_size": 30522
44
+ }
checkpoint-446/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffac8d07d7d794e077b370f4a24a3a00ce4c4ef6c07a3943bc40a33f2dea0134
3
+ size 1736561104
checkpoint-446/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:353dd026150b5608e76cebee925b6ccd55e7e8e58ec90d6b1637fa4e76c25edc
3
+ size 3473287493
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 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
47
+ "mask_token": "[MASK]",
48
+ "max_length": 8000,
49
+ "model_max_length": 32768,
50
+ "pad_to_multiple_of": null,
51
+ "pad_token": "[PAD]",
52
+ "pad_token_type_id": 0,
53
+ "padding_side": "right",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
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:c9d28c1554748c4e852ecb4292a6890e4f0b1fc576494b1f2b7a646ac50c07a2
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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Alibaba-NLP/gte-large-en-v1.5",
3
+ "architectures": [
4
+ "NewModelForCL"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
9
+ "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
10
+ "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
11
+ "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
12
+ "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
13
+ "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
14
+ "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
15
+ },
16
+ "classifier_dropout": null,
17
+ "hidden_act": "gelu",
18
+ "hidden_dropout_prob": 0.1,
19
+ "hidden_size": 1024,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 4096,
22
+ "layer_norm_eps": 1e-12,
23
+ "layer_norm_type": "layer_norm",
24
+ "logn_attention_clip1": false,
25
+ "logn_attention_scale": false,
26
+ "max_position_embeddings": 8192,
27
+ "model_type": "new",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 24,
30
+ "pack_qkv": true,
31
+ "pad_token_id": 0,
32
+ "position_embedding_type": "rope",
33
+ "rope_scaling": {
34
+ "factor": 2.0,
35
+ "type": "ntk"
36
+ },
37
+ "rope_theta": 160000,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.36.2",
40
+ "type_vocab_size": 2,
41
+ "unpad_inputs": false,
42
+ "use_memory_efficient_attention": false,
43
+ "vocab_size": 30522
44
+ }
checkpoint-669/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bd85c216db17223f4750727ba5bad9f8d86d1f9c6fffcb736dcda5a86223d8e
3
+ size 1736561104
checkpoint-669/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f493a6bb3ff0ed9cb5909b94a2757d10560478e1ca0bb7259ef76a05ba374cca
3
+ size 3473287493
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 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
47
+ "mask_token": "[MASK]",
48
+ "max_length": 8000,
49
+ "model_max_length": 32768,
50
+ "pad_to_multiple_of": null,
51
+ "pad_token": "[PAD]",
52
+ "pad_token_type_id": 0,
53
+ "padding_side": "right",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
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:c9d28c1554748c4e852ecb4292a6890e4f0b1fc576494b1f2b7a646ac50c07a2
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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Alibaba-NLP/gte-large-en-v1.5",
3
+ "architectures": [
4
+ "NewModelForCL"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
9
+ "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
10
+ "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
11
+ "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
12
+ "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
13
+ "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
14
+ "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
15
+ },
16
+ "classifier_dropout": null,
17
+ "hidden_act": "gelu",
18
+ "hidden_dropout_prob": 0.1,
19
+ "hidden_size": 1024,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 4096,
22
+ "layer_norm_eps": 1e-12,
23
+ "layer_norm_type": "layer_norm",
24
+ "logn_attention_clip1": false,
25
+ "logn_attention_scale": false,
26
+ "max_position_embeddings": 8192,
27
+ "model_type": "new",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 24,
30
+ "pack_qkv": true,
31
+ "pad_token_id": 0,
32
+ "position_embedding_type": "rope",
33
+ "rope_scaling": {
34
+ "factor": 2.0,
35
+ "type": "ntk"
36
+ },
37
+ "rope_theta": 160000,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.36.2",
40
+ "type_vocab_size": 2,
41
+ "unpad_inputs": false,
42
+ "use_memory_efficient_attention": false,
43
+ "vocab_size": 30522
44
+ }
custom_info ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ epoch=0 step=74 progress=0.111 eval info {'sparsity_loss': 1.949, 'l1l2_ratio_z12': 22.631, 'l1l2_ratio_z13': 24.155, 'l1l2_ratio_z13_all': 25.045} train info {'sparsity_loss': 3.651, 'l1l2_ratio_z12': 24.58, 'l1l2_ratio_z13': 25.062, 'l1l2_ratio_z13_all': 25.343}
2
+ epoch=0 step=148 progress=0.221 eval info {'sparsity_loss': 1.558, 'l1l2_ratio_z12': 22.342, 'l1l2_ratio_z13': 24.291, 'l1l2_ratio_z13_all': 25.219} train info {'sparsity_loss': 1.173, 'l1l2_ratio_z12': 22.703, 'l1l2_ratio_z13': 24.374, 'l1l2_ratio_z13_all': 25.265}
3
+ epoch=0 step=222 progress=0.332 eval info {'sparsity_loss': 1.27, 'l1l2_ratio_z12': 22.035, 'l1l2_ratio_z13': 24.157, 'l1l2_ratio_z13_all': 25.208} train info {'sparsity_loss': 0.651, 'l1l2_ratio_z12': 22.266, 'l1l2_ratio_z13': 24.341, 'l1l2_ratio_z13_all': 25.342}
4
+ epoch=1 step=74 progress=0.444 eval info {'sparsity_loss': 1.132, 'l1l2_ratio_z12': 22.216, 'l1l2_ratio_z13': 24.25, 'l1l2_ratio_z13_all': 25.28} train info {'sparsity_loss': 0.314, 'l1l2_ratio_z12': 21.793, 'l1l2_ratio_z13': 24.227, 'l1l2_ratio_z13_all': 25.301}
5
+ epoch=1 step=148 progress=0.555 eval info {'sparsity_loss': 1.286, 'l1l2_ratio_z12': 21.864, 'l1l2_ratio_z13': 24.165, 'l1l2_ratio_z13_all': 25.198} train info {'sparsity_loss': 0.217, 'l1l2_ratio_z12': 21.591, 'l1l2_ratio_z13': 24.223, 'l1l2_ratio_z13_all': 25.317}
6
+ epoch=1 step=222 progress=0.665 eval info {'sparsity_loss': 1.127, 'l1l2_ratio_z12': 21.936, 'l1l2_ratio_z13': 24.184, 'l1l2_ratio_z13_all': 25.2} train info {'sparsity_loss': 0.147, 'l1l2_ratio_z12': 21.386, 'l1l2_ratio_z13': 24.178, 'l1l2_ratio_z13_all': 25.285}
7
+ epoch=2 step=74 progress=0.777 eval info {'sparsity_loss': 1.143, 'l1l2_ratio_z12': 21.521, 'l1l2_ratio_z13': 24.022, 'l1l2_ratio_z13_all': 25.143} train info {'sparsity_loss': 0.073, 'l1l2_ratio_z12': 20.703, 'l1l2_ratio_z13': 24.008, 'l1l2_ratio_z13_all': 25.209}
8
+ epoch=2 step=148 progress=0.888 eval info {'sparsity_loss': 1.199, 'l1l2_ratio_z12': 21.347, 'l1l2_ratio_z13': 24.007, 'l1l2_ratio_z13_all': 25.138} train info {'sparsity_loss': 0.057, 'l1l2_ratio_z12': 20.624, 'l1l2_ratio_z13': 24.002, 'l1l2_ratio_z13_all': 25.216}
9
+ epoch=2 step=222 progress=0.999 eval info {'sparsity_loss': 1.186, 'l1l2_ratio_z12': 21.136, 'l1l2_ratio_z13': 23.883, 'l1l2_ratio_z13_all': 25.085} train info {'sparsity_loss': 0.049, 'l1l2_ratio_z12': 20.424, 'l1l2_ratio_z13': 23.957, 'l1l2_ratio_z13_all': 25.19}
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bd85c216db17223f4750727ba5bad9f8d86d1f9c6fffcb736dcda5a86223d8e
3
+ size 1736561104
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 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
47
+ "mask_token": "[MASK]",
48
+ "max_length": 8000,
49
+ "model_max_length": 32768,
50
+ "pad_to_multiple_of": null,
51
+ "pad_token": "[PAD]",
52
+ "pad_token_type_id": 0,
53
+ "padding_side": "right",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
train_results.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ epoch = 3.0
2
+ train_runtime = 6614.8366
3
+ train_samples_per_second = 0.101
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": 6614.8366,
16
+ "train_samples_per_second": 0.101
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:c9d28c1554748c4e852ecb4292a6890e4f0b1fc576494b1f2b7a646ac50c07a2
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff