Hugging Face's logo

SparseCL
/
GTE-SparseCL-msmarco

Transformers
Safetensors
new
custom_code
Inference Endpoints
Model card Files Community
xiaoxiaolin commited on
Commit
8758fec
·
verified ·
1 Parent(s): c7e738b

Upload folder using huggingface_hub

Browse files
Files changed (40) hide show
  1. checkpoint-1400/config.json +44 -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 +62 -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 +44 -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 +62 -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 +44 -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 +62 -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 +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-1400/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-1400/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10c608d9a36b7296e1602e9b0417c5e0dbb7ce722f6ecd2c5b0bafd4e4f94e61
3
+ size 1736561104
checkpoint-1400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b842dcc761015212ef93e7ad4f640cc53b44c7cf2d1758dcd1e003a27ae2ef75
3
+ size 3473287493
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 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-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 sha256:8f1d1860c201152194fec8da63c1ddd15c9b31b41cc737ce034071ce733c789b
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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-2800/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9b8140c50cf003bcc482c5258fa29b05e337fa96394eff65acbb554f585c817
3
+ size 1736561104
checkpoint-2800/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc2cb31c5e472ba8950613142a034a182c62018bf0c3ce8230768ff03d85524f
3
+ size 3473287493
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 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-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 sha256:8f1d1860c201152194fec8da63c1ddd15c9b31b41cc737ce034071ce733c789b
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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-4200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8363ad9e6f06e6bc75da9a6a5524d4c6ec5fb6816afa269b962815cad8b19236
3
+ size 1736561104
checkpoint-4200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80bf9025a46fa7a39222f1310cc0cf17aeba33a9fb735c417fcac4d55ac86055
3
+ size 3473287493
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 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-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 sha256:8f1d1860c201152194fec8da63c1ddd15c9b31b41cc737ce034071ce733c789b
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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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=466 progress=0.111 eval info {'sparsity_loss': 0.46, 'l1l2_ratio_z12': 21.945, 'l1l2_ratio_z13': 24.316, 'l1l2_ratio_z13_all': 25.81} train info {'sparsity_loss': 1.884, 'l1l2_ratio_z12': 23.299, 'l1l2_ratio_z13': 25.038, 'l1l2_ratio_z13_all': 25.553}
2
+ epoch=0 step=932 progress=0.222 eval info {'sparsity_loss': 0.409, 'l1l2_ratio_z12': 21.396, 'l1l2_ratio_z13': 24.043, 'l1l2_ratio_z13_all': 25.861} train info {'sparsity_loss': 0.277, 'l1l2_ratio_z12': 21.973, 'l1l2_ratio_z13': 24.671, 'l1l2_ratio_z13_all': 25.844}
3
+ epoch=0 step=1398 progress=0.333 eval info {'sparsity_loss': 0.338, 'l1l2_ratio_z12': 21.167, 'l1l2_ratio_z13': 23.785, 'l1l2_ratio_z13_all': 25.845} train info {'sparsity_loss': 0.144, 'l1l2_ratio_z12': 21.444, 'l1l2_ratio_z13': 24.537, 'l1l2_ratio_z13_all': 25.87}
4
+ epoch=1 step=466 progress=0.444 eval info {'sparsity_loss': 0.335, 'l1l2_ratio_z12': 19.772, 'l1l2_ratio_z13': 23.568, 'l1l2_ratio_z13_all': 25.787} train info {'sparsity_loss': 0.063, 'l1l2_ratio_z12': 20.466, 'l1l2_ratio_z13': 24.443, 'l1l2_ratio_z13_all': 25.822}
5
+ epoch=1 step=932 progress=0.555 eval info {'sparsity_loss': 0.341, 'l1l2_ratio_z12': 18.72, 'l1l2_ratio_z13': 22.955, 'l1l2_ratio_z13_all': 25.723} train info {'sparsity_loss': 0.041, 'l1l2_ratio_z12': 19.578, 'l1l2_ratio_z13': 24.308, 'l1l2_ratio_z13_all': 25.795}
6
+ epoch=1 step=1398 progress=0.666 eval info {'sparsity_loss': 0.414, 'l1l2_ratio_z12': 17.568, 'l1l2_ratio_z13': 22.579, 'l1l2_ratio_z13_all': 25.668} train info {'sparsity_loss': 0.025, 'l1l2_ratio_z12': 18.579, 'l1l2_ratio_z13': 24.139, 'l1l2_ratio_z13_all': 25.763}
7
+ epoch=2 step=466 progress=0.778 eval info {'sparsity_loss': 0.399, 'l1l2_ratio_z12': 16.844, 'l1l2_ratio_z13': 22.645, 'l1l2_ratio_z13_all': 25.691} train info {'sparsity_loss': 0.015, 'l1l2_ratio_z12': 17.588, 'l1l2_ratio_z13': 24.193, 'l1l2_ratio_z13_all': 25.747}
8
+ epoch=2 step=932 progress=0.889 eval info {'sparsity_loss': 0.421, 'l1l2_ratio_z12': 16.263, 'l1l2_ratio_z13': 22.549, 'l1l2_ratio_z13_all': 25.682} train info {'sparsity_loss': 0.013, 'l1l2_ratio_z12': 16.787, 'l1l2_ratio_z13': 24.081, 'l1l2_ratio_z13_all': 25.725}
9
+ epoch=2 step=1398 progress=1.0 eval info {'sparsity_loss': 0.417, 'l1l2_ratio_z12': 16.159, 'l1l2_ratio_z13': 22.708, 'l1l2_ratio_z13_all': 25.705} train info {'sparsity_loss': 0.015, 'l1l2_ratio_z12': 16.438, 'l1l2_ratio_z13': 24.094, 'l1l2_ratio_z13_all': 25.717}
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8363ad9e6f06e6bc75da9a6a5524d4c6ec5fb6816afa269b962815cad8b19236
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 = 24068.6912
3
+ train_samples_per_second = 0.175
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": 24068.6912,
16
+ "train_samples_per_second": 0.175
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 sha256:8f1d1860c201152194fec8da63c1ddd15c9b31b41cc737ce034071ce733c789b
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff